Information display methods, devices, storage media, and electronic devices
By displaying gameplay footage and obtaining match reference data in virtual games, the problem of users being unable to see the AI decision-making process has been solved, enabling more comprehensive information display.
Patent Information
- Application Number
- CN202210719475.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-23
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-06-23
AI Technical Summary
In virtual games, users cannot see the decision-making process of artificial intelligence, resulting in incomplete information display.
The game displays the running screen of the target virtual game and obtains game reference data. Based on this data, the execution prediction information of the candidate operations to be performed by the virtual character is displayed to provide auxiliary reference.
It enables an intuitive display of the decision-making process of artificial intelligence in virtual games, improving the comprehensiveness of information display.
Smart Images

Figure CN116999823B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computers, and more specifically, to an information display method, apparatus, storage medium, and electronic device. Background Technology
[0002] With the rapid development of artificial intelligence (AI), its application in virtual games has become a trend. However, in this trend, users typically only see the AI's decision-making results, not the decision-making process, and therefore cannot learn from its decision-making methods. The reason for this is the lack of information display regarding the AI's decision-making process in virtual games. Therefore, there is a problem of incomplete information display.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This application provides an information display method, apparatus, storage medium, and electronic device to at least solve the technical problem of insufficient information display.
[0005] According to one aspect of the embodiments of this application, an information display method is provided, comprising: displaying a running screen of a target virtual game corresponding to a first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is an artificial intelligence-driven virtual object used to simulate the control of a virtual character in the target virtual game; acquiring game reference data corresponding to the running screen, wherein the game reference data is game data fed back by the virtual character when participating in the target virtual game in the first time unit; and displaying execution prediction information corresponding to a candidate operation to be performed by the virtual character in a second time unit based on the game reference data, wherein the execution prediction information is used to provide auxiliary reference related to the game reference data for a control command initiated by the simulated object in the second time unit, the control command being an instruction initiated by the simulated object when controlling the virtual character to perform the candidate operation, and the second time unit being after the first time unit.
[0006] According to another aspect of the embodiments of this application, an information display device is also provided, comprising: a first display unit, configured to display the running screen of a target virtual game corresponding to a first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is an artificial intelligence-driven virtual object used to simulate the control of a virtual character in the target virtual game; an acquisition unit, configured to acquire game reference data corresponding to the running screen, wherein the game reference data is game data fed back by the virtual character when participating in the target virtual game in the first time unit; and a second display unit, configured to display execution prediction information corresponding to a candidate operation to be performed by the virtual character in the second time unit based on the game reference data, wherein the execution prediction information is used to provide auxiliary reference related to the game reference data for the control command initiated by the simulated object in the second time unit, the control command being the command initiated by the simulated object when controlling the virtual character to perform the candidate operation, and the second time unit being after the first time unit.
[0007] As an optional solution, the second display unit includes: a first display module, used to display first probability distribution information of the virtual character performing at least two candidate operations in the second time unit, wherein the first probability distribution information is used to predict the probability of the virtual character performing each of the at least two candidate operations in the second time unit.
[0008] As an optional solution, the second display unit includes: a second display module, used to display second probability distribution information of the virtual character performing the candidate operation on at least two pointed objects, wherein the second probability distribution information is used to predict the probability that the virtual character performs the candidate operation on each of the at least two pointed objects in the second time unit.
[0009] As an optional solution, the first display unit includes: a third display module for displaying the running screen in a first interface area of the spectator interface; the second display unit includes: a fourth display module for displaying the execution prediction information in a second interface area of the spectator interface.
[0010] As an optional solution, the third display module includes: a first display submodule, used to display the main running screen of the target virtual game corresponding to the first time unit in a first sub-area of the first interface area, and to display the running sub-screen of the target virtual game corresponding to the first time unit in a second sub-area of the spectator interface, wherein the main running screen is a real-time screen within the virtual scene of the target virtual game, and the running sub-screen is a thumbnail of the virtual scene, and the thumbnail displays the character position identifier of the virtual character; the fourth display module includes: a second display submodule, used to display the execution prediction information in the running sub-screen and in the third sub-area of the second interface area.
[0011] As an optional solution, the second display submodule includes: a first display subunit, used to display the execution prediction information in the third sub-region and to display a movement direction indicator at the associated position of the character position indicator, wherein the movement direction indicator is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit, and the movement command is used to instruct the virtual character to move.
[0012] As an optional embodiment, the device includes: a second display subunit, configured to, during the process of displaying the execution prediction information in the above-mentioned running sub-screen and the third sub-area of the above-mentioned second interface area, when the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, highlight an operation trajectory identifier associated with the target candidate operation at the associated position of the target role identifier, wherein the operation trajectory identifier is used to provide a pointing reference for the control command initiated by the simulated object in the above-mentioned second time unit, the target candidate operation is a candidate operation with the same pointing object, and the target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the above-mentioned second event unit.
[0013] As an optional solution, the second display unit includes at least one of the following: a fifth display module, configured to display execution prediction information corresponding to the pointing operation performed by the virtual character during the second time unit, wherein the execution prediction information corresponding to the pointing operation is used to provide a pointing reference for the control command initiated by the simulated object during the second time unit, and the pointing operation is used to determine the pointing object of the control command; a sixth display module, configured to display execution prediction information corresponding to at least two candidate operations performed by the virtual character during the second time unit, wherein the execution prediction information corresponding to the at least two candidate operations is used to provide a selection reference for the at least two control commands initiated by the simulated object during the second time unit, and the control commands in the at least two control commands correspond one-to-one with the candidate operations in the at least two candidate operations; a seventh display module, configured to... The system includes: an eighth display module for displaying execution prediction information corresponding to a movement operation performed by the virtual character within the second time unit, wherein the execution prediction information corresponding to the movement operation is used to provide a direction reference for a movement command initiated by the simulated object within the second time unit; a ninth display module for displaying execution prediction information corresponding to a configuration operation performed by the virtual character within the second time unit, wherein the execution prediction information corresponding to the attack operation is used to provide a direction reference for an attack command initiated by the simulated object within the second time unit; and a ninth display module for displaying execution prediction information corresponding to a configuration operation performed by the virtual character within the second time unit, wherein the execution prediction information corresponding to the configuration operation is used to provide a direction reference for a configuration command initiated by the simulated object within the second time unit, and the configuration operation is used to determine the target item of the configuration command.
[0014] As an optional solution, the second display unit includes: a tenth display module, used to display execution prediction information corresponding to the first virtual character when the screen view of the target virtual game is the character view of the first virtual character; and an eleventh display module, used to switch the screen view of the target virtual game to the character view of the second virtual character in response to a screen view switching command of the target virtual game, and display the execution prediction information corresponding to the second virtual character.
[0015] As an optional embodiment, the above-mentioned device further includes at least one of the following: a third display unit, configured to display basic game information of the at least one simulated object during the display of the running screen of the target virtual game corresponding to the first time unit, wherein the basic game information is the basic information of each simulated object among the at least one simulated object; a fourth display unit, configured to display real-time game information of the target virtual game corresponding to the first time unit during the display of the running screen of the target virtual game corresponding to the first time unit, wherein the real-time game information is the real-time information generated by the target virtual game during the running of the first time unit; a fifth display unit, configured to display historical game information of the target virtual game corresponding to the first time unit during the display of the running screen of the target virtual game corresponding to the first time unit, wherein the historical game information is the historical information generated by the target virtual game before the running of the first time unit; and a sixth display unit, configured to display prediction information of the target virtual game corresponding to the first time unit during the display of the running screen of the target virtual game corresponding to the first time unit, wherein the prediction information is prediction information of the game results of the at least one simulated object participating in the target virtual game.
[0016] As an optional embodiment, the sixth display unit includes: a first acquisition module, configured to acquire a game screen of the target virtual game during its operation, wherein the game screen includes the running screen; a second acquisition module, configured to acquire partial game state information and overall game state information using the game screen, wherein the partial game state information represents the game state of each virtual character participating in the target virtual game, and the overall game state information represents the game state of the target virtual game within the first time unit; and a first input module, configured to input the partial game state information and the overall game state information into the display unit. A game prediction model is used to obtain a first identification result and a second identification result, wherein the first identification result is used to represent the contribution of each virtual character participating in the target virtual game to the game result, and the second identification result is used to represent the contribution of the game state of the target virtual game in the first time unit to the game result; a fitting module is used to fit the first identification result and the second identification result to obtain an evaluation function value, wherein the evaluation function value is used to evaluate the game progress of at least one simulated object in the target virtual game from the perspectives of overall and local performance; a twelfth display module is used to obtain and display the game prediction information based on the evaluation function value.
[0017] As an optional embodiment, the twelfth display module includes: a determining submodule, configured to determine the predicted remaining time of each of the at least two opposing factions participating in the target virtual game using the evaluation function value, when the target virtual game is a virtual game involving simulated objects from at least two opposing factions; an obtaining submodule, configured to obtain the predicted win rate of each of the at least two opposing factions in the target virtual game based on the predicted remaining time, wherein the predicted win rate is inversely proportional to the predicted remaining time; and a third display submodule, configured to display the predicted win rate as the game prediction information.
[0018] As an optional solution, the acquisition unit includes: a second input module, used to input the running screen into the first network structure of the image recognition model to obtain the target image features corresponding to the running screen, wherein the game reference data includes the target image features, the image recognition model is a neural network model trained using target sample data for image recognition, and the first network structure is used to extract image features; the second display unit includes: a third input module, used to input the target image features into the second network structure of the image recognition model to obtain the target recognition result, wherein the execution prediction information includes the target recognition result, and the second network structure is used to output the classification result corresponding to the image features extracted by the first network structure.
[0019] As an optional solution, the second input module includes: a recognition submodule, used to perform image recognition on the running screen using the convolutional layer in the first network structure to obtain at least two screen features corresponding to the running screen; and a concatenation submodule, used to concatenate the features of the at least two screen features using the fully connected layer in the first network structure to obtain the target image features.
[0020] As an optional approach, the aforementioned concatenated submodule includes: a mapping subunit, used to map the aforementioned target image features to the attention mechanism layer in the aforementioned second network structure to obtain a target mapping result; and an input subunit, used to input the aforementioned target mapping result into the output layer in the aforementioned second network structure to obtain the aforementioned target recognition result.
[0021] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information display method described above.
[0022] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-described information display method through the computer program.
[0023] In this embodiment, a running screen of a target virtual game is displayed corresponding to a first time unit. The target virtual game is a virtual game in which at least one simulated object participates. The simulated object is an AI-driven virtual object used to simulate controlling a virtual character in the target virtual game. Game reference data corresponding to the running screen is obtained, where the game reference data is the game data fed back by the virtual character when participating in the target virtual game in the first time unit. Based on the game reference data, execution prediction information corresponding to the candidate operation to be performed by the virtual character in a second time unit is displayed. The execution prediction information is used to predict the simulated object's performance in the first time unit. The control commands initiated by the second time unit provide auxiliary references related to the aforementioned game reference data. The aforementioned control commands are the commands initiated by the simulated object when it controls the virtual character to perform the aforementioned candidate operations. The second time unit, following the first time unit, obtains the game reference data of the current time unit by detecting the running screen of the target virtual game during its operation. Then, it displays the decision-making process of calculating and executing prediction information based on the game reference data. This achieves the goal of intuitively displaying the decision-making process of artificial intelligence participating in the virtual game, thereby improving the technical effect of information display comprehensiveness and solving the technical problem of insufficient information display. Attached Figure Description
[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0025] Figure 1 This is a schematic diagram of an application environment for an optional information display method according to an embodiment of this application;
[0026] Figure 2 This is a schematic diagram of the flow of an optional information display method according to an embodiment of this application;
[0027] Figure 3 This is a schematic diagram of an optional information display method according to an embodiment of this application;
[0028] Figure 4 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0029] Figure 5 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0030] Figure 6 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0031] Figure 7 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0032] Figure 8 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0033] Figure 9 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0034] Figure 10 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0035] Figure 11 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0036] Figure 12 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0037] Figure 13 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0038] Figure 14 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0039] Figure 15 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0040] Figure 16 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0041] Figure 17 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0042] Figure 18 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0043] Figure 19 This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0044] Figure 20This is a schematic diagram of another optional information display method according to an embodiment of this application;
[0045] Figure 21 This is a schematic diagram of an optional information display device according to an embodiment of this application;
[0046] Figure 22 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application. Detailed Implementation
[0047] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0048] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0049] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.
[0050] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.
[0051] Computer vision (CV) is a science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing, acquiring, and measuring targets, and then performing image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.
[0052] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instructional learning.
[0053] With the research and advancement of artificial intelligence (AI) technology, AI is being studied and applied in various fields, such as smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, robots, smart healthcare, and smart customer service. It is believed that with the development of technology, AI will be applied in more fields and play an increasingly important role.
[0054] The solutions provided in this application involve artificial intelligence technologies such as computer vision and machine learning, which are specifically illustrated through the following embodiments:
[0055] According to one aspect of the embodiments of this application, an information display method is provided. Optionally, as an alternative implementation, the above-described information display method may be applied to, but is not limited to, [examples of other methods]. Figure 1 The environment shown may include, but is not limited to, user equipment 102 and server 112. User equipment 102 may include, but is not limited to, a display 108, a processor 106 and a memory 1004. Server 112 includes a database 114 and a processing engine 116.
[0056] The specific process can be summarized in the following steps:
[0057] Step S102, user device 102 acquires the running screen 1002 of the target virtual game in the first time unit;
[0058] Steps S104-S106: Send the screen data corresponding to the running screen 1002 to the server 112 via network 110;
[0059] In steps S108-S1110, server 112 obtains the game reference data corresponding to the running screen 1002 from database 114; furthermore, server 112 obtains the execution prediction information corresponding to the candidate operation to be executed by the virtual character in the second time unit based on the game reference data through processing engine 116.
[0060] In steps S112-S114, the execution prediction information is sent to the user equipment 102 via the network 110. The user equipment 102 displays the execution prediction information on the display 108 via the processor 106 and stores the execution prediction information in the memory 104.
[0061] remove Figure 1 Beyond the examples shown, the above steps can be completed with server assistance, i.e., the server can perform steps such as acquiring game reference data and acquiring prediction information, thereby reducing the processing load on the server. The user equipment 102 includes, but is not limited to, handheld devices (such as mobile phones), laptops, desktop computers, in-vehicle devices, etc., and this application does not limit the specific implementation of the user equipment 102.
[0062] Alternatively, as an alternative implementation method, such as Figure 2 As shown, the information display methods include:
[0063] S202, Display the running screen of the target virtual game in the first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is a virtual object driven by artificial intelligence and used to simulate the control of virtual characters in the target virtual game;
[0064] S204, Obtain the game reference data corresponding to the running screen, wherein the game reference data is the game data fed back by the virtual character when the unit participates in the target virtual game in the first time;
[0065] S206, based on game reference data, display execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit. The execution prediction information is used to provide auxiliary reference related to the game reference data for the control command initiated by the simulated object in the second time unit. The control command is the command initiated by the simulated object when controlling the virtual character to perform the candidate operation. The second time unit is after the first time unit.
[0066] Optionally, in this embodiment, the above information display method can be applied, but is not limited to, in virtual game scenarios involving artificial intelligence (AI), such as virtual games where AI battles AI (target virtual game) or virtual games where AI battles real people (target virtual game). Taking a virtual game where AI battles real people as an example, in the process of human-computer battle, in addition to displaying the AI's decision data during the battle, some key data affecting the decision can also be displayed in a clear and easy-to-understand way, such as the operation process and rewards of the AI's neural network, which can better help users participating in the battle or watching the battle to fully learn the AI's decision-making methods.
[0067] Furthermore, taking a virtual game of AI versus AI as an example, suppose the virtual game is divided into two opposing camps. Each camp's AI will autonomously execute game tasks using technologies such as computer vision and machine learning to strive for ultimate victory. Before issuing an operation command, the AI needs to use computer vision to collect information such as the game state in the virtual game and use machine learning to decide which operation command to execute. The decision-making process information is then presented in an easy-to-understand way on the viewing interface, combined with the game battle screen, to help viewers fully understand the AI's decision-making method, increasing the watchability of AI battles and making the AI explainable.
[0068] Optionally, in this embodiment, the time unit can be understood as, but is not limited to, a time period within a preset range. The target virtual game may include, but is not limited to, at least one frame of running screen within this time period. Further assuming that the target virtual game includes one frame of running screen within one time unit, the running screen corresponding to the first time unit can be understood as, but is not limited to, the current frame of running screen of the target virtual game, and the running screen corresponding to the second time unit can be understood as, but is not limited to, the next frame of running screen of the target virtual game.
[0069] Optionally, in this embodiment, the running screen can be understood as, but is not limited to, the game screen in the virtual scene of the target virtual game; in addition, to improve the efficiency of obtaining game reference data, it is possible, but not limited to, first obtaining all the game screens in the virtual scene of the target virtual game, then filtering out a portion of the game screens associated with the virtual character controlled by the simulated object from all the game screens, and determining this portion of the game screens as the running screen. In this way, efficient image recognition is performed on the filtered game screens, saving the time of obtaining game reference data and improving the efficiency of obtaining game reference data.
[0070] Optionally, in this embodiment, the process of obtaining the game reference data corresponding to the running screen may, but is not limited to, using machine vision such as computer vision to identify, collect and measure the running screen, and further performing graphic processing, which may, but is not limited to, involve technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc.
[0071] Optionally, in this embodiment, the simulated object is an artificial intelligence-driven virtual object used to simulate and control virtual characters to participate in a target virtual game, or it can be understood as a virtual object that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to instruct the virtual characters participating in the target virtual game to perform the most ideal operation.
[0072] Optionally, in this embodiment, the game reference data is the game data fed back by the virtual character when participating in the target virtual game in the first time unit, such as game status data, game resource data, etc., wherein the game status data may be used to represent the individual status of the virtual character participating in the target virtual game, and / or the local status of multiple virtual characters participating in the target virtual game, and / or the overall status of each faction participating in the target virtual game; the game resource data may be used to represent the held status, unheld status, distribution status, etc. of the virtual resources in the target virtual game, such as the status of virtual resources that have been acquired by virtual characters (held status of virtual resources), the status of virtual resources that have not been acquired by virtual characters (unheld status), the distribution of virtual resources in the virtual scene of the target virtual game (distribution status), etc.
[0073] Optionally, in this embodiment, the candidate operation that the virtual character is waiting to execute in the second time unit can be understood, but is not limited to, as an operation that the virtual character has not yet executed in the current time unit (first time unit), but may be executed in the next time unit (second time unit), such as... Figure 3As shown in (a), the virtual character 304 controlled by the simulated object 302 may have three possible operations to execute in the next time unit (second time unit): operation A, operation B, and operation C. Upon obtaining the execution prediction information 306, the simulated object 302 will decide on the operation to execute in the next time unit (second time unit) from among operation A, operation B, and operation C. Figure 3 As shown in (b), the simulated object 302 makes a decision operation A and initiates the control command corresponding to operation A to instruct the virtual character 304 to execute operation A; wherein, the execution prediction information 306 may be, but is not limited to, prediction information obtained based on the game reference data corresponding to the running screen 308-1, the running screen 308-1 may be, but is not limited to, the running screen of the target virtual game corresponding to the first time unit, and the running screen 308-2 may be, but is not limited to, the running screen of the target virtual game corresponding to the second time unit.
[0074] Optionally, in this embodiment, the control instruction is the instruction initiated by the simulated object when it controls the virtual character to perform a candidate operation. The way in which the virtual character participates in the target virtual game may include, but is not limited to, the virtual character performing the target operation. The virtual character performing the target operation may be, but is not limited to, responding to the control instruction initiated by the simulated object. In other words, the way in which the simulated object participates in the target virtual game may be, but is not limited to, the simulated object initiating a control instruction to control the virtual character to perform the target operation.
[0075] Optionally, in this embodiment, during the display of the running screen of the target virtual game corresponding to the first time unit, more diverse game information may be displayed, such as basic information of at least one simulated object participating in the target virtual game (e.g., the name of the simulated object, the historical battle record of the simulated object, etc.), real-time progress information of the target virtual game (e.g., the virtual resources currently held by the virtual character, the items currently configured by the virtual character, the current battle information of the virtual character, etc.), and progress prediction information of the target virtual game (e.g., prediction information of the battle results of the target virtual game, prediction information of the progress development of the target virtual game, etc.).
[0076] Optionally, in this embodiment, the display method of the execution prediction information may be related to, but is not limited to, candidate operations, virtual characters, etc. For example, when the candidate operation is a movement operation, the execution prediction information may be displayed according to the selection priority of each direction, such as... Figure 4 As shown, the execution prediction information 402 includes various directions in which the movement operation can be executed, and the selection priority of each direction can be reflected in the form of length, such as the length being positively related to the selection priority, that is, the longer the direction, the higher the selection priority of that direction, or it can be understood that the longest direction is the direction in which the movement operation is most likely to move.
[0077] For example, when the candidate operation is an attack operation, the execution prediction information can be displayed, but is not limited to, according to the selection priority of each target object. Further examples include... Figure 5 As shown, the execution prediction information 502 includes various target objects that can be selected for attack operations, and the selection priority of each target object can be represented by, but is not limited to, shadows. For example, the display area of the shadow is positively related to the selection priority, that is, the larger the display area of the shadow, the higher the selection priority of the target object. Specifically, if the shadow display area of target object B is greater than that of target object A and target object C, then target object B has the highest selection priority, or it can be understood that the probability of executing the attack operation on target object B is the greatest.
[0078] It should be noted that during the operation of the target virtual game, the game reference data for the current time unit is obtained by detecting the running screen. The decision-making process of calculating and executing prediction information based on the game reference data is then displayed, thereby intuitively displaying the decision-making process of artificial intelligence participating in the virtual game and improving the comprehensiveness of information display.
[0079] To further illustrate, alternatively, for example... Figure 6 As shown, the target virtual game displays screen 604 corresponding to the first time unit, such as... Figure 6 As shown in (a) in the figure, the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is an artificial intelligence-driven virtual object used to simulate the control of virtual character 602 in the target virtual game;
[0080] For example Figure 6 As shown in (b), the game reference data 606 corresponding to the running screen 604 is obtained. The game reference data 606 is the game data fed back by the virtual character 602 when participating in the target virtual game in the first time unit. Based on the game reference data 606, the execution prediction information 608 corresponding to the candidate operation (such as operation A, operation B, and operation C) to be executed by the virtual character 602 in the second time unit is displayed. The execution prediction information 608 is used to provide auxiliary reference related to the game reference data 606 for the control command initiated by the simulated object in the second time unit. The control command is the command initiated by the simulated object when controlling the virtual character 602 to execute the candidate operation. The second time unit is after the first time unit.
[0081] Furthermore, the simulated object makes decisions based on the execution prediction information 608, such as initiating the control command corresponding to operation A in the second time unit to control the virtual character 602 to execute operation A (attack the enemy character), specifically as follows: Figure 6As shown in (c) in the figure; and, but not limited to, the latest game reference data can be obtained by reusing the running screen of the target virtual game corresponding to the second time unit, and the execution prediction information of the next time unit can be obtained based on the latest game reference data. The principle is similar and will not be elaborated here.
[0082] The embodiments provided in this application display the running screen of a target virtual game in the first time unit. The target virtual game is a virtual game in which at least one simulated object participates. The simulated object is an AI-driven virtual object used to simulate controlling a virtual character in the target virtual game. Match reference data corresponding to the running screen is obtained, where the match reference data is the match data fed back by the virtual character when participating in the target virtual game in the first time unit. Based on the match reference data, execution prediction information corresponding to candidate operations to be performed by the virtual character in the second time unit is displayed. The execution prediction information is used to provide auxiliary reference related to the match reference data for the control commands initiated by the simulated object in the second time unit. The control commands are the commands initiated by the simulated object when controlling the virtual character to perform candidate operations. The second time unit is after the first time unit. During the operation of the target virtual game, the running screen of the current time unit is detected to obtain the match reference data for the current time unit. The decision-making process of calculating execution prediction information from the match reference data is then displayed, thereby achieving the purpose of intuitively displaying the decision-making process of AI participating in the virtual game, and thus realizing the technical effect of improving the comprehensiveness of information display.
[0083] As an optional approach, the execution prediction information corresponding to the candidate operation that the virtual character is scheduled to perform in the second time unit is displayed, including:
[0084] Displays first probability distribution information of a virtual character performing at least two candidate operations in a second time unit, wherein the first probability distribution information is used to predict the probability of the virtual character performing each of the at least two candidate operations in the second time unit.
[0085] Optionally, in this embodiment, the first probability distribution information may be displayed in the prediction information list, but is not limited to the prediction information list, which may be configured with probability distribution information of various candidate operations associated with each virtual character.
[0086] Optionally, in this embodiment, in order to improve display efficiency, if the number of candidate operations to be displayed is greater than the first number, the candidate operations with higher probabilities and the first number of candidate operations are displayed first. For example, if the probability of candidate operation 1 is 70%, the probability of candidate operation 2 is 50%, and the probability of candidate operation 3 is 20%, then candidate operation 1 and candidate operation 2 are displayed first.
[0087] It should be noted that the first probability distribution information of the virtual character is displayed while performing at least two candidate operations in the second time unit. The first probability distribution information is used to predict the probability of the virtual character performing each of the at least two candidate operations in the second time unit.
[0088] To further illustrate, alternatively, for example... Figure 7 As shown, the program displays the running screen 702 of the target virtual game in the first time unit and the prediction information list 704. The prediction information list 704 displays the first probability distribution information of virtual characters (such as virtual character A, virtual character B, and virtual character C) waiting to perform at least two candidate operations in the second time unit. The first probability distribution information is used to predict the probability of each candidate operation among the at least two candidate operations performed by the virtual character in the second time unit. Specifically, it displays the probability of movement operations (such as movement operations in the first direction, movement operations in the second direction, etc.) associated with virtual characters A, B, and C. Taking virtual character A as an example, the probability of movement operations in the first direction is "44.7%", the probability of movement operations in the second direction is "16.5%", etc.
[0089] Furthermore, this embodiment can also be based on Figure 7 The scene shown, for example Figure 8 As shown, the probability of skill release operations (such as the release of the first skill, the release of the second skill, etc.) associated with virtual characters A, B, and C is displayed. Taking virtual character A as an example, the probability of releasing skill A1 is "54.7%", the probability of releasing skill A2 is "16.5%", the probability of releasing skill A3 is "24.7%", and the probability of releasing skill A4 is "12.57%", etc.
[0090] Furthermore, this embodiment can also display the probability of item configuration operations associated with virtual characters (such as the configuration operation of item 1, the configuration operation of item 2, etc.), wherein the item configuration operation may include, but is not limited to, replacing, disassembling, installing, purchasing, selling, storing in the first virtual container, taking out from the second virtual container, etc.
[0091] The embodiments provided in this application display a first probability distribution information of a virtual character performing at least two candidate operations in a second time unit. The first probability distribution information is used to predict the probability of each candidate operation among the at least two candidate operations performed by the virtual character in the second time unit, thereby achieving the purpose of intuitively displaying information using probability distribution and thus realizing the technical effect of improving the intuitiveness of information display.
[0092] As an optional approach, the execution prediction information corresponding to the candidate operation that the virtual character is scheduled to perform in the second time unit is displayed, including:
[0093] Displays a second probability distribution information of a virtual character performing candidate operations on at least two pointed objects, wherein the second probability distribution information is used to predict the probability that the virtual character will perform candidate operations on each of the at least two pointed objects in a second time unit.
[0094] Optionally, in this embodiment, the second probability distribution information may be displayed in the prediction information list, but is not limited to the prediction information list, which may be configured with the probability distribution information of each target object associated with each virtual character.
[0095] Optionally, in this embodiment, in order to improve display efficiency, if the number of candidate operations to be displayed is greater than the second number, the second number of pointing objects with higher probability are displayed first. For example, if the probability of pointing object 1 is 70%, the probability of pointing object 2 is 50%, and the probability of pointing object 3 is 20%, then pointing object 1 and pointing object 2 are displayed first.
[0096] It should be noted that the second probability distribution information for the virtual character to perform candidate operations on at least two pointed objects is displayed. The second probability distribution information is used to predict the probability that the virtual character will perform candidate operations on each of the at least two pointed objects in the second time unit.
[0097] To further illustrate, optionally based on Figure 7 The scenario shown continues, for example... Figure 9 As shown, the target virtual game displays the running screen 702 and the prediction information list 704 corresponding to the first time unit. The prediction information list 704 displays the second probability distribution information of virtual characters (such as virtual character A, virtual character B, and virtual character C) performing candidate operations on at least two target objects. The second probability distribution information is used to predict the probability of virtual characters performing candidate operations on each of the at least two target objects in the second time unit. Specifically, it displays the probability of target objects associated with virtual characters A, B, and C, such as target object B (virtual character B) associated with virtual character A, target object C (virtual character C) associated with virtual character A, target object A (virtual character A) associated with virtual character B, target object C (virtual character C) associated with virtual character B, and target object A (virtual character A) and target object B (virtual character B) associated with virtual character C. Taking virtual character A as an example, the execution probability of the attack operation on target object B (virtual character B) is "54.7%" and the execution probability of the attack operation on target object C (virtual character C) is "16.5%".
[0098] The embodiments provided in this application display a second probability distribution information of a virtual character performing candidate operations on at least two pointed objects. The second probability distribution information is used to predict the probability that the virtual character will perform candidate operations on each of the at least two pointed objects in a second time unit, thereby achieving the purpose of intuitively displaying information using probability distribution and thus realizing the technical effect of improving the intuitiveness of information display.
[0099] As an optional solution, the running screen of the target virtual game is displayed in the first time unit, including: displaying the running screen in the first interface area of the spectator interface;
[0100] As an optional approach, displaying execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit includes: displaying the execution prediction information in the second interface area of the spectator interface.
[0101] It should be noted that the running screen is displayed in the first area of the spectator interface; the execution prediction information is displayed in the second area of the spectator interface.
[0102] To further illustrate, alternatively, for example... Figure 10 As shown, the game screen is displayed in the first interface area (the central area of the spectator interface 1002), and the execution prediction information (such as the target probability distribution of faction A, the movement probability distribution of faction A, the target probability distribution of faction B, the movement probability distribution of faction B, etc.) is displayed in the second interface area of the spectator interface 1002. In addition, the spectator interface 1002 also displays basic game battle data, win rate prediction, the economic composition of faction A, the damage share of faction A, the economic composition of faction B, the damage share of faction B, the minimap, and other content.
