Conversation interaction method and device, equipment and storage medium
An interaction method and technology for interactive data, applied in the fields of dialogue interaction methods, equipment and storage media, and devices, can solve the problems of insufficient stability of the human-machine dialogue system, poor user experience, and boring responses, and achieve stable and controllable interaction. , good user experience, more interactive content
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0069] see figure 1 , which shows a schematic flow chart of the dialog interaction method provided by the embodiment of the present application, the method may include:
[0070] Step S101: Obtain the user's dialog interaction data.
[0071] Wherein, the dialogue interaction data of the user may be text data obtained by performing speech recognition on speech data input by the user, or may be text data input by the user.
[0072] Step S102: From the pre-built knowledge graph, determine the knowledge nodes related to the user's dialogue interaction data, so as to obtain a node set composed of the determined knowledge nodes.
[0073] Wherein, the knowledge graph includes several knowledge nodes, and there are edges between knowledge nodes that have relationships in the knowledge graph, and each edge in the knowledge graph has a relationship between two nodes connected by the edge.
[0074] In one possible implementation, the knowledge nodes included in the knowledge graph may i...
no. 2 example
[0080] This embodiment is specific to the implementation process of "step S102: from the pre-built knowledge map, determine the knowledge nodes related to the user's dialogue interaction data to obtain a node set composed of the determined knowledge nodes" in the first embodiment Make an introduction.
[0081] see image 3 , which shows a schematic flowchart of an implementation process of determining knowledge nodes related to user dialogue interaction data from a pre-built knowledge graph, which may include:
[0082] Step S301: Determine user intent and slot value according to the user's dialog interaction data.
[0083] Optionally, the user intent can be a non-explicit open intent, and the slot value can be an entity.
[0084] Specifically, according to the user's dialog interaction data, the process of determining the user intent and the slot value may include: using the intent determination module to determine the specified type of open intent as the user intent based o...
no. 3 example
[0104] It can be known from the above embodiments that the dialog interaction method provided by the present application performs dialog interaction with the user based on the pre-built knowledge graph, and this embodiment focuses on the introduction of the process of building the knowledge graph.
[0105] see Figure 5 , showing a schematic flow diagram of building a knowledge map, which may include:
[0106] Step S501: Obtain action graphs, entity knowledge graphs and event graphs.
[0107] Among them, the action graph includes several action nodes, there are edges between the related action nodes in the action graph, and each edge has the relationship between two action nodes connected by the edge, that is, the action graph uses actions as nodes, and the action The relationship between is a graph composed of edges. The action graph defines some common actions and the relationship between actions.
[0108] see Figure 6 , showing an example of an action graph, such as ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com