A method, device and electronic equipment for determining an evaluation index

Abstract

The application discloses a method and device for determining an evaluation index and an electronic device. The method comprises the following steps: acquiring a plurality of indexes for evaluating a business service; calculating a first information entropy of each index in the plurality of indexes; screening an index corresponding to the first information entropy greater than a preset threshold as a target index; determining a target index value corresponding to each target index; calculating a second information entropy of each target index value; and performing weighted summation on the second information entropy and the first information entropy of the business service to obtain a final evaluation index of the business service. Based on the above method, the final evaluation index for evaluating the business service can be determined in combination with multiple dimensions, the problem that an inaccurate analysis result is caused by a single evaluation index system can be solved, the accuracy and coverage of the final evaluation index are effectively improved, the analysis and decision can be assisted in actual application, and the repair efficiency of the business based on the final evaluation index is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, and particularly relates to a method and device for determining an evaluation index and electronic equipment. BACKGROUND

[0002] Currently, a single evaluation index system is generally used to analyze a specific business service. For example, in a communication service, the service quality of the communication service is analyzed based on a satisfaction score related index, that is, the higher the satisfaction score, the better the service. Alternatively, the service quality of the communication service is analyzed based on a user complaint number related index, that is, the fewer the complaint numbers, the better the service.

[0003] However, the single evaluation index system has the problem of a one-sided analysis result. For example, in an actual application scenario, some users with a large number of complaint numbers have a high satisfaction score, while some users with a small number of complaint numbers or no complaint have a low satisfaction score, resulting in inaccurate service quality evaluation. SUMMARY

[0004] The present application provides a method and device for determining an evaluation index and electronic equipment, which are used to determine a final evaluation index for evaluating a business service in combination with multiple dimensions, and solve the problem of inaccurate analysis result caused by a single evaluation index system.

[0005] In a first aspect, the present application provides a method for determining an evaluation index, which comprises:

[0006] obtaining a plurality of indexes for evaluating a business service;

[0007] calculating a first information entropy of each index in the plurality of indexes, and screening an index corresponding to a first information entropy greater than a preset threshold as a target index;

[0008] determining a target index value corresponding to each target index, and calculating a second information entropy of each target index value;

[0009] performing weighted summation on the second information entropy and the first information entropy of the business service to obtain a final evaluation index of the business service.

[0010] In a possible design, after the plurality of indexes for evaluating the business service are obtained, the method further comprises:

[0011] extracting a selected index in the plurality of indexes; wherein the selected index corresponds to an index value within a preset value range;

[0012] dividing the preset value range of the selected index to obtain a plurality of sub-value ranges; wherein there is no overlapping value range between the plurality of sub-value ranges;

[0013] configure different preset values for each of the plurality of sub-value ranges, and all configured preset values are taken as the index value corresponding to the selected index.

[0014] In a possible design, the calculating the first information entropy of each of the plurality of indexes and screening the index corresponding to the first information entropy greater than a preset threshold as a target index comprises the following steps.

[0015] performing information entropy and normalization calculation on each of the plurality of indexes to obtain the first information entropy of the each of the plurality of indexes.

[0016] screening, from all the calculated first information entropies, the index corresponding to the first information entropy greater than a specified value as a target index.

[0017] In a possible design, the calculating the second information entropy of each target index value comprises the following steps.

[0018] performing the following operations on each target index value of a single target index.

[0019] obtaining a first quantity and a second quantity corresponding to the single target index value, wherein the first quantity represents the quantity of objects carrying a first identifier, and the second quantity represents the quantity of objects carrying a second identifier.

[0020] determining a first proportion of the single target index value in all target index values corresponding to the single target index.

[0021] calculating the second information entropy of the single target index value according to the first quantity, the second quantity, and the first proportion.

[0022] In a possible design, the weighted sum of the second information entropy and the first information entropy of the business service is performed to obtain a final evaluation index of the business service, which comprises the following steps.

[0023] calculating the sum of the first information entropies of the target indexes of the business service.

[0024] calculating the ratio of the first information entropy of each target index to the sum of the first information entropies.

[0025] calculating the sum of the product of the ratio of each target index to the second information entropy of each target index, to obtain the final evaluation index of the business service.

[0026] By the above method, the final evaluation index for evaluating the business service can be determined in combination with multiple dimensions, the accuracy of the final evaluation index and the multi-index coverage rate of the final evaluation index can be effectively improved, which helps to assist the analysis and decision of actual analysts or business personnel, and the repair efficiency of performing business based on the final evaluation index can be effectively improved in actual application scenarios.

[0027] In a second aspect, the present application provides a device for determining an evaluation index, the device comprising:

[0028] an acquisition module, configured to acquire a plurality of indexes for evaluating a business service;

[0029] a screening module, configured to calculate a first information entropy of each index in the plurality of indexes, and screen an index corresponding to a first information entropy greater than a preset threshold as a target index;

[0030] a calculation module, configured to determine a target index value corresponding to each target index respectively, and calculate a second information entropy of each target index value;

[0031] a generation module, configured to perform weighted summation on the second information entropy and the first information entropy of the business service to obtain a final evaluation index of the business service.

[0032] In a possible design, the device is specifically configured to extract a selected index in the plurality of indexes, wherein the index value corresponding to the selected index is within a preset value range; the preset value range of the selected index is divided to obtain a plurality of sub-value ranges; wherein there is no overlapping value range between the plurality of sub-value ranges; different preset values are configured for each sub-value range in the plurality of sub-value ranges, and all the configured preset values are taken as the index value corresponding to the selected index.

[0033] In a possible design, the screening module is specifically configured to perform information entropy and normalization calculation on each index in the plurality of indexes to obtain the first information entropy of each index; and from all the calculated first information entropies, screen an index corresponding to a first information entropy with a value greater than a specified value as a target index.

[0034] In a possible design, the calculation module is specifically configured to perform the following operation on each target index value of a single target index: acquire a first quantity and a second quantity corresponding to a single target index value; wherein the first quantity represents the number of objects carrying a first identifier, and the second quantity represents the number of objects carrying a second identifier; determine a first proportion of the single target index value in all target index values corresponding to the single target index; and calculate the second information entropy of the single target index value according to the first quantity, the second quantity, and the first proportion.

[0035] In a possible design, the generating module is specifically configured to: calculate a sum of the first information entropy of each target index of the service; calculate a ratio of the first information entropy of each target index to the sum of the first information entropy; and calculate a sum of products of the ratio of each target index and the second information entropy of each target index, to obtain the final evaluation index of the service.

[0036] In a third aspect, the present application provides an electronic device, which comprises:

[0037] a memory configured to store a computer program;

[0038] a processor configured to execute the computer program stored in the memory, to implement the method steps of determining an evaluation index.

[0039] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method steps of determining an evaluation index.

[0040] The technical effects of each of the second aspect to the fourth aspect and each of the possible solutions of the first aspect can be referred to the technical effect description of the first aspect or the possible solutions of the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 a flow chart of a method for determining an evaluation index provided by the present application;

[0042] Figure 2 a schematic diagram of a device for determining an evaluation index provided by the present application;

[0043] Figure 3 a schematic diagram of a structure of an electronic device provided by the present application. DETAILED DESCRIPTION

[0044] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The specific operation methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that, in the description of the present application, "multiple" is understood as "at least two". The association relationship of "and / or" associated objects indicates that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. A is connected with B, which can represent the following two cases: A is directly connected with B and A is connected with B through C. In addition, in the description of the present application, "first", "second", and the like are only used for the purpose of distinguishing description, and cannot be understood as indicating or implying relative importance, nor can it be understood as indicating or implying order.

[0045] The embodiments of the present application provide a method, device and electronic equipment for determining an evaluation index, which are used to determine a final evaluation index for evaluating a business service in combination with multiple dimensions, so as to solve the problem of inaccurate analysis result caused by a single evaluation index system.

[0046] The method provided by the embodiments of the present application will be further described in detail below with reference to the drawings.

[0047] Referring to Figure 1 The embodiments of the present application provide a method for determining an evaluation index, and the specific process is as follows:

[0048] Step 101: obtaining multiple indexes for evaluating a business service;

[0049] In the embodiments of the present application, first, multiple indexes for evaluating a business service are obtained.

[0050] Specifically, the process of obtaining the multiple indexes is the process of constructing an evaluation index system of the business service: the multiple indexes can jointly form a decision system, which can be seen from the following formula 1.

[0051]

[0052] Wherein, I is a decision system, U is a non-empty object set, C is an index value set, D is an evaluation index set, here, data related to the business service is generally selected as the index value set, and the satisfaction evaluation of the object to the business service is generally selected as the decision set.

[0053] For example, as shown in Table 1, a decision system of a broadband service can be established based on Table 1, and the purpose of establishing the decision system is to facilitate the subsequent steps and solve the problem of inaccurate user satisfaction prediction based on a single index.

[0054]

[0055] Table 1

[0056] As shown in Table 1 above, taking "object serial number" as "1-7" as an example, i.e. the 7 objects constitute a non-empty object set; the data related to the 6 indexes of "bandwidth rate", "bandwidth bearing mode", "bandwidth demand level", "bandwidth time in network", "whether single-band annual payment", and "urban and rural attributes" in Table 1 collectively constitute an index value set, such as "50", "lan", "3", "34", "no", and "city" corresponding to "object serial number" of "1" belong to the index values in the index value set; the data related to "whether satisfied" in Table 1 collectively constitute an evaluation index set, such as "satisfied" and "unsatisfied" can be represented as different identifiers, i.e. different evaluation indexes in the evaluation index set. Here, "satisfied" can be taken as a first identifier, and "unsatisfied" can be taken as a second identifier.

[0057] It is worth noting that Table 1 above is an exemplary explanation, which does not limit the scheme provided by the embodiments of the present application. It should be understood by those skilled in the art that the index value set and the evaluation index set can be determined according to actual application conditions.

[0058] Further, a selected index can be determined from the extracted multiple indexes. The selected standard is to determine that the index value corresponding to the selected index is within a preset value range, then divide the preset value range of the selected index to obtain multiple sub-value ranges, and there is no overlapping value range between the obtained multiple sub-value ranges, and then respectively configure different preset values for each sub-value range in the multiple sub-value ranges, and the configured preset value is taken as the index value corresponding to the selected index.

[0059] Specifically, the division of the preset value range of the selected index to obtain multiple sub-value ranges can be obtained by calculating the similarity value of two index values. The specific calculation method of the similarity value can be seen from the following formula 2.

[0060]

[0061] Wherein, a(x) and a(y) are two different index values, avg is the weighted average value of the two index values a(x) and a(y), i is the number in the index value a(x), and j is the number in the index value a(y).

[0062] As shown in formula 2 above, if The smaller the value of is, the closer the avg is to the index value a(x) or a(y), i.e. the calculated similarity value SIM aThe greater (X, Y) is. Further, a confidence interval can be set according to actual application, and the index value corresponding to the similarity value greater than the confidence interval can be taken as the index value in the same sub-value range.

[0063] For example, the value ranges of the six indexes of "wideband rate", "wideband bearing mode", "wideband demand level", "wideband time in network", "whether single wideband annual payment", and "urban and rural attribute" can be seen from Table 2 as shown below.

[0064]

[0065] Table 2

[0066] As shown in Table 2 above, "bandwidth time in network" is a selected index, and in Table 1, seven index values corresponding to the selected index "bandwidth time in network" can be determined, which are "34, 25, 22, 5, 16, 78, and 55". The formula 2 is applied to calculate the similarity values for the above seven index values. If the set confidence interval is 0.9, the similarity values greater than 0.9 are extracted, and the index values corresponding to the extracted similarity values are divided into the same sub-value range. According to the above method, the preset value range "integer value between 0 and 247" of "bandwidth time in network" is divided into five sub-value ranges "{two years or less, two years to six years, six years to ten years, ten years to fourteen years, and fourteen years or more}", and here, each sub-value range can be used to represent the index value corresponding to "bandwidth time in network".

