Index configuration method and apparatus, electronic device, and computer readable medium

Abstract

The application discloses an index configuration method and device, electronic equipment and a computer readable medium, and relates to the technical field of big data analysis and mining. A specific embodiment of the method comprises: calculating the correlation coefficient between any two indexes in an index set; according to the correlation coefficient between the any two indexes, a centroid index is screened out from the index set, and other indexes in the index set are respectively divided into groups corresponding to the centroid indexes; for each group, the centroid index of the group is updated according to the correlation coefficient between any two indexes in the group; the updated centroid index of each group is acquired respectively, and the updated centroid index of each group is configured as a default index. The embodiment can solve the technical problems of strong subjectivity, lack of data basis and easy existence of same-direction or reverse correlation of selected indexes.

Description

Technical Field

[0001] This invention relates to the field of big data analysis and mining technology, and in particular to an indicator configuration method, apparatus, electronic device, and computer-readable medium. Background Technology

[0002] When describing the characteristics of a transaction, we usually include a series of indicators to quantify those characteristics. When one indicator variable increases, another indicator also increases (or decreases); we call this phenomenon covariance, or correlation. Two variables exhibiting covariance are said to be correlated.

[0003] For example, when describing the quality of a car, the indicators include: car class, maximum horsepower, maximum torque, 0-100 km / h acceleration, whether cruise control is included, vehicle weight, wheelbase, vehicle length, and body strength. Let's say we choose three indicators: a, b, and c, and use the weighted formula a*0.3 + b*0.3 + c*0.4 to evaluate the car's quality. It's well known that higher horsepower often means higher torque and stronger power, while greater vehicle weight often means greater body strength, more space, and higher safety. If we evaluate a car with weak power and a heavy body (commonly known as "a small horse pulling a heavy cart"), choosing maximum horsepower, maximum torque, and 0-100 km / h acceleration for evaluation versus choosing body weight, wheelbase, and vehicle length for evaluation, we will arrive at two completely different conclusions: the former scores lower, and the latter scores higher.

[0004] The reason for this is that the selected indicators are strongly correlated, failing to reflect the true characteristics of the object being evaluated. Therefore, when evaluating an object, we should choose uncorrelated or weakly correlated indicators whenever possible, as this will yield more objective results.

[0005] In the process of realizing this invention, the inventors discovered at least the following problems in the prior art:

[0006] In the process of selecting indicators, the decision is mostly based on the experience of managers, which is highly subjective, lacks data foundation, and the efficiency of manual screening is relatively low. Moreover, the selected indicators are prone to having the same or opposite correlation, which leads to the calculated evaluation value being amplified or reduced. Summary of the Invention

[0007] In view of this, embodiments of the present invention provide an indicator configuration method, apparatus, electronic device, and computer-readable medium to solve the technical problems of strong subjectivity, lack of data basis, and the tendency of selected indicators to have unidirectional or inverse correlations.

[0008] To achieve the above objectives, according to one aspect of the present invention, an index configuration method is provided, comprising:

[0009] Calculate the correlation coefficient between any two indicators in the indicator set;

[0010] Based on the correlation coefficient between any two indicators, centroid indicators are selected from the indicator set, and other indicators in the indicator set are assigned to the corresponding centroid indicator groups.

[0011] For each group, the centroid index of the group is updated based on the correlation coefficient between any two indices in the group;

[0012] Obtain the updated centroid index for each group, and configure the updated centroid index for each group as the default index.

[0013] Optionally, based on the correlation coefficient between any two indicators, centroid indicators are selected from the indicator set, and other indicators in the indicator set are respectively assigned to the group containing the corresponding centroid indicator, including:

[0014] Based on a preset number of K groups, any K indicators are obtained from the indicator set, and the total correlation value of the K indicators is calculated based on the correlation coefficient between any two of the K indicators.

[0015] The correlation sums of the K indicators are sorted, and the K indicators with the smallest correlation sums are selected and used as the centroid indicators of the K groups respectively.

[0016] The other indicators in the indicator set are respectively assigned to the groups containing the corresponding K centroid indicators.

[0017] Optionally, other indicators in the indicator set are respectively divided into groups containing the corresponding K centroid indicators, including:

[0018] For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators;

[0019] The correlation coefficients of the K indicators with the centroid indicator are sorted, and the centroid indicator with the largest absolute value of the correlation coefficient with the indicator is selected. The indicator is then assigned to the group containing the centroid indicator.

[0020] Optionally, the total correlation value of the K indicators is calculated based on the correlation coefficient between any two indicators, including:

[0021] Calculate the sum of squares of the correlation coefficients between any two of the K indicators to obtain the total correlation value of the K indicators.

[0022] Optionally, for each group, the centroid index of the group is updated based on the correlation coefficient between any two indices in the group, including:

[0023] For each indicator in each group, the total correlation value of the indicator is calculated based on the correlation coefficient between the indicator and other indicators in the group.

