Information query method and device and electronic equipment
An information query, a technology for querying information, applied in the fields of devices, electronic equipment, and information query methods, can solve the problems of inability to obtain query results, and inability to identify user query intentions well, and achieve the effect of improving accuracy and high accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0067] In the embodiment of the present application, a preset thesaurus is established before information query in the map, which is used for word segmentation and word-of-interest tagging. Of course, the word segmentation and labeling of an information query method provided in this embodiment is not limited to using a preset thesaurus, and existing interest word thesaurus and existing word segmentation dictionaries in the prior art may also be used. The preset thesaurus includes multiple types of thesaurus, and each type of thesaurus contains a corresponding type of interest words. The types of interest words in the default lexicon include road words, suffix words, brand words, administrative area words, bus words, orientation words, spatial relationship words and verbs, etc.
[0068] When establishing a preset thesaurus, it is possible to classify and extract interest word thesaurus; perform classification training on input method data, map search corpus and / or web search co...
example 1
[0109] Example 1, assuming that the query information is "China Petroleum Exploration and Development Research Institute, Xueyuan Road, Haidian District, Beijing", the query information is segmented and interest words are marked: "Beijing [s] Haidian District [x] Xueyuan Road [r] China Research Institute of Petroleum Exploration and Development [k]", obtain the labeling sequence s-x-r-k, identify and obtain the sequence to meet the labeling rule ka-kb, obtain its query type is a compound query, and obtain the target entity of the user query according to the compound query, that is, the query demand is "China Research Institute of Petroleum Exploration and Development [k]", query according to the target entity to obtain and display the query results.
example 2
[0110] Example 2, assuming that the query information is "Unit 1801, Unit 4, Building 1, Wannian Huacheng, 200 meters east of the intersection of South Middle Ring Road and Old Jinci Road, Jinyuan District, Taiyuan City". In the conventional query process, the fuzzy query is performed by extracting the relevant text of the POI, but there are often unmatched corresponding query results, resulting in query failure. In this embodiment, word segmentation and tagging are first performed on the query, and then query classification is performed to obtain the query type, that is, the query intention is extracted, so as to improve the accuracy of the query. Word segmentation and annotation processing: "Taiyuan [c] Jinyuan District [x] South Central Ring [r] and [p] Old Jinci Road [r] intersection [ra1] east [i] 200 [n] meters [a16] Lunan [i] Wannian Huacheng [k] Building 1 [na6] Unit 4 [na5] 1801 [n]"; query classification to obtain query type: the label sequence includes "i-n-a16-i", ...
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