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

Method and device for behavior recognition and model training

A technology for model identification and model training, applied in the field of behavior identification and model training, can solve the problems of insufficient model behavior identification effect and low efficiency, and achieve the effect of improving accuracy, reducing parameters and improving efficiency.

Active Publication Date: 2022-03-15
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This manual marking method is inefficient, and the trained model is not good enough in behavior recognition

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 and device for behavior recognition and model training
  • Method and device for behavior recognition and model training
  • Method and device for behavior recognition and model training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will describe the technical solutions in one or more embodiments of this specification in conjunction with the drawings in one or more embodiments of this specification The technical solution is clearly and completely described, and obviously, the described embodiments are only a part of the embodiments in this specification, rather than all the embodiments. Based on one or more embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0031] The training of the behavior recognition model provided by at least one embodiment of this specification is based on the coupled hidden Markov chain, that is, a behavior recognition model is trained based on the coupled hidden Markov chain, and in ...

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 this specification provides a method and device for behavior recognition and model training, wherein the method includes: acquiring training data, the training data includes: sensor data corresponding to different physical objects with behavioral interaction correlations and hidden objects of physical objects state; the sensor data is collected during the behavior interaction process of different entity objects; multiple model parameters are initialized, each model parameter includes parameters corresponding to different entity objects, and the state transition probability in the model parameters includes: the same entity object The transition probability between the hidden states of different entity objects and the transition probability between the hidden states of different entity objects; model training is carried out according to the model parameters, wherein, in the deductive process of model training, if an entity object lacks the corresponding hidden state at the target time , the transition probability of the hidden state between the entity object and another entity object is used; and when the end condition of model training is reached, the behavior recognition model is obtained.

Description

technical field [0001] This specification relates to the field of machine learning technology, in particular to a method and device for behavior identification and model training. Background technique [0002] With the widespread use of various home entertainment devices and wearable devices, a large amount of data that can be used for behavior recognition has been generated. For example, in the scene of human-device interaction, for example, the user uses a water heater to boil water, or the user uses cleaning equipment to clean, etc., the data generated by the user during the use of the device can be collected through various sensors such as temperature sensors and capacitive sensors. , and then identify the behavior performed by the user. [0003] In related technologies, when training the model for behavior recognition based on the data collected by the sensor, the sensor data of the training set samples can be manually marked, for example, marking a piece of collected ...

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): G06N7/00
CPCG06N7/01
Inventor 张慧英
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD