Business index determination method and device, electronic equipment and medium

Abstract

The invention provides a business index determination method and device, electronic equipment and a medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining a plurality of pieces of actual data, the actual data comprises an actual overall satisfaction degree, a plurality of sub-satisfaction degrees corresponding to a plurality of business impact factors, and a business index corresponding to each business impact factor; if the plurality of actual adjustment data are all smaller than the preset satisfaction degree, adjusting a service index corresponding to the service influence factor to obtain an adjusted service index; obtaining an estimated overall satisfaction degree through a score mapping model according to the adjusted business indexes and the sub-satisfaction degrees corresponding to the adjusted business indexes; and if the estimated overall satisfaction degree is greater than or equal to the preset satisfaction degree, determining the adjusted service index as a target service index, and simulating the adjusted service index through a score mapping model before implementation, thereby providing a basis for subsequently implementing the adjusted service index.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method, device, electronic device and medium for determining a business indicator. Background Art

[0002] For the overall satisfaction of the service, we can obtain the evaluation of the overall satisfaction of different users on the service so as to improve the service and enhance the overall satisfaction of the service. In the related art, after the improvement strategy is formulated according to the user's evaluation, it is impossible to accurately predict the results after the implementation of the strategy, and thus it is impossible to judge whether the improvement strategy is effective. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a method, device, electronic device and medium for determining a business indicator.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for determining a business indicator is provided, the method comprising: obtaining actual data corresponding to each actual user among multiple actual users to obtain multiple actual data, the actual data comprising an actual overall satisfaction degree, multiple sub-satisfaction degrees corresponding to multiple business impact factors associated with the actual overall satisfaction degree, and a business indicator corresponding to each business impact factor; if the multiple actual overall satisfaction degrees are all less than a preset satisfaction degree, adjusting the business indicator corresponding to the business impact factor to obtain an adjusted business indicator; inputting the adjusted business indicator and the sub-satisfaction degree corresponding to the business indicator into a score mapping model to obtain an estimated overall satisfaction degree output by the score mapping model; if the estimated overall satisfaction degree is greater than or equal to the preset satisfaction degree, determining the adjusted business indicator as the target business indicator.

[0005] Optionally, the score mapping model includes a correspondence between multiple bins and multiple Weight of Evidence (WOE) values, and there is a one-to-one correspondence between the multiple bins and the WOE values. Each of the multiple bins includes at least one business indicator corresponding to a business impact factor. The score mapping model is used to output an estimated overall satisfaction in the following manner: determining the bin to which each business indicator in the multiple adjusted business indicators belongs based on the adjusted business indicators and the sub-satisfaction levels corresponding to the business indicators; determining the WOE value corresponding to the bin to which each business indicator in the multiple adjusted business indicators belongs based on the correspondence, and obtaining multiple WOE values; and obtaining the estimated overall satisfaction corresponding to the adjusted business indicator based on the multiple WOE values.

[0006] Optionally, the score mapping model is trained in the following manner: N sample data are obtained, each of the N sample data includes the overall satisfaction of the sample, E seed satisfaction corresponding to each business impact factor of M business impact factors associated with the overall satisfaction of the sample, and business indicators corresponding to each business impact factor of the M business impact factors, the same business impact factor in the N sample data includes N business indicators, and N, M and E are all positive integers; the N business indicators corresponding to each business impact factor in the N sample data are grouped according to the same sub-satisfaction to obtain E groups, and the sub-satisfaction corresponding to the business indicator of each group in the E groups is the same; for each sub-satisfaction in the N sample data, The E groups corresponding to the satisfaction are binned respectively to obtain W bins corresponding to each sub-satisfaction level, where W is a positive integer; the WOE value corresponding to each bin is calculated according to the W bins corresponding to each sub-satisfaction level of each business impact factor, and the W WOE values ​​corresponding to each sub-satisfaction level are obtained; the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor are processed to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, where Z is a positive integer less than or equal to W; the initial score mapping model is iteratively trained through the Z WOE values ​​corresponding to each sub-satisfaction level in the N sample data and the overall sample satisfaction level corresponding to the N sample data to obtain the trained score mapping model.

[0007] Optionally, the E groups corresponding to each sub-satisfaction level in the N sample data are binned respectively to obtain W bins corresponding to each sub-satisfaction level, including: for the discrete business impact factors among the M business impact factors of the N sample data, each business indicator corresponding to each sub-satisfaction level of the discrete business impact factors is taken as a bin to obtain W bins corresponding to each sub-satisfaction level, where W is a positive integer less than or equal to N; for the continuous business impact factors among the M business impact factors of the N sample data, the business indicators corresponding to each sub-satisfaction level of the continuous business impact factors are binned to obtain W bins corresponding to each sub-satisfaction level, where at least one of the W bins contains at least two business indicators, and W is a positive integer less than N.

[0008] Optionally, when the business impact factor is continuous, the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor are processed to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, including: monotonizing the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain F bins corresponding to each sub-satisfaction level of each business impact factor, where F is a positive integer greater than or equal to W; obtaining F information values ​​(IV) corresponding to each sub-satisfaction level of each business impact factor according to the F bins corresponding to each sub-satisfaction level of each business impact factor; obtaining Z IV values ​​greater than or equal to a preset IV value among the F IV values ​​corresponding to each sub-satisfaction level of each business impact factor, and obtaining Z WOE values ​​corresponding to the Z IV values, where F is greater than or equal to Z.

[0009] Optionally, the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor are monotonized to obtain F bins corresponding to each sub-satisfaction level of each business impact factor, including: if the W WOE values ​​corresponding to the sub-satisfaction level do not satisfy the preset monotonicity, then the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction level are merged to obtain F bins corresponding to the sub-satisfaction level, where F is a positive integer less than W; if the W WOE values ​​corresponding to the sub-satisfaction level satisfy the preset monotonicity, then the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction level are determined as F bins, where F is equal to W.

[0010] Optionally, if the W WOE values ​​corresponding to the sub-satisfaction degree do not satisfy the preset monotonicity, the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction degree are merged to obtain F bins corresponding to the sub-satisfaction degree, including: if the W WOE values ​​corresponding to the sub-satisfaction degree do not satisfy the preset monotonicity, the bin corresponding to the WOE value that does not satisfy the preset monotonicity among the W WOE values ​​is merged with an adjacent bin to obtain F bins corresponding to the sub-satisfaction degree.

[0011] Optionally, the method further includes: calculating the WOE value of each bin according to the F bins corresponding to the sub-satisfaction level, and obtaining the F WOE values ​​corresponding to the sub-satisfaction level; if the F WOE values ​​corresponding to the sub-satisfaction level do not satisfy the preset monotonicity, merging the F bins corresponding to the sub-satisfaction level until the WOE value corresponding to the sub-satisfaction level satisfies the preset monotonicity or the number of bins corresponding to the sub-satisfaction level is 1.

[0012] Optionally, the method further includes: converting the estimated overall satisfaction into a satisfaction score; if the satisfaction score is greater than or equal to a preset score, determining the adjusted business indicator as the target business indicator.

[0013] According to a second aspect of an embodiment of the present disclosure, a business indicator determination device is provided, the device comprising: an acquisition module, used to acquire actual data corresponding to each actual user among multiple actual users, to obtain multiple actual data, the actual data comprising an actual overall satisfaction degree, multiple sub-satisfaction degrees corresponding to multiple business impact factors associated with the actual overall satisfaction degree, and a business indicator corresponding to each business impact factor; an adjustment module, used to adjust the business indicator corresponding to the business impact factor if the multiple actual overall satisfaction degrees are all less than a preset satisfaction degree, to obtain an adjusted business indicator; a mapping module, used to input the multiple adjusted business indicators and the sub-satisfaction degrees corresponding to the business indicators into a score mapping model, to obtain an estimated overall satisfaction degree output by the score mapping model; a determination module, used to determine that the adjusted business indicator is a target business indicator if the estimated overall satisfaction degree is greater than or equal to the preset satisfaction degree.

[0014] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to: implement the steps of the method described in the first aspect when executing the instructions.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the business indicator determination method provided in the first aspect of the present disclosure are implemented.

[0016] The present disclosure provides a method, device, electronic device and medium for determining a business indicator, obtaining actual data corresponding to each actual user among multiple actual users, and obtaining multiple actual data, wherein the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor; if multiple actual adjustment data are all less than the preset satisfaction, the business indicator corresponding to the business impact factor is adjusted to obtain the adjusted business indicator; then, the estimated overall satisfaction corresponding to the adjusted business indicator is obtained according to the adjusted business indicator and the sub-satisfaction corresponding to the adjusted business indicator through a score mapping model; if the estimated overall satisfaction is greater than or equal to the preset satisfaction, the adjusted business indicator is determined to be the target business indicator. Through the above method, the adjusted business indicator is simulated through the score mapping model before implementation, providing a basis for the subsequent implementation of the adjusted business indicator. In addition, the improvement of the overall satisfaction is subdivided into the target business indicator corresponding to each sub-satisfaction, which can improve the accuracy of the adjustment.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0019] Figure 1 is a flow chart of a method for determining a business indicator according to an exemplary embodiment;

[0020] Figure 2 is a flow chart of a method for determining a business indicator according to another exemplary embodiment;

[0021] Figure 3 An embodiment is shown Figure 2 Flow chart of step S250 in FIG.

[0022] Figure 4 is a flow chart of a method for determining a business indicator according to another exemplary embodiment;

[0023] Figure 5 is a flow chart of a method for determining a business indicator according to another exemplary embodiment;

[0024] Figure 6 is a block diagram of a device for determining a business indicator according to an exemplary embodiment;

[0025] Figure 7 The invention is a block diagram of an electronic device showing a method for determining a business indicator according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0027] For the overall satisfaction of services, such as sales services, we can obtain different users' evaluations of their overall satisfaction with the services so as to improve the services and enhance the overall satisfaction with the services.

[0028] In the related art, there are multiple factors affecting the overall satisfaction with the service. Since multiple factors have different effects on the overall satisfaction with the service, for example, the overall satisfaction may be the overall satisfaction with the shopping service, and the multiple factors affecting the overall satisfaction may be logistics timeliness and delivery services, etc. Improvement strategies can be formulated based on the user's evaluation of the service to adjust different influencing factors. However, different influencing factors have different effects on the improvement of the overall satisfaction of users, and it is impossible to accurately predict the results achieved after the implementation of the strategy, and thus it is impossible to judge whether the improvement strategy is effective.

[0029] Based on the above technical problems, the present disclosure provides a business indicator determination method, device, electronic device and medium, which adjusts the business indicator corresponding to the business impact factor in the lower actual satisfaction, and then estimates the adjusted business indicator through a sub-mapping model to obtain an estimated overall satisfaction, thereby determining whether the adjusted business indicator meets expectations, and the adjusted business indicator can be estimated in advance before implementation, so that subsequent implementation can achieve better results. The specific business indicator determination method is described in the subsequent implementation method.

[0030] The present disclosure provides a method for determining a business indicator. Figure 1 , Figure 1 is a flowchart of a method for determining a business indicator according to an exemplary embodiment. The method for determining a business indicator can be applied to Figure 6 The business indicator determination device 500 shown, Figure 7 The electronic device 600 shown, Figure 7 The processor 620 and the computer readable storage medium in this embodiment are used as an example of an electronic device, where the electronic device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a server, etc. Figure 1 The process shown is described in detail, and the business indicator determination method may specifically include the following steps:

[0031] Step S110, obtaining actual data corresponding to each actual user among multiple actual users to obtain multiple actual data, wherein the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor.

[0032] In this embodiment, the multiple actual users may be users related to the target service, and the target service may be a sales service, an online shopping service, and the like. For example, for the online shopping service, the multiple actual users may be multiple shopping users in a recent period of time. The multiple actual data may be obtained through a questionnaire survey, for example, a satisfaction survey form is sent to multiple actual users, and the satisfaction survey form may be a total score structure, and the satisfaction survey form may ask about the actual overall satisfaction and multiple sub-satisfactions associated with the actual overall satisfaction. The actual overall satisfaction and the sub-satisfaction may both be an interval value, such as an integer value between 1 and 10, or an integer value between 1 and 5, and the actual overall satisfaction and the sub-satisfaction may also both be satisfaction levels, for example, including multiple levels such as "very satisfied", "satisfied", "average", "unsatisfied", and "very unsatisfied".

[0033] The business impact factor directly affects its corresponding sub-satisfaction. When the sub-satisfaction is a numerical value, it represents the user's satisfaction with a single business impact factor of the target service. The higher the value, the greater the satisfaction. Business impact factors include logistics carriers, logistics timeliness, product packaging, etc. When the actual overall satisfaction is an integer value, it represents the user's overall satisfaction with the target service. The higher the value, the greater the user's satisfaction.

[0034] A single business impact factor affects a sub-satisfaction, and multiple business impact factors combined affect the user's actual overall satisfaction. For example, business impact factors can be shipping warehouse, carrier, shipping place, receiving place, purchase channel, warehouse departure time, delivery time, and delivery time, among which delivery time is the time between the package leaving the warehouse and the user signing for it. The overall satisfaction can be associated with multiple business impact factors. Through the satisfaction survey form, the actual overall satisfaction and multiple sub-satisfactions corresponding to each actual user can be obtained.

[0035] For example, in a scenario where the target service is an online shopping service, after a user confirms receipt of an order, a questionnaire is displayed on a shopping application or a text message application of the user's user device. The questionnaire is shown in Table 1:

[0036] Table 1

[0037]

[0038] like Figure 1 As shown in Table 1, the questionnaire shows the overall satisfaction with the target service and multiple sub-satisfactions that constitute the overall satisfaction. As shown in Table 1, the sub-satisfaction includes the delivery service sub-satisfaction and the logistics packaging sub-satisfaction. It should be noted that the sub-satisfaction of the questionnaire is not limited to the two types in Table 1, and more types can be set according to actual needs.

[0039] The user inputs input based on the questionnaire displayed on the user device. After the user completes the questionnaire, the completed questionnaire is collected. The completed questionnaire may be as shown in Table 2:

[0040] Table 2

[0041]

[0042] According to Table 2, we can read that the user's actual overall satisfaction is 3, the delivery service sub-satisfaction is 2, and the logistics packaging sub-satisfaction is 4.