[0067] The division results of the preset value range of the selected index in Table 2 based on Table 1 by the above method can be seen from Table 3 as shown below.

[0068]

[0069] Table 3

[0070] By the above method, a plurality of indexes for evaluating business services are determined, and further, the index values corresponding to each index are determined, and the index values in the preset value range are divided, i.e., the continuous index values are transformed into discrete types through the division process, a conditional relaxed index system is realized, the influence of noise can be reduced, and the accuracy of calculating the evaluation index in the subsequent steps can be improved.

[0071] Step 102: calculating the first information entropy of each index in the plurality of indexes, and selecting the index corresponding to the first information entropy greater than the preset threshold as a target index;

[0072] In the embodiment of the present application, the information entropy and normalization of each index in the plurality of indexes obtained in step 101 are calculated to obtain the first information entropy of each index, and then the index corresponding to the first information entropy with a value greater than a specified value is selected as the target index from all the calculated first information entropies.

[0073] For example, taking the six indexes determined in Table 1 or Table 3 as an example: "broadband speed", "broadband bearing mode", "broadband demand level", "broadband time in network", "whether single broadband annual payment", and "urban and rural attributes", the information entropy of each index set is calculated, and the index set represents the index and the index value corresponding to the index, and the information entropy can be obtained: γ(C) = 1.

[0074] The first information entropy of each index is further calculated: γ{broadband speed} = 1-0.6 = 0.4; γ{broadband bearing mode} = 0; γ{broadband demand level} = 0.6; γ{broadband time in network} = 0.2; γ{broadband whether single broadband annual payment} = 0; γ{urban and rural attributes} = 0.

[0075] If the specified value is set to 0, the index with the first information entropy of 0 is removed, and the index with the first information entropy greater than 0 is selected as the target index, that is, the indexes "broadband bearing mode", "broadband whether single broadband annual payment", and "urban and rural attributes" are removed, and the target indexes "broadband speed", "broadband demand level", and "broadband time in network" are selected, and the first information entropy of each target index can be seen from Table 4 as follows.

[0076] Target metric First information entropy Broadband speed 0.4 Broadband demand level 0.6 Broadband on-net time 0.2

[0077] Table 4

[0078] In the above manner, the target index is selected as an important index for calculating the final evaluation index.

[0079] Step 103: determining the target index value corresponding to each target index, and calculating the second information entropy of each target index value;

[0080] In the embodiment of the present application, the following operations are performed on each target index value of a single target index:

[0081] The first quantity and the second quantity corresponding to the single target index value are obtained, where the first quantity represents the number of objects carrying the first identifier, and the second quantity represents the number of objects carrying the second identifier, and then the first proportion of the single target index value is determined in all the target index values corresponding to the single target index, and the second information entropy of the single target index value is calculated according to the first quantity, the second quantity, and the first proportion.

[0082] Specifically, the second information entropy of the single target indicator value can be calculated according to the following formula 3.

[0083]

[0084] wherein G (a i) is the second information entropy of the i th object corresponding to the indicator a, p (a i) is the proportion of the indicator value of the i th object corresponding to the indicator a in the table, n (a i, 1) is the number of the first identifier in the decision set corresponding to the indicator value of the i th object, n (a i, 2) is the number of the second identifier in the decision set corresponding to the indicator value of the i th object. i i

[0085] For example, based on table 3 and table 4, the second information entropy of each target indicator value of each target indicator can be obtained by using the above calculation method, as shown in the following table 5.

[0086]

[0087]

[0088] Table 5

[0089] By the above method, the second information entropy of each target indicator value of each target indicator is obtained, and the second information entropy of the importance of each target indicator value of each target indicator is calculated, which can effectively improve the accuracy of the final evaluation index calculated in the subsequent step.

[0090] Step 104: weighting and summing the second information entropy and the first information entropy of the business service to obtain the final evaluation index of the business service.

