1. A method of probe life prediction, comprising:

acquiring experimental group data and reference group data of a plurality of tested objects, wherein the experimental group data is obtained by testing the performances of the plurality of tested objects based on a probe to be predicted, and the reference group data is obtained by testing the performances of the plurality of tested objects based on a reference probe;

determining at least one relevant performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one relevant performance indicator being related to the life of the probe to be predicted;

obtaining performance test data of the at least one relevant performance index;

and predicting the service life of the probe to be predicted based on the performance test data.

2. The method of predicting the life of a probe according to claim 1, determining at least one relevant performance indicator of the probe to be predicted based on the experimental group data and the reference group data, comprising:

constructing at least one pair of test data pairs based on at least one experimental test data in the experimental group data and at least one reference test data in the reference group data, wherein the types of the reference test data and the experimental test data in the at least one pair of test data pairs are the same;

and inputting the at least one pair of test data into a pre-trained correlation prediction model to obtain the at least one correlation performance index.

3. The probe life prediction method of claim 2, the pre-trained relevance prediction model comprising a ranking model;

inputting the at least one pair of test data into a pre-trained correlation prediction model to obtain at least one correlation performance index, including:

and inputting the at least one pair of test data into the sequencing model to obtain a sequencing result of at least one relevant performance index, wherein the sequencing result represents the correlation degree of each relevant performance index in the at least one relevant performance index and the service life of the probe to be predicted.

4. The method of predicting the life of a probe according to claim 3, predicting the life of the probe to be predicted based on the performance test data, comprising:

determining a weight of the at least one relevant performance indicator based on the ranking result;

and inputting the performance test data of the at least one relevant performance index into a pre-trained life prediction model by combining the weight of the at least one relevant performance index, and determining the life of the probe to be predicted.

5. A probe life prediction system comprising:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring experimental group data and reference group data of a plurality of tested objects, the experimental group data is obtained by testing the performance of the plurality of tested objects based on a probe to be predicted, and the reference group data is obtained by testing the performance of the plurality of tested objects based on a reference probe;

a correlation determination module that determines at least one correlated performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one correlated performance indicator being correlated to a lifetime of the probe to be predicted;

the second acquisition module is used for acquiring performance test data of the at least one relevant performance index;

and the service life prediction module is used for predicting the service life of the probe to be predicted based on the performance test data of the at least one relevant performance index.

6. The probe life prediction system of claim 5, the correlation determination module, comprising:

the data pair construction sub-module is used for constructing at least one pair of test data pairs based on at least one experimental test data in the experimental group data and at least one reference test data in the reference group data, and the types of the reference test data and the experimental test data in the at least one pair of test data pairs are the same;

and the correlation determination submodule is used for inputting the at least one pair of test data into a pre-trained correlation prediction model to obtain the at least one correlation performance index.

7. The probe life prediction system of claim 6, the pre-trained relevance prediction model comprising a ranking model;

the correlation determination submodule includes:

and the sequencing unit is used for inputting the at least one pair of test data into the sequencing model to obtain a sequencing result of at least one relevant performance index, and the sequencing result represents the correlation degree between each relevant performance index in the at least one relevant performance index and the service life of the probe to be predicted.

8. The probe life prediction system of claim 7, the life prediction module comprising:

a weight determination submodule for determining a weight of the at least one relevant performance indicator based on the ranking result;

and the life prediction submodule is used for inputting the performance test data of the at least one relevant performance index into a pre-trained life prediction model by combining the weight of the at least one relevant performance index, and determining the life of the probe to be predicted.

9. A probe life prediction device comprising a processor for performing the probe life prediction method of any one of claims 1 to 5.

10. A computer readable storage medium storing computer instructions which, when read by a computer, cause the computer to perform a method of predicting the life of a probe according to any one of claims 1 to 5.

Background

In the development and production of electronic circuits, it is often necessary to perform high-precision testing of signal transmission and signal quality (e.g., current/voltage/level quantities) in various circuit boards and/or chips using probes. Specifically, the probe head of the probe is abutted against an object to be tested (e.g., a circuit board and/or a chip), and the probe tail of the probe is electrically connected with the test analysis system, so that an electrical signal picked out from the object to be tested is conducted to the test analysis system as losslessly as possible, and the test analysis system analyzes the performance of the object to be tested according to the received electrical signal. That is, the probe is actually a high-precision electronic component.

However, after a period of testing, the life of the probe is gradually weakened, for example, the needle of the probe is seriously worn and has poor contact with the object to be tested, so that the electrical signal cannot be stably received from the object to be tested, the accuracy of the performance test of the object to be tested is affected, and the probe needs to be replaced at this time. Therefore, how to accurately predict the life of the probe so as to provide a reference for replacing the probe in advance is a problem to be solved urgently.

Disclosure of Invention

One embodiment of the present disclosure provides a method for predicting a life of a probe. The probe life prediction method comprises the following steps: acquiring experimental group data and reference group data of a plurality of tested objects, wherein the experimental group data is obtained by testing the performances of the plurality of tested objects based on a probe to be predicted, and the reference group data is obtained by testing the performances of the plurality of tested objects based on a reference probe; determining at least one relevant performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one relevant performance indicator being related to the life of the probe to be predicted; obtaining performance test data of the at least one relevant performance index; and predicting the service life of the probe to be predicted based on the performance test data.

One embodiment of the present disclosure provides a probe life prediction system. The probe life prediction system comprises: the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring experimental group data and reference group data of a plurality of tested objects, the experimental group data is obtained by testing the performance of the plurality of tested objects based on a probe to be predicted, and the reference group data is obtained by testing the performance of the plurality of tested objects based on a reference probe; a correlation determination module that determines at least one correlated performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one correlated performance indicator being correlated to a lifetime of the probe to be predicted; the second acquisition module is used for acquiring performance test data of the at least one relevant performance index; and the service life prediction module is used for predicting the service life of the probe to be predicted based on the performance test data of the at least one relevant performance index.