[0043] For multiple users who have made purchases in the recent period, random sampling, stratified sampling, systematic sampling and other sampling methods can be used to determine the user sample, and then the questionnaires shown in Table 1 are distributed to each user device, thereby obtaining multiple filled questionnaires. In order to ensure the reliability of the data in the questionnaire, the multiple questionnaires collected can be cleaned. For example, the data cleaning method can delete the following questionnaires: questionnaires with answer time less than the preset time, questionnaires with the proportion of unanswered questions greater than the preset proportion, where the preset time can be pre-set according to the length of the questionnaire. For example, if the length of the questionnaire is longer, the preset time can be a longer time, for example, the preset time can be 3 minutes, 5 minutes, etc.; if the length of the questionnaire is shorter, the preset time can be a shorter time, for example, the preset time can be 15 seconds, 30 seconds. The preset proportion of the questionnaire can also be pre-set, for example, the preset proportion can be 60%, 65%, etc.

[0044] The association between sub-satisfaction and business impact factors is preset, for example, the association between logistics packaging sub-satisfaction and delivery time, and the association between delivery service and logistics carrier. It can be understood that the sub-satisfaction is affected by the business impact factor associated with it, or the sub-satisfaction is used to characterize the user's satisfaction with the associated business impact factor. The business impact factor includes specific business indicators. For example, the business impact factor is the logistics carrier, and the corresponding business indicator can be logistics carrier A, logistics carrier B, etc. For another example, the business impact factor is the delivery time, and the corresponding business indicator can be 24 hours, 30 hours, 43 hours, etc. The sub-satisfaction is presented in the form of a questionnaire, and the business impact factor can be obtained through order information. Therefore, the questionnaire after data cleaning is spliced ​​with the order information of the corresponding user. Through data splicing, the questionnaire is associated with the user's order information, and the sub-satisfaction is also associated with the corresponding business indicator.

[0045] Optionally, the order information includes but is not limited to the following information: SKU (Stock Keeping Unit), shipping warehouse, logistics carrier, shipping place, receiving place, purchase channel, shipment time, delivery time, and packaging ID (Identification).

[0046] Step S120: If the multiple actual overall satisfaction levels are all less than the preset satisfaction levels, the business indicators corresponding to the business impact factors are adjusted to obtain adjusted business indicators.

[0047] Optionally, a preset satisfaction level is pre-set. Taking the overall satisfaction level as an integer value between 1 and 5 as an example, the preset satisfaction level may be 4.

[0048] In one embodiment, multiple actual overall satisfactions that are less than a preset satisfaction are screened out from the orders. The multiple actual overall satisfactions are low, and improvements can be made to this part to improve the satisfaction of this part of users. Exemplarily, for business impact factors with low sub-satisfaction, refer to the business indicators corresponding to the same business impact factor in orders with actual overall satisfaction greater than the preset satisfaction, and adjust the business indicators corresponding to the business impact factor in orders with actual satisfaction less than the preset satisfaction. For example, the sub-satisfaction is the logistics packaging sub-satisfaction, and the business impact factor corresponding to the sub-satisfaction is the logistics carrier. The logistics carrier corresponding to the logistics packaging sub-satisfaction is adjusted from A to B, or the proportion of logistics carriers is adjusted, and the original proportion of logistics carrier A is adjusted to 25% from 30%, and the original proportion of logistics carrier B is adjusted to 35%.

[0049] In another implementation, actual data with overall satisfaction levels lower than preset satisfaction levels are all stored in the same database, and multiple actual data are directly acquired from the database.

[0050] Optionally, when conducting a questionnaire survey, if the actual overall satisfaction of the actual user is less than the preset satisfaction, the user's electronic device will be redirected to ask the reason for dissatisfaction, and the user will fill in the reason for dissatisfaction based on the inquiry. When the business indicators are subsequently adjusted, adjustments can be made based on the user's reasons for dissatisfaction to obtain adjusted business indicators.

[0051] Optionally, when making adjustments, each of the multiple business impact factors can be adjusted. Some of the multiple business impact factors can also be adjusted. For example, for a certain business impact factor, in all actual data, the proportion of business impact factors below the preset satisfaction level in the satisfaction level corresponding to the business impact factor is greater than the preset proportion. It can be considered that the satisfaction level of the business impact factor is generally low, and the business impact factor is adjusted, wherein the preset proportion can be 80%, 65%, etc. Exemplarily, in an actual data, each business impact factor corresponds to a sub-satisfaction level, then in the multiple actual data of this embodiment, each business factor corresponds to multiple sub-satisfaction levels. Calculate the average satisfaction level of the sub-satisfaction levels corresponding to each business factor. Since there are multiple business impact factors in each actual data, the number of average satisfaction levels is also multiple accordingly. Select the business impact factor to be adjusted according to the average satisfaction level, such as selecting the business impact factor corresponding to the average satisfaction level below the preset average satisfaction level for adjustment. Alternatively, sort the multiple average satisfaction levels in order from small to large, and select the business impact factor corresponding to the preset number of average satisfaction levels that are ranked first for adjustment.

[0052] Step S130: input the adjusted business indicator and the sub-satisfaction corresponding to the business indicator into a score mapping model to obtain an estimated overall satisfaction output by the score mapping model.

[0053] In one implementation, the pre-trained score mapping model is stored locally in the electronic device, the electronic device directly obtains the score mapping model locally, inputs the adjusted business indicator into the score mapping model, and obtains the estimated overall satisfaction output by the score mapping model. In this embodiment, the score mapping model is stored locally in the electronic device, and the electronic device can quickly call the score mapping model to quickly obtain the estimated overall satisfaction.

[0054] In another embodiment, the pre-trained score mapping model is stored in a server that is in communication with the electronic device. The electronic device obtains the score mapping model from the server, inputs the adjusted business indicator into the score mapping model, and obtains the estimated overall satisfaction output by the score mapping model. In this embodiment, the score mapping model is stored in the server, which can reduce the local memory usage of the electronic device.

[0055] Step S140: If the estimated overall satisfaction is greater than or equal to the preset satisfaction, determining the adjusted business indicator as the target business indicator.

[0056] If the estimated overall satisfaction is less than the preset satisfaction, the satisfaction improvement effect achieved by implementing the adjusted business indicators will not be significant. If the estimated overall satisfaction is greater than or equal to the preset satisfaction, the satisfaction improvement effect achieved by implementing the adjusted business indicators will be significant, then the adjusted business indicators will be determined as the target business indicators.

[0057] Optionally, the target business indicator can be displayed on the electronic device, or saved in a preset location of the electronic device, so as to be convenient for implementation personnel to view and provide a basis or reference for subsequent implementation.

[0058] The business indicator determination method provided in this embodiment obtains actual data corresponding to each actual user among multiple actual users to obtain multiple actual data, and the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor; if multiple actual adjustment data are all less than the preset satisfaction, the business indicator corresponding to the business impact factor is adjusted to obtain the adjusted business indicator; then, the estimated overall satisfaction corresponding to the adjusted business indicator is obtained according to the adjusted business indicator and the sub-satisfaction corresponding to the adjusted business indicator through the score mapping model; if the estimated overall satisfaction is greater than or equal to the preset satisfaction, the adjusted business indicator is determined to be the target business indicator. Through the above method, the adjusted business indicator is simulated through the score mapping model before implementation, providing a basis for the subsequent implementation of the adjusted business indicator. In addition, the improvement of overall satisfaction is subdivided into the target business indicator corresponding to each sub-satisfaction, which can improve the accuracy of adjustment.

