User query intention understanding method, system and computer terminal
A technology for querying intentions and users, applied in computing, digital data processing, special data processing applications, etc., can solve problems such as inability to extract semantic information, weak feature expression ability, and ignore contextual relations, etc., to achieve strong semantic feature expression ability Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0048] Example 1
[0049] figure 1 A schematic flowchart of a method for understanding user query intentions provided by an embodiment of the present invention is shown.
[0050] Step S110, taking the seed concept of the predetermined intent domain as a starting point, crawling the concept related to the domain in the knowledge base and the classification label of the concept.
[0051] Mark a small number of preset query sentences in the predetermined intent domain, and use the concepts in the sentences as seed concepts. The seed concept may include at least one concept in a predetermined query sentence of a predetermined intent domain;
[0052] Take the seed concept as a starting point, crawl the concept related to the field in the knowledge base and the classification label of the concept, and use the parent classification label and sub classification label of the classification label, the inclusion relationship of the classification label to the related concept and the relationship...
Example Embodiment
[0077] Example 2
[0078] figure 2 It shows a schematic flowchart of another method for understanding user query intentions according to an embodiment of the present invention. In this embodiment, the intention field of "cooking" is taken as an example to illustrate the method for understanding the user's query intention.
[0079] In step S210, the knowledge base is crawled according to the seed concept of the predetermined intent domain.
[0080] For example, mark a small number of query sentences related to the "cooking" intent, such as: "the best Chinese food", "how to make sweet and sour pork ribs", this query statement includes "Chinese food" and "sweet and sour pork ribs" "Two seed concepts.
[0081] Search the Wikipedia knowledge base and search for "Chinese cuisine" to find the concept of "Chinese cuisine", the corresponding "Chinese cuisine" classification label, and links to the concepts of "cold dish", "soy sauce", "fry", etc.; check " "Sweet and Sour Spare Ribs" can be ...
Example Embodiment
[0129] Example 3
[0130] Figure 5 It shows a schematic structural diagram of a user query intention understanding system provided by an embodiment of the present invention.
[0131] The user query intention understanding system 20 includes a data crawling module 21, a link graph building module 22, a probability calculation module 23, a concept return module 24, and an intention judgment module 25.
[0132] The data crawling module 21 uses the seed concept of the predetermined intent domain as a starting point to crawl the concept related to the domain in the knowledge base and the classification label of the concept.
[0133] The link graph construction module 22 establishes a concept link graph of a predetermined intent field according to the crawled concept and the classification label of the concept.
[0134] The probability calculation module 23 calculates the probability that a concept node in the concept link graph belongs to a predetermined intent domain.
[0135] The concept r...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap