Method and device for generating reply information based on robot emotional state
A technology for replying to messages and robots, applied in the field of intelligent robots, and can solve problems such as incompatibilities with human-human interaction
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] This embodiment provides a method for generating reply information based on the emotional state of the robot, see figure 1, the method includes:
[0061] Step S101, acquiring the emotional factors of the robot, the emotional factors including the current emotional state of the robot, the familiarity of the robot with the current user, the emotional history between the robot and the current user, the emotional history of the robot with the current environment, and the emotional state of the current user;
[0062] Specifically, the emotion factor of the robot is described by multi-dimensional data, for example, it can be described by multi-dimensional vector or multi-dimensional linked list. The current mood state of the robot refers to the current mood of the robot, for example: happy, depressed, sad, etc. The robot's familiarity with the current user includes: very familiar, generally familiar, not familiar, and so on. The emotional history between the robot and the c...
Embodiment 2
[0069] Embodiment 2 On the basis of Embodiment 1, a method for acquiring emotional factors is added.
[0070] 1. The current mood state of the robot.
[0071] In terms of emotional factor processing, for the current emotional state of the robot, see figure 2 , the specific acquisition process is as follows:
[0072] Step S201, counting the current remaining power and usage time of the robot.
[0073] Step S202, detecting the current network status and activity status of the robot.
[0074] Step S203, determine the current mood state of the robot according to the remaining power, usage time, network status, activity status or pre-received mood-specific information.
[0075] Specifically, the robot can determine the current mood based on remaining power, duration of use, network conditions, activity conditions, or mood-specific information. For example, if the remaining power of the robot is less than 10%, it is hungry, and the current mood state of the robot is to ask the ...
Embodiment 3
[0111] Embodiment 3 On the basis of the foregoing embodiments, a method for generating reply information is added.
[0112] In terms of reply information generation guidance control, the specific implementation process is as follows:
[0113] The first one is to use the emotional label of the robot as one of the input information of the training model to guide the generation of the training model; to guide the generation of reply information according to the generated training model, and to determine the specific form category used when replying to the information;
[0114] Specifically, the training model is an artificial intelligence model, and the training model is obtained by learning all robot emotion labels by the artificial intelligence model. This method can start from human learning, use artificial intelligence methods such as machine learning to model human emotional responses, determine human emotional responses under the circumstances of different values of the a...
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