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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

