Service evaluation score credibility calculation method and electronic equipment
By analyzing the metadata of service evaluation records and calculating the rating differences and correlation of service categories, the problem of customers filling in scores at will is solved, improving the credibility of service evaluation, and ensuring that the score truly reflects service quality.
Patent Information
- Application Number
- CN202411672101.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2024-12-17
AI Technical Summary
Some customers fill in the scores at will in the service evaluation, resulting in low credibility of the scores and inability to truly reflect the service quality.
By obtaining the metadata of the service evaluation record, the rating differences and correlation of the service category are determined, the credibility of the service category is calculated, and the credibility of the score is evaluated and meaningless scores are identified.
It improves the credibility of service evaluation, ensures that the score truly reflects the service quality, and helps improve service content.
Smart Images
Figure CN119151345A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method and electronic device for calculating the credibility of a service evaluation score. Background Art
[0002] In order to improve the service quality of service personnel, after the service personnel provide services to customers, they will usually invite customers to evaluate the service. For example, customers can rate the service, and the degree of the rating reflects the customer's satisfaction with the service. Therefore, the service content can be improved according to the customer's rating to improve the service quality.
[0003] However, some customers are rather casual when rating the service and may just fill out a random rating, which does not truly reflect the quality of the service and the credibility of the rating is low. Summary of the invention
[0004] At least one aspect or advantage of the invention will be set forth in part in the following description, or may be obvious from the description, or may be learned by practice of the disclosed subject matter.
[0005] According to a first aspect of the present invention, a method for calculating the credibility of a service evaluation score comprises:
[0006] Get the evaluation metadata contained in the service evaluation record;
[0007] Determine a first service category and a second service category sequence according to the difference in scores of the service categories;
[0008] determining a first relevance sequence for characterizing a degree of relevance between a service category within a second service category sequence and the first service category;
[0009] Acquire a credibility dictionary based on the evaluation scores of the service categories in the service evaluation record and the evaluation scores of the service categories in the same time period, wherein the credibility corresponding to the first service category is the first credibility;
[0010] Obtaining a second credibility based on the first association, the credibility dictionary, and the first credibility;
[0011] Obtaining a rating credibility based on the first credibility and the second credibility;
[0012] The evaluation metadata includes an evaluation identifier, a service category, an evaluation score, a scoring order, and an evaluation time, and service evaluation records with the same evaluation identifier are obtained in the same service evaluation process, the service evaluation process is obtained through two or more service evaluation interfaces, and the evaluation metadata obtained based on each of the service evaluation interfaces has a consistent evaluation time;
[0013] The score difference includes the global difference and the order difference of the service categories; the global difference is the difference of the scores of the corresponding service categories, and the order difference is obtained according to the evaluation score and the order of the scores of the corresponding service categories.
[0014] Optionally, the process of determining the first service category includes:
[0015] Grouping the evaluation metadata according to the service category to obtain a first grouping result;
[0016] Traversing the first grouping results, determining the proportion of evaluation records identified as abnormal in the grouping results by clustering as the global difference of the corresponding service category, and performing secondary grouping on the grouping results according to the scoring order, and obtaining the proportion of evaluation records identified as abnormal in each secondary grouping result as the local difference of the secondary grouping of the corresponding service category;
[0017] The order difference is obtained based on the local difference of each group in the secondary grouping results;
[0018] Obtain the score diversity of each service category based on global diversity and order diversity;
[0019] The service categories are sorted according to the score difference, and the service category with the highest score difference is obtained as the first service category, and the other service categories except the first service category are elements of the second service category sequence.
[0020] Optionally, the first correlation is obtained according to a Pearson algorithm.
[0021] Optionally, the first credibility is obtained based on a local outlier algorithm.
[0022] Optionally, the second credibility is obtained as follows:
[0023] Traverse the second service category sequence , the second credibility sequence is calculated according to the following formula ;
[0024] ;
[0025] for The corresponding credibility, for and The correlation degree, For the first credibility, For the first service category, The second service category sequence elements, is a positive integer, is the first elements;
[0026] Based on the second credibility sequence Gain second credibility.