[0059] Optionally, before step S130, the method further includes training a score mapping model, see Figure 2 , for example, the score mapping model is trained as follows:

[0060] Step S210, obtain N sample data, each of the N sample data includes the overall satisfaction of the sample, E seed satisfaction corresponding to each business impact factor of M business impact factors associated with the overall satisfaction of the sample, and business indicators corresponding to each business impact factor of the M business impact factors, the same business impact factor in the N sample data includes N business indicators, and N, M and E are all positive integers.

[0061] In one embodiment, actual data obtained according to historical questionnaires are stored in the database. N actual data are obtained from the database as N sample data, thereby obtaining N sample data.

[0062] Step S220: group the N business indicators corresponding to each business impact factor in the N sample data according to the same sub-satisfaction level to obtain E groups, wherein the sub-satisfaction level corresponding to the business indicator of each group in the E groups is the same.

[0063] Each of the N sample data contains M business impact factors, and each business impact factor in each sample data corresponds to a business indicator. Then, in the N sample data, the same business impact factor has N business indicators. The same business impact factor in the N sample data is scored by different actual users. Therefore, the N business indicators corresponding to the same business impact factor correspond to different sub-satisfactions. The N business indicators are grouped, and the business indicators corresponding to the same sub-satisfaction are divided into one group, and the N business indicators are divided into E groups.

[0064] It should be noted that the business indicators corresponding to the M business impact factors need to be divided into E groups according to the above method. For different business impact factors, the number of groups E divided is different according to the different sub-satisfactions corresponding to the actual users. For example, for the business impact factor express carrier, there are four sub-satisfactions corresponding to 2 points, 3 points, 4 points and 5 points, and the corresponding number of groups E is 4. For another example, for the business response factor delivery time, there are five types of satisfaction corresponding to 1 point, 2 points, 3 points, 4 points and 5 points, and the corresponding number of groups E is 5.

[0065] Step S230: binning the E groups corresponding to each sub-satisfaction level in the N sample data to obtain W bins corresponding to each sub-satisfaction level, where W is a positive integer.

[0066] The E groups corresponding to each sub-satisfaction level are binned according to a preset binning strategy to obtain W bins corresponding to each sub-satisfaction level. It is understandable that each of the E groups corresponding to each sub-satisfaction level of each business impact factor is binned to obtain W bins corresponding to each satisfaction level. It is understandable that each bin SFO it There are attributes in two dimensions: satisfaction dimension and business indicator scope.

[0067] It should be noted that each of the E groups in the same business impact factor is binned to obtain W bins corresponding to each group. Since the satisfaction level corresponding to each group in the E groups is different, it can also be understood as obtaining W bins corresponding to each satisfaction level. Since the number and distribution of business indicators contained in each group are different, the number of bins W obtained for each group is also different.

[0068] In one embodiment, the business impact factor has two types: discrete and continuous. The discrete business impact factor can be gender, name, preference, etc., and the continuous business impact factor can be height, age, delivery time, etc. When the business impact factor is discrete, the corresponding business indicator is also discrete. For example, the business impact factor is gender, and the corresponding business indicator is male or female. When the business impact factor is continuous, the corresponding business indicator is also continuous. For example, the business impact factor is height, and the corresponding business indicator is 172 cm, 180 cm, etc. Therefore, the type of the business impact factor is consistent with the type of the corresponding business indicator. In this embodiment, binning can be performed according to the type of the business impact factor or the business indicator. For example, for the discrete business impact factor in the M business impact factors of the N sample data, each business indicator corresponding to each sub-satisfaction of the discrete business impact factor is used as a bin, and W bins corresponding to each sub-satisfaction are obtained. W is a positive integer less than or equal to N. It can be understood that for the discrete business impact factor, the corresponding business indicator, each business indicator is used as a bin, and each bin contains only one business indicator. For the continuous business impact factors among the M business impact factors of the N sample data, the business indicators corresponding to each sub-satisfaction of the continuous business impact factors are binned to obtain W bins corresponding to each sub-satisfaction, at least one of the W bins contains at least two business indicators, and W is a positive integer less than N. Optionally, the continuous business impact factors can be binned according to binning strategies such as equal frequency binning, equal interval binning, chi-square binning, and minimum entropy binning. Exemplarily, for delivery timeliness, there are five corresponding sub-satisfactions, 1 to 5, and the delivery timeliness corresponding to each sub-satisfaction is divided into [0, 24h) and [24h, +∞). Since there are five satisfactions corresponding to delivery timeliness, the delivery timeliness is binned to obtain 2*5=10 bins.

[0069] Step S240: Calculate the WOE value corresponding to each bin according to the W bins corresponding to each sub-satisfaction level of each business impact factor, and obtain the W WOE values ​​corresponding to each sub-satisfaction level.

[0070] According to the business indicators in each sub-box, the WOE value corresponding to each sub-box is calculated. The WOE value represents the ratio of the number of good users to the number of bad users in a certain segment. In this embodiment, the WOE value represents the ratio between the sub-satisfaction representing satisfaction and the sub-satisfaction representing dissatisfaction in a sub-box.

[0071] It should be noted that, in the W sub-boxes corresponding to the E groups obtained by dividing each sub-satisfaction level of each business impact factor in the M business impact factors in the N sample data, the WOE value needs to be calculated for each sub-box.

[0072] Establish a corresponding relationship between each bin corresponding to each sub-satisfaction and its corresponding WOE value.

[0073] Step S250: Process the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, where Z is a positive integer less than or equal to W.

[0074] In one embodiment, see Figure 3 , step S250 comprises the following steps:

[0075] Step S251: Monotonize the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain F bins corresponding to each sub-satisfaction level of each business impact factor, where F is a positive integer greater than or equal to W.

[0076] The W WOE values ​​are subjected to monotonic processing, aiming at satisfying monotonically increasing or monotonically decreasing requirements of the processed W WOE values.

[0077] As a method, if the W WOE values ​​corresponding to the sub-satisfaction satisfy the preset monotonicity, the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction are determined as F bins, where F is equal to W. If the W WOE values ​​corresponding to the sub-satisfaction do not satisfy the preset monotonicity, the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction are combined to obtain F bins corresponding to the sub-satisfaction, where F is a positive integer less than W. For example, if the W WOE values ​​corresponding to the sub-satisfaction do not satisfy the preset monotonicity, the bins corresponding to the WOE values ​​that do not satisfy the preset monotonicity in the W WOE values ​​are combined with an adjacent bin to obtain F bins corresponding to the sub-satisfaction. Optionally, the business indicators in a bin adjacent to the bin corresponding to the WOE value that does not satisfy the preset monotonicity on both sides can be obtained, and an adjacent bin whose business indicator is greater than the business indicator in the bin corresponding to the WOE value that does not satisfy the preset monotonicity is selected and combined with the bin corresponding to the WOE value that does not satisfy the preset monotonicity.

[0078] Optionally, the WOE value of each bin is calculated according to the F bins corresponding to the sub-satisfaction, and the F WOE values ​​corresponding to the sub-satisfaction are obtained; if the F WOE values ​​corresponding to the sub-satisfaction do not satisfy the preset monotonicity, the F bins corresponding to the sub-satisfaction are combined until the WOE value corresponding to the sub-satisfaction satisfies the preset monotonicity or the bin corresponding to the sub-satisfaction is 1. If the sub-satisfaction is finally combined into 1 bin after the bin combination, the bin is removed.

[0079] Optionally, the preset monotonicity may be monotonically increasing or monotonically decreasing.

[0080] Step S252: Obtain F information value IV values ​​corresponding to each sub-satisfaction level of each business impact factor according to the F sub-boxes corresponding to each sub-satisfaction level of each business impact factor.

[0081] According to the business indicators in the F sub-boxes corresponding to each sub-satisfaction level, the F information value IV values ​​corresponding to each sub-satisfaction level of each business influencing factor are calculated.

[0082] Step S253: Obtain Z IV values ​​greater than or equal to the preset IV value among the F IV values ​​corresponding to each sub-satisfaction of each business impact factor, and obtain Z WOE values ​​corresponding to the Z IV values, where F is greater than or equal to Z.

[0083] Eliminate IV values ​​that are less than the preset IV value, and obtain Z IV values ​​whose IV values ​​are greater than or equal to the preset IV value.

[0084] Optionally, the preset IV value may be 0.25.

[0085] Step S260: iteratively train the initial score mapping model using the Z WOE values ​​corresponding to each sub-satisfaction level in the N sample data and the sample overall satisfaction level corresponding to the N sample data to obtain a trained score mapping model.

[0086] In one embodiment, N sample data are divided into first sample data and second sample data, and Z WOE values ​​corresponding to each sub-satisfaction of each business impact factor in the M business impact factors corresponding to the first sample data are input into the initial score mapping model to obtain the first estimated satisfaction, and the AUC (Area Under the Curve) corresponding to the first estimated satisfaction is obtained. Similarly, Z WOE values ​​corresponding to each sub-satisfaction of each business impact factor in the M business impact factors corresponding to the second sample data are input into the initial score mapping model to obtain the second estimated satisfaction, and the AUC corresponding to the second estimated satisfaction is obtained. If the absolute value of the difference between the AUC corresponding to the first estimated satisfaction and the AUC corresponding to the second estimated satisfaction is less than 0.02, it is considered that the model has a strong generalization ability, and the model is used as the trained score mapping model. On the contrary, if the absolute value of the difference between the two is greater than or equal to 0.02, it is considered that the generalization ability of the model is weak, and the model is subjected to L1 or L2 regularization processing until the absolute value of the difference between the AUCs is less than 0.02.

[0087] Optionally, the score mapping model may be a Logistic regression model.

[0088] The obtained trained score mapping model establishes a mapping relationship between multiple WOE values ​​and each overall satisfaction. The score mapping model can be expressed by the following formula:

[0089]

[0090] in, is to estimate the overall satisfaction, α is the intercept term of the score mapping model, n is the number of sub-satisfactions, m is the number of business influencing factors, g is the number of final bins of multiple actual data, and β it is the slope of the tth business impact factor of the ith sub-satisfaction, woe itr is the woe value of the rth bin of the tth business impact factor of the i-th sub-satisfaction, θ itr Whether to take the rth bin of the tth business impact factor of the ith sub-satisfaction is a binary variable, which is 1 if yes and 0 otherwise.

[0091] Optionally, the method further includes: converting the estimated overall satisfaction into a satisfaction score, and if the satisfaction score is greater than or equal to a preset score, determining the adjusted business indicator as the target business indicator.

[0092] For example, the estimated overall satisfaction is in the form of a score, the estimated overall satisfaction is in the first score formula, the satisfaction score is in the second score formula, and the conversion relationship between the first score formula and the second score formula is as follows:

[0093]

[0094] Among them, score is the satisfaction score, To estimate overall satisfaction.

[0095] The above offset and factor can be calculated based on the score interval corresponding to the first score formula and the sample corresponding to the second score formula. For example, the first score formula is a 5-point system, and the corresponding interval is [0,5], and the second score formula is a 100-point system, and the corresponding interval is [0,100]. Substituting the endpoint extreme values ​​of the two intervals into the above formula, the offset and factor can be obtained. Converting the estimated overall satisfaction into a familiar satisfaction score facilitates intuitive understanding of the adjusted business indicator after simulation.

[0096] In a possible implementation, the score mapping model includes a correspondence between multiple bins and multiple weight of evidence WOE values, which has been established in the model training stage. The multiple bins correspond to the WOE values ​​one by one, and each bin in the multiple bins includes at least one business indicator corresponding to a business impact factor. The score mapping model is used to output the estimated overall satisfaction in the following manner: according to the adjusted business indicators and the sub-satisfaction corresponding to the business indicators, determine the bin to which each business indicator in the multiple adjusted business indicators belongs, and the bins are divided according to the same sub-satisfaction of the same business impact factor. It can be understood that the business indicators corresponding to the same sub-satisfaction of the same business impact factor are obtained, and then the business indicators are binned to obtain multiple bins. Based on the correspondence, the WOE value corresponding to the bin to which each business indicator in the multiple adjusted business indicators belongs is determined to obtain multiple WOE values. According to the multiple WOE values, the estimated overall satisfaction corresponding to the adjusted business indicator is obtained, for example, based on the mapping relationship between the multiple WOE values ​​and each overall satisfaction, the estimated overall satisfaction is obtained.

[0097] Optionally, in one embodiment, in order to ensure the feasibility of the adjusted business indicators, multiple groups of samples to be improved can be collected, and the business indicators in the multiple groups of samples to be improved can be adjusted in the same adjustment method, and then the multiple groups of samples to be improved are respectively input into the score mapping model to obtain the estimated overall satisfaction corresponding to each group output by the score mapping model, and then calculate whether the overall satisfaction is greater than the preset satisfaction. If the overall satisfaction is greater than the preset satisfaction, the adjusted business indicators are determined to be the target business indicators. Among them, the multiple experimental data in step S110 can be one group of the multiple groups of samples to be improved, and the samples to be improved can be 6 groups. In this embodiment, the adjusted business indicators are respectively applied to the multiple groups of samples to be improved, and then the improved multiple groups of samples to be improved are simulated. After the mean of the simulation results of the multiple groups of samples to be improved meets the expectations, the adjusted business indicators are determined to be the target business indicators that can be implemented later, ensuring that after the adjusted business indicators are implemented, the improvement of user satisfaction can achieve the expected effect.

[0098] This disclosure also provides a method for determining a business indicator. Figure 4 , the business indicator determination method comprises the following steps:

[0099] Step S301: Questionnaire design.

[0100] It is mainly conducted on satisfaction survey questionnaires, which include overall satisfaction and sub-satisfaction of other business processes that affect the overall satisfaction, such as logistics timeliness sub-satisfaction, package sub-satisfaction, etc.

[0101] Step S302: Distribute questionnaires.

[0102] The sampling group is customers who have purchasing behavior in a certain period of time. Random sampling, stratified sampling, systematic sampling and other sampling methods can be used to determine the sample, and then the questionnaire is distributed according to the determined sample. The specific distribution method can be to push the questionnaire through short messages and other methods.

[0103] Step S303: Questionnaire collection.

[0104] Since the questionnaire survey is conducted online, users can complete the questionnaire collection by submitting it on their corresponding user devices.

[0105] Step S304: data cleaning.

[0106] Data cleaning is performed on the data that has been collected, such as deleting questionnaires with too short an answer time. Questionnaires present a large area of ​​missing data, and the missing percentage can be pre-defined. If more than 60% of the questions are not answered (excluding jump questions), it is determined to be abnormal data and deleted.

[0107] Step S305: data splicing and exploration.

[0108] The data of the customer's most recent purchase order from the time the questionnaire was distributed are spliced. The purchase order includes but is not limited to the following information: SKU, shipping warehouse, carrier, shipping location, receiving location, purchase channel, shipment time, successful delivery time, and packaging ID.

[0109] Conduct frequency distribution statistics on the cleaned data to check the distribution of various satisfaction factors of the surveyed customer groups.

[0110] Step S306: Determine the satisfactory label.

[0111] If the overall satisfaction is greater than or equal to the preset satisfaction, it is 1, otherwise it is 0.

[0112] Step S307: Determine the business indicators that affect each sub-satisfaction.

[0113] The basic structure of the questionnaire questions is the total score. First, the overall satisfaction S is inquired, followed by the sub-satisfaction Si that constitutes the overall satisfaction, such as logistics timeliness satisfaction, package sub-satisfaction, delivery service sub-satisfaction, etc. This step is mainly to determine the business influencing factors Oit of sub-satisfaction Si. For example, the business influencing factors Oit of logistics timeliness sub-satisfaction Si include the following business indicators: whether the order arrives the next day, the carrier, and the province / city where the order is located. Packaging sub-satisfaction influencing factors: packaging type (box / bag). The business influencing factors of delivery service sub-satisfaction include carriers, etc.

[0114] Step S308: construct a combination variable of each sub-satisfaction index and a business indicator.

[0115] After determining the business impact factor Oit of the sub-satisfaction Si, the business factor Oit is grouped to form a new grouping feature SFO it .

[0116] Step S309: Split the training set into a test set.

[0117] Split the sample data of the survey into a training set and a test set. For example, the training set accounts for 80% of the sample data, and the test set accounts for 20% of the sample data.

[0118] Step S310: determine the order of WOE between sub-combination variable groups.

[0119] Step S311: Calculate the WOE of the monotonic combined features.

[0120] Step S312: Combined feature screening.

[0121] Calculate the IV value of the monotonic combined feature SFOit, and then select the combined feature SFO according to the IV value greater than or equal to 0.25 it .

[0122] Step S313: Building a logistic regression model.

[0123] Step S314: construct a scorecard.

[0124] Step S315: strategy simulation.

[0125] The detailed description of steps S301 to S315 of the method for determining the business indicator provided in this embodiment can be found in the above embodiment and will not be repeated here.

[0126] This disclosure also provides a method for determining a business indicator. Figure 5 , the business indicator determination method comprises the following steps:

[0127] Step S401: Use the newly generated score card to score each customer.

[0128] Step S402: Find the passing score.

[0129] Step S403: Determine improvement items.

[0130] Step S404: Determine the goals that are expected to be achieved in the improvement project.

[0131] Step S405: Determine the impact ratio of the improvement project.

[0132] In order to improve the project, the business side needs to conduct research and judgment, and the proportion of customers with this problem that can be improved through business actions, where the improvement proportion is correct_prob. The business logic is that a business action improvement will not improve every customer, and it is generally unclear which customers have been improved. However, the proportion of customers expected to be improved can be estimated. For example, changing the carrier is expected to improve next-day delivery from 50% to 60%.

[0133] Step S406: Determine samples to be improved.

[0134] Step S407: Determine the sampling times Q.

[0135] In order to avoid the randomness caused by single sampling, it is repeated 6Q times.

[0136] Step S408: Whether the number of sampling times is greater than Q.

[0137] Step S409: Sampling is performed according to the project improvement ratio.

[0138] Step S410: modify the items to be improved among the extracted customers.

[0139] Step S411: Use the score card to score the overall customer again.

[0140] Step S412: if the score is greater than the passing score, it is considered satisfactory; otherwise, it is considered unsatisfactory.

[0141] Step S413: Calculate the satisfaction ratio of improving the item.

[0142] Step S414: Calculate the average of the satisfaction ratios as the final satisfaction ratio.

[0143] Step S415: Determine whether the improvement project meets expectations.

[0144] Step S416: The project improvement can meet expectations.

[0145] Step S417: The improvement of the project cannot meet expectations.

[0146] The detailed description of steps S401 to S417 of the method for determining the business indicator provided in this embodiment can be found in the above embodiment and will not be repeated here.

[0147] The business indicator determination method provided by the present disclosure solves the problem that the scorecard cannot be built due to the lack of a strong relationship between business indicators and overall satisfaction. The solution to this problem has greatly helped business improvements oriented to improve overall satisfaction. The output after simulation can quantify the relationship between linkage business improvements and overall satisfaction improvement. The provision of a model simulation method provides a mathematical basis for the impact of indicator improvement on overall satisfaction, and can determine whether the business clearly sets the overall satisfaction indicator. By simulating the impact of business action improvements on overall satisfaction, the business can clearly see whether the business actions can achieve the expected results, which also provides a management basis and data support for the business's later business improvement direction. Under limited cost conditions, through simulation, the business can be guided in the fastest and lowest cost direction to improve satisfaction.

[0148] To implement the above method embodiments, the present disclosure also provides a business indicator determination device, see Figure 6 , the business indicator determination device 500 includes:

[0149] An acquisition module 510 is used to acquire actual data corresponding to each actual user among multiple actual users, and obtain multiple actual data, wherein the actual data includes an actual overall satisfaction degree, multiple sub-satisfaction degrees corresponding to multiple business impact factors associated with the actual overall satisfaction degree, and a business indicator corresponding to each business impact factor;

[0150] An adjustment module 520, configured to adjust the business indicator corresponding to the business impact factor to obtain an adjusted business indicator if the multiple actual overall satisfaction levels are all less than a preset satisfaction level;

[0151] A mapping module 530 is used to input the multiple adjusted business indicators and the sub-satisfactions corresponding to the business indicators into a score mapping model to obtain an estimated overall satisfaction output by the score mapping model;

[0152] The determination module 540 is configured to determine that the adjusted business indicator is a target business indicator if the estimated overall satisfaction level is greater than or equal to the preset satisfaction level.

[0153] Optionally, the score mapping model includes a correspondence between a plurality of bins and a plurality of weight of evidence WOE values, the plurality of bins correspond to the WOE values ​​one-to-one, each bin in the plurality of bins includes at least one business indicator corresponding to a business impact factor, and the business indicator determination device 500 further includes:

[0154] A bin determination module, configured to determine the bin to which each business indicator in the plurality of adjusted business indicators belongs according to the adjusted business indicator and the sub-satisfaction level corresponding to the adjusted business indicator;

[0155] A WOE value determination module, configured to determine, based on the corresponding relationship, the WOE value corresponding to the sub-box to which each business indicator in the plurality of adjusted business indicators belongs, and obtain a plurality of WOE values;

[0156] A mapping module is used to obtain the estimated overall satisfaction corresponding to the adjusted business indicator according to the multiple WOE values.