[0103] The embodiments provided in this application display the running screen in the first interface area of the spectator interface and the execution prediction information in the second interface area of the spectator interface, thereby achieving the purpose of displaying more comprehensive information in the spectator interface and realizing the technical effect of improving the comprehensiveness of information display.
[0104] As an optional solution, the running screen is displayed in the first interface area of the spectator interface, including: displaying the main running screen of the target virtual game in the first sub-area of the first interface area corresponding to the first time unit, and displaying the sub-running screen of the target virtual game in the second sub-area of the spectator interface corresponding to the first time unit. The main running screen is the real-time screen of the virtual scene of the target virtual game, and the sub-running screen is a thumbnail of the virtual scene, with the character position marker of the virtual character displayed on the thumbnail.
[0105] As an optional solution, the execution prediction information is displayed in the second interface area of the spectator interface, including: displaying the execution prediction information in the running sub-screen and in the third sub-area of the second interface area.
[0106] Optionally, in this embodiment, the running screen and the execution prediction information may be displayed in the same or different interface areas, or in other words, the running screen is displayed in the first interface area of the spectator interface and the execution prediction information is displayed in the second interface area of the spectator interface. However, it is not limited to the running screen and the execution prediction information being displayed in different interface areas; they may also be displayed in the same interface area.
[0107] Optionally, in this embodiment, during AI battles, the real-time position of each virtual character can be displayed on the minimap, and arrows can be used on each virtual character's portrait to indicate the direction with the highest probability in the virtual character's movement probability distribution. Furthermore, it can also support displaying the two highest probability directions simultaneously, helping spectators quickly understand the virtual characters' decision-making information on the minimap (running sub-screen) and better comprehend the AI's decision-making process. Moreover, when two or more virtual characters on one side have the same enemy virtual character as their primary target, this event can be classified as a concentrated attack and displayed on the minimap, allowing users to intuitively understand the AI's intentions.
[0108] It should be noted that the target virtual game's main running screen corresponding to the first time unit is displayed in the first sub-area of the first interface area, and the target virtual game's sub-running screen corresponding to the first time unit is displayed in the second sub-area of the spectator interface. The main running screen is the real-time screen within the virtual scene of the target virtual game, and the sub-running screen is a thumbnail of the virtual scene, displaying the character's position indicator on the thumbnail. Execution prediction information is displayed in the sub-running screen and the third sub-area of the second interface area.
[0109] To further illustrate, alternatively, for example... Figure 11 As shown, the main running screen 1104 of the target virtual game in the first time unit is displayed in the spectator interface 1102, and the sub-running screen 1106 of the target virtual game in the first time unit is also displayed in the spectator interface 1102. The main running screen 1104 is a real-time screen within the virtual scene of the target virtual game, and the sub-running screen 1106 is a thumbnail of the virtual scene, on which the character position marker of the virtual character is displayed. In addition, but not limited to, execution prediction information can also be displayed in the sub-running screen 1106 and the spectator interface 1102.
[0110] Through the embodiments provided in this application, the main running screen of the target virtual game corresponding to the first time unit is displayed in the first sub-area of the first interface area, and the sub-running screen of the target virtual game corresponding to the first time unit is displayed in the second sub-area of the spectator interface. The main running screen is a real-time screen within the virtual scene of the target virtual game, and the sub-running screen is a thumbnail of the virtual scene, displaying the character position identifier of the virtual character on the thumbnail. Execution prediction information is displayed in the sub-running screen and the third sub-area of the second interface area, thereby achieving the purpose of efficiently displaying information in the spectator interface and realizing the technical effect of improving the display efficiency of information.
[0111] As an optional solution, execution prediction information is displayed in the running sub-screen and in a third sub-area within the second interface area, including:
[0112] The execution prediction information is displayed in the third sub-region, and the movement direction indicator is displayed at the associated position of the character position indicator. The movement direction indicator is used to provide a directional reference for the movement command initiated by the simulated object in the second time unit. The movement command is used to instruct the virtual character to move.
[0113] Optionally, in this embodiment, displaying the movement direction indicator at the associated location of the character position indicator can be understood, but is not limited to, displaying the execution prediction information in combination with the character position indicator in the second sub-area where the running sub-screen is located.
[0114] To further illustrate, optionally based on Figure 11 As shown, continue for example Figure 12 As shown, the execution prediction information is displayed on the running sub-screen 1106. Specifically, the movement direction indicator 1204 is displayed at the associated position of the character position indicator 1202. The movement direction indicator 1204 is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit. The movement command is used to instruct the virtual character to move.
[0115] Through the embodiments provided in this application, execution prediction information is displayed in the third sub-region, and a movement direction indicator is displayed at the associated position of the character position indicator. The movement direction indicator is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit. The movement command is used to instruct the virtual character to move, thereby achieving the purpose of conveniently and intuitively displaying execution prediction information using the information of the running sub-screen, thus realizing the technical effect of improving the intuitiveness of information display.
[0116] As an optional approach, the method for displaying execution prediction information in the running sub-screen and the third sub-area within the second interface area includes:
[0117] When the number of target candidate operations indicated by the prediction information reaches a preset threshold, the operation trajectory identifier associated with the target candidate operation is highlighted at the associated position of the target role position identifier. The operation trajectory identifier is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The target candidate operation is a candidate operation that points to the same object. The target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the second event unit.
[0118] Optionally, in this embodiment, in order to improve the display efficiency of the execution prediction information, when the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, the operation trajectory identifier associated with the target candidate operation is highlighted at the associated position of the target role location identifier. For example, when the execution prediction information indicates that more than a preset threshold number of virtual roles will perform attack operations on the same virtual role, the operation trajectory identifier associated with the attack operation will be highlighted at the associated position of the corresponding role location identifier.
[0119] To further illustrate, optionally based on Figure 11 As shown, continue for example Figure 13 As shown, when the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, the execution prediction information that meets specific conditions is highlighted on the running sub-screen 1106. Specifically, the operation trajectory identifier 1302 associated with the target candidate operation is highlighted at the associated position of the target role position identifier. The operation trajectory identifier 1302 is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The target candidate operation is a candidate operation that points to the same object, and the target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the second event unit.
[0120] Through the embodiments provided in this application, when the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, the operation trajectory identifier associated with the target candidate operation is highlighted at the associated position of the target role position identifier. The operation trajectory identifier is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The target candidate operation is a candidate operation pointing to the same object. The target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the second event unit. This achieves the purpose of highlighting the execution prediction information that meets specific conditions, thereby realizing the technical effect of improving the display efficiency of the execution prediction information.
[0121] As an optional approach, displaying execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit includes at least one of the following:
[0122] S1, display the execution prediction information corresponding to the pointing operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the pointing operation is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The pointing operation is used to determine the target of the control command.
[0123] S2, display the execution prediction information corresponding to at least two candidate operations performed by the virtual character in the second time unit, wherein the execution prediction information corresponding to at least two candidate operations is used to provide a selection reference for at least two control instructions initiated by the simulated object in the second time unit, and the control instructions in the at least two control instructions correspond one-to-one with the candidate operations in the at least two candidate operations.
[0124] S3 displays the execution prediction information corresponding to the movement operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the movement operation is used to provide directional reference for the movement command initiated by the simulated object in the second time unit.
[0125] S4 displays the execution prediction information corresponding to the attack operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the attack operation is used to provide a reference for the attack command initiated by the simulated object in the second time unit.
[0126] S5 displays the execution prediction information corresponding to the configuration operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the configuration operation is used to provide a reference for the configuration command initiated by the simulated object in the second time unit. The configuration operation is used to determine the target item of the configuration command.
[0127] Optionally, in this embodiment, during AI battles, the list of targets to be attacked and their corresponding attack probabilities can be calculated using the battle data of the current frame of the game, and the AI will eventually attack the target with the highest probability. In addition, to make the data intuitive and easy to understand, only the top two targets with the highest probabilities in the target list can be displayed, and the target list records at least two target objects.
[0128] Optionally, in this embodiment, during AI battles, the candidate operations to be executed and their corresponding execution probabilities can be calculated using the battle data of the current frame of the game. Ultimately, the AI will execute the candidate operation with the highest probability. In addition, to make the data intuitive and easy to understand, only the top two most probable candidate operations can be displayed, and the candidate operations to be executed include at least two candidate operations.
[0129] Optionally, in this embodiment, during AI battles, the direction to be moved and its corresponding probability can be calculated using the battle data of the current frame of the game, and the AI will eventually move in the direction with the highest probability. In addition, to make the data intuitive and easy to understand, only the top two directions with the highest probability in the direction list can be displayed, and the direction to be moved includes at least two movement directions.
[0130] Optionally, in this embodiment, during AI battles, the virtual items to be configured and their corresponding probabilities can be calculated using the battle data of the current frame of the game. Ultimately, the AI will configure the virtual item with the highest probability. In addition, to make the data intuitive and easy to understand, only the two virtual items with the highest probabilities can be displayed, including at least two pointing items.
[0131] As an optional approach, the execution prediction information corresponding to the candidate operation that the virtual character is scheduled to perform in the second time unit is displayed, including:
[0132] S1, when the screen view of the target virtual game is the view of the first virtual character, display the execution prediction information corresponding to the first virtual character;
[0133] S2, in response to the command to switch the screen view of the target virtual game, switches the screen view of the target virtual game to the character view of the second virtual character, and displays the execution prediction information corresponding to the second virtual character.
[0134] Optionally, in this embodiment, to improve the display accuracy of the execution prediction information, spectators can switch between the perspectives of different virtual characters to adjust the screen view of the target virtual game, and can also adjust the display of the execution prediction information corresponding to different virtual characters accordingly.
[0135] As an optional approach, in the process of displaying the running screen of the target virtual game in the first time unit, the method further includes at least one of the following:
[0136] S1, Display the basic game information of at least one simulated object, wherein the basic game information is the basic information of each simulated object in at least one simulated object;
[0137] S2 displays the real-time information of the target virtual game in the first time unit, where the real-time information is the real-time information generated by the target virtual game during the first time unit.
[0138] S3 displays the game history information of the target virtual game in the first time unit, where the game history information is the historical information generated before the target virtual game runs in the first time unit;
[0139] S4, display the game prediction information of the target virtual game in the first time unit, wherein the game prediction information is the prediction information of the game result of at least one simulated object participating in the target virtual game.
[0140] It should be noted that the following functions are displayed: Basic game information for at least one simulated object, where the basic game information refers to the basic information of each simulated object among the at least one simulated object; Real-time game information for the target virtual game corresponding to the first time unit, where the real-time game information is the real-time information generated by the target virtual game during the first time unit; Historical game information for the target virtual game corresponding to the first time unit, where the historical game information is the historical information generated before the target virtual game started running in the first time unit; and Predictive game information for the target virtual game corresponding to the first time unit, where the Predictive game information is the predicted game result of at least one simulated object participating in the target virtual game.
[0141] To further illustrate, the display of the (event) spectator interface can be used as an example. Optionally, the spectator interface consists of a game screen and a data module. After the game starts, spectators can switch the perspective of different virtual characters by clicking on the corresponding icons of the virtual characters.
[0142] Optionally, in this embodiment, the data module may refer to Figure 10 The data shown refers to the data displayed on the spectator interface, including basic game data, win rate prediction, economic composition and damage percentage, target probability distribution, movement probability distribution, minimap, etc.
[0143] Optionally, in this embodiment, the basic data may refer to, but is not limited to, the data presented during real-person battles. During AI battles, corresponding basic data is also extracted and presented, including game data, team data, and basic data of virtual characters, etc.
[0144] Optionally, in this embodiment, the game data may include, but is not limited to, battle screen (real-time game information), battle duration (game history information), and may include, but is not limited to, displaying the battle status of multiple AIs in the target virtual game in real time through the battle screen;
[0145] Optionally, in this embodiment, team data may include, but is not limited to, the team name to which the AI model belongs (basic game information), KDA (game history information), number of Tyrants defeated (game history information), economic composition (game history information), and percentage of damage to virtual characters (game history information). The economic composition and percentage of damage to virtual characters are used to help spectators understand the operational strategies of both AI models during the game, thereby reflecting the different focuses of participating users when training AI. The economic composition may be used to display the total economy of the faction (excluding naturally growing economy).
[0146] Based on this, it is also possible to... Figure 14 As shown, the total economy is divided into multiple sources: defeating virtual characters, defeating NPC characters (such as virtual minions, virtual monsters, etc.), and NPC buildings (such as virtual defense towers, virtual crystal buildings, etc.). The proportion of each source to the total economy is displayed on the battle interface.
[0147] In addition, it is also possible to Figure 14 On the basis of, such as Figure 15 As shown, the percentage of damage dealt by virtual characters is displayed, such as the total damage dealt to enemy virtual characters and the percentage of damage dealt by each virtual character to enemy virtual characters.
[0148] Optionally, in this embodiment, the data module may also include, but is not limited to, basic virtual character data, such as virtual character avatar, health points, summoner skills and status, and further based on... Figure 15 The scenario shown continues, for example... Figure 16 As shown, the basic data of the virtual character 1602 is displayed, including the virtual character's avatar, name, KDA, etc. In addition, after clicking on the virtual character's avatar, the game screen can be adjusted to the perspective of that virtual character.
[0149] Optionally, in this embodiment, the data module may also include, but is not limited to, win rate prediction (game prediction information), such as predicting and displaying win rates based on real-time game data of both AI players, and further based on... Figure 14 The scenario shown continues, for example... Figure 17 As shown, the win rate is predicted based on the real-time battle data of both AIs, and the result information of the win rate prediction is displayed, such as AI 1's win rate being 69% and AI 2's win rate being 31%.
[0150] The embodiments provided in this application display basic game information of at least one simulated object, wherein the basic game information is the basic information of each simulated object among the at least one simulated object; display real-time game information of the target virtual game corresponding to the first time unit, wherein the real-time game information is the real-time information generated by the target virtual game during the first time unit; display historical game information of the target virtual game corresponding to the first time unit, wherein the historical game information is the historical information generated by the target virtual game before the first time unit started; and display game prediction information of the target virtual game corresponding to the first time unit, wherein the game prediction information is the prediction information of the game results of at least one simulated object participating in the target virtual game, thereby achieving the objective and realizing the technical effect.
[0151] As an optional approach, display the game prediction information for the target virtual game in the first time unit, including:
[0152] S1, acquire the game screen of the target virtual game during operation, wherein the game screen includes the running screen;
[0153] S2, using the game screen to obtain local game state information and overall game state information, wherein the local game state information is used to represent the game state of each virtual character participating in the target virtual game in the target virtual game, and the overall game state information is used to represent the game state of the target virtual game in the first time unit.
[0154] S3, input the local game state information and the overall game state information into the game prediction model to obtain the first identification result and the second identification result. The first identification result is used to represent the contribution of each virtual character participating in the target virtual game to the game result, and the second identification result is used to represent the contribution of the target virtual game's game state to the game result in the first time unit.
[0155] S4, Fit the first identification result and the second identification result to obtain the evaluation function value, wherein the evaluation function value is used to evaluate the game progress of at least one simulated object in the target virtual game from the perspective of the overall and local performance of the object;
[0156] S5 obtains and displays game prediction information based on the evaluation function value.
[0157] Optionally, in this embodiment, a supervised learning model (game prediction model) that takes the current game state (game screen) as input and the evaluation function value as output can be used to process the game screen of the target virtual game during its operation to obtain the evaluation function value used to obtain game prediction information.
[0158] Optionally, in this embodiment, the game prediction model may be, but is not limited to, as follows: Figure 18 As shown, the algorithm is divided into two substructures. First, the individual (Ind) part takes the state of each individual in the current state as input (e.g., individual feature 1, individual feature 2, and individual feature 3 in individual part 1802), processes it using a fully connected layer, and outputs the contribution of each individual to the game situation (e.g., individual contribution 1, individual contribution 2, and individual contribution 3 in contribution set 1806). The global (Glo) part takes the global state in the current state as input (e.g., the global feature in global part 1804), processes it using a fully connected layer, and outputs the contribution of the global state to the game situation (e.g., the global contribution in contribution set 1806). Finally, the outputs of the two substructures are integrated to predict the above evaluation function value 1808.
[0159] As an optional approach, game prediction information is obtained and displayed based on the evaluation function value, including:
[0160] S1, In the case that the target virtual game is a virtual game in which simulated objects from at least two opposing factions participate, the predicted remaining time of each of the at least two opposing factions participating in the target virtual game is determined by using the evaluation function value.
[0161] S2, based on the predicted remaining time, obtain the predicted win rate of each opposing faction in at least two opposing factions against the target virtual game, wherein the predicted win rate is inversely proportional to the predicted remaining time;
[0162] S3 displays the predicted win rate as game prediction information.
[0163] Optionally, in this embodiment, the evaluation function value can be used, but is not limited to, to evaluate the relative advantage between game teams. Assuming the target virtual game is a game between team A and team B, the evaluation function value can be used, but is not limited to, to reflect the advantage of team A relative to team B, or the advantage of team B relative to team A. For details, please refer to the following formulas (1) and (2):
[0164]
[0165] In this context, DE represents the discount assessment value, the absolute value of which is inversely proportional to the remaining time of the game. That is, the greater the advantage, the greater the probability of winning, which will result in a shorter time to end the game. R represents the reward (or can be understood as the game result report, such as 1 for victory and -1 for defeat), t represents the remaining time of the game, and r represents the difference in importance between the future reward and the current reward.
[0166] As an optional approach, obtaining game reference data corresponding to the running screen includes: inputting the running screen into the first network structure of the image recognition model to obtain the target image features corresponding to the running screen, wherein the game reference data includes the target image features, the image recognition model is a neural network model trained using target sample data for recognizing images, and the first network structure is used to extract image features;
[0167] Optionally, in this embodiment, the first network structure may include, but is not limited to, an input layer, a convolutional layer, a pooling layer, and a fully connected layer. The convolutional layer may consist of, but is not limited to, several convolutional units, and the parameters of each convolutional unit are optimized through backpropagation. The purpose of convolution is to extract different features from the input. The first convolutional layer may only extract some low-level features such as edges, lines, and corners. More layers can iteratively extract more complex features from low-level features. The pooling layer may, but is not limited to, follow the convolutional layer and also consists of multiple feature surfaces. Each feature surface corresponds to a feature surface in the previous layer, without changing the number of feature surfaces. The fully connected layer may, but is not limited to, have each node connected to all nodes in the previous layer, used to synthesize the previously extracted features. Due to its fully connected nature, the fully connected layer generally has the most parameters.
[0168] As an optional approach, based on game reference data, the execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit is displayed, including: inputting the target image features into the second network structure in the image recognition model to obtain the target recognition result, wherein the execution prediction information includes the target recognition result, and the second network structure is used to output the classification result corresponding to the image features extracted by the first network structure.
[0169] Optionally, in this embodiment, the second network structure may include, but is not limited to, an output layer. The activation function used in the output layer may include, but is not limited to, the sigmoid function, the tanh function, etc., and the activation function may, but is not limited to, consist of a basic structure of a single neuron composed of linear and nonlinear units.
[0170] As an optional approach, the running screen is input into the first network structure of the image recognition model to obtain the target image features corresponding to the running screen, including:
[0171] S1, using the convolutional layer in the first network structure to perform image recognition on the running screen, and obtain at least two screen features corresponding to the running screen;
[0172] S2, using the fully connected layer in the first network structure, concatenate the features of at least two images to obtain the target image features.
[0173] Optionally, in this embodiment, the network uses convolution to encode image features, vector features, and game state information, and then uses a fully connected layer (FC) to concatenate all feature codes to obtain state codes.
[0174] As an optional approach, the target image features are input into the second network structure of the image recognition model to obtain the target recognition result, including:
[0175] S1, map the target image features to the attention mechanism layer in the second network structure to obtain the target mapping result;
[0176] S2, input the target mapping result into the output layer of the second network structure to obtain the target recognition result.
[0177] It should be noted that the target image features are mapped to the attention mechanism layer in the second network structure to obtain the target mapping result; the target mapping result is input into the output layer in the second network structure to obtain the target recognition result.
[0178] To further illustrate, alternatively, for example... Figure 19 As shown, based on a deep reinforcement learning framework, an actor-critic network is used to model the action control dependencies in a target virtual game. First, the network uses convolutions to encode image features, vector features, and game state information. Then, a fully connected layer (FC) concatenates all feature encodings to obtain state encodings. Next, the state encodings are mapped from LSTM recurrent units to hLSTM (attention mechanism layer). The hLSTM is then input into the FC layer to predict the final action outputs, including movement, attack, skill release, and target selection. Furthermore, to assist the AI in making more accurate choices during gameplay in the target virtual game, a target attention mechanism is introduced into the network structure. This mechanism uses the FC output of the hLSTM as the query and the stack of all unit encodings as the key to calculate target attention, i.e., the AI's attention to each target in the current game state. Visualizing the AI's attention to each target provides a more intuitive understanding of the AI's decisions in the current state.
[0179] As an optional approach, for ease of understanding, this embodiment assumes that the above information display method is applied to a battle scenario in a multiplayer online battle arena (MOBA) game involving AI. The overall process is as follows: Figure 20 As shown:
[0180] Step S2002: The AI model engages in combat within the game environment;
[0181] Step S2004: Extract battle data while playing the game;
[0182] Step S2006: Generate the corresponding battle files;
[0183] Step S2008: Then the front end loads the game screen and renders the corresponding data in the corresponding module;
[0184] Among them, data extraction in real-time AI model battles includes extracting economic and damage data during AI battles, visualizing it, and predicting win rates based on the relevant data; extracting decision data (move and target) during AI battles, structuring it, and presenting it to spectators in a clear and easy-to-understand way.
[0185] Optionally, in this embodiment, win rate prediction can help spectators understand the game screen. By observing the changes in win rate, even spectators who are not familiar with the game can roughly guess the goal of winning. At the same time, the dynamically changing win rate expectation can also increase the dramatic tension of the game.
[0186] Optionally, in this embodiment, in games with scoring mechanisms, it is usually easy to determine which player or team has an advantage from the scores. However, the design of MOBA games is very complex, with many variables changing throughout the game. Therefore, it is difficult to evaluate the real-time game situation in such a vast knowledge domain. Traditionally, related technologies have assessed relative advantages through vague methods such as intuition or game experience, but they cannot provide a unified standard to measure the relative advantages between game teams.
[0187] Optionally, in this embodiment, in a MOBA game, the current state represents the game situation at a specific time slice, including individual states and global states. Individual states include the level, economy, and survival status of team virtual characters, while global states include the status of minion waves and turrets. This information used to represent the current game state can be found in game records, such as replay files.
[0188] Optionally, in this embodiment, the data content is not limited to basic data, target probability distribution, movement probability distribution, and minimap. More dimensions of data can be added based on the game type, and the data is displayed in a visual format, such as line charts or heatmaps. The terminal device is not limited to PCs but can also be mobile devices, large-screen devices, etc. The interaction methods are not limited to mouse and keyboard but can also include gestures, voice control, etc.
[0189] Through the embodiments provided in this application, AI game battles are a competition between reinforcement learning models. Unlike real-person game battles, they focus more on the training ideas and algorithm optimization of AI models, without incorporating human factors such as emotions, feelings, and reactions. This application presents the decision-making process and data of the AI model and displays it to spectators in real time in conjunction with the game footage. It innovatively proposes a unique real-time presentation method for AI battles in MOBA games, making the AI interpretable while effectively enhancing the viewing experience of AI game battles.
[0190] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0191] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0192] According to another aspect of the embodiments of this application, an information display device for implementing the above-described information display method is also provided. For example... Figure 21 As shown, the device includes:
[0193] The first display unit 2102 is used to display the running screen of the target virtual game in the first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is a virtual object driven by artificial intelligence for simulating the control of virtual characters to participate in the target virtual game;
[0194] The acquisition unit 2104 is used to acquire the game reference data corresponding to the running screen. The game reference data is the game data fed back by the virtual character when the unit participates in the target virtual game in the first time.
[0195] The second display unit 2106 is used to display execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit based on the game reference data. The execution prediction information is used to provide auxiliary reference related to the game reference data for the control command initiated by the simulated object in the second time unit. The control command is the command initiated by the simulated object when controlling the virtual character to perform the candidate operation. The second time unit is after the first time unit.
[0196] Optionally, in this embodiment, the aforementioned information display device may be applied, but is not limited to, in virtual game scenarios involving artificial intelligence (AI), such as virtual games where AI battles AI (target virtual game) or virtual games where AI battles real people (target virtual game). Taking a virtual game where AI battles real people as an example, in the process of human-computer interaction, in addition to displaying the AI's decision-making data during the battle, some key data affecting the decision can also be displayed in a clear and easy-to-understand way, such as the operation process and rewards of the AI's neural network, which can better help users participating in the battle or watching the battle to fully learn the AI's decision-making methods.
[0197] Furthermore, taking a virtual game of AI versus AI as an example, suppose the virtual game is divided into two opposing camps. Each camp's AI will autonomously execute game tasks using technologies such as computer vision and machine learning to strive for ultimate victory. Before issuing an operation command, the AI needs to use computer vision to collect information such as the game state in the virtual game and use machine learning to decide which operation command to execute. The decision-making process information is then presented in an easy-to-understand way on the viewing interface, combined with the game battle screen, to help viewers fully understand the AI's decision-making method, increasing the watchability of AI battles and making the AI explainable.
[0198] Optionally, in this embodiment, the time unit can be understood as, but is not limited to, a time period within a preset range. The target virtual game may include, but is not limited to, at least one frame of running screen within this time period. Further assuming that the target virtual game includes one frame of running screen within one time unit, the running screen corresponding to the first time unit can be understood as, but is not limited to, the current frame of running screen of the target virtual game, and the running screen corresponding to the second time unit can be understood as, but is not limited to, the next frame of running screen of the target virtual game.
[0199] Optionally, in this embodiment, the running screen can be understood as, but is not limited to, the game screen in the virtual scene of the target virtual game; in addition, to improve the efficiency of obtaining game reference data, it is possible, but not limited to, first obtaining all the game screens in the virtual scene of the target virtual game, then filtering out a portion of the game screens associated with the virtual character controlled by the simulated object from all the game screens, and determining this portion of the game screens as the running screen. In this way, efficient image recognition is performed on the filtered game screens, saving the time of obtaining game reference data and improving the efficiency of obtaining game reference data.
[0200] Optionally, in this embodiment, the process of obtaining the game reference data corresponding to the running screen may, but is not limited to, using machine vision such as computer vision to identify, collect and measure the running screen, and further performing graphic processing, which may, but is not limited to, involve technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc.
[0201] Optionally, in this embodiment, the simulated object is an artificial intelligence-driven virtual object used to simulate and control virtual characters to participate in a target virtual game, or it can be understood as a virtual object that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to instruct the virtual characters participating in the target virtual game to perform the most ideal operation.
[0202] Optionally, in this embodiment, the game reference data is the game data fed back by the virtual character when participating in the target virtual game in the first time unit, such as game status data, game resource data, etc., wherein the game status data may be used to represent the individual status of the virtual character participating in the target virtual game, and / or the local status of multiple virtual characters participating in the target virtual game, and / or the overall status of each faction participating in the target virtual game; the game resource data may be used to represent the held status, unheld status, distribution status, etc. of the virtual resources in the target virtual game, such as the status of virtual resources that have been acquired by virtual characters (held status of virtual resources), the status of virtual resources that have not been acquired by virtual characters (unheld status), the distribution of virtual resources in the virtual scene of the target virtual game (distribution status), etc.
[0203] Optionally, in this embodiment, the control instruction is the instruction initiated by the simulated object when it controls the virtual character to perform a candidate operation. The way in which the virtual character participates in the target virtual game may include, but is not limited to, the virtual character performing the target operation. The virtual character performing the target operation may be, but is not limited to, responding to the control instruction initiated by the simulated object. In other words, the way in which the simulated object participates in the target virtual game may be, but is not limited to, the simulated object initiating a control instruction to control the virtual character to perform the target operation.
[0204] Optionally, in this embodiment, during the display of the running screen of the target virtual game corresponding to the first time unit, more diverse game information may be displayed, such as basic information of at least one simulated object participating in the target virtual game (e.g., the name of the simulated object, the historical battle record of the simulated object, etc.), real-time progress information of the target virtual game (e.g., the virtual resources currently held by the virtual character, the items currently configured by the virtual character, the current battle information of the virtual character, etc.), and progress prediction information of the target virtual game (e.g., prediction information of the battle results of the target virtual game, prediction information of the progress development of the target virtual game, etc.).
[0205] It should be noted that during the operation of the target virtual game, the game reference data for the current time unit is obtained by detecting the running screen. The decision-making process of calculating and executing prediction information based on the game reference data is then displayed, thereby intuitively displaying the decision-making process of artificial intelligence participating in the virtual game and improving the comprehensiveness of information display.
[0206] For specific embodiments, please refer to the examples shown in the above information display device, which will not be repeated here.
[0207] The embodiments provided in this application display the running screen of a target virtual game in the first time unit. The target virtual game is a virtual game in which at least one simulated object participates. The simulated object is an AI-driven virtual object used to simulate controlling a virtual character in the target virtual game. Match reference data corresponding to the running screen is obtained, where the match reference data is the match data fed back by the virtual character when participating in the target virtual game in the first time unit. Based on the match reference data, execution prediction information corresponding to candidate operations to be performed by the virtual character in the second time unit is displayed. The execution prediction information is used to provide auxiliary reference related to the match reference data for the control commands initiated by the simulated object in the second time unit. The control commands are the commands initiated by the simulated object when controlling the virtual character to perform candidate operations. The second time unit is after the first time unit. During the operation of the target virtual game, the running screen of the current time unit is detected to obtain the match reference data for the current time unit. The decision-making process of calculating execution prediction information from the match reference data is then displayed, thereby achieving the purpose of intuitively displaying the decision-making process of AI participating in the virtual game, and thus realizing the technical effect of improving the comprehensiveness of information display.
[0208] As an alternative, the second display unit 2106 includes:
[0209] The first display module is used to display the first probability distribution information of the virtual character performing at least two candidate operations in the second time unit, wherein the first probability distribution information is used to predict the probability of the virtual character performing each of the at least two candidate operations in the second time unit.
[0210] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0211] As an alternative, the second display unit 2106 includes:
[0212] The second display module is used to display the second probability distribution information of the virtual character performing candidate operations on at least two pointed objects, wherein the second probability distribution information is used to predict the probability that the virtual character will perform candidate operations on each of the at least two pointed objects in the second time unit.