[0024] The total correlation values ​​of each indicator are sorted, and the indicator with the largest total correlation value is selected as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

[0025] Optionally, after updating the centroid index of the group, the method further includes:

[0026] The total correlation value of the centroid index of each group is summed to obtain the total correlation value of the groups.

[0027] Determine whether the number of iterations is greater than or equal to the number threshold and whether the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration;

[0028] If all are yes, then the process ends; otherwise, update the indicators in each group.

[0029] Optionally, the metrics in each group can be updated, including:

[0030] The other indicators in the indicator set are respectively assigned to the group containing the corresponding updated centroid indicator;

[0031] For each group, the centroid index of the group is updated based on the correlation coefficient between any two indices in the group.

[0032] Additionally, according to another aspect of the present invention, an index configuration device is provided, comprising:

[0033] The calculation module is used to calculate the correlation coefficient between any two indicators in the indicator set;

[0034] The grouping module is used to filter out centroid indicators from the indicator set based on the correlation coefficient between any two indicators, and to divide the other indicators in the indicator set into the corresponding centroid indicator groups.

[0035] An update module is used to update the centroid index of each group based on the correlation coefficient between any two indicators in the group.

[0036] The configuration module is used to obtain the updated centroid index for each group and configure the updated centroid index for each group as the default index.

[0037] Optionally, the grouping module is further configured to:

[0038] Based on a preset number of K groups, any K indicators are obtained from the indicator set, and the total correlation value of the K indicators is calculated based on the correlation coefficient between any two of the K indicators.

[0039] The correlation sums of the K indicators are sorted, and the K indicators with the smallest correlation sums are selected and used as the centroid indicators of the K groups respectively.

[0040] The other indicators in the indicator set are respectively assigned to the groups containing the corresponding K centroid indicators.

[0041] Optionally, the grouping module is further configured to:

[0042] For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators;

[0043] The correlation coefficients of the K indicators with the centroid indicator are sorted, and the centroid indicator with the largest absolute value of the correlation coefficient with the indicator is selected. The indicator is then assigned to the group in which the centroid indicator belongs.

[0044] Optionally, the grouping module is further configured to:

[0045] Calculate the sum of squares of the correlation coefficients between any two of the K indicators to obtain the total correlation value of the K indicators.

[0046] Optionally, the update module is further configured to:

[0047] For each indicator in each group, the total correlation value of the indicator is calculated based on the correlation coefficient between the indicator and other indicators in the group.

[0048] The total correlation values ​​of each indicator are sorted, and the indicator with the largest total correlation value is selected as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

[0049] Optionally, the update module is further configured to:

[0050] After updating the centroid index of the group, the total correlation value of the centroid index of each group is summed to obtain the total correlation value of the groups.

[0051] Determine whether the number of iterations is greater than or equal to the number threshold and whether the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration;

[0052] If all are yes, then the process ends; otherwise, update the indicators in each group.

[0053] Optionally, the update module is further configured to:

[0054] The other indicators in the indicator set are respectively assigned to the group containing the corresponding updated centroid indicator;

[0055] For each group, the centroid index of the group is updated based on the correlation coefficient between any two indices in the group.

[0056] According to another aspect of the present invention, an electronic device is also provided, comprising:

[0057] One or more processors;

[0058] Storage device for storing one or more programs.

[0059] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0060] According to another aspect of the present invention, a computer-readable medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0061] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods described in any of the above embodiments.

[0062] One embodiment of the above invention has the following advantages or beneficial effects: Because it employs a technique that uses the correlation coefficient between any two indicators to select centroid indicators from the indicator set, assigns other indicators in the indicator set to the corresponding centroid indicator's group, updates the centroid indicator of each group based on the correlation coefficient between any two indicators in that group, and then uses the updated centroid indicator of each group as the default indicator for configuration, it overcomes the technical problems of strong subjectivity, lack of data foundation, and the tendency for selected indicators to exhibit unidirectional or inverse correlations in existing technologies. This embodiment of the invention groups indicators by the correlation coefficient between them, assisting users in indicator configuration. This not only improves the objectivity and comprehensiveness of the evaluation results but also increases decision-making efficiency and reduces manual time consumption.

[0063] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0065] Figure 1 This is a flowchart of an indicator configuration method according to an embodiment of the present invention;

[0066] Figure 2 This is a flowchart of an indicator configuration method according to a possible embodiment of the present invention;

[0067] Figure 3 This is a flowchart of an indicator configuration method according to another possible embodiment of the present invention;

[0068] Figure 4 This is a flowchart of an index configuration method according to another possible embodiment of the present invention;

[0069] Figure 5 This is a schematic diagram of an indicator configuration device according to an embodiment of the present invention;

[0070] Figure 6 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied;

[0071] Figure 7 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0072] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0073] It should be noted that the collection, analysis, use, transmission, and storage of user personal information involved in the technical solution of this invention all comply with relevant laws and regulations, are used for legitimate and reasonable purposes, and are not shared, disclosed, or sold outside of these legitimate uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken to prevent unauthorized access to such personal information data, ensure that personnel authorized to access personal information data comply with relevant laws and regulations, and ensure the security of user personal information. Once this user personal information data is no longer needed, the risk should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0074] When applicable, including in certain relevant applications, user privacy is protected by de-identifying data, such as by removing specific identifiers (e.g., name, age, date of birth, etc.), controlling the amount or specificity of stored data (e.g., collecting location data at the city level rather than at the specific address level), controlling how data is stored, and / or other methods of de-identification.

[0075] Figure 1 This is a flowchart of an indicator configuration method according to an embodiment of the present invention. As one embodiment of the present invention, such as... Figure 1 As shown, the indicator configuration method may include:

[0076] Step 101: Calculate the correlation coefficient between any two indicators in the indicator set.

[0077] First, select indicator data for each indicator within a certain time range (e.g., the past year, past six months, past three months, past month, or past week). Then, calculate the correlation coefficient between any two indicators and store the results in a record table. The record table can contain fields such as indicator code, indicator name, associated indicator number, associated indicator name, and correlation coefficient with the associated indicator, as shown in Table 1.

[0078] Table 1 records the various fields in the table.

[0079] Field Name type Indicator Number varchar Indicator Name varchar Related indicator number varchar Related indicator name varchar Correlation coefficient value double

[0080] Alternatively, the correlation coefficient R between indicator X and indicator Y can be calculated using the following formula. XY :

[0081]

[0082] Among them, X i This represents the indicator data for indicator X. Y represents the average of n data points for indicator X. i This represents the indicator data for indicator Y. This represents the average of n data points for indicator Y.

[0083] It should be noted that |R XY |≤1, if R XY If R > 0, then indicator X and indicator Y are positively correlated; if R < 0, then indicator X and indicator Y are positively correlated. XY If R < 0, then indicator X and indicator Y are negatively correlated. XY The closer the correlation is to zero, the weaker the correlation.

[0084] Taking the assessment of the completeness of insurance operations as an example, indicators such as the number of scanned items, the number of items entered, the number of items submitted, the number of items approved, the amount approved, the number of items delayed, the amount delayed, the number of items charged, and the amount charged can be selected as indicators to form an indicator set, and the correlation coefficient between any two indicators in the indicator set can be calculated.

[0085] Step 102: Based on the correlation coefficient between any two indicators, select the centroid indicators from the indicator set, and assign the other indicators in the indicator set to the corresponding centroid indicator groups.

[0086] After calculating the correlation coefficient between any two indicators, K centroid indicators (K is pre-configured) are selected from the indicator set in step 101 based on the correlation coefficient. Each centroid indicator belongs to one group, meaning there are a total of K groups. Then, the remaining indicators in the indicator set are assigned to the group containing a centroid indicator. It should be noted that an indicator can only be assigned to one group.

[0087] Optionally, step 102 may include: obtaining any K indicators from the indicator set according to a preset number of K groups; calculating the total correlation value of the K indicators based on the correlation coefficient between any two of the K indicators; sorting the total correlation values ​​of each of the K indicators; selecting the K indicators with the smallest total correlation value and using them as centroid indicators for the K groups; and assigning the remaining indicators in the indicator set to the groups containing the corresponding K centroid indicators. In an embodiment of the present invention, according to a preset number of K groups (i.e., the number of K centroid indicators), any K indicators are randomly obtained from the indicator set; the total correlation value of these K indicators is calculated based on the correlation coefficient between any two of these K indicators; the aforementioned steps are repeated to calculate the total correlation value of all K indicators; then, the total correlation values ​​of these K indicators are sorted to select the K indicators with the smallest total correlation value; the K indicators with the smallest total correlation value are used as centroid indicators for the K groups; and finally, the remaining indicators in the indicator set are assigned to the groups containing a centroid indicator.

[0088] Optionally, the total correlation of the K indicators is calculated based on the correlation coefficient between any two indicators among the K indicators. This includes calculating the sum of the squares of the correlation coefficients between any two indicators among the K indicators, thereby obtaining the total correlation of the K indicators. Specifically, the squares of the correlation coefficients between any two indicators among the K indicators are calculated separately, and then the squares of each correlation coefficient are summed to obtain the total correlation of the K indicators.

[0089] Optionally, other indicators in the indicator set are assigned to groups containing the corresponding K centroid indicators. This includes: for each other indicator in the indicator set, obtaining the correlation coefficient between the indicator and the K centroid indicators; sorting the absolute values ​​of the correlation coefficients between the K indicators and the centroid indicators, selecting the centroid indicator with the largest absolute value of its correlation coefficient, and assigning the indicator to the group containing the centroid indicator. After determining the centroid indicator for each group, the correlation coefficients between each other indicator and these K indicators are obtained from the record table. Based on the principle of strongest correlation, for each indicator, the absolute values ​​of its correlation coefficient with the centroid indicator are sorted, and the centroid indicator with the largest absolute value of its correlation coefficient is assigned to the group containing that centroid indicator. In other words, the indicator is assigned to the group containing the centroid indicator with the strongest correlation with it, meaning the indicator and the centroid indicator are in the same group.

[0090] Step 103: For each group, update the centroid index of the group based on the correlation coefficient between any two indices in the group.

[0091] After grouping all indicators in the indicator set, update the centroid of each group, that is, find the most suitable indicator as the centroid for each group.

[0092] Optionally, step 103 may include: for each indicator in each group, calculating the total correlation value of the indicator based on the correlation coefficient between the indicator and other indicators in the group; sorting the total correlation values ​​of each indicator, selecting the indicator with the largest total correlation value as the new centroid indicator of the group, thereby updating the centroid indicator of the group. Assuming there are T indicators in a group, for each of the T indicators, calculating the total correlation value of the indicator with the other T-1 indicators in the group based on the correlation coefficient, repeating the aforementioned steps, the total correlation value of each indicator in the group can be obtained. Then, the total correlation values ​​of each indicator in the group are sorted to select the indicator with the largest total correlation value, which is then used as the centroid indicator of the group, and the centroid indicator of the group is updated.

[0093] It should be noted that the updated centroid indicator may or may not be the original centroid indicator.

[0094] Optionally, for each indicator in each group, calculating the total correlation value of the indicator based on the correlation coefficient between the indicator and other indicators in the group may include: for each indicator in each group, calculating the square of the correlation coefficient between the indicator and other indicators in the group, and then summing the squares of the correlation coefficients to obtain the total correlation value of the indicator.

[0095] Optionally, after updating the centroid index of the group, the method further includes: summing the correlation sum of the centroid indices of each group to obtain a group correlation sum; determining whether the number of iterations is greater than or equal to a threshold and whether the group correlation sum of the current iteration is greater than the group correlation sum of the previous iteration; if both are yes, the process ends; otherwise, the indices in each group are updated. To improve the cohesion of the groups and make the grouping results more convergent, after updating the centroid indices of K groups, for each group, the correlation sum of the centroid indices of that group is calculated, and then the correlation sum of the centroid indices of the K groups is summed to obtain a group correlation sum. The method then determines whether the number of iterations is greater than or equal to a threshold and whether the group correlation sum of the current iteration is greater than the group correlation sum of the previous iteration. If both are yes, the process ends; otherwise, the indices in each group are updated until the number of iterations is greater than or equal to a threshold and the group correlation sum of the current iteration is greater than the group correlation sum of the previous iteration. This ensures better group cohesion and results in better grouping performance.

[0096] It should be noted that the embodiments of the present invention use the total correlation value to evaluate the clustering performance. The larger the total correlation value, the higher the cohesion of the group and the better the grouping effect.

[0097] Optionally, the number of iterations threshold can be set to 2-4 times, 5-6 times, or 9-10 times; this embodiment of the invention does not impose any limitation on this. If the number of iterations has exceeded the threshold, and the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration, it indicates that the result has converged. Grouping is stopped, and the grouping results of each indicator are stored in the grouping table, as shown in Table 2.

[0098] Each field in the grouped table in Table 2

[0099] Field Name type Group numbering varchar Indicator Number varchar Indicator Name varchar Centroid Marker varchar

[0100] Optionally, the indicators in each group are updated, including: assigning other indicators in the indicator set to the corresponding updated centroid indicators; for each group, updating the centroid indicator of the group based on the correlation coefficient between any two indicators in the group. Since the centroid of each group has been updated, steps 102 and 103 are executed again in the next iteration. Specifically, other indicators in the indicator set are assigned to the corresponding K updated centroid indicators, and then the centroid indicator of each group is updated based on the correlation coefficient between any two indicators in each group.

[0101] Therefore, embodiments of the present invention can divide all indicators in the indicator set into several groups, and group highly correlated indicators into one group.

[0102] Step 104: Obtain the updated centroid index for each group and configure the updated centroid index for each group as the default index.

[0103] After grouping all indicators in the indicator set and updating the centroid indicators, obtain the updated centroid indicators for each group and configure these K centroid indicators as default indicators. In other words, select the centroid indicator from each group as the default indicator (obtain the indicator with the centroid flag set to "yes" from the grouping table). This reduces interference from correlations between indicators, and the indicator with the lowest overall correlation is configured as the default indicator.

[0104] In some embodiments of the present invention, if the user selects the default indicator configuration scheme, the system directly selects the centroid indicator from each group and returns it to the user. When the user configures the indicator scheme themselves, the system will select the centroid indicator from the group and prompt the user, and will also suggest other indicators (with the least correlation with the selected indicators) based on the user's selected indicators, in order to help the user avoid selecting highly correlated indicators as much as possible.

[0105] Based on the various embodiments described above, it can be seen that the embodiments of the present invention solve the technical problems of strong subjectivity, lack of data foundation, and the tendency for selected indicators to have similar or opposite correlations in the prior art by grouping indicators according to the correlation coefficient between any two indicators, and then updating the centroid indicators of each group according to the correlation coefficient between any two indicators in the group, and finally configuring the updated centroid indicators of each group as the default indicators.

[0106] Figure 2 This is a flowchart of an index configuration method according to a possible embodiment of the present invention. As another embodiment of the present invention, such as... Figure 2 As shown, the indicator configuration method may include:

[0107] Step 201: Calculate the correlation coefficient between any two indicators in the indicator set.

[0108] Select indicator data for each indicator within a certain time range, then calculate the correlation coefficient between any two indicators, and store the results in a record table. The record table may contain fields such as indicator code, indicator name, associated indicator number, associated indicator name, and correlation coefficient with the associated indicator.

[0109] Step 202: Select centroid indicators from the set of indicators based on the correlation coefficient between any two indicators.

[0110] In an embodiment of the present invention, according to a preset number of K groups, any K indicators are randomly selected from the indicator set. Based on the correlation coefficient between any two of these K indicators, the total correlation value of these K indicators is calculated. The aforementioned steps are repeated to calculate the total correlation value of all K indicators. Then, the total correlation values ​​of these K indicators are sorted to select the K indicators with the smallest total correlation value. The K indicators with the smallest total correlation value are used as the centroid indicators of the K groups.

[0111] Step 203: Divide the other indicators in the indicator set into the groups where the corresponding centroid indicators are located.

[0112] After determining the centroid index for each group, the correlation coefficients between each of the other indices and these K indices are obtained from the record table. Based on the principle of strongest correlation, for each index, the absolute values ​​of its correlation coefficient with the centroid index are ranked. The centroid index with the largest absolute value of its correlation coefficient is assigned to the group containing that centroid index. In other words, the index is assigned to the group containing the centroid index with the strongest correlation to it; the index and the centroid index are now in the same group.

[0113] Step 204: For each group, update the centroid index of the group based on the correlation coefficient between any two indices in the group.

[0114] For each group, calculate the total correlation value of each indicator in the group, then sort the total correlation values ​​of each indicator in the group to select the indicator with the largest total correlation value. Use the indicator with the largest total correlation value as the centroid indicator of the group and update the centroid indicator of the group.

[0115] Step 205: Sum the total correlation values ​​of the centroid indicators of each group to obtain the total correlation value of the groups.

[0116] For each group, calculate the total correlation of the centroid indices of that group, and then sum the total correlation of the centroid indices of the K groups to obtain the total correlation of the groups.

[0117] Step 206: Determine whether the number of iterations is greater than or equal to the number threshold and whether the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration; if yes, proceed to step 207; if no, proceed to step 203.

[0118] Determine whether the number of iterations is greater than or equal to the threshold and whether the total correlation value of the groups in the current iteration is greater than the total correlation value of the groups in the previous iteration. If both are true, the process ends. Otherwise, continue to update the indicators in each group until the number of iterations is greater than or equal to the threshold and the total correlation value of the groups in the current iteration is greater than the total correlation value of the groups in the previous iteration. This ensures better cohesion of the groups and results in better grouping performance.

[0119] Step 207: Obtain the updated centroid index for each group and configure the updated centroid index for each group as the default index.

[0120] After the iteration is completed, obtain the K updated centroid indicators for each group, and configure the K centroid indicators as default indicators.

[0121] Furthermore, the specific implementation details of the indicator configuration method in one of the reference embodiments of the present invention have been described in detail in the indicator configuration method described above, so the details will not be repeated here.

[0122] Figure 3 This is a flowchart of an index configuration method according to another possible embodiment of the present invention. As another embodiment of the present invention, such as... Figure 3 As shown, the indicator configuration method may include:

[0123] Step 301: Calculate the correlation coefficient between any two indicators in the indicator set.

[0124] Step 302: Based on the preset number of K groups, obtain any K indicators from the indicator set, calculate the sum of squares of the correlation coefficients between any two indicators among the K indicators, and thus obtain the total correlation value of the K indicators.

[0125] Specifically, the square of the correlation coefficient between any two of the K indicators is calculated, and then the squares of each correlation coefficient are added together to obtain the total correlation value of the K indicators.

