A smart customer service construction method and system based on scene clustering analysis

Abstract

This invention provides a method and system for constructing intelligent customer service based on scenario clustering analysis, belonging to the field of intelligent scenario technology. Specifically, it includes: determining the similarity between different question-and-answer data from users in an information system; classifying the different question-and-answer data into different question scenario groups based on similarity; determining when the consultation popularity of a business module meets the requirements based on the consultation popularity of different question scenario groups matched with different business modules; obtaining usage data of different types of users and the number of users of different types of question-and-answer data for different business modules; selecting business modules based on the consultation popularity of different business modules; and constructing matching scripts for intelligent customer service based on the question scenario groups of the selected business modules, thereby improving the response and processing efficiency of intelligent customer service.

Description

Technical Field

[0001] This invention belongs to the field of intelligent customer service technology, and in particular relates to a method and system for constructing intelligent customer service based on scenario clustering analysis. Background Technology

[0002] As the construction of the intelligent customer service system for information customer service progresses, the application scenarios of intelligent information customer service are gradually expanding. In order to improve the efficiency of handling user problems in information systems and enhance the intelligent service capabilities of information customer service, as well as improve data analysis and intelligent technology support capabilities, how to utilize the value of existing information customer service data to improve the efficiency of information customer service work has become an urgent technical problem to be solved.

[0003] To address the aforementioned technical problems, the existing technical solution, as described in invention patent CN201811550825.5 "Method for generating a set of recommended dialogue phrases, method and apparatus for generating recommended dialogue phrases," uses clusters of similar questions obtained through semantic matching, and generates recommended dialogue phrases for users based on the candidate dialogue phrase set corresponding to the similar question question clusters. This improves the efficiency of information customer service. However, analysis reveals the following technical problems:

[0004] Due to the resource limitations of the intelligent customer service system's backend server, if a matching solution is built for all questions from users without considering the popularity of different types of questions, the efficiency of recommending matching solutions cannot be guaranteed, and it will also waste the resources of the backend server.

[0005] To address the aforementioned technical problems, this invention provides a method and system for constructing intelligent customer service based on scenario clustering analysis. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted:

[0007] According to one aspect of the present invention, a method for constructing intelligent customer service based on scenario clustering analysis is provided.

[0008] A method for constructing intelligent customer service based on scenario clustering analysis, characterized by specifically including:

[0009] S1 determines the similarity between different question consultation data based on the question consultation data of different question consultation users in the information system, and classifies the different question consultation data into different question scenario groups based on the similarity;

[0010] S2 determines the consultation popularity of different problem scenario groups by the similarity between different problem consultation data of different problem scenario groups and the number of users consulting different types of problems. When it is determined that the problem scenario group does not belong to the popular scenario group based on the consultation popularity, proceed to the next step.

[0011] S3 determines that the consultation popularity of a business module meets the requirements based on the consultation popularity of different problem scenario groups matched with different business modules, and then proceeds to the next step;

[0012] S4 acquires usage data of different types of users in different business modules and the number of users consulting on different types of questions. It then filters and determines the business modules based on the consultation popularity of different business modules, and constructs matching scripts for intelligent customer service based on the question scenario groups of the filtered business modules.

[0013] The beneficial effects of this invention are as follows:

[0014] 1. By assessing the similarity between different question consultation data from different question scenario groups and the number of users consulting different types of questions, the consultation popularity of different question scenario groups is determined. This approach not only considers the differences in consultation popularity caused by the differences between question scenario groups, but also takes into account the number of users consulting questions, thus determining consultation popularity from two perspectives. This allows for the screening of question scenario groups with high consultation popularity and lays the foundation for constructing matching scripts for further question scenario groups with high consultation popularity.

[0015] 2. Based on the usage data of different types of users and the number of users with different types of questions, as well as the popularity of module inquiries, business modules are selected. This allows for the selection of business modules from three perspectives: user frequency of use, number and type of users with questions, and popularity of module inquiries. This ensures that all questions and inquiries from business modules with high usage frequency and high popularity are matched with appropriate scripts, thereby improving the response and processing efficiency of intelligent customer service.

