Action simulation interaction method and device for intelligent equipment and intelligent equipment
An intelligent device, motion simulation technology, applied in the input/output of user/computer interaction, mechanical mode conversion, character and pattern recognition, etc., can solve the problems of no motion simulation process, low information dissemination efficiency, limited information, etc. To achieve the effect of vivid interactive form, accurate information interaction, and improved accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0120] The principle and steps of the action simulation interaction method for smart devices of the present invention will be described below with reference to Embodiment 1.
[0121] Step 1: Analyze and extract the selected action samples to obtain corresponding action instructions
[0122] First, search the action videos of various animals through the Internet, or use the camera of the intelligent robot to capture the action videos of animals in real time. Action videos of various animals may include action videos of cats, action videos of dogs, and the like. For action videos, you can also customize more detailed action samples, such as cats sleeping, cats walking, dogs barking, etc. These action videos serve as action samples to be imitated.
[0123] Then, feature extraction is performed on the acquired action samples frame by frame, and recognition is performed based on the extracted features to obtain action instructions corresponding to the action samples. Then, split...
Embodiment 2
[0187] The principle and steps of the action simulation interaction method for smart devices of the present invention will be further described with reference to Embodiment 2 below.
[0188] In this embodiment, steps 1 and 2 are the same as in embodiment 1.
[0189] In step 3, the voice command issued by the user is "Imitate a dog barking", and the voice command is converted into the target text as "Imitate a dog barking". The verb phrase (that is, "imitate") and the object (that is, "a dog's barking") in the target text can be obtained through semantic analysis. Therefore, the target event corresponding to the target text is "imitating a dog's barking".
[0190] In step 4, since the event matching model established in step 2 cannot identify "dogs", the probability for all animals is 0:
[0191] p(dog barking|dog)=0, p(dog barking|tiger)=0, p(dog barking|cat)=0
[0192] In this case, the smart device asks the user: "What kind of animal is a dog?", and the user replies: "Dog"...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com