1. An index correlation analysis method is characterized by comprising the following steps:

acquiring a target index of an object in a selected time range;

calculating the degree of association between the target index and each index; wherein the correlation comprises a positive correlation and a negative correlation;

acquiring a preset number of association indexes according to the association degree and a preset threshold value;

sorting the associated indexes from high to low according to the magnitude of the association degree, dividing the associated indexes of the preset number into N areas according to a sorting result, and displaying the associated indexes, wherein the associated indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the associated indexes displayed in the last 1 areas are in dotted distribution; the index name and the sorting sequence number are in direct proportion to the relevance, and N is a positive integer greater than 1.

2. The index association analysis method according to claim 1, wherein the calculating of the degree of association between the target index and each index includes:

calculating a unit rate of change of the target index, and calculating a unit rate of change of the index;

determining a change level of the target index according to a unit change rate of the target index, and determining a change level of the index according to a unit change rate of the index;

calculating a grade difference value between the change grade of the target index and the change grade of the index, acquiring an absolute value of the grade difference value, and calculating an average value corresponding to the absolute value of the grade difference value in the selected time range;

calculating the change grade of the target index and the grade and value of the change grade of the index, acquiring the absolute value of the grade and value, and calculating the average value corresponding to the absolute value of the grade and value in the selected time range;

when the average value corresponding to the absolute value of the grade difference is larger than the average value corresponding to the absolute value of the grade sum, taking the average value corresponding to the absolute value of the grade difference as a positive correlation coefficient, and mapping the positive correlation coefficient to a range from zero to one as the degree of correlation between the target index and each index;

and under the condition that the average value corresponding to the absolute value of the grade difference value is less than or equal to the average value corresponding to the absolute value of the grade sum value, taking the average value corresponding to the absolute value of the grade sum value as a negative correlation coefficient, and mapping the negative correlation coefficient to a range from zero to one as the degree of association between the target index and each index.

3. The index correlation analysis method according to claim 1, wherein the obtaining of a preset number of correlation indexes according to the correlation degree and a preset threshold value comprises:

and the association degrees are sorted from large to small according to numerical values, the association degrees are compared with the preset threshold value, and the pre-sorting preset quantity association index with the association degrees larger than the preset threshold value is obtained.

4. The index relevance analysis method according to claim 1, wherein the relevance indexes are sorted from high to low according to the relevance degree, the relevance indexes of the preset number are divided into N areas according to the sorting result, the relevance indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the relevance indexes displayed in the last 1 area are in point distribution; wherein, the index name and the sorting sequence number are in direct proportion to the degree of association, and N is a positive integer greater than 1, and the method includes:

taking the association degree as a horizontal axis coordinate; wherein the coordinate value of the abscissa corresponds to the magnitude of the degree of association from high to low from left to right;

dividing the longitudinal axis region corresponding to the horizontal axis coordinate into N regions for display, displaying the index name and the sequencing sequence number with positive correlation of the correlation degree in the first N-1 regions corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the index name and the sequencing sequence number with negative correlation of the correlation degree in the first N-1 regions corresponding to the negative longitudinal axis direction of the horizontal axis coordinate; the index name and the sorting serial number are in direct proportion to the relevance degree;

and displaying the correlation index with the correlation degree as positive correlation in a dot distribution form in the last 1 area corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the correlation index with the correlation degree as negative correlation in a dot distribution form in the last 1 area corresponding to the negative longitudinal axis direction of the horizontal axis coordinate.

5. The index association analysis method according to any one of claims 1 to 4, characterized by further comprising:

receiving a click request; the click request comprises a correlation index to be inquired;

and acquiring and displaying the index association degree and the index ring ratio information of the associated index to be inquired.

6. The index association analysis method according to claim 5, further comprising:

displaying a plurality of associated indexes and index relevance and index ring ratio information of each associated index in a target area in a list form according to the index relevance;

and when the click request is received, positioning the correlation index to be queried in the list, and displaying the index correlation degree, the index ring ratio information and the detail link of the correlation index to be queried.

7. The index association analysis method according to claim 6, further comprising:

and clicking the detail link, and jumping to a detail page for intelligent analysis of the correlation index to be inquired.

8. The index association analysis method according to claim 4, further comprising:

and adjusting the size of the index name according to the value of the association degree.

9. The index association analysis method according to claim 4, further comprising:

and displaying the N areas through different colors to distinguish the relevance degree of the target index and the relevance index.

10. The index association analysis method according to claim 1, further comprising:

and adjusting the preset threshold value.

Background

Currently, association analysis is widely applied to precise marketing in the e-commerce industry, such as commodity recommendation, promotion of gift bags or preferential combination sets.

However, in the related art, as long as the association analysis is performed by data mining, the association data cannot be displayed visually, and the subsequent processing efficiency is low.

Disclosure of Invention

In order to solve the technical problem described above or at least partially solve the technical problem described above, the present disclosure provides an index association analysis method.

The present disclosure provides an index relevance analysis method, including:

acquiring a target index of an object in a selected time range;

calculating the degree of association between the target index and each index; wherein the correlation comprises a positive correlation and a negative correlation;

acquiring a preset number of association indexes according to the association degree and a preset threshold value;

sorting the associated indexes from high to low according to the magnitude of the association degree, dividing the associated indexes of the preset number into N areas according to a sorting result, and displaying the associated indexes, wherein the associated indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the associated indexes displayed in the last 1 areas are in dotted distribution; the index name and the sorting sequence number are in direct proportion to the relevance, and N is a positive integer greater than 1.

In an optional embodiment of the present disclosure, the calculating a degree of association between the target index and each index includes:

calculating a unit rate of change of the target index, and calculating a unit rate of change of the index;

determining a change level of the target index according to a unit change rate of the target index, and determining a change level of the index according to a unit change rate of the index;

calculating a grade difference value between the change grade of the target index and the change grade of the index, acquiring an absolute value of the grade difference value, and calculating an average value corresponding to the absolute value of the grade difference value in the selected time range;

calculating the change grade of the target index and the grade and value of the change grade of the index, acquiring the absolute value of the grade and value, and calculating the average value corresponding to the absolute value of the grade and value in the selected time range;

when the average value corresponding to the absolute value of the grade difference is larger than the average value corresponding to the absolute value of the grade sum, taking the average value corresponding to the absolute value of the grade difference as a positive correlation coefficient, and mapping the positive correlation coefficient to a range from zero to one as the degree of correlation between the target index and each index;

and under the condition that the average value corresponding to the absolute value of the grade difference value is less than or equal to the average value corresponding to the absolute value of the grade sum value, taking the average value corresponding to the absolute value of the grade sum value as a negative correlation coefficient, and mapping the negative correlation coefficient to a range from zero to one as the degree of association between the target index and each index.

In an optional embodiment of the present disclosure, the obtaining a preset number of association indexes according to the association degree and a preset threshold includes:

and the association degrees are sorted from large to small according to numerical values, the association degrees are compared with the preset threshold value, and the pre-sorting preset quantity association index with the association degrees larger than the preset threshold value is obtained.

In an optional embodiment of the present disclosure, the associated indexes are sorted from high to low according to the degree of association, and the associated indexes of the preset number are divided into N regions according to a sorting result for display, where the associated indexes displayed in the first N-1 regions include an index name and a sorting sequence number, and the associated indexes displayed in the last 1 regions are in a dotted distribution; wherein, the index name and the sorting sequence number are in direct proportion to the degree of association, and N is a positive integer greater than 1, and the method includes:

taking the association degree as a horizontal axis coordinate; wherein the coordinate value of the abscissa corresponds to the magnitude of the degree of association from high to low from left to right;

dividing the longitudinal axis region corresponding to the horizontal axis coordinate into N regions for display, displaying the index name and the sequencing sequence number with positive correlation of the correlation degree in the first N-1 regions corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the index name and the sequencing sequence number with negative correlation of the correlation degree in the first N-1 regions corresponding to the negative longitudinal axis direction of the horizontal axis coordinate; the index name and the sorting serial number are in direct proportion to the relevance degree;

and displaying the correlation index with the correlation degree as positive correlation in a dot distribution form in the last 1 area corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the correlation index with the correlation degree as negative correlation in a dot distribution form in the last 1 area corresponding to the negative longitudinal axis direction of the horizontal axis coordinate.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

receiving a click request; the click request comprises a correlation index to be inquired;

and acquiring and displaying the index association degree and the index ring ratio information of the associated index to be inquired.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

displaying the plurality of related indexes and the index relevance and index ring ratio information of each related index in a target area in a list form according to the index relevance;

and when the click request is received, positioning the correlation index to be queried in the list, and displaying the index correlation degree, the index ring ratio information and the detail link of the correlation index to be queried.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

and clicking the detail link, and jumping to a detail page for intelligent analysis of the correlation index to be inquired.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

and adjusting the size of the index name according to the value of the association degree.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

and displaying the N areas through different colors to distinguish the relevance degree of the target index and the relevance index.