[0091] In the embodiment of the present application, the sum of the first information entropy of each target indicator of the business service is calculated first, then the ratio of the first information entropy of each target indicator to the sum of the first information entropy is calculated, and finally the sum of the product of the ratio of each target indicator and the second information entropy of each target indicator is calculated to obtain the final evaluation index of the business service, wherein the final evaluation index is used to evaluate the service quality of the business service.

[0092] Specifically, the specific calculation of the final evaluation index can be seen from the following formula 4.

[0093] M = ∑ γG (formula 4)

[0094] Wherein M represents the final evaluation index, γ represents the first information entropy of each target indicator, and G represents the second information entropy of each target indicator value.

[0095] ​​​​For example, the first information entropy of each target index can be as shown in Table 4, the second information entropy of each target index value of each target index can be as shown in Table 5, if taking an object as an example, assuming that the "broadband rate" of the object is "100", the "broadband demand level" is "3", and the "broadband time in network" is "34", then the specific calculation formula of the final evaluation index of the user can be:

[0096] Here, the calculated 0.48 is the final evaluation index of the user, which can be specifically used to represent that the degree of dissatisfaction of the user will increase by 48% when a negative perception service event occurs in the broadband service.

[0097] In the broadband service, by calculating the final evaluation index, the score of the object-based satisfaction prediction can be corrected, and the satisfaction degree of the object for the broadband service can be truly reflected, thereby providing strong technical support for data analysis, decision-making, customer maintenance, and service improvement.

[0098] In the above manner, the final evaluation index for evaluating the business service can be determined in combination with multiple dimensions, the accuracy of the final evaluation index and the multi-index coverage rate of the final evaluation index can be effectively improved, which helps to assist the analysis and decision-making of actual analysts or business personnel, and the repair efficiency of performing the business based on the final evaluation index can be effectively improved in actual application scenarios.

[0099] Based on the same inventive concept, the application further provides a device for determining an evaluation index, which is used to determine a final evaluation index for evaluating a business service in combination with multiple dimensions, solves the problem of inaccurate analysis results caused by a single evaluation index system, effectively improves the accuracy of the final evaluation index and the multi-index coverage rate of the final evaluation index, and refers to Figure 2 The device comprises:

[0100] An acquisition module 201 acquires a plurality of indexes for evaluating a business service;

[0101] A screening module 202 calculates a first information entropy of each index in the plurality of indexes, and screens an index corresponding to a first information entropy greater than a preset threshold value as a target index;

[0102] A calculation module 203 determines a target index value corresponding to each target index respectively, and calculates a second information entropy of each target index value;

[0103] A generation module 204 performs weighted summation on the second information entropy and the first information entropy of the business service to obtain a final evaluation index of the business service.

[0104] In a possible design, the apparatus is specifically configured to extract a selected indicator from the plurality of indicators, where the selected indicator corresponds to an indicator value within a preset value range; divide the preset value range of the selected indicator to obtain a plurality of sub-value ranges, where there is no overlapping value range between the plurality of sub-value ranges; configure different preset values for each of the plurality of sub-value ranges, and use all the configured preset values as the indicator value corresponding to the selected indicator.

[0105] In a possible design, the screening module 202 is specifically configured to perform information entropy and normalization calculation on each indicator in the plurality of indicators to obtain a first information entropy of each indicator; and screen, from all the calculated first information entropies, an indicator corresponding to a first information entropy with a value greater than a specified value as a target indicator.

[0106] In a possible design, the calculation module 203 is specifically configured to perform the following operations on each target indicator value of a single target indicator: obtain a first quantity and a second quantity corresponding to the single target indicator value, where the first quantity represents a quantity of objects carrying a first identifier, and the second quantity represents a quantity of objects carrying a second identifier; determine a first proportion of the single target indicator value in all target indicator values corresponding to the single target indicator; and calculate a second information entropy of the single target indicator value according to the first quantity, the second quantity, and the first proportion.

[0107] In a possible design, the generation module 204 is specifically configured to calculate a sum of first information entropies of all target indicators of the business service; calculate a ratio of the first information entropy of each target indicator to the sum of the first information entropies; and calculate a sum of products of the ratio of each target indicator and the second information entropy of the target indicator, to obtain a final evaluation indicator of the business service.

