A method and device for extracting user time-series behavior features
A technology of feature extraction and behavior, applied in special data processing applications, unstructured text data retrieval, instruments, etc., can solve problems such as difficult to distinguish users with consistent operation behaviors, and achieve the effect of flexible implementation methods and simple calculation processes
Active Publication Date: 2022-06-17
上海上湖信息技术有限公司
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, the feature extraction method in the prior art that only uses user behavior data as the basis for feature extraction has a one-sided response and is difficult to distinguish users with consistent operating behaviors.
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
[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0055]Existing websites or application clients are composed of pages in a certain order and process. Each page carries user browsing, completing certain information entry, or clicking different buttons and other operation behaviors. The technology can perform feature extraction based on these operation behaviors. However, when the user operation behaviors are c...
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 method and device for extracting user time-series behavior features, wherein the method includes: constructing a behavior dictionary according to each behavior data of a single user in each page within a certain period of time and the time stamp of each behavior data, and the behavior dictionary Including: page information, behavior data corresponding to the page information, and behavior time corresponding to the behavior data; time normalization and time discretization processing are performed on the behavior dictionaries of multiple users, and the behavior corpus is constructed using the processed behavior dictionaries; based on The behavior corpus uses the TF-IDF feature extraction method to generate user time-series behavior feature vectors. The invention integrates the time consumption of different behaviors of users on different pages into the behavior dictionary, so that there are differences in the same behaviors of different users, and feature extraction is performed more accurately.
Description
technical field [0001] The present invention relates to the technical field of feature extraction, and in particular, to a method and device for extracting user timing behavior features. Background technique [0002] TF-IDF is a commonly used weighting technique for information retrieval and information mining to assess the importance of a word to a document set or a document in a corpus. The importance of a word increases proportionally to the number of times it appears in the document, but decreases inversely to the frequency it appears in the corpus. Therefore, in mobile applications, TF-IDF is usually used to analyze user behavior data, and extract user behavior feature vectors based on the TF-IDF method. The extraction of general user behavior feature vectors is only based on behavior data, and rarely refers to the time of operation behavior. Once the user's operation behavior is always difficult to distinguish the user, and the user's operation time can often convey a...
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 Patents(China)
IPC IPC(8): G06F16/36G06F16/383G06F16/9537G06F16/958
CPCG06F16/374G06F16/383G06F16/9537G06F16/958
Inventor 李君浩胡宏辉
Owner 上海上湖信息技术有限公司