[0126] Step 303: Sort the total correlation values ​​of the K indicators, select the K indicators with the smallest total correlation values ​​and use them as the centroid indicators of the K groups respectively.

[0127] Step 304: For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators.

[0128] Step 305: Sort the correlation coefficients of the K indicators with the centroid indicator, select the centroid indicator with the largest absolute value of the correlation coefficient with the indicator, and classify the indicator into the group where the centroid indicator is located.

[0129] Step 306: For each indicator in each group, calculate the sum of squares of the correlation coefficients between the indicator and all other indicators in the group, thereby obtaining the total correlation value of the indicator.

[0130] For each indicator in each group, the square of the correlation coefficient between the indicator and each other indicator in the group is calculated, and then the squares of each correlation coefficient are added together to obtain the total correlation value of the indicator.

[0131] Step 307: Sort the total correlation values ​​of each indicator, select the indicator with the largest total correlation value and use it as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

[0132] Step 308: Obtain the updated centroid index for each group and configure the updated centroid index for each group as the default index.

[0133] In addition, the specific implementation details of the indicator configuration method in another reference embodiment of the present invention have been described in detail in the indicator configuration method described above, so the details will not be repeated here.

[0134] Figure 4 This is a flowchart of an index configuration method according to another possible embodiment of the present invention. As another embodiment of the present invention, such as... Figure 4 As shown, the indicator configuration method may include:

[0135] Step 401: Calculate the correlation coefficient between any two indicators in the indicator set.

[0136] Step 402: Based on the preset number of K groups, obtain any K indicators from the indicator set, calculate the sum of squares of the correlation coefficients between any two indicators among the K indicators, and thus obtain the total correlation value of the K indicators.

[0137] Step 403: Sort the total correlation values ​​of the K indicators, select the K indicators with the smallest total correlation values, and use them as the centroid indicators of the K groups.

[0138] Step 404: For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators.

[0139] Step 405: Sort the correlation coefficients of the K indicators with the centroid indicator, select the centroid indicator with the largest absolute value of the correlation coefficient with the indicator, and classify the indicator into the group where the centroid indicator is located.

[0140] Step 406: For each indicator in each group, calculate the sum of squares of the correlation coefficients between the indicator and all other indicators in the group, thereby obtaining the total correlation value of the indicator.

[0141] For each indicator in each group, the square of the correlation coefficient between the indicator and each other indicator in the group is calculated, and the squares of each correlation coefficient are added together to obtain the total correlation value of the indicator.

[0142] Step 407: Sort the total correlation values ​​of each indicator, select the indicator with the largest total correlation value and use it as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

[0143] Step 408: Sum the total correlation values ​​of the centroid indicators of each group to obtain the total correlation value of the groups.

[0144] Step 409: Determine whether the number of iterations is greater than or equal to the number threshold and whether the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration; if yes, proceed to step 410; if no, proceed to step 404.

[0145] Step 410: Obtain the updated centroid index for each group and configure the updated centroid index for each group as the default index.

[0146] Furthermore, the specific implementation details of the indicator configuration method in another reference embodiment of the present invention have been described in detail in the indicator configuration method described above, so the details will not be repeated here.

[0147] Figure 5This is a schematic diagram of an indicator configuration device according to an embodiment of the present invention. Figure 5 As shown, the indicator configuration device 500 includes a calculation module 501, a grouping module 502, an update module 503, and a configuration module 504. The calculation module 501 calculates the correlation coefficient between any two indicators in the indicator set. The grouping module 502 selects centroid indicators from the indicator set based on the correlation coefficient between the two indicators and assigns other indicators in the indicator set to the corresponding centroid indicator groups. The update module 503 updates the centroid indicator of each group based on the correlation coefficient between any two indicators in the group. The configuration module 504 obtains the updated centroid indicator for each group and configures it as a default indicator.

[0148] Optionally, the grouping module 502 is further configured to:

[0149] Based on a preset number of K groups, any K indicators are obtained from the indicator set, and the total correlation value of the K indicators is calculated based on the correlation coefficient between any two of the K indicators.

[0150] The correlation sums of the K indicators are sorted, and the K indicators with the smallest correlation sums are selected and used as the centroid indicators of the K groups respectively.

[0151] The other indicators in the indicator set are respectively assigned to the groups containing the corresponding K centroid indicators.

[0152] Optionally, the grouping module 502 is further configured to:

[0153] For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators;

[0154] The correlation coefficients of the K indicators with the centroid indicator are sorted, and the centroid indicator with the largest absolute value of the correlation coefficient with the indicator is selected. The indicator is then assigned to the group in which the centroid indicator belongs.

[0155] Optionally, the grouping module 502 is further configured to:

[0156] Calculate the sum of squares of the correlation coefficients between any two of the K indicators to obtain the total correlation value of the K indicators.

