Artificial intelligence combat method based on deep learning and robot system
A deep learning and matching technology, applied in the information field, can solve problems such as limited application of artificial intelligence and insufficient samples of combat cases, and achieve the effect of improving the effect and the ability of assisting decision-making in combat, and improving subjective initiative and intelligence
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0067] Embodiment 1 provides a method of combat, such as figure 1 As shown, the method includes step S110 to step S150.
[0068] Step S110 to Step S120: Generate combat case samples and combat deep learning models through self-learning. In the stage of combat speculation, the robot is allowed to understand the combat situation and combat intention, and to speculate on combat decision-making. This stage also corresponds to the self-study stage of the teaching method, because this stage is mainly the self-learning of the robot to generate combat case samples and combat deep learning models.
[0069] Sample generating step S110: generating a plurality of first combat case samples, the first combat case samples including combat situation, combat intention, and combat decision of the preset party. Preferably, when the number of the first combat case samples is large, the first combat case sample big data can be formed. Adding multiple first combat case samples to the first comba...
Embodiment 2
[0075] Embodiment 2 provides a preferred combat method, according to the combat method described in Embodiment 1,
[0076] Such as figure 2 As shown, the specific process generated in the sample generation step S110 includes:
[0077] Situation generating step S111: generating the combat situation in the first combat case sample according to the preset combat situation knowledge base. Preferably, the combat situation knowledge base is pre-built, and the combat situation knowledge base pre-stores the combat situation composition rule sub-knowledge base and the combat situation composition element sub-knowledge base. Combat situation composition rule sub-knowledge base includes combination rules of enemy attributes, enemy capabilities, enemy real-time status, our attributes, our capabilities, and our real-time status. Combat situation component sub-knowledge base includes attribute knowledge table, capability knowledge table, real-time status knowledge table, and other relate...
Embodiment 3
[0085] Embodiment 3 provides a kind of preferred combat method, according to the combat method described in embodiment 1 or embodiment 2, such as Figure 4 As shown, step S210 and step S220 are also included after step S150:
[0086] Steps S210 to S220 belong to the combat demonstration stage (essentially the stage of verifying the combat deep learning model). This stage also corresponds to the teaching stage of the teaching method, because this stage is mainly to test and improve the combat deep learning model generated in the self-study stage through real combat cases.
[0087] Model verification step S210: Screen out a plurality of real combat case samples whose matching degree between the combat result and the combat intention is greater than a preset threshold, and verify the combat deep learning model. The real combat case samples include combat situation, combat intention, combat decision, and combat result. Comprehensible samples of real combat cases are samples of com...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap