Seat-assisted question-answering method and system fusing semantic classification and knowledge graph

Abstract

The invention discloses a seat-assisted question-answering method and system fusing semantic classification and a knowledge graph. The method comprises the following steps: S1, collecting and preprocessing corpora; S2, constructing a knowledge graph question and answer library: constructing a data set according to the data preprocessed in the step S1, and establishing the knowledge graph question and answer library by using the constructed triple data set, each triple being composed of a question entity, a question attribute and an answer; S3, constructing an entity recognition model; S4, retrieving the knowledge graph; S5, extracting keywords: performing keyword extraction on the corpus preprocessed in the step S1, and storing an extraction result into a database; S6, clusting k-means problems; and S7, similarity calculation of candidate answers: performing text similarity calculation on the candidate answers obtained in the steps S4 and S6 and the question input by the user to obtain a text answer with the highest similarity value, and outputting the text answer to the user. According to the invention, the wire incoming intention of the user can be accurately identified and corresponding knowledge can be retrieved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and relates to an agent-assisted question answering method and system integrating semantic classification and knowledge graph. Background technique [0002] With the development of AI intelligent quality inspection technology, more and more companies use intelligent quality inspection technology to detect the customer service situation of customer service work. Through the design of certain quality inspection rules, the polite language of customer service, business answers, speech guidance, etc. Scored and evaluated on multiple fronts. However, such quality inspection technology often evaluates and inspects the behavior of customer service after the discourse. Whether the customer service answer is good or not, the result is definite. Optimize customer service and improve customer satisfaction. [0003] In actual work, many users complained that the customer service staff spoke ...

AI Technical Summary

Problems solved by technology

However, such quality inspection technology often evaluates and inspects the behavior of customer service after the discourse. Whether the customer service answer is good or not, the result is definite. Optimize customer service and improve customer satisfaction

[0003] In actual work, many users complain that the customer service personnel speak too fast, the business answers are incomplete, the service attitude is bad, etc.

From the perspective of customer service itself, they also have many pain points, such as the business knowledge system is too complex, the business process is too long, and the emotional instability caused by the boring sense of the business itself cannot guarantee 100% satisfaction.

Images