[0027] Optionally, the second credibility is obtained in the following manner:
[0028] Traverse the second credibility sequence , the second credibility is calculated according to the following formula ;
[0029] ;
[0030] in, For the The ratio of the number of evaluation metadata corresponding to the first service category sequence to the number of evaluation metadata corresponding to the second service category sequence.
[0031] Optionally, the step of acquiring the credibility dictionary includes:
[0032] Obtain the evaluation scores of each service category within the same time period;
[0033] Determine the local outlier factor L of the evaluation score of each service category;
[0034] The second credibility M is obtained according to the following formula:
[0035] ;
[0036] The second credibility and the corresponding service category are added to the credibility dictionary.
[0037] Optionally, the scoring credibility is the average of the first credibility and the second credibility.
[0038] According to a second aspect of the present invention, an electronic device includes a processor and a memory, wherein the memory is used to store a program, and the processor executes the program to implement a method for calculating the credibility of a service evaluation score as described in the first aspect of the present invention.
[0039] According to a third aspect of the present invention, a computer-readable storage medium stores a program, and the program is executed by a processor to implement a method for calculating the credibility of a service evaluation score as described in the first aspect of the present invention.
[0040] The present invention determines the first service category and the second service category sequence through the difference in the scores of the service categories, finds the first service category with the highest score difference, and then determines the correlation between the second service category and the first service category. If there is no correlation, it means that the score may be random and the credibility is low. The second credibility is calculated based on the first correlation, the credibility dictionary and the first credibility. The second credibility is used to represent the credibility corresponding to each service category in the second service category sequence, and then the scoring credibility is calculated based on the first credibility and the second credibility. The scoring credibility truly reflects the credibility of the scores of each evaluation item in the service evaluation process, and can detect meaningless scores. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 The present invention is a flowchart of a method for calculating the credibility of a service evaluation score in an embodiment of the present invention. DETAILED DESCRIPTION
[0042] The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thus implement the present disclosure, rather than implying any limitation on the scope of the present disclosure.
[0043] As used herein, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "based at least in part on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment". The term "another embodiment" is to be interpreted as "at least one other embodiment". The orientation or position relationship indicated by the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "vertical", "horizontal", "lateral", "longitudinal" and the like is based on the orientation or position relationship shown in the accompanying drawings. These terms are mainly for better describing the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation. In addition, in addition to being used to indicate an orientation or position relationship, some of the above terms may also be used to indicate other meanings, such as the term "upper" may also be used to indicate a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the terms "install", "set", "provided with", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be an internal connection between two devices, elements or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. In addition, the terms "first", "second", etc. are mainly used to distinguish different devices, elements or components (the specific types and structures may be the same or different), and are not used to indicate or imply the relative importance and quantity of the indicated devices, elements or components. Unless otherwise specified, "plurality" means two or more.
[0044] like Figure 1 As shown, this embodiment provides a method for calculating the credibility of a service evaluation score, including steps 1100-1600.
[0045] Step 1100: Obtain the evaluation metadata contained in the service evaluation record.
[0046] The evaluation metadata includes an evaluation identifier, a service category, an evaluation score, a scoring order, and an evaluation time, and service evaluation records with the same evaluation identifier are obtained in the same service evaluation process. The service evaluation process is obtained through more than two service evaluation interfaces, and the evaluation metadata obtained based on each of the service evaluation interfaces has a consistent evaluation time.
[0047] After the service personnel provide services to customers, customers can rate the services, and after the rating is completed, the corresponding service evaluation record is generated. In a service provided by the service personnel to the customer, there may be multiple service items, and when rating, multiple service items need to be rated separately.
[0048] Scoring of multiple service items will be performed in the same service evaluation process, and multiple evaluation items will appear in the service evaluation process. The evaluation records of multiple service items in the same service evaluation process will have the same evaluation identifier. The evaluation identifier is a unique identifier corresponding to each service evaluation process.
[0049] The scoring order is the order in which multiple evaluation items are scored in the service evaluation process. For example, if a service evaluation process includes 5 evaluation items, these 5 evaluation items can be randomly displayed on the service evaluation interface, and the scores are given in the order in which the 5 evaluation items are displayed.
[0050] For multiple evaluation items in the same service evaluation process, multiple evaluation items are scored in turn during the actual evaluation process. When all evaluation items are scored, the evaluation record data corresponding to each evaluation item is generated, and the evaluation time corresponding to each evaluation item is the same and will not change due to the order of evaluation.
[0051] The evaluation score can reflect the service quality. The higher the service quality, the higher the evaluation score.
[0052] Step 1200: Determine a first service category and a second service category sequence according to the difference in scores of the service categories.
[0053] The score differences include the global difference and the order difference of the service categories; the global difference is the difference in the scores of the corresponding service categories, and the order difference is obtained according to the evaluation scores and the order of the scores of the corresponding service categories.
[0054] The score difference of the service category indicates the difference between different scores of the same service category. The first service category is the service category with the highest score difference. The second service category sequence contains other service categories except the first service category. For example, four service categories are obtained based on the evaluation metadata, namely service category 1, service category 2, service category 3, and service category 4. Among them, the score difference of service category 4 is the highest. Then service category 4 is used as the first service category, and service category 1, service category 2, and service category 3 are saved in the second service category sequence.
[0055] Step 1300: Determine a first association sequence for characterizing the association between a service category within a second service category sequence and a first service category.
[0056] The elements in the first correlation sequence are the correlation between each service category in the second service category sequence and the first service category. For example, if the second service category sequence includes service category 1, service category 2, and service category 3, and the first service category is service category 4, then the first correlation sequence includes the correlation between service category 1 and service category 4, the correlation between service category 2 and service category 4, and the correlation between service category 3 and service category 4.
[0057] Specifically, the first correlation is obtained according to the Pearson algorithm.
[0058] Step 1400: Obtain a credibility dictionary based on the evaluation scores of the service categories in the service evaluation record and the evaluation scores of the service categories in the same time period, wherein the credibility corresponding to the first service category is the first credibility.
[0059] The credibility dictionary records the credibility corresponding to each service category, and the credibility dictionary can be obtained through the evaluation scores of the service categories in the same time period.
[0060] In this embodiment, the first credibility is obtained based on a local outlier algorithm.
[0061] Specifically, the step of obtaining the credibility dictionary includes: obtaining the evaluation score of each service category in the same time period; determining the local outlier factor L of the evaluation score of each service category; and obtaining the second credibility M according to the following formula:
[0062] ;
[0063] The second credibility M and the corresponding service category are added to the credibility dictionary.
[0064] The local outlier factor L of the evaluation score of each service category is calculated, and then the second credibility corresponding to each service category is determined according to the local outlier factor L.
[0065] When the local outlier factor of the evaluation score of a service category is less than or equal to 1, the larger the local outlier factor is, the higher the credibility of the score of the service category is. In this case, the local outlier factor can be directly used as the second credibility.
[0066] When the local outlier factor of the evaluation score of a service category is greater than 1, the larger the local outlier factor, the lower the credibility of the score of the service category. In this case, As the second credibility corresponding to the service category, on the one hand, the value of the second credibility is made less than 1, which is convenient for calculation. On the other hand, it can reflect the relationship that when the local outlier factor is greater than 1, the greater the local outlier factor, the lower the credibility.
[0067] Step 1500: Obtain a second credibility based on the first association, the credibility dictionary and the first credibility.
[0068] The first correlation is the correlation between the service categories in the second service category sequence and the first service category. The first credibility is the credibility corresponding to the first service category, that is, the credibility of the score of the service category with the highest score difference. The second credibility represents the credibility of the second service category sequence.
[0069] Step 1600: Obtain scoring credibility based on the first credibility and the second credibility.
[0070] After obtaining the first credibility and the second credibility, the scoring credibility is calculated. The scoring credibility indicates the credibility of the scoring in the entire service evaluation process.
[0071] Specifically, the scoring credibility is the average of the first credibility and the second credibility.
[0072] The present invention determines the first service category and the second service category sequence through the difference in the scores of the service categories, finds the first service category with the highest score difference, and then determines the correlation between the second service category and the first service category. If there is no correlation, it means that the score may be random and the credibility is low. The second credibility is calculated based on the first correlation, the credibility dictionary and the first credibility. The second credibility is used to represent the credibility corresponding to each service category in the second service category sequence, and then the scoring credibility is calculated based on the first credibility and the second credibility. The scoring credibility truly reflects the credibility of the scores of each evaluation item in the service evaluation process, and can detect meaningless scores.
