1. A method for analyzing a fusion relationship, comprising:

acquiring event record information, wherein the event record information comprises: determining the incidence relation of related personnel in each event type according to the event record information;

determining a first affinity score of two persons about an incidence relation through the occurrence attribute of the incidence relation of the two persons, wherein the occurrence attribute comprises occurrence times and occurrence time;

acquiring first affinity scores of multiple incidence relations of two persons, and determining a second affinity score according to the first affinity scores of the multiple incidence relations;

and performing fusion relation analysis on the personnel to be analyzed through the second intimacy degree score.

2. The fusion relationship analysis method according to claim 1, wherein the occurrence number includes a historical total number and a recent number, and the occurrence time further includes a time from the most recent association relationship to the current time.

3. The fusion relationship analysis method according to claim 1 or 2, wherein the mathematical expression of the first affinity score is:

wherein f is_intimacy(R_iA → b) is that persons a and b are about event type R_iA first affinity score of; c. C_pThe number of times in the near term; c. C_tIs the total number of times of history; g_tA coefficient which influences the increase of the intimacy score for the total historical times; g_pA coefficient that influences the increase of the intimacy score for the recent increase; d is the influence coefficient of the lowest value reserved by the intimacy degree score when the recent times are 0; t is t_lThe time from the last incidence relation to the current time; g_lIs t_lThe coefficient that increases has an effect on the increase in the intimacy score.

4. The fusion relationship analysis method according to claim 3, wherein the mathematical expression of the second affinity score is:

wherein, F_intimacy(a → b) is the second affinity score, max (f), for persons a and b_intimacy(R_iA → b)) is the maximum value of the first affinity score for persons a and b, avg (f)_intimacy(R_iA → b)) is the average of the first affinity scores of the persons a and b, n is the number of event types of the persons a and b, g_aThe coefficient that has an effect on increasing the intimacy score is n.

5. The fusion relationship analysis method according to claim 1, wherein the step of performing the fusion relationship analysis on the person to be analyzed by the second affinity score includes:

establishing a fusion relationship between the personnel and the second affinity scores, and synchronizing the fusion relationship to a graph database;

and processing the intimacy of the person to be analyzed by utilizing the fusion relation.

6. A fused relationship analysis system, comprising:

the data acquisition module is used for acquiring event record information, wherein the event record information comprises: determining the incidence relation of related personnel in each event type according to the event record information;

the system comprises a relationship analysis module, a correlation analysis module and a correlation analysis module, wherein the relationship analysis module is used for determining first intimacy scores of two persons about the correlation according to occurrence attributes of the correlation of the two persons, the occurrence attributes comprise occurrence times and occurrence time, the first intimacy scores of various correlations of the two persons are obtained, and a second intimacy score is determined according to the first intimacy scores of various correlations;

the relationship mining module is used for carrying out fusion relationship analysis on the personnel to be analyzed through the second intimacy degree score;

the data acquisition module, the relation analysis module and the relation mining module are in signal connection.

7. The fused relationship analysis system of claim 6, further comprising:

the synchronization module is used for establishing a fusion relationship among the personnel, the association relationship and the second affinity score and synchronizing the fusion relationship to a graph database;

and the interface module is used for providing an access interface and connecting the relationship mining module.

8. The fused relationship analysis system according to claim 6, wherein the number of occurrences comprises a total number of histories and a recent number, and the time of occurrence further comprises a time from the most recent association to the current time.

9. An electronic device, comprising:

one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the method recited in any of claims 1-5.

10. A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the method of any of claims 1-5.

Background

With the rapid development of the industries such as social contact, e-commerce, finance, retail, internet of things and the like, a huge and complex relationship network is organized in the real society, and the traditional database is difficult to process relationship operation. The relationship between data needing to be processed in the big data industry increases in a geometric progression along with the data volume, and a database for supporting massive complex data relational operation, such as a database, is also needed.

In a graph database, data is stored in a graph manner, the most important elements of the data structure are nodes and relations, each node represents an entity, such as a person, an object, a place, a category or other data, and each relation represents an event type between two entities, such as a connection relation between objects, a social relation between persons, an attribution relation between persons and objects, and the like. Compared with the traditional database, the storage mode of the method more intuitively reflects the complex relationship between the entities, and meanwhile, the method has extremely high efficiency in relation query and calculation.

The relationship map can be based on a map database, and various entities and relationships among the entities are collected and stored in the map database after being refined, so that further data mining, retrieval, analysis and other applications can be facilitated. According to different application requirements, the relationship graph has different emphasis points on the content structure, such as a character relationship graph, a knowledge graph, a recommendation system, bank fraud detection and the like.

The person relationship graph stores connection relationships between persons, such as family consanguinity relationships, communication relationships, social relationships and the like. When a person relationship map is constructed, various relationships often exist between persons, and the complicated relationship brings trouble in two aspects to users. Firstly, effective information cannot be visually displayed in numerous relationships, and key attention objects cannot be screened and excluded; and secondly, an effective weight index is not convenient to provide as a judgment basis for the strength of the relationship.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, the present invention provides a method and a system for analyzing a fusion relationship, which are used to solve the problem that it is inconvenient to analyze various relationships between people in the prior art.

To achieve the above and other related objects, the present invention provides a fusion relationship analysis method, including:

acquiring event record information, wherein the event record information comprises: determining the incidence relation of related personnel in each event type according to the event record information;

determining a first affinity score of two persons about an incidence relation through the occurrence attribute of the incidence relation of the two persons, wherein the occurrence attribute comprises occurrence times and occurrence time;

acquiring first affinity scores of multiple incidence relations of two persons, and determining a second affinity score according to the first affinity scores of the multiple incidence relations;

and performing fusion relation analysis on the personnel to be analyzed through the second intimacy degree score.

Optionally, the occurrence number includes a total historical number and a recent number, and the occurrence time further includes a time from the last association relationship to the current time.

Optionally, the mathematical expression of the first affinity score is:

wherein f is_intimacy(R_iA → b) is that persons a and b are about event type R_iA first affinity score of; c. C_pThe number of times in the near term; c. C_tIs the total number of times of history; g_tA coefficient which influences the increase of the intimacy score for the total historical times; g_pA coefficient that influences the increase of the intimacy score for the recent increase; d is the influence coefficient of the lowest value reserved by the intimacy degree score when the recent times are 0; t is t_lThe time from the last incidence relation to the current time; g_lIs t_lThe coefficient that increases has an effect on the increase in the intimacy score.

Optionally, the mathematical expression of the second affinity score is:

wherein, F_intimacy(a → b) is the second affinity score, max (f), for persons a and b_intimacy(R_iA → b)) is the maximum value of the first affinity score for persons a and b, avg (f)_intimacy(R_iA → b)) is the average of the first affinity scores of the persons a and b, n is the number of event types of the persons a and b, g_aThe coefficient that has an effect on increasing the intimacy score is n.

Optionally, the step of performing fusion relationship analysis on the person to be analyzed through the second affinity score includes:

establishing a fusion relationship between the personnel and the second affinity scores, and synchronizing the fusion relationship to a graph database;

and processing the intimacy of the person to be analyzed by utilizing the fusion relation.

A fused relationship analysis system comprising:

the data acquisition module is used for acquiring event record information, wherein the event record information comprises: determining the incidence relation of related personnel in each event type according to the event record information;

the system comprises a relationship analysis module, a correlation analysis module and a correlation analysis module, wherein the relationship analysis module is used for determining first intimacy scores of two persons about the correlation according to occurrence attributes of the correlation of the two persons, the occurrence attributes comprise occurrence times and occurrence time, the first intimacy scores of various correlations of the two persons are obtained, and a second intimacy score is determined according to the first intimacy scores of various correlations;

the relationship mining module is used for carrying out fusion relationship analysis on the personnel to be analyzed through the second intimacy degree score;

the data acquisition module, the relation analysis module and the relation mining module are in signal connection.

Optionally, the system for analyzing fusion relationship further includes:

the synchronization module is used for establishing a fusion relationship among the personnel, the association relationship and the second affinity score and synchronizing the fusion relationship to a graph database;

and the interface module is used for providing an access interface and connecting the relationship mining module.

Optionally, the occurrence number includes a total historical number and a recent number, and the occurrence time further includes a time from the last association relationship to the current time.

An electronic device, comprising:

one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform any of the methods.

A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform any of the methods described.

As described above, the fusion relationship analysis method and system of the present invention have the following advantages:

and taking the event type, the occurrence frequency and the occurrence time in the association relationship as weights or influence factors, acquiring first affinity scores of the two persons about the event type under the condition of single dimension, acquiring second affinity scores of the two persons under the condition of multiple dimensions according to the first affinity scores of multiple event types, determining the association between the persons according to the second affinity scores, and providing reference values for subsequent analysis and mining.

Drawings

Fig. 1 is a schematic flow chart of a fusion relationship analysis method according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of a fusion relation analysis system according to an embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a fusion relation analysis system according to another embodiment of the present invention.

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.

It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated. The structures, proportions, sizes, and other dimensions shown in the drawings and described in the specification are for understanding and reading the present disclosure, and are not intended to limit the scope of the present disclosure, which is defined in the claims, and are not essential to the art, and any structural modifications, changes in proportions, or adjustments in size, which do not affect the efficacy and attainment of the same are intended to fall within the scope of the present disclosure. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.

Referring to fig. 1, an embodiment of the invention provides a fusion relationship analysis method, including:

s1: acquiring event record information, wherein the event record information comprises: and determining the association relationship between the persons related to each event type according to the event record information, for example, the event record information about the accommodation includes the person who lives with the event record information and the time type of the living with the event record information, and the manner of acquiring the event record information may be at least one of the following: the big data platform accesses and collects an original data set, lists the original data set by collecting and summarizing a plurality of event record information, determines the correlation information of related personnel in each event type, and can upload the personnel, the event type and the correlation relationship to a local system or a server;

s2: determining first affinity scores of two persons about an incidence relation through an occurrence attribute of the incidence relation of the two persons, wherein the occurrence attribute comprises occurrence times and occurrence time, the occurrence times of the incidence relation are positively correlated with the affinity of the incidence relation between the two persons to a certain extent, and the first affinity scores of the two persons about the event type can be obtained through the occurrence times of the incidence relation of the two persons under the condition of single dimensionality, for example, the persons and the incidence relation can be added into a relation list of a database according to the occurrence time as an index, and the database can adopt a relational database;

s3: acquiring first intimacy scores of multiple incidence relations of two persons, determining second intimacy scores according to the first intimacy scores of the multiple incidence relations, acquiring second intimacy scores of the two persons about various event types under the condition of multiple dimensions, and taking the second intimacy scores as judgment indexes for judging intimacy of fusion relations between the two persons;

s4: and performing fusion relation analysis on the personnel to be analyzed through the second intimacy degree score. For example, a fusion relationship between the person and the second affinity score is established, a person is queried for associated persons/important persons with a higher second affinity score, and the associated persons/important persons corresponding to the person are queried by using the second affinity score as a weight. And taking the event type, the occurrence frequency and the occurrence time in the association relationship as weights or influence factors, acquiring first affinity scores of the two persons about the event type under the condition of single dimension, acquiring second affinity scores of the two persons under the condition of multiple dimensions according to the first affinity scores of multiple event types, determining the association between the persons according to the second affinity scores, and providing reference values for subsequent analysis and mining.

In some implementations, the number of times the association occurs includes at least one of: total number of history times and recent times. For example, the historical total number of times includes the number of total correlations of two persons with respect to the occurrence of an event type, the recent number of times includes the number of correlations of two persons with respect to the occurrence of an event type within a recent period including the last one day/month/year, two days/months/years, three days/months/years, … …, n days/months/years, and n is a positive integer. The influence of the historical total times and the recent times is considered, the influence weight of the time factor on the intimacy degree score is improved, the recent times are reduced to represent the reduction of the relation activity, and the intimacy degree score is reduced due to the reduction of the relation generation times in the preset recent time. The occurrence time also includes a time from the last association to the current time.

In order to improve the referential and authenticity of the first affinity score, the recent times of the association relationship of two persons about an event type can be used as a measuring weight or an influence factor, and the historical total times and the influence of the recent times on the first affinity score are comprehensively considered, wherein the mathematical expression of the first affinity score is as follows:

wherein f is_intimacy(R_iA → b) is that persons a and b are about event type R_iA first affinity score of; c. C_pThe number of times in the near term; c. C_tIs the total number of times of history; g_tA coefficient which influences the increase of the intimacy score for the total historical times; g_pA coefficient that influences the increase of the intimacy score for the recent increase; d is the influence coefficient of the lowest value reserved by the intimacy degree score when the recent times are 0; t is t_lThe time from the last incidence relation to the current time; g_lIs t_lThe coefficient that increases has an effect on the increase in the intimacy score. For example, data information of people a and b about the event type as a call can be called from a public security big data platform, and the recent times c can be obtained_pAnd total number of history c_t. For example, the time type is live, the total number of history times is more than 30, and the last time is closedWhen the time of the association relation is 30 days from the current time and the coefficient of the first intimacy score of the recent number of the same live is 10 is 0.8, g can be set_t＝0.3，d＝9，g_p＝4，g_l＝0.004。

An event type of one type can only measure the intimacy score between two persons about the specific type from a single dimension, so the purpose of measuring the intimacy of the two persons about various event types under the condition of multiple dimensions can be achieved by acquiring corresponding first intimacy scores of the event types of the two persons, wherein the mathematical expression of the second intimacy score is as follows:

wherein, F_intimacy(a → b) is the second affinity score, max (f), for persons a and b_intimacy(R_iA → b)) is the maximum value of the first affinity score for persons a and b, avg (f)_intimacy(R_iA → b)) is the average of the first affinity scores of the persons a and b, n is the number of event types of the persons a and b, g_aThe coefficient that has an effect on increasing the intimacy score is n. The method avoids the situation that the influence weight of individual event types on the intimacy degree score is high, so that useful information is not convenient to screen and useless information is not convenient to eliminate. The incidence relation of the event type with the highest first affinity score is used as a basic value, the average value of the first affinity scores of the incidence relations of other event types is used as an additional value, when the incidence relation quantity is more and the average value is higher, the obtained result of the second affinity score is higher, the situation that the overall score of the second affinity score is lowered after a new incidence relation with a lower first affinity score is added can be avoided, and the measuring accuracy of the second affinity score is improved.

In some implementations, the step of performing a fusion relationship analysis on the person to be analyzed by the second affinity score includes:

establishing a fusion relationship between the personnel and the second affinity score, for example, establishing database information by adopting Python language, and synchronizing the association relationship to a big data platform or a database;

and processing the intimacy of the person to be analyzed through the fusion relationship.

In some implementations, the persons and the corresponding fusion relations may be acquired from a public security big data platform or another information platform, and the detail data may be acquired by processing types of events among the persons, where the types of events include at least one of: a conversation, a peer, a co-residence, a relative, a colleague, wherein a peer also includes boarding the same vehicle, e.g., a train, a bus, a flight, a cargo ship.

Referring to fig. 2, in an embodiment of the present invention, a fusion relationship analysis system is further provided, including:

the data acquisition module is used for acquiring event record information, wherein the event record information comprises: determining the incidence relation of related personnel in each event type according to the event record information;

the system comprises a relationship analysis module, a correlation analysis module and a correlation analysis module, wherein the relationship analysis module is used for determining first intimacy scores of two persons about the correlation according to occurrence attributes of the correlation of the two persons, the occurrence attributes comprise occurrence times and occurrence time, the first intimacy scores of various correlations of the two persons are obtained, and a second intimacy score is determined according to the first intimacy scores of various correlations;

the relationship mining module is used for carrying out fusion relationship analysis on the personnel to be analyzed through the second intimacy degree score;

the data acquisition module, the relation analysis module and the relation mining module are in signal connection.

Optionally, the occurrence number includes a total historical number and a recent number, and the occurrence time further includes a time from the last association relationship to the current time.

Optionally, the mathematical expression of the first affinity score is:

wherein f is_intimacy(R_iA → b) is that persons a and b are about event type R_iA first affinity score of; c. C_pThe number of times in the near term; c. C_tIs the total number of times of history; g_tA coefficient which influences the increase of the intimacy score for the total historical times; g_pA coefficient that influences the increase of the intimacy score for the recent increase; d is the influence coefficient of the lowest value reserved by the intimacy degree score when the recent times are 0; t is t_lThe time from the last incidence relation to the current time; g_lIs t_lThe coefficient that increases has an effect on the increase in the intimacy score.

Optionally, the mathematical expression of the second affinity score is:

wherein, F_intimacy(a → b) is the second affinity score, max (f), for persons a and b_intimacy(R_iA → b)) is the maximum value of the first affinity score for persons a and b, avg (f)_intimacy(R_iA → b)) is the average of the first affinity scores of the persons a and b, n is the number of event types of the persons a and b, g_aThe coefficient that has an effect on increasing the intimacy score is n.

Optionally, the step of performing fusion relationship analysis on the person to be analyzed through the second affinity score includes:

establishing a fusion relationship of the personnel, the incidence relationship and the second intimacy degree score, and synchronizing the fusion relationship to a graph database;

and processing the intimacy of the person to be analyzed by utilizing the fusion relation.

Referring to fig. 3, another embodiment of the present invention further provides a fusion relationship analysis system, which further includes:

the synchronization module is used for establishing a fusion relationship between the personnel and the second affinity scores and synchronizing the fusion relationship to the graph database;

and the interface module is used for providing an access interface and connecting the relationship mining module, and can access the graph database of the relationship mining module and inquire the required fusion relationship of the personnel based on the java development back-end interface module.

An embodiment of the present invention provides an electronic device, including: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform one or more of the methods. The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

Embodiments of the invention also provide one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods described herein. The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.