[0016] A further technical solution is that the similarity between the different problem consultation data is determined based on the number of matching keywords in the problem consultation data.

[0017] A further technical solution involves classifying different question consultation data into different question scenario groups based on the similarity, specifically including:

[0018] Questions with a similarity greater than a preset similarity will be grouped into the same question scenario group.

[0019] A further technical solution is that the type of user seeking advice is determined based on the job information of the user seeking advice.

[0020] A further technical solution involves determining the consultation popularity of the aforementioned problem scenario group as follows:

[0021] The popularity of the questions in the problem scenario group is determined based on the number of questions in the group and the similarity between different questions.

[0022] The types of users who consult about problems in the problem scenario group are identified, and the user consultation popularity of the problem scenario group is determined by combining the number of users who consult about different types of problems.

[0023] The consultation popularity of the problem scenario group is determined based on the consultation popularity of the questions and the consultation popularity of the users.

[0024] A further technical solution is that the consultation popularity of the problem scenario group is between 0 and 1, wherein when the consultation popularity of the problem scenario group is greater than a preset popularity, the problem scenario group is determined to be a popular scenario group.

[0025] A further technical solution involves constructing matching scripts for intelligent customer service based on the problem scenario group when the problem scenario group belongs to the popular scenario group.

[0026] A further technical solution is that the method for determining the filtering business module is as follows:

[0027] Based on the usage data of users of the preset type of the business module, the number of times users of the preset type of the business module are used and the number of users of the preset type of the business module are determined. In combination with the number of users who consulted on the preset type of questions, the usage question evaluation quantity of users of the preset type of the business module is determined.

[0028] The overall usage problem assessment of the business module is determined by evaluating the usage problems of users of different preset types, and the overall module assessment of the business module is determined by combining the module consultation popularity of the business module. Based on the overall module assessment of the business module, it is determined whether the business module is a screening business module.

[0029] On the other hand, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-described intelligent customer service construction method based on scene clustering analysis.

[0030] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0031] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0032] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0033] Figure 1 This is a flowchart of a method for building intelligent customer service based on scenario clustering analysis;

[0034] Figure 2 This is a flowchart illustrating the method for determining the consultation popularity of problem scenario groups;

[0035] Figure 3 This is a flowchart illustrating the method for determining the selection of business modules. Detailed Implementation

[0036] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0037] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0038] Example 1

[0039] To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, according to one aspect of the present invention, a method for constructing intelligent customer service based on scenario clustering analysis is provided, characterized in that it specifically includes:

[0040] S1 determines the similarity between different question consultation data based on the question consultation data of different question consultation users in the information system, and classifies the different question consultation data into different question scenario groups based on the similarity;

[0041] Specifically, the similarity between the different question and consultation data is determined based on the number of keyword matches in the question and consultation data.

[0042] Furthermore, based on the aforementioned similarity, different question consultation data are divided into different question scenario groups, specifically including:

[0043] Questions with a similarity greater than a preset similarity will be grouped into the same question scenario group.

[0044] S2 determines the consultation popularity of different problem scenario groups by the similarity between different problem consultation data of different problem scenario groups and the number of users consulting different types of problems. When it is determined that the problem scenario group does not belong to the popular scenario group based on the consultation popularity, proceed to the next step.

[0045] It should be noted that the type of user seeking advice is determined based on their job position information.

[0046] Specifically, such as Figure 2 As shown, the method for determining the consultation popularity of the aforementioned problem scenario group is as follows:

[0047] The popularity of the questions in the problem scenario group is determined based on the number of questions in the group and the similarity between different questions.

[0048] The types of users who consult about problems in the problem scenario group are identified, and the user consultation popularity of the problem scenario group is determined by combining the number of users who consult about different types of problems.

[0049] The consultation popularity of the problem scenario group is determined based on the consultation popularity of the questions and the consultation popularity of the users.

[0050] Furthermore, the consultation popularity of the problem scenario group ranges from 0 to 1. When the consultation popularity of the problem scenario group is greater than the preset popularity, the problem scenario group is determined to be a popular scenario group.

[0051] It is understandable that when the problem scenario group belongs to the popular scenario group, the matching script for intelligent customer service will be constructed based on the problem scenario group.

[0052] In another possible embodiment, the method for determining the consultation popularity of the problem scenario group is as follows:

[0053] Obtain the number of question consultation data for the problem scenario group, and determine whether the number of question consultation data for the problem scenario group is greater than a preset number threshold. If yes, determine that the problem scenario group is a popular scenario group; otherwise, proceed to the next step.

[0054] Obtain the number of users who consulted the question in the question scenario group, and determine whether the number of users who consulted the question is greater than the preset number of users. If yes, then determine that the question scenario group is a popular scenario group. If not, proceed to the next step.

[0055] The popularity of the consultation questions in the problem scenario group is determined based on the number of consultation questions in the problem scenario group and the similarity between different consultation questions. Based on the popularity of the consultation questions in the problem scenario group, it is determined whether the problem scenario group is a popular scenario group. If yes, the problem scenario group is determined to be a popular scenario group. If not, proceed to the next step.

[0056] Obtain the types of users who consult about problems in the problem scenario group, and determine the user consultation popularity of the problem scenario group by combining the number of users who consult about different types of problems. Based on the user consultation popularity of the problem scenario group, determine whether the problem scenario group is a popular scenario group. If yes, then determine that the problem scenario group is a popular scenario group. If not, proceed to the next step.

[0057] The consultation popularity of the problem scenario group is determined based on the consultation popularity of the questions and the consultation popularity of the users.

[0058] In another possible embodiment, the method for determining the consultation popularity of the problem scenario group is as follows:

[0059] Based on the number of users consulting different questions in the question consultation data of the question scenario group, the question consultation data with a number of users greater than the preset number of consulting users is determined and used as the filtering consultation data. It is then determined whether the number of the filtering consultation data is greater than the preset consultation number threshold. If yes, the question scenario group is determined to be a popular scenario group; otherwise, proceed to the next step.

[0060] The data consultation popularity of the filtered resource data is determined by the number of users consulting different questions about the filtered resource data. It is then determined whether the data consultation popularity of the filtered resource data is greater than a preset popularity threshold. If so, the question scenario group is determined to be a popular scenario group. If not, proceed to the next step.

[0061] Based on the similarity of the question consultation data of the question scenario group, the number of question consultation data with a similarity greater than a preset similarity is determined. Based on the number of question consultation data with a similarity greater than the preset similarity, it is determined whether the question scenario group is a popular scenario group. If yes, the question scenario group is determined to be a popular scenario group. If no, proceed to the next step.

[0062] The popularity of the questions in the problem scenario group is determined based on the number of questions in the problem scenario group and the similarity between different questions in the problem scenario group. The types of users who ask questions in the problem scenario group are obtained, and the user popularity of the problem scenario group is determined by combining the number of users of different types of questions.

[0063] The consultation popularity of the problem scenario group is determined based on the consultation popularity of the questions and the consultation popularity of the users.

[0064] S3 determines that the consultation popularity of a business module meets the requirements based on the consultation popularity of different problem scenario groups matched with different business modules, and then proceeds to the next step;

[0065] Specifically, determining whether the consultation popularity of the business module meets the requirements includes:

[0066] Based on the consultation popularity of the problem scenario groups matched by the business module, the problem scenario groups are divided into filter scenario groups and other scenario groups;

[0067] The consultation popularity of the selected scenario groups is determined based on the number of selected scenario groups and the consultation popularity of different selected scenario groups. The consultation popularity of other scenario groups is determined based on the number of other scenario groups and the consultation popularity of different other scenario groups.

[0068] The number of problem scenario groups matched by the business module is obtained, and the consultation popularity of the business module is determined by combining the consultation popularity of the filtered scenario groups with the consultation popularity of other scenario groups. Based on the consultation popularity of the business module and a preset consultation popularity threshold, it is determined whether the consultation popularity of the business module meets the requirements.

[0069] It is understandable that, based on the consultation popularity of the problem scenario groups matched by the business module, the problem scenario groups are divided into filtered scenario groups and other scenario groups, specifically including:

[0070] Problem scenarios with a consultation popularity exceeding a preset consultation popularity threshold are selected as the filter scenario groups, while problem scenarios with a consultation popularity not exceeding the preset consultation popularity threshold are selected as other scenario groups.

[0071] Furthermore, based on the module's consultation popularity and a preset consultation popularity threshold, it is determined whether the consultation popularity of the business module meets the requirements, specifically including:

[0072] If the consultation popularity of a business module exceeds a preset consultation popularity threshold, then the consultation popularity of the business module is determined to be unsatisfactory.

[0073] Specifically, when the consultation popularity of the business module does not meet the requirements, the matching script for intelligent customer service is constructed based on the problem scenario group matched by the business module.

[0074] In another possible embodiment, determining that the consultation popularity of the business module meets the requirements specifically includes:

[0075] Obtain the number of problem scenario groups matched by the business module, and determine whether the number of problem scenario groups matched by the business module is greater than the preset number of scenario groups. If not, proceed to the next step; if yes, determine that the module consultation popularity of the business module does not meet the requirements.

[0076] Determine whether the sum of the consultation popularity of the problem scenario group matched by the business module meets the requirements. If yes, proceed to the next step; otherwise, determine that the consultation popularity of the business module does not meet the requirements.

[0077] Based on the consultation popularity of the problem scenario groups matched by the business module, the problem scenario groups are divided into filter scenario groups and other scenario groups. It is determined whether the number of filter scenario groups meets the requirements. If yes, proceed to the next step. If no, it is determined that the consultation popularity of the business module does not meet the requirements.

[0078] The consultation popularity of the selected scenario groups is determined based on the number of selected scenario groups and the consultation popularity of different selected scenario groups. It is then determined whether the consultation popularity of the selected scenario groups meets the requirements. If yes, proceed to the next step; otherwise, it is determined that the consultation popularity of the business module does not meet the requirements.

[0079] The group consultation popularity of other scenario groups is determined based on the number of other scenario groups and the consultation popularity of different other scenario groups. The number of problem scenario groups matched by the business module is obtained. The module consultation popularity of the business module is determined by combining the group consultation popularity of the filtered scenario groups and the group consultation popularity of other scenario groups. Based on the module consultation popularity and the preset consultation popularity threshold, it is determined whether the module consultation popularity of the business module meets the requirements.

[0080] In another possible embodiment, determining that the consultation popularity of the business module meets the requirements specifically includes:

[0081] The problem consultation data matched by the business module is determined by the problem scenario group matched by the business module. It is then determined whether the number of problem consultation data matched by the business module meets the requirements. If yes, proceed to the next step; otherwise, it is determined that the module consultation popularity of the business module does not meet the requirements.

[0082] Based on the question consultation data, determine the number of question consultation users matched by the business module, and determine whether the number of question consultation users matched by the business module meets the requirements. If yes, proceed to the next step; otherwise, determine that the module consultation popularity of the business module does not meet the requirements.

[0083] Based on the consultation popularity of the problem scenario groups matched by the business module, the problem scenario groups are divided into screening scenario groups and other scenario groups. The consultation popularity of the screening scenario groups is determined according to the number of screening scenario groups and the consultation popularity of different screening scenario groups. It is determined whether the consultation popularity of the screening scenario groups meets the requirements. If yes, proceed to the next step. If no, it is determined that the consultation popularity of the business module does not meet the requirements.