In an optional embodiment of the present disclosure, the index association analysis method further includes:

and adjusting the preset threshold value.

Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:

according to the index relevance analysis method provided by the embodiment of the disclosure, the target index of an object in a selected time range is obtained; calculating the association degree of the target index and each index; the correlation degree comprises positive correlation and negative correlation; acquiring a preset number of association indexes according to the association degree and a preset threshold value; sorting the associated indexes from high to low according to the magnitude of the association degree, dividing the associated indexes of a preset number into N areas according to a sorting result, and displaying, wherein the associated indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the associated indexes displayed in the last 1 areas are in dotted distribution; the index name and the sorting serial number are in direct proportion to the relevance. Therefore, the relevance between the target index and the relevant index can be simply and intuitively acquired, so that when data is abnormal, the reason of the data abnormality can be analyzed through the change of the strongly-relevant index, and a business strategy is specified by combining the core index.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

Fig. 1 is a schematic flowchart of an index association analysis method according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart of another index correlation analysis method provided in the embodiment of the present disclosure;

FIG. 3 is a schematic illustration of an information presentation provided by an embodiment of the present disclosure;

fig. 4 is a schematic diagram of another information presentation provided by the embodiments of the present disclosure.

Detailed Description

In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.

At present, an association analysis model widely quoted in enterprises is a very useful data mining model, can help enterprises to do a plurality of very useful product combination recommendations and preferential promotion combinations, and can also guide whether shelf placement is reasonable, and more potential customers can be found, so that data mining is really dropped to the real places.

The index relevance analysis method provided by the disclosure can consider a wider application scene of relevance analysis, when abnormal data problems occur in enterprises, relevance relations also exist among different indexes, and the rising and falling of one index indirectly influence the abnormal fluctuation of other indexes. For example, in order to promote a landing page of a certain activity, an advertisement and a push message are simultaneously delivered by a certain enterprise, so that the opening amount of the advertisement increases, the browsing amount of the landing page increases, and the opening rate of the push decreases within one day. The three indexes occur in different scenes, but are mutually associated and influenced, and the method is suitable for association analysis of abnormal indexes.

Fig. 1 is a schematic flow chart of an index relevance analysis method according to an embodiment of the present disclosure. As shown in fig. 1, the method includes:

step 101, obtaining a target index of an object within a selected time range.

102, calculating the association degree of the target index and each index; wherein the correlation includes a positive correlation and a negative correlation.

The selected time range can be selected and set according to actual application needs, for example, XX pointing in XX month XX day to XX pointing in XX month XX day XX of XX year, an object can also be selected and set according to actual application needs, for example, an advertisement of an enterprise, an application program of the enterprise, popularization information of the enterprise and the like, indexes corresponding to different target objects are different, for example, the target object is the advertisement of the enterprise, the indexes can be indexes such as the opening amount of the advertisement, the pushing amount of the advertisement and the like, the target index is any specified index, the setting can be selected according to needs, and for example, the target object is the application program of the enterprise, the indexes can be the click amount of application program elements, the version stability rate of the application program, the click rate of search results and the like.

The target index is the click rate of the application program element, the index can be the version stability rate of the application program, the click rate of the search result and the like, the index and the target index can be positively correlated, such as the version stability rate of the application program, and the index and the target index can be negatively correlated, such as the click rate of the search result.

In an embodiment of the present disclosure, obtaining the target index of the object in the selected time range includes: and receiving the information selection triggering operation based on the triggering operation of the user on the preset information selection control on the display page, and acquiring the selected time range and the target index. The display page is a page for displaying the index selection, the information selection control is an anchor point arranged in the display page for information selection, the expression form of the information selection control is not limited, and the information selection control can be an icon or text information, for example.