One of the embodiments of the present specification provides a probe life prediction apparatus, which includes a processor for executing a probe life prediction method.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions, and when the computer instructions in the storage medium are read by a computer, the computer executes a probe life prediction method.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1a is an exemplary flow chart of a method for probe life prediction according to some embodiments described herein;

FIG. 1b is a schematic flow chart of data in a method of probe life prediction according to some embodiments of the present description;

FIG. 2 is an exemplary flowchart of step S120 of a method for predicting the life of a probe according to some embodiments described herein;

FIG. 3 is an exemplary flowchart of step S140 of a method for predicting the life of a probe according to some embodiments described herein;

FIG. 4 is an exemplary block diagram of a correlation prediction model and a life prediction model in a method of predicting life of a probe according to some embodiments of the present disclosure;

FIG. 5 is an exemplary block diagram of a probe life prediction system in accordance with some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

The probe is an electronic element and has various performance indexes, after a period of test use, the performance indexes are gradually weakened, the service life of the probe is gradually weakened, and the accurate prediction of the service life of the probe can provide a certain reference for replacing the probe in advance. However, even when two probes of the same type and specification are used in the same lot in different use environments, it is obvious that the life of one probe used in a relatively severe environment is shorter than that of a probe used in a relatively excellent environment. That is, the service environments of the probes are different from one another, and the life spans of the probes are different from one another, and the individual differences are not restricted and are irregular, so that the life spans of the probes are predicted with certain technical difficulty. Some embodiments of the present disclosure provide that data obtained by testing performance of a tested object based on a probe to be predicted is compared with data obtained by testing performance of the same tested object based on a reference probe, a performance index (referred to as a related performance index) related to a life of the probe is determined from various performance indexes of the probe to be predicted, performance corresponding to the related performance index of the probe to be predicted is tested to obtain performance test data corresponding to the related performance index, and the life of the probe to be predicted is predicted based on the performance test data corresponding to the related performance index. The technical difficulty of service life prediction of the probe caused by individual difference of the use environment of the probe is overcome, the service life of the probe can be predicted to a certain degree, and certain reference is provided for replacing the probe in advance.

The embodiment of the invention provides a method, a system, a device and a storage medium for predicting the service life of a probe.

In some embodiments, the probe life prediction device may be specifically integrated in an electronic device, which may be a terminal, a server, or the like. The terminal can be a mobile phone, a tablet Computer, an intelligent bluetooth device, a notebook Computer, or a Personal Computer (PC), and the like; the server may be a single server or a server cluster composed of a plurality of servers.

In some embodiments, the probe life prediction device may be integrated into a plurality of electronic devices, for example, the probe life prediction device may be integrated into a plurality of servers, and the probe life prediction method of the present invention is implemented by the plurality of servers.

In some embodiments, the server may also be implemented in the form of a terminal.

The following are detailed below.

FIG. 1a is an exemplary flow chart of a method for probe life prediction according to some embodiments described herein. As shown in fig. 1a, the process 100 includes the following steps S110 to S140. In some embodiments, the process 100 may be performed by the aforementioned electronic device. FIG. 1b is a schematic flow chart of data in a method of probe life prediction according to some embodiments of the present description; this is explained in detail below with reference to fig. 1a and 1 b.

Step S110, acquiring experimental group data and reference group data of a plurality of objects to be tested, wherein the experimental group data is obtained by testing the performance of the plurality of objects to be tested based on the probe to be predicted, and the reference group data is obtained by testing the performance of the plurality of objects to be tested based on the reference probe. In some embodiments, step S110 may be performed by the first obtaining module 501 (shown in fig. 5).

The probe is a high-precision electronic component and has various performance indexes. The performance indicators include, but are not limited to: mechanical properties and/or electrical properties. Among the mechanical properties are, but not limited to: elasticity, heat resistance of the needle, and/or rigidity of the needle; electronic properties include, but are not limited to: resistance, impedance, and/or conductivity, etc.

The probe to be predicted means a probe whose life is to be predicted. For example, the probe to be predicted is a probe that has been used for a certain period of time.

In some embodiments, probes to be predicted include, but are not limited to, any of the following: high frequency probes, PCB (printed Circuit Board) probes, ICT (In-Circuit Tet) functional test probes, BGA (ball Grid Array Package) test probes, semiconductor probes, and the like.

The reference probe is a standard probe of the same type and model as the probe to be predicted. For example, if the probe to be predicted is a high frequency probe, the reference probe is a standard high frequency probe of the same type; if the probe to be predicted is a PCB probe, the reference probe is a standard PCB probe with the same model; if the probe to be predicted is an ICT functional test probe, the reference probe is a standard ICT functional test probe with the same model number; if the probe to be predicted is a BGA probe, the reference probe is a standard BGA probe with the same model; if the probe to be predicted is a semiconductor probe, the reference probe is a standard semiconductor probe of the same type. The standard probe is a probe which passes a calibration test in advance, namely, each performance index of the standard probe meets the technical standard. For example, the reference probe may be a completely new probe.

The object to be measured is an object to be measured that matches the type of probe to be predicted. For example, if the probe to be predicted is a high frequency probe primarily used for high frequency signal testing, then the subject under test includes, but is not limited to: BGA chips and/or semiconductor devices; if the probe to be predicted is a PCB probe, the objects under test include, but are not limited to: a PCB board with components and/or a PCB empty board; if the probe to be predicted is an ICT functional test probe mainly used for online circuit test and functional test, the tested object comprises but is not limited to a PCB empty board; if the probe to be predicted is a BGA probe, the tested object comprises but is not limited to a BGA chip; if the probe to be predicted is a semiconductor probe, the object under test includes, but is not limited to, a semiconductor device.

The test group is a test group for testing the performance of the tested object by applying the probes to be predicted to the tested object and receiving the electric signals from the tested object, and the reference group is a test group for testing the performance of the tested object by applying the probes to the tested object and receiving the electric signals from the tested object.

In some embodiments, the number of subjects in the experimental and reference groups may be one or more.

In some embodiments, the plurality of test objects are a plurality of same kind of test objects. For example, the probe to be predicted is a high-frequency probe, and the plurality of objects under test are all BGA chips of the same model and specification or semiconductor devices of the same model and specification.

In some embodiments, the plurality of test objects are a plurality of different kinds of test objects. For example, the probe to be predicted is a high frequency probe, and a part of the objects to be tested is a BGA chip and a part of the objects to be tested is a semiconductor device.

In some embodiments, for example, a plurality of subjects are listed with a set X ═ { X ═ X₁,x₂,…,x_nDenotes x_nDenotes an nth object (a plurality of objects are numbered in advance in the order of 1 to n), and n is a positive integer.

