Knowledge recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a knowledge recommendation method and device, electronic equipment and a storage medium, which can be applied to the field of artificial intelligence or finance. For first search information input by a user, a first process node matched with the first search information can be detected in the business process, the next hop node of the first process node, namely a second process node, can be determined, a search term of the second process node is further packaged, and the knowledge searched in a knowledge base by the search term is output. Based on the method and the device, after the user inputs the search information for the first time, the next-hop knowledge of the business logic is searched and recommended to the user by matching the search information with the process node, so that more accurate knowledge recommendation can be provided for the user, and the business requirements of the user are met.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and more specifically, to a knowledge recommendation method, device, electronic equipment and storage medium. Background technique [0002] At this stage, knowledge search is carried out in the knowledge base system of commercial banks. The search principle is generally full-text search using search engines, mainly through fuzzy matching queries between search content and knowledge content. [0003] However, when users search for knowledge, they may also have the next-hop knowledge query requirements of business logic. For example, users first search for "what types of credit cards issued by a certain bank", and then they may also want to query "Introduction of credit cards and handling process”, which requires the user to use the search engine to do full-text search twice, which is likely to cause the problem that the knowledge found in the two searches is not very releva...

AI Technical Summary

Problems solved by technology

[0003] However, the user may also have the next-hop knowledge query requirement of business logic when performing knowledge search. For example, the user first searches for "what types of credit cards issued by a certain bank", and then may also want to query "the introduction of credit cards". and handling process", which requires the user to use the search engine twice to do full-text search, which is likely to cause the problem that the knowledge found in the two searches is not very relevant, and cannot meet the needs of the user

Images