Search

CN-122022282-A - Online customer service scheduling method and device, computer equipment and storage medium

CN122022282ACN 122022282 ACN122022282 ACN 122022282ACN-122022282-A

Abstract

The invention relates to the field of communication and discloses an online customer service scheduling method, device, computer equipment and storage medium, wherein the method comprises the steps of performing feature modeling on a user request to be distributed currently to obtain request feature data; the method comprises the steps of identifying at least one customer service person in an online state, obtaining portrait data of the customer service person, calculating matching degree between each customer service person and a user request based on request feature data and portrait data, and distributing the user request to a corresponding target customer service person according to the matching degree. The invention solves the problems of low matching precision and unbalanced system load caused by lack of feature modeling of the user request and dynamic calculation based on multi-factor matching in the existing customer service scheduling method.

Inventors

  • HUANG LIANGCHENG

Assignees

  • 北京白龙马科技有限公司

Dates

Publication Date
20260512
Application Date
20260112

Claims (10)

  1. 1. An online customer service scheduling method, comprising the steps of: performing feature modeling on a user request to be distributed currently to obtain request feature data; Identifying at least one customer service person in an online state, and acquiring portrait data of the customer service person; calculating the matching degree of each customer service person and the user request based on the request feature data and the portrait data; and distributing the user request to a corresponding target customer service personnel according to the matching degree.
  2. 2. The method according to claim 1, wherein the feature modeling of the user request to be currently distributed to obtain request feature data includes: extracting text content in the user request; carrying out semantic analysis on the text content to obtain user intention; And generating corresponding request characteristic data according to the user intention, wherein the request characteristic data at least comprises a problem category and urgency.
  3. 3. The method of claim 1, wherein said calculating a degree of matching of each of said customer service personnel with said user request based on said request feature data and said portrayal data comprises: Analyzing skill labels, business information and historical processing data in the portrait data; Calculating the skill matching degree between the problem category in the request feature data and the skill label; And determining a load factor based on the service information, and calculating the matching degree of the customer service personnel and the user request according to the skill matching degree, the load factor and the historical processing data.
  4. 4. A method according to claim 3, wherein said determining a loading factor based on said traffic information comprises: acquiring working data of the customer service personnel, wherein the working data at least comprises the number of service requests, the processing progress of each service request and the duration; Predicting estimated remaining processing time of the customer service personnel based on the number of service requests, the processing progress and the duration of each service request; and calculating the load factor of the customer service personnel according to the estimated remaining processing time, wherein the load factor and the estimated remaining processing time are positively correlated.
  5. 5. A method according to claim 3, wherein said calculating a match of said customer service person to said user request based on said skill match, said load factor, and said historical processing data comprises: extracting scheduling scores of the customer service personnel from the historical processing data; determining a corresponding request priority according to the user information corresponding to the user request; And carrying out fusion calculation on the skill matching degree, the load factor, the scheduling score and the request priority according to a preset weight list to obtain the matching degree of the customer service personnel and the user request.
  6. 6. The method of claim 1, wherein said assigning the user request to a corresponding target customer service person according to the degree of matching comprises: comparing the matching degree corresponding to each customer service person with a preset matching degree to obtain a comparison result; If the comparison result shows that the customer service personnel with the matching degree larger than the preset matching degree exist, determining the customer service personnel with the highest matching degree as the target customer service personnel, and distributing the user request to the target customer service personnel; and if the comparison result shows that no customer service personnel with the matching degree larger than the preset matching degree exist, the user request is moved to a candidate queue.
  7. 7. The method of claim 5, wherein after assigning the user request to the corresponding target customer service person according to the degree of matching, the method further comprises: detecting a processing process of the user request; When the processing progress of the user request reaches an end node, session feedback data are obtained; And optimizing the preset weight list according to the session feedback data to obtain an optimized weight list.
  8. 8. An on-line customer service dispatch apparatus, the apparatus comprising: the processing module is used for carrying out feature modeling on the user request to be distributed currently to obtain request feature data; the identification module is used for identifying at least one customer service person in an online state and acquiring portrait data of the customer service person; The computing module is used for computing the matching degree of each customer service person and the user request based on the request feature data and the portrait data; And the distribution module is used for distributing the user request to the corresponding target customer service personnel according to the matching degree.
  9. 9. A computer device, comprising: a memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 7.
  10. 10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.

Description

Online customer service scheduling method and device, computer equipment and storage medium Technical Field The present invention relates to the field of communications, and in particular, to an online customer service scheduling method, an online customer service scheduling device, a computer device, and a storage medium. Background With the rapid development of the internet, the demand of online customer service is rapidly increased, and customer service scheduling becomes a key link affecting customer experience and enterprise efficiency. The current common customer service dispatching mode mainly comprises methods of polling allocation, idle priority, manual assignment and the like. These approaches may achieve allocation of requests to some extent, but generally rely on simple rules or manual intervention, failing to adequately account for the differences in the specific content characteristics of customer requests and the actual capabilities of customer service personnel. However, the existing scheduling method has obvious defects in practical application that firstly, matching accuracy is low, skill labels, real-time states and historical processing data of customer service personnel are not combined because semantic analysis and feature extraction are not carried out on a user request, so that customer problems cannot be accurately distributed to the most suitable customer service, secondly, system loads are unbalanced, distribution is carried out only on the basis of sequence or idle states, overload of part of customer service is easy to cause, the other part of customer service is idle, the utilization rate of the whole resources is not high, thirdly, response speed is limited, multi-dimensional real-time matching calculation of the request and the customer service is lacked, and customer waiting time is long. The root of these problems is that existing methods lack modeling mechanisms for request features and dynamic scheduling capabilities based on multi-factor matching. Disclosure of Invention In view of the above, the embodiments of the present invention provide an online customer service scheduling method, apparatus, computer device, and storage medium, so as to solve the problems of low matching precision and unbalanced system load caused by lack of feature modeling of a user request and dynamic computation based on multi-factor matching in the existing customer service scheduling method. In a first aspect, an embodiment of the present invention provides an online customer service scheduling method, where the method includes: performing feature modeling on a user request to be distributed currently to obtain request feature data; Identifying at least one customer service person in an online state, and acquiring portrait data of the customer service person; calculating the matching degree of each customer service person and the user request based on the request feature data and the portrait data; and distributing the user request to a corresponding target customer service personnel according to the matching degree. Further, the feature modeling for the user request to be allocated currently to obtain request feature data includes: extracting text content in the user request; carrying out semantic analysis on the text content to obtain user intention; And generating corresponding request characteristic data according to the user intention, wherein the request characteristic data at least comprises a problem category and urgency. Further, the calculating, based on the request feature data and the portrait data, the matching degree between each customer service person and the user request includes: Analyzing skill labels, business information and historical processing data in the portrait data; Calculating the skill matching degree between the problem category in the request feature data and the skill label; And determining a load factor based on the service information, and calculating the matching degree of the customer service personnel and the user request according to the skill matching degree, the load factor and the historical processing data. Further, the determining the loading factor based on the service information includes: acquiring working data of the customer service personnel, wherein the working data at least comprises the number of service requests, the processing progress of each service request and the duration; Predicting estimated remaining processing time of the customer service personnel based on the number of service requests, the processing progress and the duration of each service request; and calculating the load factor of the customer service personnel according to the estimated remaining processing time, wherein the load factor and the estimated remaining processing time are positively correlated. Further, the calculating the matching degree between the customer service personnel and the user request according to the skill matching degree, the load factor and the h