Specifically, a trigger operation of the user on the display page may be detected, and when a click operation or a hover operation of the user on the information selection control is detected, the information selection trigger operation may be received, so as to obtain the selected time range and the target index.

Further, other indexes are obtained, such as a plurality of indexes obtained by querying from a preset list.

Wherein, the relevance refers to the relevance degree of the target index and each index, and comprises positive relevance and negative relevance; the positive correlation can be understood as that the index and the target index have the same ascending/descending trend; negative correlation may be understood as the indicator having an upward/downward trend opposite to the target indicator.

In the embodiment of the disclosure, the change grade of the target index and the change grade of the index may be determined by calculating the unit change rate of the target index and the unit change rate of the index, further determining the target absolute value of the target index and the grade difference value of the index, calculating the absolute value of each grade difference value, taking the grade difference value of the index as a negative value, calculating the absolute value of each grade and the absolute value of each value, and determining whether the index is positively or negatively correlated with the target index according to the average value of the grade difference absolute values in the selected time range and the magnitude value between the average values of the grade and the absolute value in the selected time range.

Wherein the unit rate of change may be a daily rate of change or an hourly rate of change, associated with the selected time range.

And 103, acquiring a preset number of association indexes according to the association degree and a preset threshold value.

The preset threshold may be set according to the application scene needs, and it can be understood that the larger the preset threshold is, the less the obtained association indexes of the preset number may be, and the smaller the preset threshold is, the more the obtained association indexes of the preset number may be.

In the embodiment of the present disclosure, the association degrees may be sorted from large to small according to the numerical values, and the association degrees are compared with the preset threshold, so as to obtain the preset number of association indexes before sorting, such as 100 association indexes, of which the association degrees are greater than the preset threshold.

And 104, sorting the associated indexes from high to low according to the degree of association, dividing the associated indexes of a preset number into N areas according to a sorting result, and displaying the associated indexes, wherein the associated indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the associated indexes displayed in the last 1 area are in point distribution.

The index name and the sorting sequence number are in direct proportion to the relevance, N is a positive integer greater than 1, and the display form can be selected and set according to needs, such as a map, a dot, a list form and the like.

In the embodiment of the present disclosure, the association degree is taken as a horizontal axis coordinate; wherein, the coordinate value of the horizontal axis coordinate corresponds to the degree of association from left to right from high to low; dividing a longitudinal axis region corresponding to a horizontal axis coordinate into N regions for display, displaying the index name and the sequencing sequence number with positive correlation in the first N-1 regions corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the index name and the sequencing sequence number with negative correlation in the first N-1 regions corresponding to the negative longitudinal axis direction of the horizontal axis coordinate; the index name and the sequencing serial number are in direct proportion to the relevance; and displaying the correlation index with positive correlation in a dot distribution form in the last 1 area corresponding to the positive longitudinal axis direction of the horizontal axis coordinate, and displaying the correlation index with negative correlation in a dot distribution form in the last 1 area corresponding to the negative longitudinal axis direction of the horizontal axis coordinate.

According to the index relevance analysis method provided by the embodiment of the disclosure, the target index of an object in a selected time range is obtained; calculating the association degree of the target index and each index; the correlation degree comprises positive correlation and negative correlation; acquiring a preset number of association indexes according to the association degree and a preset threshold value; sorting the associated indexes from high to low according to the magnitude of the association degree, dividing the associated indexes of a preset number into N areas according to a sorting result, and displaying, wherein the associated indexes displayed in the first N-1 areas comprise index names and sorting sequence numbers, and the associated indexes displayed in the last 1 areas are in dotted distribution; the index name and the sorting serial number are in direct proportion to the relevance. Therefore, the relevance between the target index and the relevant index can be simply and intuitively acquired, so that when data is abnormal, the reason of the data abnormality can be analyzed through the change of the strongly-relevant index, and a business strategy is specified by combining the core index.

In some embodiments, the index association analysis method may further include: receiving a click request; the click request comprises the correlation index to be inquired, and index correlation degree and index ring ratio information of the correlation index to be inquired are obtained and displayed.

In some embodiments, the index association analysis method may further include: displaying a plurality of associated indexes, and index association degree and index ring ratio information of each associated index in a target area in a list form according to the size of the index association degree; and when a click request is received, positioning the correlation indexes to be queried in the list, and displaying the index correlation degree, the index ring ratio information and the detail link of the correlation indexes to be queried.

