Search

CN-121998647-A - Customer service distribution method and device apparatus, medium, and program product

CN121998647ACN 121998647 ACN121998647 ACN 121998647ACN-121998647-A

Abstract

The application discloses a customer service distribution method, a customer service distribution device, customer service distribution equipment, a customer service distribution medium and a customer service distribution program product, and belongs to the field of customer service distribution. The method comprises the steps of obtaining the consultation problem of a service object and the working state information of each of a plurality of candidate customer services, performing classification operation on the consultation problem through a first artificial intelligent model to obtain a first problem category, screening a first number of candidate customer services carrying a first problem category label from the plurality of candidate customer services, wherein the first problem category label corresponds to the first problem category, screening a second number of candidate customer services with working states meeting working state conditions from the plurality of candidate customer services based on the working state information of each of the plurality of candidate customer services, and determining the customer services for processing the consultation problem based on the intersection of the first number of candidate customer services and the second number of candidate customer services. According to the application, the problem classification is carried out through the first artificial intelligent model, and compared with the keyword matching of the related technology, the classification result is more accurate.

Inventors

  • PENG YANG

Assignees

  • 腾讯科技（深圳）有限公司

Dates

Publication Date
20260508
Application Date
20241107

Claims (15)

  1. 1. A customer service distribution method, the method comprising: acquiring the consultation problem of the service object and the respective working state information of a plurality of candidate customer services; performing classification operation on the consultation questions through a first artificial intelligent model to obtain first question categories; Screening a first number of candidate customer services carrying a first question category label from the plurality of candidate customer services, wherein the first question category label corresponds to the first question category; And screening a second number of candidate customer services with working states meeting working state conditions from the plurality of candidate customer services based on the respective working state information of the plurality of candidate customer services; and determining customer service for processing the consultation problem based on the intersection of the first number of candidate customer service and the second number of candidate customer service.
  2. 2. The method of claim 1, wherein the performing, by the first artificial intelligence model, a classification operation on the consultation questions to obtain a first question category comprises: Extracting key information in the consultation problem through a natural language processing technology; based on the key information, extracting and obtaining the problem characteristics of the consultation problem; And inputting the problem characteristics into the first artificial intelligent model to obtain the first problem category.
  3. 3. The method of claim 2, wherein extracting key information in the consultation questions via natural language processing techniques comprises: Executing at least one of word segmentation processing, part-of-speech tagging, named entity recognition, syntactic analysis and semantic analysis on the consultation problem to obtain a processed consultation problem; extracting the key information in the processed consultation questions, wherein the key information comprises at least one of the theme of the consultation questions, actions in the consultation questions and objects in the consultation questions.
  4. 4. The method of any one of claims 1 to 3, wherein the operating state information comprises at least one of a real-time idle state, a workload condition, and an operating state that addresses a problem recently.
  5. 5. The method of claim 4, wherein the screening a second number of candidate customer services whose operational status satisfies an operational status condition from the plurality of candidate customer services based on the operational status information of each of the plurality of candidate customer services comprises: For a first candidate customer service in the plurality of candidate customer services, obtaining a working state score of the first candidate customer service based on weighted summation of first working state data, second working state data and third working state data of the first candidate customer service, wherein the first working state data is used for indicating a real-time idle state of the first candidate customer service, the second working state data is used for indicating a working load condition of the first candidate customer service, and the third working state data is used for indicating a working state of a recent processing problem of the first candidate customer service; And screening the candidate customer services with the working state scores meeting the score conditions from the plurality of candidate customer services to obtain the second number of candidate customer services.
  6. 6. A method according to any one of claims 1 to 3, wherein the method further comprises: Assigning, by a second artificial intelligence model, a problem category label to each of the plurality of candidate customer services based on the work skills information of each of the plurality of candidate customer services, the work skills information including at least one of historical training conditions, work experience, and historical treatment problems.
  7. 7. The method of claim 6, wherein the method further comprises: Generating updated multiple problem category labels according to the historical service objects and feedback information provided by the multiple candidate customer service in the first preset time period after each first preset time period passes; Retraining the second artificial intelligence model according to the updated plurality of question category labels and the updated working skill information of each of the plurality of candidate customer services.
  8. 8. A method according to any one of claims 1 to 3, wherein the method further comprises: acquiring a problem category label carried by each candidate customer service in the plurality of candidate customer services; And according to the actual treatment effect of each candidate customer service on the historical treatment problem, adjusting the problem category label carried by each candidate customer service to obtain the updated problem category label carried by each candidate customer service.
  9. 9. A method according to any one of claims 1 to 3, wherein the method further comprises: Generating a plurality of updated problem category labels according to the historical service objects and feedback information provided by the plurality of candidate customer services in the second preset time period after the second preset time period passes, and generating an updated problem library based on consultation problems proposed by the historical service objects in the second preset time period; and retraining the first artificial intelligent model according to the updated plurality of problem category labels and the updated problem library.
  10. 10. A method according to any one of claims 1 to 3, wherein before obtaining the operational status information of each of the plurality of candidate customer services and the consultation questions of the service object, the method further comprises: And reading a plurality of customer service distribution requests in batches, and determining to distribute customer service for a plurality of service objects, wherein the service objects are in one-to-one correspondence with the customer service distribution requests.
  11. 11. The method of claim 10, wherein the determining of the customer service to address the consultation problem based on the intersection of the first number of candidate customers and the second number of candidate customers further comprises: and writing a plurality of customer service distribution results in batches, wherein the plurality of customer service distribution results are in one-to-one correspondence with the plurality of customer service distribution requests.
  12. 12. A customer service distribution device, the device comprising: The acquisition module is used for acquiring the consultation problem of the service object and the respective working state information of the plurality of candidate customer services; The classification module is used for executing classification operation on the consultation problems through the first artificial intelligent model to obtain a first problem category; The screening module is used for screening a first number of candidate customer services carrying first problem category labels from the plurality of candidate customer services, and the first problem category labels correspond to the first problem categories; The screening module is further configured to screen a second number of candidate customer services whose working states meet the working state conditions from the plurality of candidate customer services based on the respective working state information of the plurality of candidate customer services; And the determining module is used for determining the customer service for processing the consultation problem based on the intersection of the first number of candidate customer service and the second number of candidate customer service.
  13. 13. Computer device, characterized in that it comprises a processor and a memory, the memory storing a computer program, which is loaded and executed by the processor to implement the customer service allocation method according to any of claims 1 to 11.
  14. 14. A computer readable storage medium storing a computer program, the computer program being loaded and executed by a processor to implement the customer service allocation method according to any one of claims 1 to 11.
  15. 15. A computer program product, characterized in that the computer program product stores a computer program that is loaded and executed by a processor to implement the customer service allocation method according to any of claims 1 to 11.