[0084] The group consultation popularity of other scenario groups is determined based on the number of other scenario groups and the consultation popularity of different other scenario groups. The number of problem scenario groups matched by the business module is obtained. The module consultation popularity of the business module is determined by combining the group consultation popularity of the filtered scenario groups and the group consultation popularity of other scenario groups. Based on the module consultation popularity and the preset consultation popularity threshold, it is determined whether the module consultation popularity of the business module meets the requirements.

[0085] S4 acquires usage data of different types of users in different business modules and the number of users consulting on different types of questions. It then filters and determines the business modules based on the consultation popularity of different business modules, and constructs matching scripts for intelligent customer service based on the question scenario groups of the filtered business modules.

[0086] Specifically, such as Figure 3 As shown, the method for determining the filtering business module is as follows:

[0087] Based on the usage data of users of the preset type of the business module, the number of times users of the preset type of the business module are used and the number of users of the preset type of the business module are determined. In combination with the number of users who consulted on the preset type of questions, the usage question evaluation quantity of users of the preset type of the business module is determined.

[0088] The overall usage problem assessment of the business module is determined by evaluating the usage problems of users of different preset types, and the overall module assessment of the business module is determined by combining the module consultation popularity of the business module. Based on the overall module assessment of the business module, it is determined whether the business module is a screening business module.

[0089] Furthermore, the method for determining the filtering business module is as follows:

[0090] Based on the usage data of users of the preset type of the business module, determine the number of users using the business module, and determine whether the number of users using the business module is greater than the preset number of users. If yes, then the business module is determined to be a filtering business module; otherwise, proceed to the next step.

[0091] Based on the usage data of users of the preset type of the business module, the number of times users of the preset type of the business module are used and the number of users of the preset type of the business module are determined. Combined with the number of users who consulted on the preset type of the problem, the usage problem evaluation quantity of users of the preset type of the business module is determined. It is determined whether there are users of the preset type whose usage problem evaluation quantity does not meet the requirements. If so, the business module is determined to be a screening business module. If not, proceed to the next step.

[0092] The comprehensive usage problem assessment of the business module is determined by evaluating the usage problem assessment of users of different preset types. It is then determined whether the comprehensive usage problem assessment of the business module meets the requirements. If not, the business module is determined to be a screening business module. If so, proceed to the next step.

[0093] The overall evaluation score of a business module is determined based on the comprehensive usage problem assessment volume and the consultation popularity of the business module. Based on the overall evaluation score of the business module, it is determined whether the business module is a screening business module.

[0094] Example 2

[0095] On the other hand, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-described intelligent customer service construction method based on scene clustering analysis.

[0096] Through the above embodiments, this application achieves the following technical effects:

[0097] 1. By assessing the similarity between different question consultation data from different question scenario groups and the number of users consulting different types of questions, the consultation popularity of different question scenario groups is determined. This approach not only considers the differences in consultation popularity caused by the differences between question scenario groups, but also takes into account the number of users consulting questions, thus determining consultation popularity from two perspectives. This allows for the screening of question scenario groups with high consultation popularity and lays the foundation for constructing matching scripts for further question scenario groups with high consultation popularity.

[0098] 2. Based on the usage data of different types of users and the number of users with different types of questions, as well as the popularity of module inquiries, business modules are selected. This allows for the selection of business modules from three perspectives: user frequency of use, number and type of users with questions, and popularity of module inquiries. This ensures that all questions and inquiries from business modules with high usage frequency and high popularity are matched with appropriate scripts, thereby improving the response and processing efficiency of intelligent customer service.