[0073] In this embodiment, the process of determining the first service category includes steps 2100-2500.
[0074] Step 2100: Group the evaluation metadata according to the service category to obtain a first grouping result.
[0075] The evaluation metadata is grouped according to the service category, and each group contains data corresponding to one service category.
[0076] Step 2200: Traverse the first grouping results, determine the proportion of evaluation records identified as abnormal in the grouping results through clustering as the global difference of the corresponding service category, and perform secondary grouping on the grouping results in order of scoring, and obtain the proportion of evaluation records identified as abnormal in each secondary grouping result as the local difference of the secondary grouping of the corresponding service category.
[0077] For the first grouping result, determine the abnormal evaluation records contained in each group. The proportion of abnormal evaluation records in the group is used as the global difference of the service category corresponding to the group. The higher the proportion of abnormal evaluation records, the lower the credibility of the evaluation records of the group.
[0078] Then, secondary grouping is performed based on the first grouping result, and the grouping is performed according to the scoring order. The abnormal evaluation records in the secondary grouping result are determined, and the proportion of abnormal evaluation records in the secondary grouping result to the secondary grouping result is used as the local difference of the corresponding service category.
[0079] For example, there are multiple evaluation items in a service evaluation project, and each evaluation item has its own service category. During the evaluation process, only a part of the evaluation items will be displayed in the service evaluation interface each time. After all the evaluation items displayed this time are scored, the next batch of evaluation items will continue to be displayed. For the same batch of evaluation items displayed, the scoring order is the same.
[0080] In the first grouping, the service evaluation items are grouped, and then the second grouping is performed based on the results of the first grouping according to the scoring order. The scoring order and service category are the same in each group of the second grouping results. Local differences reflect the differences in the scores in the second grouping results.
[0081] Step 2300: Obtain order difference according to the local difference of each group in the secondary grouping result.
[0082] Order differences reflect the differences between the scoring results of the same service category in different scoring orders.
[0083] Step 2400: Obtain the score difference of each service category according to the global difference and the order difference.
[0084] For example, the average of the global difference and the order difference can be determined as the score difference. Alternatively, the global difference and the order difference can be weighted and summed according to preset weights, and the result of the weighted sum can be used as the score difference.
[0085] Step 2500: sort the service categories according to the difference in scores, obtain the service category with the highest difference in scores as the first service category, and the other service categories except the first service category are elements of the second service category sequence.
[0086] After obtaining the score difference of each service category, the service categories are sorted according to the score difference, and the first service category and the second service category sequence can be determined according to the sorting result.
[0087] In this embodiment, the second credibility is obtained as follows:
[0088] Traverse the second service category sequence , the second credibility sequence is calculated according to the following formula ;
[0089] ;
[0090] for The corresponding credibility, for and The correlation degree, For the first credibility, For the first service category, The second service category sequence elements, is a positive integer, is the first elements;
[0091] Based on the second credibility sequence Gain second credibility.
[0092] For the second service class sequence Service categories in , which can be obtained through the credibility dictionary The corresponding credibility The second service category sequence is stored in the first association sequence Each service category and the first service category The correlation between them can be obtained through the first correlation sequence. and The correlation .
[0093] Specifically, the second credibility is obtained in the following manner:
[0094] Traverse the second credibility sequence , the second credibility is calculated according to the following formula ;
[0095] ;
[0096] in, For the The ratio of the number of evaluation metadata corresponding to the first service category sequence to the number of evaluation metadata corresponding to the second service category sequence.
[0097] For the second credibility sequence , calculate the The number of evaluation metadata corresponding to each service category ,Will As the second credibility sequence No. Elements The more the evaluation metadata, the greater the corresponding weight. Then the second credibility sequence Perform weighted summation to obtain the second credibility The second service category sequence is reflected by the second credibility credibility.
[0098] This embodiment introduces an electronic device, including a processor and a memory, wherein the memory is used to store a program, and the processor executes the program to implement a method for calculating the credibility of a service evaluation score as described in an embodiment of the present invention.
