Information processing method and device
The technology of an information processing device and an information processing method, which is applied in the field of communication, can solve problems such as restricting the application of DQN and the inability to obtain numerical data information, so as to achieve the effect of accelerating the process of feature extraction and convergence and improving the scope of application
Active Publication Date: 2018-06-29
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] This solution requires the cooperation of the game developer. When the game developer cannot provide data or the data provided is incomplete, DQN cannot obtain the numerical data information that can be used, resulting in the inability to realize the purpose of AI automatic game play through DQN. Scenarios where DQN can be applied
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] Embodiments of the present invention provide an information processing method and device for obtaining game information directly from a game interface without the cooperation of game developers, and improving the application range of deep reinforcement learning DQN.
[0044] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of practice in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device compris...
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
Login to View More Abstract
An embodiment of the invention discloses an information processing method and device. The method includes: determining a plurality of reference objects in a target application; acquiring a template image of each of the reference objects and interface images of the target application in an operating process, wherein the interface images include an image of a target object, and the reference objectsinclude the target object; matching the template images with the interface images to obtain a matching result for indicating state information of the target object; converting the state information into data information of the target application. The information processing method and the device are used for directly acquiring game information from a game interface without cooperation of a game developer, and a DQN (deep Q-learning network) application range is expanded.
Description
technical field [0001] The present invention relates to the communication field, in particular to an information processing method and device. Background technique [0002] With the rapid development of artificial intelligence (AI) technology, more and more fields have begun to use AI technology. In the field of games, in order to improve the user experience, in some scenarios, it is necessary to allow AI to play games automatically. In general, deep reinforcement learning (deep Q-Learning network, DQN) is used to train game AI to play games automatically. In addition to the game screen image, the DQN network input needs to integrate more game data information as input, because the numerical data information in the game data information is difficult to obtain from the game screen image through a convolutional neural network (CNN). Therefore, the normalized numerical data information and the features extracted by CNN are generally fused together to form a feature layer. [...
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
Login to View More IPC IPC(8): A63F13/67A63F13/822
CPCA63F2300/6027A63F2300/807A63F13/67A63F13/822
Inventor 王洁梅周大军张力柯荆彦青
Owner TENCENT TECH (SHENZHEN) CO LTD