Stay point recognition and prediction model training method and device and storage medium
A technology of prediction model and identification method, applied in the field of computer applications, can solve the problems of low recall rate, identification of stop points, and inability to handle well, and achieve the effect of improving recall rate and high accuracy
Active Publication Date: 2020-01-03
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the above two methods will have certain problems in practical applications, such as: method 1) can handle the situation of continuous and dense trajectory points better, but can not handle other situations better, accuracy and recall In method 2), although the positioning points connected to the wifi of fixed POIs are usually stay points, the stay points are not necessarily connected to the wifi of fixed POIs. For example, when the user is in a scenic spot without wifi coverage , this method cannot be used to identify the stop point, so the recall rate of this method is relatively low
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] In order to make the technical solution of the present invention more clear and understandable, the solution of the present invention will be further described below with reference to the accompanying drawings and examples.
[0045] Apparently, the described embodiments are some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.
[0046] In addition, it should be understood that the term "and / or" in this article is only an association relationship describing associated objects, which means that there may be three relationships, for example, A and / or B may mean: A exists alone, and A exists at the same time. and B, there are three cases of B alone. In addition, the character " / " in this article generally indicates that the contextual objects are an "or" relationship.
[0047] fi...
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
Login to View More Abstract
The invention discloses a stay point recognition and prediction model training method and device and a storage medium, and the method can comprise the steps: obtaining the features of N preset dimensions of a to-be-recognized positioning point for the to-be-recognized positioning point, wherein N is a positive integer greater than one; generating a feature vector of a to-be-identified positioningpoint according to the obtained features; and determining whether a to-be-identified positioning point is a stay point based on the feature vector by using a prediction model obtained by pre-training.By applying the scheme of the invention, the accuracy, recall rate and the like of stay point identification can be improved.
Description
【Technical field】 [0001] The invention relates to computer application technology, in particular to a method, a device and a storage medium for identifying a staying point and training a prediction model. 【Background technique】 [0002] In practical applications, video or feed streams can be pushed to users based on their behavior patterns. User behavior patterns can be divided into staying and moving, and different behavior patterns can correspond to different push strategies. [0003] Correspondingly, it is necessary to identify the positioning point of the user, so as to identify whether the positioning point is a stay point or a moving point. At present, the following stay point identification methods are usually used: 1) space-time window method, the algorithm assumes that the user's positioning point is a continuous trajectory point, and judges the point that meets the specific time and space threshold conditions as the stay point; 2) based on wireless protection The...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06F16/9537G06K9/62G06N3/08G06N20/00G06N20/10H04L29/08
CPCG06F16/9535G06F16/9537G06N3/08G06N20/00G06N20/10H04L67/55G06F18/214H04W4/029G06N20/20G06N5/01G06N5/04
Inventor 李岩岩段建国熊辉
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD