Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method, device, computing device and medium for discovering poi transition events

A technology for discovering methods and events, applied in computing, instruments, electrical and digital data processing, etc., can solve the problems of time-consuming and labor-intensive, low judgment accuracy, low recall rate, etc., to improve recall rate, ensure accuracy, solve problems Judging less accurate effects

Active Publication Date: 2021-04-02
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, in order to remove sentences that have no connection between POI and trigger words, when using linguistic tools to associate POI and trigger words, it is necessary to manually summarize the rules of each link (that is, there are many components of manual intervention), which may cause POI and trigger words. The association between words is wrong, and this type of method does not have the generalization ability, and manual intervention also makes the existing method time-consuming and labor-intensive; in addition, due to the complexity and variability of the language, the extraction tool itself also has problems with POI and trigger words. The extraction error further leads to the low accuracy and low recall rate of existing methods for judging POI change events

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device, computing device and medium for discovering poi transition events
  • Method, device, computing device and medium for discovering poi transition events
  • Method, device, computing device and medium for discovering poi transition events

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 It is a flow chart of the method for discovering POI transition events provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where the information describing POI transition events is confirmed through mining massive network information. The method can be executed by a POI change event discovery device, which can be implemented in software and / or hardware, and can be integrated on any computing device, including but not limited to a server.

[0027] Such as figure 1 As shown, the POI transition event discovery method provided in this embodiment may include:

[0028] S110. Determine a first sentence vector of the training sentence in the training text based on the correlation between each word in the training sentence.

[0029] Before training the model based on deep learning ideas, it is necessary to prepare the training text in advance. The training text can be any social media text, such as various information text...

Embodiment 2

[0047] figure 2 It is a flow chart of the method for discovering POI transition events provided by Embodiment 2 of the present invention, and this embodiment is further optimized on the basis of the foregoing embodiments. Such as figure 2 As shown, the method may include:

[0048] S210. Segment the training sentence, and use the word vector analysis model to determine the word vector, position vector and part-of-speech vector of each word obtained through word segmentation in the training text.

[0049] In this embodiment, the vector representation of each word obtained by segmenting the training sentence is composed of three parts of vectors: word embeddings (Word Embeddings), position vectors (Position Embedding) and part-of-speech vectors (POSEembedding). Among them, the word vector can be obtained by using a pre-trained unsupervised model, such as the word2vector model, etc. The unsupervised model can be obtained based on existing open source word vectors or self-built...

Embodiment 3

[0062] Figure 4 It is a schematic structural diagram of a POI transition event discovery device provided in Embodiment 3 of the present invention. This embodiment is applicable to the situation where the information describing POI transition events is confirmed by mining massive network information. The device can be implemented in the form of software and / or hardware, and can be integrated on any computing device, including but not limited to a server.

[0063] Such as Figure 4 As shown, the POI transition event discovery device provided in this embodiment may include a first vector determination module 310, a second vector determination module 320, and a model training module 330, wherein:

[0064]The first vector determination module 310 is used to determine the first sentence vector of the training sentence in the training text based on the relevance between each word in the training sentence;

[0065] The second vector determination module 320 is used to determine the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the present invention discloses a POI transition event discovery method, device, computing device and medium, wherein the method includes: determining the first sentence of the training sentence in the training text based on the correlation between each word in the training sentence Vector; Utilize preset language model, determine the second sentence vector of training sentence in training text, and the POI vector of POI in training text in training sentence; With the first sentence vector, the second sentence vector and POI vector as input, The POI transition event labeling result of the training sentence is used as an output, and the POI transition event recognition model is trained to determine whether the target sentence is a POI transition event sentence by using the POI transition event recognition model. The embodiments of the present invention can accurately and efficiently discover POI change events from massive network information, improve the recall rate for determining POI change events, and thus provide accurate POI information for downstream services.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of Internet information processing, and in particular, to a POI transition event discovery method, device, computing device, and medium. Background technique [0002] Current network social content (such as all kinds of information published on platforms such as Weibo, webpages, and official accounts) contains some POI (Point of Interest, point of interest) change event information, such as shopping malls "relocation", "suspension of business" or "Business hours adjustment", etc., this kind of information plays a very important role in the map. For example, when a user retrieves a POI, such as "xx Museum", if the user can be reminded of the information such as the suspension of business or the adjustment of business hours through a strong style, it can reduce the user's invalid travel, and at the same time, it can also improve the user experience of map users . However, useful POI cha...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9537G06F40/279
CPCG06F16/9537G06F40/279
Inventor 潘禄梁海金陈玉光彭卫华罗雨刘远圳韩翠云施茜
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More