In some embodiments, the subjects tested in the experimental group and the reference group may be identical in number and type, and the test conditions for the same subject in the experimental group and the reference group may also be identical, so as to control the distinction between the experimental group and the reference group to a variable that is only the probe difference (i.e., the experimental group corresponds to the probe to be predicted, and the reference group corresponds to the reference probe).

In some embodiments, each of the plurality of test objects is subjected to a performance test under a respective one or more test conditions. Wherein the test conditions include, but are not limited to: temperature and/or humidity, etc. Illustratively, for example, object under test X ═ { X ═ X₁,x₂,…,x_nTest object number 1 x in₁Respectively at (temperature T)₁Humidity H₁) (temperature T)₁Humidity H₂) (temperature T)₂Humidity H₁) (temperature T)₂Humidity H₂) Performance testing under four test conditions, object No. 2, tested x₂Are respectively at (temperature T)₃Humidity H₃) (temperature T)₄Humidity H₄) Performance testing was performed under two test conditions, … …, number n object x_nAre respectively at (temperature T)_aHumidity H_b) (temperature T)_aHumidity H_b+j) (temperature T)_a+iHumidity H_b) … …, (temperature T)_a+iHumidity H_b+j) Total Z_nPerformance tests were performed under i x j test conditions. Wherein, T₁Representing a first temperature value, T₂Representing a second temperature value, …, T_aRepresents the a temperature value, T_a+iRepresents the (a + i) th temperature value, a>0, a is a positive integer, i is not less than 0, and i is a positive integer; h₁Denotes a first humidity value, H₂Denotes a second humidity value, …, H_bDenotes the value of the b-th humidity, T_b+jRepresents the (b + j) th humidity value, b>0, b is a positive integer, j is not less than 0, and j is a positive integer. The test conditions for different subjects may be completely different, partially the same, or completely the same. Some of the similarities may include: wherein one or more of the parameters are equal.

The data obtained after the test of the experimental group is experimental group data, namely the experimental group data is the data obtained by testing the performance of the tested object based on the probe to be predicted in the experimental group. The data obtained after the test of the reference group is the reference group data, that is, the reference group data is the data obtained by testing the performance of the object to be tested based on the reference probe in the reference group.

In some embodiments, after completion of the testing, experimental group data were obtained: collection It is shown that,representing the object x under test_nThe resulting performance test data set is tested in the experimental group under each of its corresponding test conditions, illustratively, asWherein the content of the first and second substances,representing the object x under test₁At (temperature T)₁Humidity H₁) Experimental test data under the test conditions were,representing the object x under test₁At (temperature T)₁Humidity H₂) Experimental test data under the test conditions were,representing the object x under test₁At (temperature T)₂Humidity H₁) Experimental test data under the test conditions were,representing the object x under test₁At (temperature T)₂Humidity H₂) Experimental test data under test conditions; such as Wherein the content of the first and second substances,representing the object x under test_nAt (temperature T)_aHumidity H_b) Experimental test data under the test conditions were,representing the object x under test_nAt (temperature T)_aHumidity H_b+j) Experimental test data under the test conditions were,representing the object x under test_nAt (temperature T)_a+iHumidity H_b) Experimental test data under test conditions, …,representing the object x under test_nAt (temperature T)_a+iHumidity H_b+j) Experimental test data under test conditions; and, reference group data: representing the object x under test_nTesting the obtained performance test data set under each corresponding test condition in the reference group; illustratively, such as Wherein the content of the first and second substances,representing the object x under test₁At (temperature T)₁Humidity H₁) The reference test data under the test conditions is,representing the object x under test₁At (temperature T)₁Humidity H₂) The reference test data under the test conditions is,representing the object x under test₁At (temperature T)₂Humidity H₁) The reference test data under the test conditions is,representing the object x under test₁At (temperature T)₂Humidity H₂) Reference test data under test conditions; such as Wherein the content of the first and second substances,representing the object x under test_nAt (temperature T)_aHumidity H_b) Reference test data under test conditions，Representing the object x under test_nAt (temperature T)_aHumidity H_b+j) The reference test data under the test conditions is,representing the object x under test_nAt (temperature T)_a+iHumidity H_b) The reference test data under test conditions, …,representing the object x under test_nAt (temperature T)_a+iHumidity H_b+j) Reference test data under test conditions.

In some embodiments, the experimental group test and the reference group test are previously completed to obtain experimental group data and reference group data, and the experimental group data is stored in the storage medium and/or the storage device. And reading the experimental group data and the reference group data from a storage medium and/or a storage device when the service life of the probe to be predicted is predicted.

In some embodiments, exemplarily, experimental group data is read (i.e., acquired) And reference group data

Step S120, determining at least one relevant performance index of the probe to be predicted based on the experimental group data and the reference group data, wherein the at least one relevant performance index is relevant to the service life of the probe to be predicted. In some embodiments, step S120 may be performed by the relevance determining module 502 (shown in fig. 5).

Please refer to the description of the probe, the probe has various performance indexes. For example, elasticity in mechanical properties. Also for example, impedance in electronic performance. The related performance index is a performance index which is determined from various performance indexes of the probe to be predicted and has relevance with the service life to be predicted.

In some embodiments, the at least one performance indicator includes, but is not limited to: mechanical properties and/or electrical properties. Among the mechanical properties are, but not limited to: elasticity, heat resistance of the needle, and/or rigidity of the needle; electronic properties include, but are not limited to: resistance, impedance, and/or conductivity, etc.

In some embodiments, as shown in fig. 1b, the performance indicators determined based on the experimental group data M and the reference group data N are related performance indicators 1 (e.g., spring force F), related performance indicators 2 (e.g., impedance Z), and other related performance indicators N, etc.

In some embodiments, step S120 is implemented based on a data analysis method, and the performance data obtained by testing any one of the plurality of tested objects in the experimental group is compared with the performance data obtained by testing any one of the plurality of tested objects in the reference group, so as to determine the relevant performance index from the performance indexes of the probe to be predicted. For example, a plurality of objects X ═ { X ═ X₁,x₂,…,x_nAny object x under test_nExperimental group test data ofAnd reference group data And carrying out comparison analysis so as to determine the related performance index of the probe to be predicted. For example, the determined relevant performance indicators include a relevant performance indicator 1 (e.g., spring force F) and a relevant performance indicator 2 (e.g., impedance Z).

