Unlock instant, AI-driven research and patent intelligence for your innovation.

Target behavior recognition system

A technology for identifying systems and behaviors, applied in the computer field, can solve the problems of large workload of user feature review and low efficiency in identifying target behaviors, and achieve the effect of improving the efficiency and accuracy of identification

Active Publication Date: 2021-06-25
北京云真信科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the advent of the era of big data, the number of user characteristics and types of data is huge, which will result in a heavy workload for manual screening of user characteristics corresponding to target behaviors and auditing, and low efficiency in identifying target 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Target behavior recognition system
  • Target behavior recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The preset model is a single classification model, and the step S3 may include:

[0047] Step S31: Construct an input feature vector based on the first feature information (c1, c2, ... cm) corresponding to each first sample user id, and use the target behavior value corresponding to the first sample user id as the actual classification result, and input the pre-set Train in the first classification model provided to obtain the first classification model;

[0048] Step S32: Construct an input feature vector based on the first feature information (c1, c2, ... cm) corresponding to each first sample user id, and use the target behavior value corresponding to the first sample user id as the actual classification result, and input the pre-set Training is carried out in the second classification model of setting, obtains the second classification model;

[0049] Step S33: Construct an input feature vector based on the first feature information (c1, c2, ... cm) corresponding t...

Embodiment 2

[0052] The preset model is a combined classification model, including a first classification model, a second classification model and a third classification model, and the step S3 includes:

[0053] Step S301. Construct input feature vectors based on the first feature information (c1, c2, ...cm) corresponding to each first sample user id, and use the target behavior value corresponding to the first sample user id as the actual classification result, and input In the first classification model, the second classification model and the third classification model;

[0054] Step S302, using the average of the output results of the three models as the output result of the combined model for training to obtain a first combined classification model.

Embodiment 3

[0056] The preset model is a combined classification model, including a first classification model, a second classification model and a third classification model, and the step S3 includes:

[0057] Step S311: Construct input feature vectors based on the first feature information (c1, c2, ... cm) corresponding to each first sample user id, and use the target behavior value corresponding to the first sample user id as the actual classification result, and input In the first classification model, the second classification model and the third classification model;

[0058] Step S302 , vote on the output results of the three models, and use the result with the highest vote as the output result of the combined model for training to obtain a second combined classification model.

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 invention relates to a target behavior recognition system, which comprises a pre-constructed first database, a second database, a processor and a memory in which a computer program is stored, and is characterized in that the first database is used for storing user feature records, and fields of the user feature records comprise users and corresponding preset M pieces of feature information (C1, C2,... CM); and the second database is used for storing records of sample target behaviors, the fields of the records of the sample target behaviors comprise a sample user id and a target behavior numerical field, the target behavior numerical field is 0 and indicates that the sample user does not have the target behavior, and the target behavior numerical field is 1 and indicates that the sample user has the target behavior. According to the invention, the target behavior identification efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a target behavior recognition system. Background technique [0002] At present, the traditional identification technology of target behavior mainly relies on manual feature screening and analysis of persons who have been confirmed to have target behavior records in history, establishes a variety of judgment rules, and predicts whether the user to be identified has target behavior through the judgment rules. However, with the advent of the era of big data, the number and types of user characteristics are huge, which will result in a heavy workload for manual screening of user characteristics corresponding to target behaviors and review, and low efficiency in identifying target behaviors. In addition, artificially established judgment rules tend to have more interpretable features, while non-interpretable features are often easily ignored, but some non-interpretable features also...

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 Applications(China)
IPC IPC(8): G06F16/9035G06F16/906G06F16/901
CPCG06F16/9035G06F16/906G06F16/901Y02D10/00
Inventor 朱金星张静雅段力阁
Owner 北京云真信科技有限公司