[0157] Optionally, the update module 503 is further configured to:

[0158] For each indicator in each group, the total correlation value of the indicator is calculated based on the correlation coefficient between the indicator and other indicators in the group.

[0159] The total correlation values ​​of each indicator are sorted, and the indicator with the largest total correlation value is selected as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

[0160] Optionally, the update module 503 is further configured to:

[0161] After updating the centroid index of the group, the total correlation value of the centroid index of each group is summed to obtain the total correlation value of the groups.

[0162] Determine whether the number of iterations is greater than or equal to the number threshold and whether the total group correlation value of the current iteration is greater than the total group correlation value of the previous iteration;

[0163] If all are yes, then the process ends; otherwise, update the indicators in each group.

[0164] Optionally, the update module 503 is further configured to:

[0165] The other indicators in the indicator set are respectively assigned to the group containing the corresponding updated centroid indicator;

[0166] For each group, the centroid index of the group is updated based on the correlation coefficient between any two indices in the group.

[0167] It should be noted that the specific implementation details of the indicator configuration device described in this invention have been described in detail in the indicator configuration method described above, so the details will not be repeated here.

[0168] Figure 6 An exemplary system architecture 600 is shown that can be applied to the indicator configuration method or indicator configuration apparatus of the present invention.

[0169] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, and 603, a network 604, and a server 605. Network 604 serves as the medium for providing communication links between terminal devices 601, 602, and 603 and server 605. Network 604 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0170] Users can use terminal devices 601, 602, and 603 to interact with server 605 via network 604 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0171] Terminal devices 601, 602, and 603 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0172] Server 605 can be a server that provides various services, such as a backend management server that supports shopping websites browsed by users using terminal devices 601, 602, and 603 (this is just an example). The backend management server can analyze and process data such as received item information query requests, and then feed the processing results back to the terminal devices.

[0173] It should be noted that the indicator configuration method provided in this embodiment of the invention is generally executed by server 605, and correspondingly, the indicator configuration device is generally set in server 605. The indicator configuration method provided in this embodiment of the invention can also be executed by terminal devices 601, 602, and 603, and correspondingly, the indicator configuration device can be set in terminal devices 601, 602, and 603.

[0174] It should be understood that Figure 6 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0175] The following is for reference. Figure 7 It shows a schematic diagram of the structure of a computer system 700 suitable for implementing a terminal device of the present invention. Figure 7 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0176] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 702 or programs loaded from storage section 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the system 700. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0177] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0178] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs the functions defined above in the system of this invention.

[0179] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0180] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer programs according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0181] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor can be described as including a computing module, a grouping module, an update module, and a configuration module, wherein the names of these modules do not necessarily limit the module itself.

[0182] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device implements the following method: calculating the correlation coefficient between any two indicators in the indicator set; based on the correlation coefficient between the two indicators, selecting centroid indicators from the indicator set, and assigning other indicators in the indicator set to the corresponding centroid indicator groups; for each group, updating the centroid indicator of the group based on the correlation coefficient between any two indicators in the group; obtaining the updated centroid indicator for each group, and configuring the updated centroid indicator for each group as a default indicator.

[0183] In another aspect, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the methods described in any of the above embodiments.

[0184] According to the technical solution of this invention, by employing a method of selecting centroid indicators from an indicator set based on the correlation coefficient between any two indicators, assigning other indicators in the indicator set to the corresponding centroid indicator groups, updating the centroid indicators of each group based on the correlation coefficient between any two indicators in the group, and then configuring the updated centroid indicators of each group as default indicators, this overcomes the technical problems of strong subjectivity, lack of data foundation, and the tendency for selected indicators to exhibit unidirectional or inverse correlations in the prior art. This invention's method of grouping indicators by correlation coefficients to assist users in indicator configuration not only improves the objectivity and comprehensiveness of evaluation results but also increases decision-making efficiency and reduces manual time consumption.

[0185] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of configuring an indicator, characterized by, The method comprises the following steps: calculating the correlation coefficient between any two indicators in the indicator set; the indicators are indicators describing the quality of the automobile; selecting a centroid indicator from the indicator set according to the correlation coefficient between any two indicators, and dividing other indicators in the indicator set into corresponding groups according to the centroid indicators; updating the centroid indicator of each group according to the correlation coefficient between any two indicators in the group; obtaining the updated centroid indicators of each group respectively, and configuring the updated centroid indicators of each group as default indicators; after updating the centroid indicators of the groups, the method further comprises the following steps: adding the correlation sum of the centroid indicators of each group to obtain a group correlation sum; the correlation sum of the centroid indicators refers to the sum of the squares of the correlation coefficients between the centroid indicators and other indicators in the group; judging whether the iteration number is greater than or equal to a threshold value and whether the group correlation sum of the current iteration is greater than the group correlation sum of the last iteration; if both are yes, the process ends; otherwise, the indicators in each group are updated; updating the indicators in each group comprises the following steps: dividing other indicators in the indicator set into corresponding groups according to the updated centroid indicators; updating the centroid indicator of each group according to the correlation coefficient between any two indicators in the group.