In some embodiments, clicking on the detail link jumps to a detail page of intelligent analysis of the correlation index to be queried.

In the embodiment of the disclosure, the relevance index can be clicked, the relevance index and the index ring ratio information can be displayed, and the list is quickly positioned to the selected index and expanded. After clicking to view details, jumping to an early warning detail page, so that the associated indexes are further known, the associated index information is rapidly and comprehensively known, and analysis is facilitated.

In some embodiments, the index name is resized according to the magnitude value of the degree of association.

In some embodiments, the root displays the N regions in different colors to distinguish the degree of association of the target index with the associated index.

In some embodiments, the preset threshold is adjusted.

In the embodiment of the disclosure, the correlation analysis distribution condition among multiple indexes can be clearly and quickly identified by arranging different display sizes and adjusting the preset threshold value through different region colors.

Fig. 2 is a schematic flow chart of another index relevance analysis method provided in the embodiment of the present disclosure, and the embodiment further optimizes the index relevance analysis method on the basis of the above embodiment. As shown in fig. 2, the method includes:

step 201, receiving an information selection trigger operation based on a trigger operation of a user on a preset information selection control on a display page, and acquiring a target index within a selected time range.

For example, fig. 3 is a schematic diagram of information display provided by an embodiment of the present disclosure, and fig. 3 shows a schematic diagram of a display page, where the display page includes a neutralization target index within a selected time range and a preset information selection control, and when a user triggers the information selection control, the terminal may receive an information selection trigger operation to display the neutralization target index within the selected time range.

Specifically, the target index is application element click, the pull-down list triggers the information selection control, other existing indexes can be switched to serve as the target index, the pull-down list triggers the information selection control, and the selection is carried out according to hours, such as 15 click at 07-month-09 in 2021 to 21 click at 07-month-09 in 2021; on a daily basis, such as 0 o' clock at 29/2021 to 0/07/06/2021 as shown in fig. 3.

Step 202, calculating the unit change rate of the target index, calculating the unit change rate of the index, determining the change level of the target index according to the unit change rate of the target index, and determining the change level of the index according to the unit change rate of the index.

Specifically, the unit change rate may be obtained by, for example, subtracting a difference between a value corresponding to the target index on the second day and a value corresponding to the target index on the first day from the value corresponding to the target index on the second day, and dividing the difference by the value corresponding to the target index on the first day to obtain the unit change rate from the first day to the second day.

Wherein, the preset rule may be-0.03 < change _ ratio <0.03, and change _ level ═ 0; 0.03 ═ change _ ratio <0.1, change _ level ═ 1; 0.1 ═ change _ ratio <0.5, change _ level ═ 2; 0.5 ═ change _ ratio <1, change _ level ═ 3; change _ ratio > 1, change _ level 4; -0.1< change _ ratio < -0.03, change _ level < -1; -0.34< change _ ratio < -0.1, change _ level < -2; -0.5 change _ ratio, -0.34, change _ level, -3; change _ ratio is-0.5 and change _ level is-4.

Wherein, change _ ratio is a unit change rate, and change _ level is a change level.

Step 203, calculating a grade difference between the change grade of the target index and the change grade of the index, acquiring an absolute value of the grade difference, and calculating an average value corresponding to the absolute value of the grade difference in the selected time range.

And 204, calculating the change grade of the target index and the grade and value of the change grade of the index, acquiring the absolute values of the grade and value, and calculating the average value corresponding to the absolute values of the grade and value in the selected time range.

In step 205, when the average value corresponding to the absolute value of the level difference is greater than the average value corresponding to the absolute value of the level sum, the average value corresponding to the absolute value of the level difference is used as a positive correlation coefficient, and the positive correlation coefficient is mapped between zero and one to be used as the correlation degree between the target index and each index.

And step 206, under the condition that the average value corresponding to the absolute value of the grade difference value is less than or equal to the average value corresponding to the absolute value of the grade sum value, taking the average value corresponding to the absolute value of the grade sum value as a negative correlation coefficient, and mapping the negative correlation coefficient to a range between zero and one as the correlation degree of the target index and each index.

In the embodiment of the present disclosure, the absolute value of the difference between the unit rate of change levels of the target indicator and the other indicators is calculated, the absolute value of the sum of the unit rate of change levels of the alarm indicator and the other indicators is calculated, and the average value of the absolute values of a plurality of level differences within a selected time range, for example, 6 absolute values of level differences within seven days, is further calculated, so as to calculate the average value of the absolute values of level differences, and similarly, the average value of the absolute values of a plurality of levels within a selected time range is calculated.

In the embodiment of the present disclosure, the positive correlation is represented when the average value corresponding to the absolute value of the level difference is greater than the average value corresponding to the absolute value of the level sum, and the average value corresponding to the absolute value of the level difference is used as a positive correlation coefficient; and expressing negative correlation under the condition that the average value corresponding to the absolute value of the grade difference value is less than or equal to the average value corresponding to the absolute value of the grade sum value, taking the average value corresponding to the absolute value of the grade sum value as a negative correlation coefficient, and mapping a positive correlation coefficient or the negative correlation coefficient between zero and one as the correlation degree of the target index and each index.

Mapping the positive correlation coefficient or the negative correlation coefficient to 0-1 in a calculation mode of (4-releasecy)/4, wherein the releasecy is the positive correlation coefficient or the negative correlation coefficient, if the adjusted positive correlation coefficient is less than 0, the adjusted positive correlation coefficient is regarded as 0, and the more the mapped positive correlation coefficient is close to 1, the more the two indexes are positively correlated; if the adjusted negative correlation coefficient is smaller than 0, the adjusted negative correlation coefficient is regarded as 0, and the more the mapped negative correlation coefficient is close to 1, the more the two indexes are negatively correlated.

And step 207, sorting the association degrees from large to small according to the numerical values, comparing the association degrees with a preset threshold value, and acquiring a preset quantity association index before sorting, wherein the association degrees are larger than the preset threshold value.

Step 208, taking the association degree as a horizontal axis coordinate, dividing a vertical axis region corresponding to the horizontal axis coordinate into N regions for display, and respectively displaying the index name and the sequencing serial number with positive correlation and the index name and the sequencing serial number with negative correlation in the first N-1 regions corresponding to the positive and negative vertical axis directions of the horizontal axis coordinate; and displaying the correlation index with positive correlation and the correlation index with negative correlation in a dot distribution mode in the last 1 area corresponding to the positive and negative longitudinal axis directions of the horizontal axis coordinate.

The preset threshold value can be selected to be set, for example, 0.54 in fig. 3, and sorted according to the degree of association, and the associated indexes corresponding to the first 10 positive correlations are displayed by the index names and the sorting sequence numbers; and displaying the associated indexes corresponding to the negative correlations of the top 10 sorted in sequence by index names and sorting serial numbers.

Illustratively, in fig. 3, the correlation indexes are divided into positive correlation and negative correlation, the left graph shows the correlation index of the top 20 by default, and 80 correlation indexes except 20 are distributed in a dot shape. The caliper is at the 20 th correlation index by default, and if the 20 th correlation index is 0.54, the caliper is at 0.5. And the first 20 relevant indexes are divided into 3 equal parts of areas through the current caliper position. Through different region colors and different display sizes, the use experience is further improved.

The relevance digit of the caliper can be adjusted left and right, and the operation of enlarging and reducing can be carried out according to the set relevance digit. If the index is changed from 0.5 to 0.6, the index in the interval of 1.0-0.6 is displayed. The degree of correlation of the index is defined as an X-axis, and a Y-axis is a random value. And 5000Y-axis random values were recorded as supported by the browser. The user checks for many times in the day, and the index position cannot change.

For example, as shown in fig. 4, the left relevance index may be clicked, relevance index and index ring ratio information may be displayed, and the right list may be quickly located to the selected index and expanded. After clicking to view details, skipping to an early warning details page, for example, clicking a second associated index shown in fig. 4, automatically testing the execution number of the case, quickly positioning to the selected index in the right list, and expanding.

Therefore, when data is abnormal, index association analysis can be applied in real time, indexes strongly associated with alarm indexes can be automatically analyzed, and through the rising and falling of the associated indexes, analysts of enterprises can be helped to understand the reasons of data fluctuation and provide a global visual field, and the indexes are understood to fluctuate on the whole business.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.