[0157] Optionally, the business indicator determination device 500 further includes:

[0158] A sample acquisition module is used to acquire N sample data, each of the N sample data includes the overall satisfaction of the sample, E seed satisfaction corresponding to each business impact factor of M business impact factors associated with the overall satisfaction of the sample, and a business indicator corresponding to each business impact factor of the M business impact factors, the same business impact factor in the N sample data includes N business indicators, and N, M and E are all positive integers;

[0159] A grouping module, used for grouping the N business indicators corresponding to each business impact factor of the M business impact factors of the N sample data according to the same sub-satisfaction degree to obtain E groups, wherein the sub-satisfaction degree corresponding to the business indicator of each group in the E groups is the same;

[0160] A binning processing module is used to bin the E groups corresponding to each sub-satisfaction level of each business impact factor in the M business impact factors of the N sample data, to obtain W bins corresponding to each sub-satisfaction level, where W is a positive integer;

[0161] A WOE value calculation module, used to calculate the WOE value corresponding to each sub-box according to the W sub-boxes corresponding to each sub-satisfaction of each business impact factor, and obtain the W WOE values ​​corresponding to each sub-satisfaction;

[0162] A WOE value processing module, used to process W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, where Z is a positive integer less than or equal to W;

[0163] A training module is used to iteratively train the initial score mapping model through the Z WOE values ​​corresponding to each sub-satisfaction of each business impact factor in the M business impact factors of the N sample data and the overall sample satisfaction corresponding to the N sample data to obtain a trained score mapping model.

[0164] Optionally, the WOE value calculation module includes:

[0165] A first WOE value calculation module is used to, for the discrete business impact factors among the M business impact factors of the N sample data, take each business indicator corresponding to each sub-satisfaction of the discrete business impact factors as a bin, and obtain W bins corresponding to each sub-satisfaction, where W is a positive integer less than or equal to N;

[0166] The second WOE value calculation module is used to bin the business indicators corresponding to each sub-satisfaction of the continuous business impact factors among the M business impact factors of the N sample data, and obtain W bins corresponding to each sub-satisfaction, at least one of the W bins contains at least two business indicators, and W is a positive integer less than N.

[0167] Optionally, when the service impact factor is continuous, the second WOE value calculation module includes:

[0168] A monotonic processing module, used for performing monotonic processing on the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain F bins corresponding to each sub-satisfaction level of each business impact factor, where F is a positive integer greater than or equal to W;

[0169] An IV value calculation module is used to obtain F information value IV values ​​corresponding to each sub-satisfaction level of each business impact factor according to the F sub-bins corresponding to each sub-satisfaction level of each business impact factor;

[0170] The screening module is used to obtain Z IV values ​​greater than or equal to the preset IV value among the F IV values ​​corresponding to each sub-satisfaction of each business impact factor, and obtain Z WOE values ​​corresponding to the Z IV values, where F is greater than or equal to Z.

[0171] Optionally, the monotonization processing module includes:

[0172] A bin merging processing module is used for merging the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction level if the W WOE values ​​corresponding to the sub-satisfaction level do not meet the preset monotonicity, so as to obtain F bins corresponding to the sub-satisfaction level, where F is a positive integer less than W.

[0173] The monotonicity judgment module is used to determine the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction as F bins if the W WOE values ​​corresponding to the sub-satisfaction satisfy the preset monotonicity, where F is equal to W.

[0174] Optionally, the box closing processing module includes:

[0175] The first bin merging processing module is used for merging the bin corresponding to the WOE value that does not satisfy the preset monotonicity among the W WOE values ​​and its adjacent bin to obtain F bins corresponding to the sub-satisfaction level if the W WOE values ​​corresponding to the sub-satisfaction level do not satisfy the preset monotonicity.

[0176] Optionally, the business indicator determination device 500 further includes:

[0177] A WOE value determination module is used to calculate the WOE value of each sub-box according to the F sub-boxes corresponding to the sub-satisfaction level, and obtain the F WOE values ​​corresponding to the sub-satisfaction level;

[0178] The second box merging processing module is used to merge the F sub-boxes corresponding to the sub-satisfaction if the F WOE values ​​corresponding to the sub-satisfaction do not satisfy the preset monotonicity, until the WOE value corresponding to the sub-satisfaction satisfies the preset monotonicity or the sub-box corresponding to the sub-satisfaction is 1.

[0179] Optionally, the business indicator determination device 500 further includes:

[0180] A satisfaction conversion module, used to convert the estimated overall satisfaction into a satisfaction score;

[0181] The target business indicator determination module is used to determine the adjusted business indicator as the target business indicator if the satisfaction score is greater than or equal to a preset score.

[0182] Regarding the business indicator determination device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0183] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, and when the program instructions are executed by a processor, the steps of the business indicator determination method provided by the present disclosure are implemented.

[0184] Figure 7 6 is a block diagram of an electronic device for a method for determining a business indicator according to an exemplary embodiment. For example, the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0185] Reference Figure 7 , the electronic device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output interface 612 , a sensor component 614 , and a communication component 616 .

[0186] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0187] The memory 604 is configured to store various types of data to support operations on the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0188] The power supply component 606 provides power to the various components of the electronic device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 600.

[0189] The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0190] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the electronic device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0191] The input / output interface 612 provides an interface between the processing component 602 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0192] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the electronic device 600. For example, the sensor assembly 614 can detect the open / closed state of the electronic device 600, the relative positioning of the components, such as the display and keypad of the electronic device 600, and the sensor assembly 614 can also detect the position change of the electronic device 600 or a component of the electronic device 600, the presence or absence of contact between the user and the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and the temperature change of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0193] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0194] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0195] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the instructions can be executed by a processor 620 of an electronic device 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0196] In addition to being an independent electronic device, the above-mentioned device can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be an IC or a collection of multiple ICs; the chip can include but is not limited to the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip, SoC, system on chip or system-level chip), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or codes) to implement the above-mentioned business indicator determination method. The executable instructions can be stored in the integrated circuit or chip, or can be obtained from other devices or equipment, for example, the integrated circuit or chip includes a processor, a memory, and an interface for communicating with other devices. The executable instruction can be stored in the memory, and when the executable instruction is executed by the processor, the above-mentioned business indicator determination method can be implemented; alternatively, the integrated circuit or chip can receive the executable instruction through the interface and transmit it to the processor for execution, so as to implement the above-mentioned business indicator determination method.

[0197] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned business indicator determination method when executed by the programmable device.

[0198] In summary, the business indicator determination method, device, electronic device and medium provided by the present disclosure obtain actual data corresponding to each actual user among multiple actual users, and obtain multiple actual data, the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor; if multiple actual adjustment data are less than the preset satisfaction, the business indicator corresponding to the business impact factor is adjusted to obtain the adjusted business indicator; then, the estimated overall satisfaction corresponding to the adjusted business indicator is obtained according to the adjusted business indicator and the sub-satisfaction corresponding to the adjusted business indicator through the score mapping model; if the estimated overall satisfaction is greater than or equal to the preset satisfaction, the adjusted business indicator is determined to be the target business indicator. Through the above method, the adjusted business indicator is simulated by the score mapping model before implementation, providing a basis for the subsequent implementation of the adjusted business indicator. In addition, the improvement of overall satisfaction is subdivided into the target business indicator corresponding to each sub-satisfaction, which can improve the accuracy of adjustment.

[0199] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0200] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining a business indicator, characterized in that: The method comprises: Acquire actual data corresponding to each actual user among multiple actual users to obtain multiple actual data, wherein the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor; If the multiple actual overall satisfaction levels are all lower than the preset satisfaction levels, the business indicators corresponding to the business impact factors are adjusted to obtain adjusted business indicators; Inputting the adjusted business indicator and the sub-satisfaction corresponding to the business indicator into a score mapping model to obtain an estimated overall satisfaction output by the score mapping model; If the estimated overall satisfaction is greater than or equal to the preset satisfaction, the adjusted business indicator is determined as the target business indicator.

2. The method according to claim 1, characterized in that The score mapping model includes a correspondence between multiple bins and multiple weight of evidence WOE values, the multiple bins correspond to the WOE values ​​one by one, each bin in the multiple bins includes at least one business indicator corresponding to a business impact factor, and the score mapping model is used to output the estimated overall satisfaction in the following manner: Determining, according to the adjusted business indicator and the sub-satisfaction level corresponding to the business indicator, the sub-box to which each business indicator in the plurality of adjusted business indicators belongs; Based on the corresponding relationship, determine the WOE value corresponding to the sub-box to which each business indicator in the multiple adjusted business indicators belongs, and obtain multiple WOE values; The estimated overall satisfaction level corresponding to the adjusted business indicator is obtained according to the multiple WOE values.

3. The method according to claim 1, characterized in that The score mapping model is trained in the following way: Obtain N sample data, each of the N sample data includes the overall satisfaction of the sample, E seed satisfaction corresponding to each business impact factor of M business impact factors associated with the overall satisfaction of the sample, and a business indicator corresponding to each business impact factor of the M business impact factors, the same business impact factor in the N sample data includes N business indicators, and N, M and E are all positive integers; The N business indicators corresponding to each business impact factor in the N sample data are grouped according to the same sub-satisfaction level to obtain E groups, wherein the sub-satisfaction level corresponding to the business indicator of each group in the E groups is the same; The E groups corresponding to each sub-satisfaction level in the N sample data are binned respectively to obtain W bins corresponding to each sub-satisfaction level, where W is a positive integer; Calculate the WOE value corresponding to each bin according to the W bins corresponding to each sub-satisfaction level of each business impact factor, and obtain the W WOE values ​​corresponding to each sub-satisfaction level; Processing the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, where Z is a positive integer less than or equal to W; The initial score mapping model is iteratively trained using the Z WOE values ​​corresponding to each sub-satisfaction level in the N sample data and the sample overall satisfaction level corresponding to the N sample data to obtain a trained score mapping model.

4. The method according to claim 3, characterized in that The E groups corresponding to each sub-satisfaction level in the N sample data are binned respectively to obtain W bins corresponding to each sub-satisfaction level, including: For the discrete business impact factors among the M business impact factors of the N sample data, each business indicator corresponding to each sub-satisfaction of the discrete business impact factors is used as a bin, and W bins corresponding to each sub-satisfaction are obtained, where W is a positive integer less than or equal to N; For the continuous business impact factors among the M business impact factors of the N sample data, the business indicators corresponding to each sub-satisfaction of the continuous business impact factors are binned to obtain W bins corresponding to each sub-satisfaction, at least one of the W bins contains at least two business indicators, and W is a positive integer less than N.

5. The method according to claim 3, characterized in that: When the business impact factor is continuous, the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor are processed to obtain Z WOE values ​​corresponding to each sub-satisfaction level of each business impact factor, including: Performing monotonic processing on the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain F bins corresponding to each sub-satisfaction level of each business impact factor, where F is a positive integer greater than or equal to W; According to the F bins corresponding to each sub-satisfaction level of each business impact factor, F information value IV values ​​corresponding to each sub-satisfaction level of each business impact factor are obtained; Obtain Z IV values ​​greater than or equal to a preset IV value among the F IV values ​​corresponding to each sub-satisfaction of each business impact factor, and obtain Z WOE values ​​corresponding to the Z IV values, where F is greater than or equal to Z.

6. The method according to claim 5, characterized in that The monotonizing the W WOE values ​​corresponding to each sub-satisfaction level of each business impact factor to obtain F bins corresponding to each sub-satisfaction level of each business impact factor includes: If the W WOE values ​​corresponding to the sub-satisfaction do not meet the preset monotonicity, the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction are merged to obtain F bins corresponding to the sub-satisfaction, where F is a positive integer less than W; If the W WOE values ​​corresponding to the sub-satisfaction satisfy the preset monotonicity, the bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction are determined as F bins, where F is equal to W.

7. The method according to claim 6, characterized in that If the W WOE values ​​corresponding to the sub-satisfaction do not satisfy the preset monotonicity, the sub-bins corresponding to the W WOE values ​​corresponding to the sub-satisfaction are combined to obtain F sub-bins corresponding to the sub-satisfaction, including: If the W WOE values ​​corresponding to the sub-satisfaction value do not satisfy the preset monotonicity, the bin corresponding to the WOE value that does not satisfy the preset monotonicity among the W WOE values ​​and its adjacent bin are merged to obtain F bins corresponding to the sub-satisfaction value.

8. The method according to claim 7, characterized in that Also includes: Calculate the WOE value of each bin according to the F bins corresponding to the sub-satisfaction, and obtain the F WOE values ​​corresponding to the sub-satisfaction; If the F WOE values ​​corresponding to the sub-satisfaction value do not satisfy the preset monotonicity, the F sub-boxes corresponding to the sub-satisfaction value are merged until the WOE value corresponding to the sub-satisfaction value satisfies the preset monotonicity or the number of sub-boxes corresponding to the sub-satisfaction value is 1.

9. The method according to any one of claims 1 to 8, characterized in that: Also includes: Convert estimated overall satisfaction into a satisfaction score; If the satisfaction score is greater than or equal to the preset score, the adjusted business indicator is determined to be the target business indicator.

10. A device for determining a business indicator, characterized in that: The device comprises: An acquisition module, used to acquire actual data corresponding to each actual user among multiple actual users, to obtain multiple actual data, wherein the actual data includes actual overall satisfaction, multiple sub-satisfactions corresponding to multiple business impact factors associated with the actual overall satisfaction, and business indicators corresponding to each business impact factor; An adjustment module, configured to adjust the business indicator corresponding to the business impact factor to obtain an adjusted business indicator if the multiple actual overall satisfaction levels are all less than a preset satisfaction level; A mapping module, used for inputting the plurality of adjusted business indicators and the sub-satisfactions corresponding to the business indicators into a score mapping model to obtain an estimated overall satisfaction output by the score mapping model; A determination module is used to determine the adjusted business indicator as a target business indicator if the estimated overall satisfaction is greater than or equal to the preset satisfaction.

11. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the steps of the method described in any one of claims 1 to 9 when executing the instructions.

12. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.

Images