[0213] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0214] As an optional solution, the first display unit 2102 includes: a third display module, used to display the running screen in the first interface area of the spectator interface;
[0215] The second display unit 2106 includes: a fourth display module, used to display execution prediction information in the second interface area of the spectator interface.
[0216] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0217] As an optional solution, the third display module includes: a first display submodule, used to display the main running screen of the target virtual game in a first sub-area of the first interface area and the sub-running screen of the target virtual game in a second sub-area of the spectator interface, wherein the main running screen is a real-time screen within the virtual scene of the target virtual game, and the sub-running screen is a thumbnail of the virtual scene, and the thumbnail displays the character position identifier of the virtual character.
[0218] The fourth display module includes: a second display submodule, used to display execution prediction information in the running subscreen and in the third sub-area of the second interface area.
[0219] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0220] As an optional solution, the second display submodule includes:
[0221] The first display subunit is used to display the execution prediction information in the third sub-region and to display the movement direction indicator at the associated position of the character position indicator. The movement direction indicator is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit. The movement command is used to instruct the virtual character to move.
[0222] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0223] As an alternative, the device includes:
[0224] The second display subunit is used to display the execution prediction information in the running sub-screen and the third sub-area of the second interface area. When the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, the operation trajectory identifier associated with the target candidate operation is highlighted at the associated position of the target role position identifier. The operation trajectory identifier is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The target candidate operation is a candidate operation that points to the same object. The target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the second event unit.
[0225] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0226] As an alternative, the second display unit 2106 includes at least one of the following:
[0227] The fifth display module is used to display the execution prediction information corresponding to the pointing operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the pointing operation is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The pointing operation is used to determine the pointing object of the control command.
[0228] The sixth display module is used to display the execution prediction information corresponding to at least two candidate operations that the virtual character is executing in the second time unit. The execution prediction information corresponding to at least two candidate operations is used to provide a selection reference for at least two control commands initiated by the simulated object in the second time unit. The control commands in the at least two control commands correspond one-to-one with the candidate operations in the at least two candidate operations.
[0229] The seventh display module is used to display the execution prediction information corresponding to the movement operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the movement operation is used to provide directional reference for the movement command initiated by the simulated object in the second time unit.
[0230] The eighth display module is used to display the execution prediction information corresponding to the attack operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the attack operation is used to provide a reference for the attack command launched by the simulated object in the second time unit.
[0231] The ninth display module is used to display the execution prediction information corresponding to the configuration operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the configuration operation is used to provide a reference for the configuration command initiated by the simulated object in the second time unit. The configuration operation is used to determine the target item of the configuration command.
[0232] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0233] As an alternative, the second display unit 2106 includes:
[0234] The tenth display module is used to display the execution prediction information corresponding to the first virtual character when the screen view of the target virtual game is the character's view.
[0235] The eleventh display module is used to respond to the command to switch the screen view of the target virtual game, switch the screen view of the target virtual game to the character view of the second virtual character, and display the execution prediction information corresponding to the second virtual character.
[0236] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0237] As an alternative, the device may also include at least one of the following:
[0238] The third display unit is used to display the basic game information of at least one simulated object during the process of displaying the running screen of the target virtual game in the first time unit. The basic game information is the basic information of each simulated object in at least one simulated object.
[0239] The fourth display unit is used to display the real-time game information of the target virtual game in the first time unit while displaying the running screen of the target virtual game in the first time unit. The real-time game information is the real-time information generated by the target virtual game when it runs in the first time unit.
[0240] The fifth display unit is used to display the game history information of the target virtual game in the first time unit while displaying the running screen of the target virtual game in the first time unit. The game history information is the historical information generated before the target virtual game runs in the first time unit.
[0241] The sixth display unit is used to display the game prediction information of the target virtual game in the first time unit while displaying the running screen of the target virtual game in the first time unit. The game prediction information is the prediction information of the game result of at least one simulated object participating in the target virtual game.
[0242] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0243] As an alternative, the sixth display unit includes:
[0244] The first acquisition module is used to acquire the game screen of the target virtual game during operation, wherein the game screen includes the running screen;
[0245] The second acquisition module is used to acquire local game status information and overall game status information using the game screen. The local game status information is used to represent the game status of each virtual character participating in the target virtual game in the target virtual game, and the overall game status information is used to represent the game status of the target virtual game in the first time unit.
[0246] The first input module is used to input local game state information and overall game state information into the game prediction model to obtain a first identification result and a second identification result. The first identification result is used to represent the contribution of each virtual character participating in the target virtual game to the game result, and the second identification result is used to represent the contribution of the target virtual game's game state to the game result in the first time unit.
[0247] The fitting module is used to fit the first identification result and the second identification result to obtain the evaluation function value, wherein the evaluation function value is used to evaluate the game progress of at least one simulated object in the target virtual game from the perspective of the overall and local performance of the object.
[0248] The twelfth display module is used to obtain and display game prediction information based on the evaluation function value.
[0249] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0250] As an alternative, the twelfth display module includes:
[0251] The determination submodule is used to determine the predicted remaining time of each of the at least two opposing factions' participation in the target virtual game, in the case where the target virtual game is a virtual game in which simulated objects from at least two opposing factions participate, by using the evaluation function value.
[0252] The acquisition submodule is used to obtain the predicted win rate of each opposing faction in at least two opposing factions against the target virtual game based on the predicted remaining time, wherein the predicted win rate is inversely proportional to the predicted remaining time.
[0253] The third display submodule is used to display the predicted win rate as game prediction information.
[0254] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0255] As an optional solution, the acquisition unit 2104 includes: a second input module, used to input the running screen into the first network structure of the image recognition model to obtain the target image features corresponding to the running screen, wherein the game reference data includes the target image features, the image recognition model is a neural network model trained using target sample data for recognizing images, and the first network structure is used to extract image features;
[0256] The second display unit 2106 includes: a third input module, used to input target image features into a second network structure in an image recognition model to obtain target recognition results, wherein the execution prediction information includes the target recognition results, and the second network structure is used to output the classification results corresponding to the image features extracted by the first network structure.
[0257] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0258] As an alternative, the second input module includes:
[0259] The recognition submodule is used to perform image recognition on the running screen using the convolutional layer in the first network structure, and obtain at least two screen features corresponding to the running screen.
[0260] The concatenation submodule is used to concatenate features from at least two images using the fully connected layer in the first network structure to obtain the target image features.
[0261] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0262] As an optional solution, the serial submodule includes:
[0263] The mapping subunit is used to map the target image features to the attention mechanism layer in the second network structure to obtain the target mapping result;
[0264] The input subunit is used to input the target mapping result into the output layer of the second network structure to obtain the target recognition result.
[0265] For specific implementation examples, please refer to the examples shown in the above information display method; these examples will not be repeated here.
[0266] According to another aspect of the embodiments of this application, an electronic device for implementing the above-described information display method is also provided, such as... Figure 22 As shown, the electronic device includes a memory 2202 and a processor 2204. The memory 2202 stores a computer program, and the processor 2204 is configured to execute the steps of any of the above method embodiments through the computer program.
[0267] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.
[0268] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:
[0269] S1, display the running screen of the target virtual game in the first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is a virtual object driven by artificial intelligence and used to simulate the control of virtual characters in the target virtual game;
[0270] S2, obtain the game reference data corresponding to the running screen, where the game reference data is the game data fed back by the virtual character when the unit participates in the target virtual game in the first time;
[0271] S3, based on the game reference data, displays the execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit. The execution prediction information is used to provide auxiliary reference related to the game reference data for the control command initiated by the simulated object in the second time unit. The control command is the command initiated by the simulated object when controlling the virtual character to perform the candidate operation. The second time unit is after the first time unit.
[0272] Alternatively, as those skilled in the art will understand, Figure 22 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 22 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 22 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 22 The different configurations shown.
[0273] The memory 2202 can be used to store software programs and modules, such as the program instructions / modules corresponding to the information display method and apparatus in this embodiment. The processor 2204 executes various functional applications and data processing by running the software programs and modules stored in the memory 2202, thereby realizing the aforementioned information display method. The memory 2202 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 2202 may further include memory remotely located relative to the processor 2204, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 2202 may be used, but is not limited to, to store running screens, game reference data, and execution prediction information. As an example, such as... Figure 22 As shown, the memory 2202 may include, but is not limited to, the first display unit 2102, the acquisition unit 2104, and the second display unit 2106 of the information display device. Furthermore, it may include, but is not limited to, other module units of the information display device, which will not be elaborated upon in this example.
[0274] Optionally, the transmission device 2206 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 2206 includes a Network Interface Controller (NIC), which can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 2206 is a radio frequency (RF) module, used for wireless communication with the Internet.
[0275] In addition, the aforementioned electronic device also includes: a display 2208 for displaying the aforementioned running screen, game reference data, and execution prediction information; and a connection bus 2210 for connecting the various module components in the aforementioned electronic device.
[0276] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal, or other electronic device, can become a node in the blockchain system by joining this peer-to-peer network.
[0277] According to one aspect of this application, a computer program product is provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions provided in embodiments of this application.
[0278] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0279] It should be noted that the computer system of the electronic device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0280] A computer system includes a Central Processing Unit (CPU), which performs various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) or loaded from RAM. ROM also stores various programs and data required for system operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output interfaces (I / O interfaces) are also connected to the bus.
[0281] The following components are connected to the input / output interface: input sections including keyboards, mice, etc.; output sections including cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; storage sections including hard drives; and communication sections including network interface cards such as LAN cards and modems. The communication section performs communication processing via a network such as the Internet. Drives are also connected to the input / output interface as needed. Removable media, such as disks, optical discs, magneto-optical discs, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as required.
[0282] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions defined in the system of this application.
[0283] According to one aspect of this application, a computer-readable storage medium is provided, wherein a processor of a computer device reads computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.
[0284] Optionally, in this embodiment, the computer-readable storage medium described above may be configured to store a computer program for performing the following steps:
[0285] S1, display the running screen of the target virtual game in the first time unit, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is a virtual object driven by artificial intelligence and used to simulate the control of virtual characters in the target virtual game;
[0286] S2, obtain the game reference data corresponding to the running screen, where the game reference data is the game data fed back by the virtual character when the unit participates in the target virtual game in the first time;
[0287] S3, based on the game reference data, displays the execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit. The execution prediction information is used to provide auxiliary reference related to the game reference data for the control command initiated by the simulated object in the second time unit. The control command is the command initiated by the simulated object when controlling the virtual character to perform the candidate operation. The second time unit is after the first time unit.
