Information processing method and device, storage medium and equipment

Abstract

The embodiment of the invention discloses an information processing method and device, a storage medium and equipment. The method comprises the steps of performing keyword extraction on acquired business consultation information to obtain N first keywords; determining entity categories respectively corresponding to the N first keywords from the first mapping table, splicing the entity categories respectively corresponding to the N first keywords to obtain a to-be-matched sentence pattern, and determining a target annotated sentence pattern matched with the to-be-matched sentence pattern from the target annotated sentence pattern set; and querying data information associated with the target annotated sentence pattern and the N first keywords in a business database, and outputting the data information. According to the invention, the accuracy of the data information used for replying the service consultation information can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to an information processing method, device, storage medium and equipment. Background technique [0002] Since the early days of artificial intelligence research, people have been committed to developing intelligent human-computer dialogue systems to serve the people and replace part of the labor. Man-machine dialogue is widely used in various fields and applications, such as Apple's siri, Microsoft's cortana, Baidu Dumi, Ali Xiaomi and other personal assistants, wearable devices, smart home, smart customer service, etc. also include dialogue system. The man-machine dialogue system can provide services to people quickly, efficiently and uninterruptedly, so as to improve the service experience and help enterprises improve service quality while effectively reducing labor costs. [0003] In current dialogue systems, intent recognition methods or standard question matc...

AI Technical Summary

Problems solved by technology

[0003] In current dialogue systems, intent recognition methods or standard question matching methods are generally used to understand user questions. However, since user questions cannot be clearly defined, there is uncertainty in understanding, and single intent matching or question matching is less accurate. Low, the understanding of words in special fields (such as finance or chemistry) is relatively inaccurate, which leads to low accuracy of replies to user questions

Images