[0108] Based on the apparatus, the final evaluation indicator for evaluating the business service is determined by combining multiple dimensions, which effectively improves the accuracy of the final evaluation indicator and the multi-indicator coverage rate of the final evaluation indicator, and helps to assist the analysis and decision of actual analysts or business personnel, and effectively improves the repair efficiency of performing business based on the final evaluation indicator in an actual application scenario.

[0109] Based on the same inventive concept, the embodiments of the present application further provide an electronic device, which can implement the functions of the foregoing apparatus for determining an evaluation indicator, and the details are referred to the foregoing description of the apparatus for determining an evaluation indicator. Figure 3 The electronic device includes:

[0110] The at least one processor 301 and the memory 302 connected with the at least one processor 301 are not limited to the specific connection medium between the processor 301 and the memory 302 in the embodiments of the present application, Figure 3 The processor 301 and the memory 302 are connected through the bus 300 in the embodiments of the present application. The bus 300 is used to connect the processor 301 and the memory 302 in the embodiments of the present application. Figure 3 The connection mode between other components is only schematically illustrated, and is not limited to the thick line in the embodiments of the present application. The bus 300 can be divided into an address bus, a data bus, a control bus, etc., for the convenience of representation, Figure 3 The bus 300 is only represented by one thick line in the embodiments of the present application, but does not mean that there is only one bus or only one type of bus. Alternatively, the processor 301 can also be referred to as a controller, and the name is not limited.

[0111] In the embodiments of the present application, the memory 302 stores instructions executable by the at least one processor 301. The at least one processor 301 can execute the instructions stored in the memory 302 to perform the method of determining the evaluation index discussed above. The processor 301 can realize the functions of various modules in the apparatus shown in the embodiments of the present application. Figure 2

[0112] The processor 301 is the control center of the apparatus, can utilize various interfaces and lines to connect various parts of the whole control device, and through running or executing instructions stored in the memory 302 and calling data stored in the memory 302, the apparatus can process data and realize various functions, thereby monitoring the whole apparatus.

[0113] In a possible design, the processor 301 can include one or more processing units, and the processor 301 can integrate an application processor and a modem processor. The application processor mainly processes the operating system, user interface, application program and the like, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 301. In some embodiments, the processor 301 and the memory 302 can be implemented on the same chip, and in some embodiments, they can also be implemented on independent chips respectively.

[0114] The processor 301 can be a general-purpose processor, for example, a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can realize or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method for determining the evaluation index disclosed in the embodiments of the present application can be directly embodied as execution completed by a hardware processor, or executed by a combination of hardware and software modules in the processor. ​

[0115] The memory 302, as a non-volatile computer readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 302 can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. The memory 302 is any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory 302 in the embodiments of the present application can also be a circuit or any other device capable of realizing a storage function, used to store program instructions and / or data.

[0116] By designing and programming the processor 301, the code corresponding to the method for determining the evaluation index introduced in the foregoing embodiments can be fixed in the chip, so that the chip can execute the steps of the method for determining the evaluation index of the embodiments shown in the running time. Figure 1 How to design and program the processor 301 is a technology known to those skilled in the art, which will not be described here.

[0117] Based on the same inventive concept, the embodiments of the present application also provide a storage medium storing computer instructions, when the computer instructions run on a computer, the computer instructions make the computer execute the method for determining the evaluation index discussed above.

[0118] In some possible implementation manners, various aspects of the method for determining the evaluation index provided by the present application can also be implemented in the form of a program product, which includes program codes, when the program product runs on the device, the program codes are used to make the control device execute the steps in the method for determining the evaluation index according to various exemplary embodiments of the present application described above in the specification.

[0119] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In one

[0120] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0121] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0122] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0123] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the apparatus and methods disclosed herein, equivalents and substitutions thereof could be made by one of ordinary skill in the art without departing from the spirit and scope of the disclosure. Any and all such modifications and variations are intended to be included herein within the scope of the present application and expressed as a part thereof.

Claims

1. A method for determining evaluation indicators, characterized in that, The method includes: Obtain multiple metrics for evaluating business services; For each of the multiple indicators, calculate the information entropy and normalization to obtain the first information entropy of each indicator, and select the indicators with the first information entropy greater than a preset threshold as target indicators. Determine the target indicator value corresponding to each target indicator, and calculate the second information entropy of each target indicator value; Calculate the sum of the first information entropy of each target indicator of the business service; Calculate the ratio of the first information entropy of each target indicator to the sum of the first information entropies; The final evaluation index of the business service is obtained by summing the products of the ratio of each target index and the second information entropy of each target index. The second information entropy for calculating each target indicator value includes: Perform the following operation for each target metric value of a single target metric: Obtain a first quantity and a second quantity corresponding to a single target indicator value; wherein, the first quantity represents the number of objects carrying a first identifier, and the second quantity represents the number of objects carrying a second identifier; Among all the target indicator values ​​corresponding to the single target indicator, determine the first proportion of the single target indicator value; The second information entropy of the single target indicator value is calculated based on the first quantity, the second quantity, and the first proportion. The second information entropy of the single target indicator value satisfies the following expression: in, For target indicators The second information entropy of the corresponding i-th object, For target indicators The corresponding indicator value of the i-th object is the first percentage in the table. Let be the number of the first identifiers in the decision set corresponding to the index value of the i-th object. The number of second identifiers in the decision set corresponding to the index value of the i-th object.

2. The method as described in claim 1, characterized in that, Following the acquisition of multiple metrics for evaluating business services, the process also includes: Extract a selected indicator from the plurality of indicators; wherein the indicator value corresponding to the selected indicator is within a preset value range; The selected indicator is divided into a preset value range to obtain multiple sub-value ranges; wherein, there are no overlapping value ranges among the multiple sub-value ranges. Configure different preset values ​​for each of the multiple sub-value ranges, and use all configured preset values ​​as the index value corresponding to the selected index.

3. An apparatus for determining evaluation indicators, characterized in that, The device includes: The acquisition module retrieves multiple metrics used to evaluate business services. The filtering module calculates the information entropy and normalization for each of the multiple indicators to obtain the first information entropy of each indicator, and filters the indicators with the first information entropy greater than a preset threshold as target indicators. The calculation module determines the target indicator value corresponding to each target indicator and calculates the second information entropy of each target indicator value. The calculation module is specifically used to perform the following operations on each target indicator value of a single target indicator: obtain a first quantity and a second quantity corresponding to the single target indicator value; wherein, the first quantity represents the number of objects carrying a first identifier, and the second quantity represents the number of objects carrying a second identifier; determine a first proportion of the single target indicator value among all target indicator values ​​corresponding to the single target indicator; and calculate a second information entropy of the single target indicator value based on the first quantity, the second quantity, and the first proportion. The generation module calculates the sum of the first information entropy of each target indicator of the business service; calculates the ratio of the first information entropy of each target indicator to the sum of the first information entropy; and calculates the sum of the products of the ratio of each target indicator and the second information entropy of each target indicator to obtain the final evaluation index of the business service. The second information entropy of the single target indicator value satisfies the following expression: in, For target indicators The second information entropy of the corresponding i-th object, For target indicators The corresponding indicator value of the i-th object is the first percentage in the table. Let be the number of the first identifiers in the decision set corresponding to the index value of the i-th object. The number of second identifiers in the decision set corresponding to the index value of the i-th object.

4. The apparatus as described in claim 3, characterized in that, The acquisition module is specifically used to extract a selected indicator from the plurality of indicators; wherein the indicator value corresponding to the selected indicator is within a preset value range; the preset value range of the selected indicator is divided to obtain a plurality of sub-value ranges; wherein there are no overlapping value ranges among the plurality of sub-value ranges; different preset values ​​are configured for each of the plurality of sub-value ranges, and all configured preset values ​​are used as the indicator value corresponding to the selected indicator.

5. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a computer program stored in the memory, implements the method steps of any one of claims 1-2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-2.

Images