[0288] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0289] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0290] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0291] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0292] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.
[0293] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0294] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0295] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. An information display method, characterized in that, include: The spectator interface displays the running screen of the target virtual game in the first time unit. The target virtual game is a virtual game in which at least one simulated object participates. The simulated object is an artificial intelligence-driven virtual object used to simulate the control of virtual characters in the target virtual game. Obtain the game reference data corresponding to the running screen, wherein the game reference data is the game data fed back by the virtual character when participating in the target virtual game in the first time unit; In the spectator interface, based on the match reference data, execution prediction information corresponding to the candidate operation that the virtual character is scheduled to perform in the second time unit is displayed, wherein the second time unit is after the first time unit, including: When the candidate operation is a movement operation, the execution prediction information is displayed in terms of the selection priority of each direction. The selection priority of each direction is represented by a length, and the length is positively related to the selection priority of the direction. When the candidate operation is an attack operation, the execution prediction information is displayed according to the selection priority of each target object. The selection priority of each target object is represented by a shadow, and the display area of the shadow is positively related to the selection priority of the target object.
2. The method according to claim 1, characterized in that, The process of displaying the execution prediction information corresponding to the candidate operation to be executed by the virtual character in the second time unit includes: The first probability distribution information is displayed so that the virtual character is to perform at least two candidate operations in the second time unit, wherein the first probability distribution information is used to predict the probability of the virtual character performing each of the at least two candidate operations in the second time unit.
3. The method according to claim 1, characterized in that, The process of displaying the execution prediction information corresponding to the candidate operation to be executed by the virtual character in the second time unit includes: The second probability distribution information is displayed for the virtual character to perform the candidate operation on at least two pointer objects, wherein the second probability distribution information is used to predict the probability that the virtual character will perform the candidate operation on each of the at least two pointer objects in the second time unit.
4. The method according to claim 1, characterized in that, The display of the target virtual game's running screen in the first time unit includes: displaying the running screen in the first interface area of the spectator interface; The step of displaying the execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit includes: displaying the execution prediction information in the second interface area of the spectator interface.
5. The method according to claim 4, characterized in that, The step of displaying the running screen in the first interface area of the spectator interface includes: displaying the main running screen of the target virtual game corresponding to the first time unit in the first sub-area of the first interface area, and displaying the sub-running screen of the target virtual game corresponding to the first time unit in the second sub-area of the spectator interface, wherein the main running screen is the real-time screen of the virtual scene of the target virtual game, and the sub-running screen is a thumbnail of the virtual scene, and the thumbnail displays the character position identifier of the virtual character; Displaying the execution prediction information in the second interface area of the spectator interface includes displaying the execution prediction information in the running sub-screen and in the third sub-area of the second interface area.
6. The method according to claim 5, characterized in that, The display of the execution prediction information in the running sub-screen and the third sub-area in the second interface area includes: The execution prediction information is displayed in the third sub-region, and a movement direction indicator is displayed at the associated position of the character position indicator. The movement direction indicator is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit. The movement command is used to instruct the virtual character to move.
7. The method according to claim 5, characterized in that, During the process of displaying the execution prediction information in the running sub-screen and the third sub-area in the second interface area, the method includes: When the number of target candidate operations indicated by the execution prediction information reaches a preset threshold, the operation trajectory identifier associated with the target candidate operation is highlighted at the associated position of the target role position identifier. The operation trajectory identifier is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The target candidate operation is a candidate operation pointing to the same object. The target role position identifier is the role position identifier corresponding to the virtual role that initiates the target candidate operation in the second time unit.
8. The method according to claim 1, characterized in that, The execution prediction information corresponding to the candidate operation that the virtual character is scheduled to perform in the second time unit includes at least one of the following: The display shows the execution prediction information corresponding to the pointing operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the pointing operation is used to provide a pointing reference for the control command initiated by the simulated object in the second time unit. The pointing operation is used to determine the pointing object of the control command. Display execution prediction information corresponding to at least two candidate operations performed by the virtual character while in the second time unit, wherein the execution prediction information corresponding to the at least two candidate operations is used to provide selection reference for at least two control instructions initiated by the simulated object while in the second time unit, and the control instructions in the at least two control instructions correspond one-to-one with the candidate operations in the at least two candidate operations; The execution prediction information corresponding to the movement operation performed by the virtual character in the second time unit is displayed, wherein the execution prediction information corresponding to the movement operation is used to provide a direction reference for the movement command initiated by the simulated object in the second time unit; The display shows the execution prediction information corresponding to the attack operation performed by the virtual character while in the second time unit, wherein the execution prediction information corresponding to the attack operation is used to provide a reference for the attack command initiated by the simulated object while in the second time unit; The display shows the execution prediction information corresponding to the configuration operation performed by the virtual character in the second time unit. The execution prediction information corresponding to the configuration operation is used to provide a reference for the configuration instruction initiated by the simulated object in the second time unit. The configuration operation is used to determine the target item of the configuration instruction.
9. The method according to claim 1, characterized in that, The process of displaying the execution prediction information corresponding to the candidate operation to be executed by the virtual character in the second time unit includes: When the screen view of the target virtual game is the view of the first virtual character, the execution prediction information corresponding to the first virtual character is displayed; In response to a command to switch the viewpoint of the target virtual game, the viewpoint of the target virtual game is switched to the viewpoint of the second virtual character, and the execution prediction information corresponding to the second virtual character is displayed.
10. The method according to claim 1, characterized in that, During the process of displaying the running screen of the target virtual game corresponding to the first time unit, the method further includes at least one of the following: Display the basic game information of the at least one simulated object, wherein the basic game information is the basic information of each simulated object among the at least one simulated object; Display the real-time game information of the target virtual game in the first time unit, wherein the real-time game information is the real-time information generated by the target virtual game during the first time unit. Display the game history information of the target virtual game in the first time unit, wherein the game history information is the historical information generated before the target virtual game runs in the first time unit; The game prediction information of the target virtual game is displayed in the first time unit, wherein the game prediction information is the prediction information of the game results of the at least one simulated object participating in the target virtual game.
11. The method according to claim 10, characterized in that, The step of displaying the game prediction information of the target virtual game in the first time unit includes: Acquire the game screen of the target virtual game during its operation, wherein the game screen includes the running screen; The game screen is used to obtain local game state information and overall game state information. The local game state information is used to represent the game state of each virtual character participating in the target virtual game in the target virtual game, and the overall game state information is used to represent the game state of the target virtual game in the first time unit. The local game state information and the overall game state information are input into the game prediction model to obtain a first identification result and a second identification result. The first identification result is used to represent the contribution of each virtual character participating in the target virtual game to the game result, and the second identification result is used to represent the contribution of the game state of the target virtual game in the first time unit to the game result. The first identification result and the second identification result are fitted to obtain an evaluation function value, wherein the evaluation function value is used to evaluate the game progress of the at least one simulated object in the target virtual game from the perspectives of the overall and local performance of the object; The game prediction information is obtained and displayed based on the evaluation function value.
12. The method according to claim 11, characterized in that, The process of obtaining and displaying the game prediction information based on the evaluation function value includes: In the case where the target virtual game is a virtual game in which simulated objects from at least two opposing factions participate, the predicted remaining time for each of the at least two opposing factions to participate in the target virtual game is determined using the evaluation function value. Based on the predicted remaining time, the predicted win rate of each of the at least two opposing factions in the target virtual game is obtained, wherein the predicted win rate is inversely proportional to the predicted remaining time. The predicted win rate is displayed as the game prediction information.
13. The method according to claim 1, characterized in that, The step of obtaining the game reference data corresponding to the running screen includes: inputting the running screen into the first network structure in the image recognition model to obtain the target image features corresponding to the running screen, wherein the game reference data includes the target image features, the image recognition model is a neural network model trained using target sample data for recognizing images, and the first network structure is used to extract image features; The step of displaying the execution prediction information corresponding to the candidate operation to be performed by the virtual character in the second time unit based on the game reference data includes: inputting the target image features into the second network structure in the image recognition model to obtain the target recognition result, wherein the execution prediction information includes the target recognition result, and the second network structure is used to output the classification result corresponding to the image features extracted by the first network structure.
14. The method according to claim 13, characterized in that, The step of inputting the running screen into the first network structure of the image recognition model to obtain the target image features corresponding to the running screen includes: Using the convolutional layers in the first network structure, image recognition is performed on the running screen to obtain at least two screen features corresponding to the running screen; The target image features are obtained by concatenating the features of at least two images using the fully connected layer in the first network structure.
15. The method according to claim 14, characterized in that, The step of inputting the target image features into the second network structure of the image recognition model to obtain the target recognition result includes: The target image features are mapped to the attention mechanism layer in the second network structure to obtain the target mapping result; The target mapping result is input into the output layer of the second network structure to obtain the target recognition result.
16. An information display device, characterized in that, include: The first display unit is used to display the running screen of the target virtual game in the first time unit on the spectator interface, wherein the target virtual game is a virtual game in which at least one simulated object participates, and the simulated object is an artificial intelligence-driven virtual object used to simulate the control of virtual characters in the target virtual game; The acquisition unit is used to acquire the game reference data corresponding to the running screen, wherein the game reference data is the game data fed back by the virtual character when participating in the target virtual game in the first time unit; The second display unit is configured to display, on the spectator interface, execution prediction information corresponding to a candidate operation to be performed by the virtual character in a second time unit, based on the match reference data, wherein the second time unit is after the first time unit, including: When the candidate operation is a movement operation, the execution prediction information is displayed in terms of the selection priority of each direction. The selection priority of each direction is represented by a length, and the length is positively related to the selection priority of the direction. When the candidate operation is an attack operation, the execution prediction information is displayed according to the selection priority of each target object. The selection priority of each target object is represented by a shadow, and the display area of the shadow is positively related to the selection priority of the target object.
17. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program can be executed by a terminal device or computer at runtime as described in any one of claims 1 to 15.
18. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1 to 15.
19. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 15 through the computer program.