2. The method of claim 1, wherein, The method comprises the following steps: selecting a centroid indicator from the indicator set according to the correlation coefficient between any two indicators, and dividing other indicators in the indicator set into corresponding groups according to the centroid indicators; comprises the following steps: obtaining any K indicators from the indicator set according to a preset number of K groups, and calculating the group correlation sum of the K indicators according to the correlation coefficient between any two indicators in the K indicators; 3. The method of claim 2, wherein, sorting the group correlation sums of the K indicators, selecting the K indicators with the smallest group correlation sum as the centroid indicators of the K groups, and dividing other indicators in the indicator set into corresponding groups according to the K centroid indicators. comprises the following steps: for each indicator in the other indicators in the indicator set, obtaining the correlation coefficient between the indicator and the K centroid indicators; 4. The method of claim 2, wherein, sorting the correlation coefficients between the K indicators and the centroid indicators, selecting the centroid indicator with the largest absolute value of the correlation coefficient, and dividing the indicator into the group of the centroid indicator. comprises the following steps:

5. The method according to any one of claims 1 to 4, characterized in that, calculating the sum of the squares of the correlation coefficients between any two indicators in the K indicators to obtain the group correlation sum of the K indicators. comprises the following steps: for each indicator in each group, calculating the group correlation sum of the indicator according to the correlation coefficient between the indicator and other indicators in the group. Sort the correlation aggregate values of each of the indicators, filter out the indicator with the largest correlation aggregate value and take it as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

6. An index configuration apparatus characterized by comprising: Comprise: A calculation module configured to calculate a correlation coefficient between any two indicators in an indicator set; the indicators are indicators describing the quality of a car; A grouping module configured to filter out a centroid indicator from the indicator set according to the correlation coefficient between any two indicators, and divide other indicators in the indicator set into corresponding groups according to the centroid indicators; An updating module configured to update the centroid indicator of each group according to the correlation coefficient between any two indicators in the group; A configuration module configured to obtain the updated centroid indicator of each group respectively, and configure the updated centroid indicator of each group as a default indicator; The updating module is further configured to: After updating the centroid indicator of the group, add the correlation aggregate values of the centroid indicators of each group, thereby obtaining a group correlation aggregate value; the correlation aggregate value of the centroid indicator is the sum of the squares of the correlation coefficients between the centroid indicator and other indicators in the group; Determine whether the number of iterations is greater than or equal to a threshold value and whether the group correlation aggregate value of the current iteration is greater than the group correlation aggregate value of the last iteration; If both are yes, end; otherwise, update the indicators in each group; The updating module is further configured to: Divide other indicators in the indicator set into corresponding groups according to the updated centroid indicators; For each group, update the centroid indicator of the group according to the correlation coefficient between any two indicators in the group.

7. The apparatus of claim 6, wherein, The grouping module is further configured to: According to a preset number of K groups, obtain any K indicators from the indicator set, and calculate the correlation aggregate value of the K indicators according to the correlation coefficient between any two indicators in the K indicators; Sort the correlation aggregate values of each of the K indicators, filter out the K indicators with the smallest correlation aggregate values and take them as the centroid indicators of the K groups respectively; Divide other indicators in the indicator set into corresponding groups according to the K centroid indicators.

8. The apparatus of claim 7, wherein, The grouping module is further configured to: For each of the other indicators in the indicator set, obtain the correlation coefficient between the indicator and the K centroid indicators respectively; Sort the correlation coefficients between the K indicators and the centroid indicators, filter out the centroid indicator with the largest absolute value of the correlation coefficient with the indicator, and divide the indicator into the group where the centroid indicator is located.

9. The apparatus of claim 7, wherein, The grouping module is further configured to: Calculate the sum of the squares of the correlation coefficients between any two indicators in the K indicators, thereby obtaining the correlation aggregate value of the K indicators.

10. The apparatus of any one of claims 6-9, wherein, The updating module is further configured to: For each indicator in each group, calculate the correlation aggregate value of the indicator according to the correlation coefficient between the indicator and other indicators in the group; Sort the correlation aggregate values of each of the indicators, filter out the indicator with the largest correlation aggregate value and take it as the new centroid indicator of the group, thereby updating the centroid indicator of the group.

11. An electronic device, comprising: comprising: one or more processors; a memory device for storing one or more programs, the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-5.

12. A computer readable medium having stored thereon a computer program, characterized in that, the program, when executed by the processor, causes the processor to perform the method of any of claims 1-5.

13. A computer program product comprising a computer program, characterized in that, the computer program, when executed by the processor, causes the processor to perform the method of any of claims 1-5.

Images