2results about How to "Smart service" patented technology

The invention provides an unmanned special vehicle operation-oriented scene updating method and a storage medium, the unmanned special vehicle operation-oriented scene updating method comprises a cloud end, a vehicle end and a vehicle cloud intermediate service library, the vehicle cloud intermediate service library comprises middleware arranged at a cloud service end and middleware arranged at a vehicle-mounted client, and the middleware of the cloud service end comprises a cloud end-scene service scheduling component; the cloud-scene service scheduling component comprises cloud-scene analysis and a cloud local service library; the middleware of the vehicle-mounted client comprises a scene service scheduling assembly, and the scene service scheduling assembly comprises scene analysis, vehicle cloud service scheduling and a vehicle cloud local service library; the middleware of the cloud server side and the middleware of the vehicle-mounted client side are both provided with vehicle cloud interconnection assemblies for vehicle cloud communication. The cloud end further comprises a cloud end micro-service, and the cloud end micro-service configures a scene API and other components. According to the invention, the vehicle cloud middleware is taken as a core, creation, updating, synchronization and issuing of the scene mode file are realized, and accurate scene operation is supported.

This invention relates to a knowledge graph-based intelligent customer service question-and-answer precision recommendation and processing method, belonging to the field of electronic digital data technology. The method includes: constructing a conversation prediction knowledge graph based on the historical conversation counts from multiple channels; predicting the future conversation counts from multiple channels based on the conversation prediction knowledge graph and the current conversation counts from multiple channels; setting the number of robot agents and human agents based on the future conversation counts from multiple channels; accessing conversations from multiple channels, using robot agents to perform semantic understanding of user questions in the conversation, constructing a user demand profile, and determining whether to assign a human agent; if so, assigning the optimal human agent based on the status data of the human agent; if not, generating answers based on the user demand profile, conducting a dialogue, and generating recommended questions based on a question association graph. The question association graph records the relationships between multiple questions, which has the advantage of improving the quality and efficiency of customer service.