In some embodiments, step S120 is implemented based on artificial intelligence techniques. FIG. 2 is an exemplary flowchart of step S120 in a method of probe life prediction according to some embodiments described herein. Please refer to fig. 4, the step S120 will be described in detail. As shown in fig. 2, step S120 includes the steps of:

step S121, at least one pair of test data pairs is constructed based on at least one experimental test data in the experimental group data and at least one reference test data in the reference group data, and the types of the reference test data and the experimental test data in the at least one pair of test data pairs are the same.

Based on the foregoing description, after performance tests are performed on a plurality of test subjects in the experimental group and the reference group, respectively, experimental group data and reference group data of the plurality of test subjects are obtained. That is, data obtained by the plurality of test objects completing the performance test based on the probe to be predicted is included in the experimental group data, and data obtained by the plurality of test objects completing the performance test based on the reference probe is included in the reference group data. The test data is obtained by completing the performance test of one tested object in the test group based on the probe to be predicted under one test condition, and the reference test data is obtained by completing the performance test of one tested object in the reference group based on the probe to be predicted under one test condition. For example, if a certain test object performs a performance test under a certain test condition in the test group to obtain an experimental test data, the test object also performs the performance test under the certain test condition in the reference group to obtain a reference test data.

In some embodiments, illustratively, for subject x_nThe experimental group test data of (1) are The corresponding reference group data is By way of example, the temperature profile may, among others,is the data of an experimental test, and the test data,is a reference test data.

In some embodiments, the test data of a test object in the test data is represented by a matrix, the reference test data of a test object in the reference data is represented by a matrix, and the first test condition corresponding to each column element in the matrix is the same and the second test condition corresponding to each row element in the matrix is the same. The first test condition and the second test condition refer to two different types of test conditions. For example, the first test condition is temperature and the second test condition is humidity.

In some embodiments, for example, X ═ X for a subject under test₁,x₂,…，x_nExperimental group data of }Expressed in a matrix as follows: wherein, the matrix A₁Representing the object x under test₁Experimental test data, matrix A, completed under different test conditions in the experimental group₂Representing the object x under test₂Experimental test data, …, matrix A, completed under different test conditions in the experimental group_nRepresenting the object x under test_nExperimental test data completed under different test conditions in the experimental group; and a plurality of tested objects corresponding to each row element in the matrix are tested at the same temperature T, and a plurality of tested objects corresponding to each row element are tested at the same humidity HAnd (6) testing. For an object under test X ═ { X ═ X₁,x₂，…，x_nReference group data of }Expressed in a matrix as follows:wherein, the matrix B₁Representing the object x under test₁Reference test data, matrix B, performed under different test conditions in the reference group₂Representing the object x under test₂Reference test data, …, matrix B, performed under different test conditions in the reference set_nRepresenting the object x under test_nThe reference test data is completed under different test conditions in the reference group, a plurality of tested objects corresponding to each row element in the matrix are tested at the same temperature T, a plurality of tested objects corresponding to each row element are tested at the same humidity H, and the matrix B_nAnd matrix A_nCorresponding to the same object x_nAnd matrix B_nAnd matrix A_nWherein each coordinate of the same element corresponds to the same test condition. For the test conditions corresponding to each element in the matrix, please refer to the related description in the foregoing, and will not be described herein again. It should be noted that, when the tested object is not tested under a certain test condition, zero padding processing is performed at the position of the element marked by the test condition in the matrix for the processor to execute. For example object x under test₂Is not at (temperature T)₃Humidity H₄) The test is carried out under the condition that the matrix A is₂Zero padding is carried out at the position of the first row in the first column.

The same type of reference test data and experimental test data in the test data pair means that the types of tests are the same, for example, both include tests of impedance and voltage. In some embodiments, each pair of test data pairs may be reference test data and experimental test data for the same subject under the same test conditions, or may be reference test data and experimental test data for the same subject under all test conditions. For example, from experimental groups respectivelySelecting experimental test data and reference test data of the same tested object under the same test condition from the data and reference group data to form a pair of test data pairs; accordingly, have (Z) in common₁+Z₂+…+Z_n) For the test data pair, wherein Z₁Representing the object x under test₁Number of test conditions, Z₂Representing the object x under test₂Number of test conditions of (2), … …, Z_nRepresenting the object x under test_nNumber of test conditions of (1). For another example, experimental test data and reference test data of the same tested object under all test conditions are respectively selected from the experimental group data and the reference group data, so that a pair of test data pairs is formed; accordingly, the number of test data pairs corresponds to the number of subjects, i.e., there are n pairs of test data pairs.

In some embodiments, illustratively, the data is derived from experimental group dataAnd reference group dataSelecting any measured object x_nThe experimental test data under a certain test condition isAnd with reference to the test data isForm test data pairsFinally obtaining a test data pair set

In some embodiments, illustratively, from experimentsGroup dataAnd reference group dataSelecting any measured object x_nThe test data of the experimental group under all test conditions areAnd the reference group data isForm test data pairsFinally obtaining a test data pair setAccordingly, when the experimental and reference set data are represented in a matrix, the test data pair is represented as

And step S122, inputting at least one pair of test data into a pre-trained correlation prediction model to obtain at least one correlation performance index.

The correlation prediction model is obtained by training a first preset model for a training sample according to a plurality of sample test data pairs and a performance index label corresponding to each sample test data pair. One sample test data pair is composed of two groups of test data of the same sample tested object, one group of the two groups of test data is data obtained by testing the performance of a sample probe on the same sample tested object under a plurality of preset test conditions, the other group of test data is data obtained by testing the performance of a reference probe on the same sample tested object under the plurality of preset test conditions, the performance index label is used for representing each performance index corresponding to the sample test data pair, the performance index related to the service life of the sample probe, the influence degree of each performance index on the service life of the sample probe, the influence degree refers to the correlation degree of each performance index of the sample probe and the service life of the sample probe, the sample probe is a probe for performing a test when acquiring a training sample, and the sample test object is a test object for performing a test when acquiring a training sample. The first predetermined model is a classification model. The training of the correlation prediction model may specifically include: and constructing a loss function based on the prediction results of the label and the model, iteratively updating parameters of the first preset model based on the loss function until preset conditions are met, and stopping training. The preset conditions may include: the number of iterations reaches a threshold number, the loss function converges, etc.