[0099] This embodiment introduces a computer-readable storage medium, which stores a program. The program is executed by a processor to implement a method for calculating the credibility of a service evaluation score as described in an embodiment of the present invention.
[0100] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0103] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.
[0104] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0105] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
[0106] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.
[0107] It should be understood that the size of the sequence number of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. For the purpose of example and description, the foregoing description of the implementation of the present disclosure has been given. The foregoing description is not exhaustive and is not intended to limit the present disclosure to the exact form disclosed. Various deformations and modifications may exist according to the above teachings, or various deformations and modifications may be obtained from the practice of the present disclosure. These embodiments are selected and described to illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can use the present disclosure in various embodiments and various modifications suitable for the specific purpose conceived.
Claims
1. A method for calculating the credibility of service evaluation scores, characterized in that: include: Get the evaluation metadata contained in the service evaluation record; Determine a first service category and a second service category sequence according to the difference in scores of the service categories; determining a first relevance sequence for characterizing a degree of relevance between a service category within a second service category sequence and the first service category; Acquire a credibility dictionary based on the evaluation scores of the service categories in the service evaluation record and the evaluation scores of the service categories in the same time period, wherein the credibility corresponding to the first service category is the first credibility; Obtaining a second credibility based on the first association, the credibility dictionary, and the first credibility; Obtaining a rating credibility based on the first credibility and the second credibility; The evaluation metadata includes an evaluation identifier, a service category, an evaluation score, a scoring order, and an evaluation time, and service evaluation records with the same evaluation identifier are obtained in the same service evaluation process, the service evaluation process is obtained through two or more service evaluation interfaces, and the evaluation metadata obtained based on each of the service evaluation interfaces has a consistent evaluation time; The score difference includes the global difference and the order difference of the service categories; the global difference is the difference of the scores of the corresponding service categories, and the order difference is obtained according to the evaluation score and the order of the scores of the corresponding service categories.
2. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The process of determining the first service category includes: Grouping the evaluation metadata according to the service category to obtain a first grouping result; Traversing the first grouping results, determining the proportion of evaluation records identified as abnormal in the grouping results by clustering as the global difference of the corresponding service category, and performing secondary grouping on the grouping results according to the scoring order, and obtaining the proportion of evaluation records identified as abnormal in each secondary grouping result as the local difference of the secondary grouping of the corresponding service category; The order difference is obtained based on the local difference of each group in the secondary grouping results; Obtain the score diversity of each service category based on global diversity and order diversity; The service categories are sorted according to the score difference, and the service category with the highest score difference is obtained as the first service category, and the other service categories except the first service category are elements of the second service category sequence.
3. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The first correlation is obtained according to a Pearson algorithm.
4. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The first credibility is obtained based on a local outlier algorithm.
5. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The second credibility is obtained as follows: Traverse the second service category sequence , the second credibility sequence is calculated according to the following formula ; ； for The corresponding credibility, for and The correlation degree, For the first credibility, For the first service category, The second service category sequence elements, is a positive integer, is the first elements; Based on the second credibility sequence Gain second credibility.
6. A method for calculating the credibility of service evaluation scores as claimed in claim 5, characterized in that: The second credibility is obtained as follows: Traverse the second credibility sequence , the second credibility is calculated according to the following formula ; ； in, For the The ratio of the number of evaluation metadata corresponding to the first service category sequence to the number of evaluation metadata corresponding to the second service category sequence.
7. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The step of obtaining the credibility dictionary includes: Obtain the evaluation scores of each service category within the same time period; Determine the local outlier factor L of the evaluation score of each service category; The second credibility M is obtained according to the following formula: ； The second credibility and the corresponding service category are added to the credibility dictionary.
8. A method for calculating the credibility of service evaluation scores as claimed in claim 1, characterized in that: The scoring credibility is the average of the first credibility and the second credibility.
9. An electronic device, characterized in that: It includes a processor and a memory, the memory is used to store a program, and the processor executes the program to implement a method for calculating the credibility of a service evaluation score as described in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement a method for calculating the credibility of a service evaluation score according to any one of claims 1 to 8.