[0099] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0100] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0101] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for constructing intelligent customer service based on scenario clustering analysis, characterized in that, Specifically, it includes: Based on the question and inquiry data of different users in the information system, the similarity between different question and inquiry data is determined, and based on the similarity, the different question and inquiry data are divided into different question scenario groups; The consultation popularity of different problem scenario groups is determined by the similarity between different consultation data of different problem scenario groups and the number of users consulting different types of problems. When it is determined that the problem scenario group does not belong to the popular scenario group based on the consultation popularity, proceed to the next step. When the consultation popularity of a business module meets the requirements based on the consultation popularity of different problem scenario groups matched with different business modules, proceed to the next step. The system acquires usage data of different types of users in different business modules and the number of users consulting on different types of questions. It then uses the consultation popularity of different business modules to filter and determine the business modules. Based on the question scenario groups of the filtered business modules, it constructs matching scripts for intelligent customer service. The method for determining the filtering business module is as follows: Based on the usage data of users of the preset type of the business module, the number of times users of the preset type of the business module are used and the number of users of the preset type of the business module are determined. In combination with the number of users who consulted on the preset type of questions, the usage question evaluation quantity of users of the preset type of the business module is determined. The overall usage problem assessment of the business module is determined by evaluating the usage problems of users of different preset types, and the overall module assessment of the business module is determined by combining the module consultation popularity of the business module. Based on the overall module assessment of the business module, it is determined whether the business module is a screening business module.

2. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, The similarity between different question and consultation data is determined based on the number of keyword matches in the question and consultation data.

3. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, Based on the similarity, different question consultation data are divided into different question scenario groups, specifically including: Questions with a similarity greater than a preset similarity will be grouped into the same question scenario group.

4. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, The type of user seeking advice is determined based on their job position information.

5. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, The method for determining the consultation popularity of the aforementioned problem scenario group is as follows: The popularity of the questions in the problem scenario group is determined based on the number of questions in the group and the similarity between different questions. The types of users who consult about problems in the problem scenario group are identified, and the user consultation popularity of the problem scenario group is determined by combining the number of users who consult about different types of problems. The consultation popularity of the problem scenario group is determined based on the consultation popularity of the questions and the consultation popularity of the users.

6. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, The consultation popularity of the problem scenario group ranges from 0 to 1. When the consultation popularity of the problem scenario group is greater than the preset popularity, the problem scenario group is determined to be a popular scenario group.

7. The intelligent customer service construction method based on scenario clustering analysis as described in claim 1, characterized in that, Determining that the consultation popularity of the business module meets the requirements specifically includes: Based on the consultation popularity of the problem scenario groups matched by the business module, the problem scenario groups are divided into filter scenario groups and other scenario groups; The consultation popularity of the selected scenario groups is determined based on the number of selected scenario groups and the consultation popularity of different selected scenario groups. The consultation popularity of other scenario groups is determined based on the number of other scenario groups and the consultation popularity of different other scenario groups. The number of problem scenario groups matched by the business module is obtained, and the consultation popularity of the business module is determined by combining the consultation popularity of the filtered scenario groups with the consultation popularity of other scenario groups. Based on the consultation popularity of the business module and a preset consultation popularity threshold, it is determined whether the consultation popularity of the business module meets the requirements.

8. The intelligent customer service construction method based on scenario clustering analysis as described in claim 7, characterized in that, Based on the consultation popularity of the problem scenario groups matched by the business modules, the problem scenario groups are divided into filtered scenario groups and other scenario groups, specifically including: Problem scenarios with a consultation popularity exceeding a preset consultation popularity threshold are selected as the filter scenario groups, while problem scenarios with a consultation popularity not exceeding the preset consultation popularity threshold are selected as other scenario groups.

9. The intelligent customer service construction method based on scenario clustering analysis as described in claim 7, characterized in that, Determining whether the consultation popularity of a business module meets the requirements based on the module's consultation popularity and a preset consultation popularity threshold specifically includes: If the consultation popularity of a business module exceeds a preset consultation popularity threshold, then the consultation popularity of the business module is determined to be unsatisfactory.

10. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes a smart customer service construction method based on scenario clustering analysis as described in any one of claims 1-9.

Images