In some embodiments, in the course of training, the sample test data pairs are represented in the form of matrix pairs. One matrix (marked as a first matrix) in the matrix pair is data obtained by testing the performance of the sample probe on the same sample tested object under a plurality of preset test conditions, the other matrix (marked as a second matrix) is data obtained by testing the performance of the reference probe on the same sample tested object under the plurality of preset test conditions, wherein the recording modes of the first matrix and the second matrix are respectively the same as the matrix A_nAnd matrix B_nThe same is true.

In some embodiments, the sample subjects are a plurality of subjects of different types, and the first weights of the first matrix and the second matrix corresponding to each sample subject are determined according to the type of each sample subject (it should be noted that the first weights of the first matrix and the second matrix of the same sample subject are the same). In some embodiments, the second weights corresponding to the elements in the first matrix (or the second matrix) corresponding to the test conditions are determined according to the test conditions of the sample test object. (it should be noted that elements in the first matrix and second weights corresponding to elements of the second matrix, which are obtained by the same sample object under the same test condition, are the same.) in which the determining manners of the first weight and the second weight are the same as the determining manners of the third weight and the fourth weight, respectively, please refer to the description about the third weight and the fourth weight in the following text, and details are not repeated here.

In some embodiments, the supervised learning training is performed on the first preset model based on the sample test data composed of the first matrix and the second matrix, in which the first weight and/or the second weight is/are determined, until the first preset model reaches a preset convergence condition, a correlation prediction model is obtained.

As shown in FIG. 4, one or more pairs of test data pairs (e.g., test data pair sets) to be constructed in step S121 Or test data pair as Inputting a correlation prediction model, and outputting at least one correlation performance index after the correlation prediction model is processed; namely, based on the input test data pair, the relevant performance index is determined from various performance indexes of the probe to be predicted.

In some embodiments, a third weight of the respective experimental group data matrix and the reference group data matrix for each sample object is determined according to the type of each object (it should be noted that the experimental group data matrix a of the same sample object is_nAnd reference group data matrix B_nIs the same. ). Of course, the third weight for the same type of object under test isThe same applies. For example, if the first type of test object is actually acted upon by the probe, the third weight for the corresponding experimental and reference set data matrices for the first type of test object is configured to be relatively high, whereas if the second type of test object is actually acted upon by the probe, the third weight for the corresponding experimental and reference set data matrices is configured to be relatively low. For another example, when the probe tests a first type of test object, the life of the probe is easily affected (for example, the needle of the probe is easier), so the weights of the experimental group data matrix and the reference group data matrix corresponding to the first type of test object are higher, whereas when the probe tests a second type of test object, the weights of the experimental group data matrix and the reference group data matrix corresponding to the second type of test object are lower, and the weights of the experimental group data matrix and the reference group data matrix corresponding to the second type of test object are not easily affected.

In some embodiments, for example, X is determined from the subject X ═ { X ═ X₁,x₂,…，x_nDetermining the type of each object under test, and determining the third weight e corresponding to each object under test in turn₁、e₂、…、e_n. Accordingly, the test data pair represented by the matrix, given a third weight, can be represented as

In some embodiments, the fourth weight corresponding to the experimental test data and the reference test data is determined according to the test condition of the object under test, that is, the fourth weight corresponding to the element in the experimental group data matrix and the reference group data matrix determined according to the test condition of the object under test. (it should be noted that the fourth weights corresponding to the experimental test data and the reference test data obtained by the same subject under the same test condition are the same.) for example, the fourth weights of the experimental test data and the reference test data corresponding to the common test environment of the probe are higher, and the fourth weights of the experimental test data and the reference test data corresponding to the extreme test environment of the probe are lower.

In some embodiments, for example, X is determined from the subject X ═ { X ═ X₁，x₂，…，x_nIn the method, the following steps: number 1 object x under test₁Respectively at (temperature T)₁Humidity H₁) (temperature T)₁Humidity H₂) (temperature T)₂Humidity H₁) (temperature T)₂Humidity H₂) The performance test is carried out under four test conditions, and the fourth weight corresponding to each test condition isExpressed in a matrix:number 2 object x₂Are respectively at (temperature T)₃Humidity H₃) (temperature T)₄Humidity H₄) The performance test is carried out under two test conditions, and the first weight respectively corresponding to the two test conditions isExpressed in a matrix:… …, n number object x_nAre respectively at (temperature T)_aHumidity H_b) (temperature T)_aHumidity H_b+j) (temperature T)_a+iHumidity H_b) … …, (temperature T)_a+iHumidity H_b+j) Total Z_nPerformance testing under i x j test conditions, Z_nThe first weight corresponding to each test condition isExpressed in a matrix: accordingly, the test data pair represented by the matrix, given the third weight, can be expressed as:

…，

in some embodiments, the third weight and the fourth weight may be determined simultaneously and assigned to the corresponding matrices. For example, for object x_nThe determined third weight is e_nThe matrix corresponding to the fourth weight isThe corresponding test data pair is given the third weight and the fourth weight, and is expressed as

In some embodiments, the test data pair represented in the form of a matrix and determined by the third weight and/or the fourth weight in the above embodiments is input into a correlation prediction model, and after being processed by the correlation prediction model, at least one correlation performance index is output; namely, based on the input test data pair, the relevant performance index is determined from various performance indexes of the probe to be predicted. The third weight is determined according to the type of the tested object, and the fourth weight is determined according to the test condition of the tested object, so that the influence degree of different tested object types on the service life of the probe and the influence degree of different test conditions on the service life of the probe can be combined to determine the correlation prediction model when predicting the correlation performance index, and the output result of the correlation prediction model when predicting the correlation performance index is more accurate.

In some embodiments, the relevance prediction model may be a multi-classification model, including, for example, but not limited to: DNN (deep neural network), and the like. Illustratively, when the relevance prediction model is DNN, after inputting the test data pairs, the DNN will output at least one relevant performance indicator and a probability P corresponding to each relevant performance indicator that is output.

In some embodiments, the pre-trained relevance prediction model comprises a ranking model. Step S122 further includes the steps of:

and inputting at least one pair of test data into the sequencing model to obtain a sequencing result of at least one relevant performance index, wherein the sequencing result represents the correlation degree of each correlation in the at least one relevant performance index and the service life of the probe to be predicted.

The ordering model may be XGboost, RankSVM, LambdaMart, or the like.

The sequencing model is obtained by training a first preset model for a training sample according to a plurality of sample testing data pairs and a performance index label corresponding to each sample testing data pair. One sample test data pair consists of two groups of test data of the same sample tested object, one group of test data in the two groups of test data is data obtained by testing the performance of the same sample tested object by a sample probe under a preset test condition, the other group of test data is data obtained by testing the performance of the same tested object by a reference probe under the preset test condition, the performance index label is used for representing the correlation degree of each performance index of the sample test data pair and the life of the sample probe in each corresponding performance index, the performance index related to the life of the sample probe, the influence degree of each performance index on the life of the sample probe and the influence degree ranking of each performance index, the influence degree refers to the correlation degree of each performance index of the sample probe and the life of the sample probe, and the sample probe is used for testing when acquiring a training sample, the sample subjects are subjects to be tested in order to obtain a training sample.

In some embodiments, the supervised learning training is performed on the first preset model based on the sample test data composed of the first matrix and the second matrix, in which the first weight and/or the second weight is/are determined, until the first preset model reaches a preset convergence condition, a correlation prediction model is obtained. For a detailed description of the test data pairs, reference is made to the related description in the foregoing, and further description is omitted here.

The pre-trained correlation prediction model comprises a sequencing model, and when the correlation model is used for prediction, not only are correlation performance indexes output, but also a plurality of output correlation performance indexes are sequenced to represent the correlation degree of each correlation performance index and the service life of the probe to be predicted.

As shown in fig. 4, in some embodiments, illustratively, the test data pairs constructed in step S121 (e.g., or test data pair as Or test data pairs expressed in matrix form and having the third weight and/or the fourth weight determined in the above-described embodiment (for example, ) Inputting a correlation prediction model, and outputting at least one correlation performance index and a sequencing result thereof after the correlation prediction model processes; namely, based on the input test data pair, relevant performance indexes and sequencing results thereof are determined from various performance indexes of the probe to be predicted. For example, the obtained ranking result of the correlation performance indicators is: performance index 1 (e.g., spring force F), performance index 2 (e.g., impedance Z), … …, performance index n. The sequencing result can be ascending sequencing, namely the relevance of the performance index and the service life of the probe is gradually increased according to the sequence from the performance index 1 to the performance index n; the sorting result can also be descending sorting, namely according to the sequence from the performance index 1 to the performance index n, the correlation degree of the performance index and the service life of the probe is gradually reduced.

Referring back to fig. 1, in step S130, performance test data of the at least one relevant performance index is obtained. In some embodiments, step S130 may be performed by the second obtaining module 503 (shown in fig. 5).

The performance test data of at least one relevant performance index is data obtained after performance test is carried out on the performance marked by the relevant performance index of the probe to be predicted. For example, as shown in fig. 1b and fig. 4, the relevant performance indexes of the probe to be predicted include: performance index 1 (e.g., spring force F), performance index 2 (e.g., impedance Z), … …, performance index n, the performance test data includes: data sets { performance test data 1 (test data corresponding to the performance index 1), performance test data 2 (test data corresponding to the performance index 2), … and performance test data n (test data corresponding to the performance index n) } are sequentially obtained after testing the performance index 1 (such as the elasticity F), the performance index 2 (such as the impedance Z), … … and the performance index n of the probe to be predicted.

In some embodiments, the performance test data includes at least one performance test parameter for each of the at least one associated performance indicators. For example, relevant performance indicators for probes to be predicted include: performance index 1 (e.g., spring force F), performance index 2 (e.g., impedance Z), … …, and performance index n, then performance test data 1, performance test data 2, …, and performance test data n each include one or more performance test parameters.

In some embodiments, after the performance test of the relevant performance index of the probe to be predicted is completed, performance test data of the relevant performance index is obtained, and the performance test data is stored in the storage medium and/or the storage device. And reading the performance test data from the storage medium and/or the storage equipment when the service life of the probe to be predicted is predicted.

And step S140, predicting the service life of the probe to be predicted based on the performance test data. In some embodiments, step S140 may be performed by the lifetime prediction module 504 (shown in fig. 5).

The life of the probe to be predicted is the length of time that the probe to be predicted can still be used.

In some embodiments, step S140 is implemented based on a data regression analysis method, and regression analysis is performed on the life of the probe to be predicted based on the acquired performance test data, so as to determine the life of the probe to be predicted. For example, the life of the probe to be predicted is determined as Y years, Y > 0. For a specific method of data regression analysis, please refer to related technologies, which are not described in detail herein.

In some embodiments, the step S140 is implemented based on a data analysis method, and the life of the probe to be predicted is analyzed based on the acquired performance test data, so as to determine a life range to which the life of the probe to be predicted belongs. For example, it is determined that the life of the probe to be predicted is Y₁Year to Y₂Year, Y₂>Y₁>0. For a specific method of data analysis, please refer to related arts, which is not described in detail herein.

Compared with the method for determining the service life of the probe based on all the test data of all the performance indexes of the probe, the method for determining the service life of the probe based on the performance test data of the probe can reduce the data operation amount and is beneficial to improving the data processing efficiency, and on the other hand, the related performance indexes are indexes directly related to the service life of the probe, so that the service life of the probe can be predicted more accurately based on the performance test data of the related performance indexes.

In some embodiments, step S140 is implemented based on artificial intelligence techniques. FIG. 3 is an exemplary flowchart of step S140 in a method of probe life prediction according to some embodiments described herein. Please refer to fig. 4, the step S140 will be described in detail. As shown in fig. 3, step S140 includes the steps of:

step S141, determining a weight of the at least one relevant performance indicator based on the ranking result.