Description

Customer service distribution method and device apparatus, medium, and program product Technical Field The embodiment of the application relates to the field of customer service distribution, in particular to a customer service distribution method, a customer service distribution device, customer service distribution equipment, a customer service distribution medium and a customer service distribution program product. Background In daily life, a user can initiate a consultation problem to customer service to seek help when encountering difficulty. In the related art, when a user submits a consultation problem to a customer service center, the customer service center determines a target category of the consultation problem in a keyword matching mode, then determines candidate customer service belonging to the target category from a plurality of candidate customer service as target customer service, and solves the consultation problem to the user through the target customer service. In the related technology, the accuracy of problem classification is poor in a keyword matching mode, and then the matched target customer service is inaccurate, so that the consultation problem of the user cannot be timely and correctly solved. Disclosure of Invention The application provides a customer service distribution method, a customer service distribution device, customer service distribution equipment, a customer service distribution medium and a customer service distribution program product. The technical scheme is as follows: According to an aspect of the present application, there is provided a customer service allocation method, the method including: acquiring the consultation problem of the service object and the respective working state information of a plurality of candidate customer services; performing classification operation on the consultation questions through a first artificial intelligent model to obtain a first question category; screening a first number of candidate customer services carrying first problem category labels from the plurality of candidate customer services, wherein the first problem category labels correspond to the first problem categories; and screening a second number of candidate customer services with working states meeting the working state conditions from the plurality of candidate customer services based on the respective working state information of the plurality of candidate customer services; based on the intersection of the first number of candidate customer services and the second number of candidate customer services, a customer service that addresses the consultation problem is determined. According to another aspect of the present application, there is provided a customer service distribution apparatus, the apparatus comprising: The acquisition module is used for acquiring the consultation problem of the service object and the respective working state information of the plurality of candidate customer services; The classification module is used for performing classification operation on the consultation problems through the first artificial intelligent model to obtain a first problem category; the screening module is used for screening a first number of candidate customer services carrying first problem category labels from the plurality of candidate customer services, and the first problem category labels correspond to the first problem categories; The screening module is further used for screening a second number of candidate customer services with working states meeting the working state conditions from the plurality of candidate customer services based on the respective working state information of the plurality of candidate customer services; the determining module is used for determining customer service for processing consultation problems based on the intersection of the first number of candidate customer service and the second number of candidate customer service. According to one aspect of the present application there is provided a computer device comprising a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement a customer service allocation method as described above. According to another aspect of the present application, there is provided a computer readable storage medium storing a computer program loaded and executed by a processor to implement the customer service allocation method as described above. According to another aspect of the present application, a computer program product is provided, the computer program product comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the customer service allocation method provided in the above aspect. The