Method and device for determining recalled interest point information, equipment and medium
A technology for determining methods and points of interest, applied in the field of retrieval, which can solve problems such as repeated recall
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] figure 1 It is a flow chart of a method for determining recalled POI information provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of deduplicating the repeatedly recalled POI information in the retrieval system. The method can be executed by a device for determining information on recalled points of interest, and the device can be implemented by software and / or hardware. see figure 1 , the method for determining the recall point of interest information provided in this embodiment includes:
[0031] S110. Select the current main word from each word included in the query sentence, and use the point-of-interest information including the current main word as candidate point-of-interest information.
[0032] Optionally, any word included in the query sentence can be used as the current main word.
[0033] Typically, the current main word is selected from each word included in the query sentence, including:
[0034] Accord...
Embodiment 2
[0060] figure 2 It is a flow chart of a method for determining recalled interest point information provided by Embodiment 2 of the present invention. This embodiment is an optional solution proposed on the basis of the foregoing embodiments. see figure 2 , the method for determining the recall point of interest information provided in this embodiment includes:
[0061] S210. Select the current main word from each word included in the query sentence, and use the point-of-interest information including the current main word as candidate point-of-interest information.
[0062] S220, according to the historical main word state of each word in the query sentence and the occurrence situation in the candidate point of interest information, perform POI occurrence state node, default state node and historical main word state node included in each branch in the state merging tree assignment.
[0063] Specifically, according to the historical main word status of each word in the qu...
Embodiment 3
[0073] This embodiment is based on the above-mentioned embodiment image 3 The state merge tree shown as an example is an optional solution proposed.
[0074] see image 3 , where AND (also expressed as and) is an AND operation, OR (also expressed as and) is an OR operation, and XOR (also expressed as xor) is an exclusive OR operation, all of which are logic operations. The XOR operation rule is: 0XOR 0=0, 0XOR 1=1, 1XOR 0=1, 1XOR 1=0. The circular node on the same layer as the OR node is the state node of the historical main word, and the value is 0 or 1. The term node under the OR node is a POI occurrence status node, which takes a value of 0 or 1, and the other is a default status node, which also takes a value of 0 or 1. The number of branches of the state merging tree is determined according to the number of words generated after the word segmentation processing of the query sentence.
[0075] Taking the query sentence as: China Merchants Industrial and Commercial Ban...
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