The weights are used to characterize the degree of correlation of the relevant performance indicators with the life of the probe to be predicted. For example, relevant performance indicators include: performance index 1 (e.g., spring force F), performance index 2 (e.g., impedance Z), … …, performance index n, where the correlation of performance index 1 (e.g., spring force F) with lifetime is greater than the correlation of performance index 2 (e.g., impedance Z), the weight of performance index 1 (e.g., spring force F) may be determined as Z₁The weight of performance index 2 (e.g., impedance Z) is determined as Z₂，z₁>z₂>0。

In the sub-step of step S122, the relevant performance indicators and the ranking results thereof are output, and the weight of each relevant performance indicator is determined based on the ranking results. In some embodiments, when the ranking result is an ascending ranking, the higher the weight value of the associated performance indicators; when the sorting result is a descending sort, the weight value of the related performance index at the later stage is larger. For example, the sort result (descending sort) is: performance index 1 (e.g., spring force F), performance index 2 (e.g., impedance Z), … …, performance index n. Then the weight of performance index 1 (e.g., spring force F) can be determined as z₁The weight of the performance index 1 (e.g., the elastic force F) is determined as z₂… …, determining the weight of the performance index n as z_n，z₁>z₂>z_n>0。

And step S142, combining the weight of the at least one relevant performance index, inputting the performance test data of the at least one relevant performance index into a pre-trained life prediction model, and determining the life of the probe to be predicted.

The probe life prediction model is obtained by training a second preset model by using performance sample parameters of various relevant performance indexes corresponding to the sample probes and preset weights of the relevant performance indexes. The second predetermined model may be a regression model, and the second predetermined model may also be a classification model. The training is supervised learning, and when the second preset model can be a regression model, a supervision signal is the actual life of the sample probe corresponding to the performance sample parameter; when the second predetermined model may be a classification model, the supervision signal is a life span of the sample probe corresponding to the performance sample parameter. The training of the life prediction model may specifically include: and constructing a loss function based on the actual service life of the sample probe (or the service life range of the probe) and the prediction result of the model, iteratively updating parameters of the second preset model based on the loss function until preset conditions are met, and stopping training. The preset conditions may include: the number of iterations reaches a threshold number, the loss function converges, etc.

In some embodiments, the relevance prediction model (ranking model) and the lifetime prediction model are jointly trained on the first preset model and the second preset model. The training process comprises the following steps:

a. in each training round, obtaining a sample test data pair and a performance index label corresponding to the sample test data pair;

b. inputting the sample test data pair into a first preset model, and performing current round training on the first preset model by combining with a corresponding performance index label of the sample test data pair;

c. determining the current round weight of each relevant performance index in the at least one relevant performance index output by the first preset model in the current training round according to the at least one relevant performance index output by the first preset model in the current training round and the sequencing result of the at least one relevant performance index output by the first preset model in the current training round;

d. acquiring performance sample parameters of various performance indexes corresponding to the sample probes;

e. and taking the performance sample parameters of each performance index corresponding to each of the plurality of sample probes as training samples, and finishing the current round training of the first preset model by combining the current round weight of each relevant performance index in at least one relevant performance index output by the first preset model in the current training round.

f. And (4) circulating the steps a-e until a correlation prediction model (a sequencing model) and a service life prediction model are obtained.

As shown in fig. 4, the performance test data corresponding to each performance index with the determined weight is input into a pre-trained life prediction model for processing, so as to obtain the life of the probe to be predicted. For example, the performance index n determines the weight of the performance index 1 (elastic force F) as z₁The weight of the performance index 2 (impedance Z) is determined as Z₂… …, determining the weight of the performance index n as z_n，z₁>z₂>z_n>Performance index n performance test data 1 for performance index 1 (spring force F) are: f₁、F₂The performance test data 2 of the performance index 2 (impedance Z) is: z₁、Z₂The performance test data n of the performance index n is as follows: g₁(Performance test data 1), G₂(Performance test data 2), …, G_K(Performance test data K), wherein K>0, K is a positive integer, G_KKth individual performance test data representing a performance index n; will z₁F₁、z₁F₂、z₁Z₁、z₁Z₂、z_nG₁、z_nG₂、…、z_nG_kAnd inputting the service life prediction model for processing, and determining that the service life of the probe to be predicted is Y years. The above manner of giving the weight corresponding to each performance index to the performance test data corresponding to each performance index is only an example, and in some embodiments, the weight and the performance test data corresponding to each performance index may be fused in other manners, so that the model may combine each performance index when predicting the lifeThe importance of the target is determined and is not limited herein.

And determining the correlation between each related performance index and the service life of the probe according to the sequencing result, and determining the weight of each related performance index according to the correlation (namely the sequencing result), so that the correlation of the influence of different related performance indexes on the service life of the probe can be combined when the service life prediction model is processed, and the result output by the service life prediction model when the service life is predicted is more accurate.

The method comprises the steps of comparing data for testing the performance of a tested object based on a probe to be predicted with data for testing the performance of the same tested object based on a reference probe, determining performance indexes (recorded as related performance indexes) related to the service life of the probe from various performance indexes of the probe to be predicted, testing the performance corresponding to the related performance indexes of the probe to be predicted to obtain performance test data corresponding to the related performance indexes, and predicting the service life of the probe to be predicted based on the performance test data corresponding to the related performance indexes. The technical difficulty of service life prediction of the probe caused by individual difference of the use environment of the probe is overcome, the service life of the probe can be predicted to a certain degree, and certain reference is provided for replacing the probe in advance.

It should be noted that the above description of the flow probe life prediction method is for illustration and description only, and does not limit the scope of the application of the present specification. Various modifications and alterations to the flow probe lifetime prediction method will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are intended to be within the scope of the present description. For example, the correlation prediction model or the lifetime prediction model described above is simply transformed.

In order to better implement the method, an embodiment of the present invention further provides a probe life prediction system, where the probe life prediction system may be specifically integrated in an electronic device, and the electronic device may be a terminal, a server, or other devices. The terminal can be a mobile phone, a tablet computer, an intelligent Bluetooth device, a notebook computer, a personal computer and other devices; the server may be a single server or a server cluster composed of a plurality of servers.

FIG. 5 is a schematic diagram of an exemplary configuration of a probe life prediction system in accordance with some embodiments of the present description. As shown in fig. 5, in some embodiments, the probe life prediction system 500 may include a first acquisition module 501, a correlation determination module 502, a second acquisition module, and a life prediction module 503.

The first obtaining module 501 is configured to obtain experimental group data and reference group data of a plurality of objects to be tested, where the experimental group data is obtained by testing the performance of the plurality of objects to be tested based on a probe to be predicted, and the reference group data is obtained by testing the performance of the plurality of objects to be tested based on a reference probe;

the correlation determination module 502, based on the experimental group data and the reference group data, determines at least one relevant performance indicator of the probe to be predicted, the at least one relevant performance indicator being related to the lifetime of the probe to be predicted;

the second obtaining module 503 is configured to obtain performance test data of the at least one relevant performance indicator;

the life prediction module 504 is configured to predict the life of the probe to be predicted based on the performance test data of the at least one relevant performance indicator.

In some embodiments, the relevance determination module comprises:

the data pair construction sub-module is used for constructing at least one pair of test data pairs based on at least one experimental test data in the experimental group data and at least one reference test data in the reference group data, and the types of the reference test data and the experimental test data in the at least one pair of test data pairs are the same;

and the correlation determination submodule is used for inputting the at least one pair of test data into a pre-trained correlation prediction model to obtain the at least one correlation performance index.

In some embodiments, the pre-trained relevance prediction model comprises a ranking model; the correlation determination submodule includes:

and the sequencing unit is used for inputting the at least one pair of test data into the sequencing model to obtain a sequencing result of at least one relevant performance index, and the sequencing result represents the correlation degree between each relevant performance index in the at least one relevant performance index and the service life of the probe to be predicted.

In some embodiments, the life prediction module comprises:

a weight determination submodule for determining a weight of the at least one relevant performance indicator based on the ranking result;

and the life prediction submodule is used for inputting the performance test data of the at least one relevant performance index into a pre-trained life prediction model by combining the weight of the at least one relevant performance index, and determining the life of the probe to be predicted.

It should be understood that the system and its modules shown in FIG. 5 may be implemented in a variety of ways. For example, in some embodiments, the probe life prediction system and its modules may be integrated into an electronic device, which may be a terminal, a server, or the like.

In a specific implementation, each module and/or unit may be implemented as an independent entity, or may be combined arbitrarily and implemented as one or several entities, and specific implementations of each unit may refer to the foregoing method embodiments, and are not described herein again.

It should be noted that the above descriptions of the candidate item display and determination system and the modules thereof are only for convenience of description, and the description is not limited to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the first obtaining module, the correlation determining module, the second obtaining module, and the life predicting module disclosed in fig. 5 may be different modules in one system, or may be one module that implements the functions of two or more of the above modules. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

The embodiment of the invention also provides the electronic equipment which can be equipment such as a terminal, a server and the like. The terminal can be a mobile phone, a tablet computer, an intelligent Bluetooth device, a notebook computer, a personal computer and the like; the server may be a single server, a server cluster composed of a plurality of servers, or the like.

In some embodiments, the probe life prediction device may be integrated into a plurality of electronic devices, for example, the probe life prediction device may be integrated into a plurality of servers, and the probe life prediction method of the present invention is implemented by the plurality of servers.

In this embodiment, the electronic device of this embodiment is described in detail as an example of a computer, for example, the computer may include one or more processors of a processing core, one or more memories of a computer-readable storage medium, a power supply, an input module, and a communication module. Wherein:

the processor is a control center of the computer, connects various parts of the whole computer by various interfaces and lines, and performs various functions and processes data by running or executing software programs and/or modules stored in the memory and calling data stored in the memory, thereby performing overall monitoring. In some embodiments, a processor may include one or more processing cores; in some embodiments, the processor may integrate an application processor that handles primarily operating systems, user interfaces, applications, etc., and a modem processor that handles primarily wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor.

The memory may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the computer, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.

The computer also includes a power supply for supplying power to the various components, and in some embodiments, the power supply may be logically coupled to the processor via a power management system, such that the power management system may manage charging, discharging, and power consumption. The power supply may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The computer may also include an input module operable to receive entered numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

The computer may also include a communication module, which in some embodiments may include a wireless module, through which the computer may wirelessly transmit over short distances, thereby providing wireless broadband internet access to the user. For example, the communication module may be used to assist a user in emailing, browsing web pages, accessing streaming media, and the like.

Although not shown, the computer may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, a processor in the computer loads an executable file corresponding to a process of one or more application programs into a memory according to the following instructions, and the processor runs the application programs stored in the memory, thereby implementing various functions as follows:

acquiring experimental group data and reference group data of a plurality of tested objects, wherein the experimental group data is data obtained by testing the performance of the plurality of tested objects by a probe to be predicted, and the reference group data is data obtained by testing the performance of the plurality of tested objects by a reference probe;

determining at least one relevant performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one relevant performance indicator being related to the life of the probe to be predicted;

obtaining performance test data of the at least one relevant performance index;

and predicting the service life of the probe to be predicted based on the performance test data.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

As can be seen from the above, data obtained by testing the performance of a tested object based on a probe to be predicted is compared with data obtained by testing the performance of the same tested object based on a reference probe, a performance index (referred to as a related performance index) related to the life of the probe is determined from various performance indexes of the probe to be predicted, the performance corresponding to the related performance index of the probe to be predicted is tested to obtain performance test data corresponding to the related performance index, and the life of the probe to be predicted is predicted based on the performance test data corresponding to the related performance index. The technical difficulty of service life prediction of the probe caused by individual difference of the use environment of the probe is overcome, the service life of the probe can be predicted to a certain degree, and certain reference is provided for replacing the probe in advance.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, embodiments of the present invention provide a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the probe life prediction methods provided by the embodiments of the present invention. For example, the instructions may perform the steps of:

acquiring experimental group data and reference group data of a plurality of tested objects, wherein the experimental group data is data obtained by testing the performance of the plurality of tested objects by a probe to be predicted, and the reference group data is data obtained by testing the performance of the plurality of tested objects by a reference probe;

determining at least one relevant performance indicator of the probe to be predicted based on the experimental group data and the reference group data, the at least one relevant performance indicator being related to the life of the probe to be predicted;

obtaining performance test data of the at least one relevant performance index;

and predicting the service life of the probe to be predicted based on the performance test data.

Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the method of providing probe life prediction in the various alternative implementations provided in the embodiments described above.

Since the instructions stored in the storage medium may execute the steps in any of the probe life prediction methods provided by the embodiments of the present invention, the beneficial effects that can be achieved by any of the probe life prediction methods provided by the embodiments of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described again here.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.