Model training method and device, task generation method and device and storage medium
By training the model to generate game tasks that match user levels and preferences, the problem of high complexity caused by task fixation in existing games is solved and the user experience is improved.
Patent Information
- Application Number
- CN202510345063.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-21
- Publication Date
- 2025-07-11
AI Technical Summary
The game tasks in existing games are fixed and the user level differences are not considered, resulting in high operation complexity for users with poor game levels.
By obtaining user historical behavior data, the target model is trained to determine user level information, generate configuration files that match user level, and adjust game task difficulty and type.
Reduces the complexity of users' games with lower user levels, improves the user experience, and generates game tasks that match user levels and preferences.
Smart Images
Figure CN120285570A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a model training method, a task generation method, a device, and a storage medium. Background Art
[0002] With the advancement of computer technology, the game industry has developed rapidly, and new types of games have emerged, such as simulation games, role-playing games, etc.
[0003] In existing games, various game tasks (such as resource collection tasks, confrontation tasks, etc.) are often fixed. Therefore, each user can only perform these fixed game tasks in sequence when operating the game. In addition, the game tasks generated in existing games do not take into account the differences in game levels between different users, which will lead to higher complexity when users with poor game levels operate the game. Summary of the invention
[0004] This specification provides a model training method, a task generation method, a device and a storage medium to partially solve the above-mentioned problems existing in the prior art.
[0005] This manual adopts the following technical solutions:
[0006] This specification provides a model training method, including:
[0007] Acquire historical behavior data of a user, where the historical behavior data is used to characterize the historical game behavior of the user in a target game;
[0008] Input the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, and generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file, and generates and displays the target game task in a preset interface according to the parsed data;
[0009] In response to the user's execution operation on the target game task in the preset interface, determining task execution information when the user executes the target game task;
[0010] A target reward value is determined according to the task execution information, so as to adjust the parameters of the target model according to the target reward value to obtain a trained target model.
[0011] Optionally, the step of inputting the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data and generates a corresponding target profile based on the user level information specifically includes:
[0012] Input the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user and the user preference information of the user according to the historical behavior data, and generates a corresponding target profile based on the user level information and the user preference information.
[0013] Optionally, the step of determining a target reward value according to the task execution information specifically includes:
[0014] When there are multiple target game tasks, for each target game task, determine the reward value corresponding to the target game task according to the task execution information when the user executes the target game task;
[0015] Determine the target reward value according to the reward value corresponding to each target game task and the task weight corresponding to each target game task.
[0016] Optionally, the step of determining a target reward value according to the task execution information specifically includes:
[0017] Determine the target reward value according to the task completion degree when the user executes the target game task, and there is a positive correlation between the task completion degree and the target reward value.
[0018] Optionally, the step of inputting the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data and generates a corresponding target profile based on the user level information specifically includes:
[0019] Input the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user and the task level of the historical game tasks executed by the user in history according to the historical behavior data, and generates an initial task profile based on the user level information, and determines the level deviation between the task level of the game task corresponding to the initial task profile and the task level of the historical game task, so as to adjust the initial task profile according to the level deviation to obtain the target profile.
[0020] This specification provides a task generation method, including: obtaining historical behavior data of a user, where the historical behavior data is used to characterize the historical game behavior of the user in a target game;
[0021] Input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target profile based on the user level information, and transmits the target profile to the client where the target game is located, so that the client parses the target profile and generates and displays a target game task in a preset interface. The target model is trained by the model training method as described above.
[0022] This specification provides a model training device, including:
[0023] An acquisition module: used to acquire the historical behavior data of the user, where the historical behavior data is used to characterize the historical game behavior of the user in the target game;
[0024] A generation module: used to input the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target profile based on the user level information, and transmits the target profile to the client where the target game is located, so that the client parses the target profile and generates and displays a target game task in a preset interface;
[0025] A determination module: used to determine the task execution information when the user executes the target game task in response to the execution operation of the user on the target game task in the preset interface;
[0026] An adjustment module: used to determine a target reward value according to the task execution information, and adjust the parameters of the target model according to the target reward value to obtain a trained target model.
[0027] This specification provides a task generation device, including:
[0028] An acquisition module: used to acquire the historical behavior data of the user, where the historical behavior data is used to characterize the historical game behavior of the user in the target game;
[0029] Generation module: configured to input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays a target game task in a preset interface according to the parsed data. The target model is trained by the model training method as described above.
[0030] This specification provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above model training method or task generation method.
[0031] This specification provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the above model training method or task generation method.
[0032] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:
[0033] The model training method provided in this specification can obtain the historical behavior data of a user, input it into a target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays a target game task in a preset interface according to the parsed data. In response to an execution operation of the user on the target game task in the preset interface, determine the task execution information when the user executes the target game task, determine the target reward value according to the task execution information, and adjust the parameters of the target model according to the target reward value to obtain the trained target model.
[0034] It can be seen from this that the target model trained by the above model training method can generate a target configuration file configured with game task information matching the user level based on the user level information. Furthermore, the client where the target game is located can generate a target game task matching the user's own level information according to the data obtained by parsing the target configuration file. That is, for users with a lower user level, there is no need to execute high-difficulty target game tasks that do not match their own level, greatly reducing the complexity of operating the game. Similarly, for users of other user levels, they can all execute target game tasks matching their own user levels, greatly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:
[0036] Figure 1 A flowchart of a model training method provided in this specification;
[0037] Figure 2 A flowchart of a task generation method provided in this specification;
[0038] Figure 3 A schematic diagram of a model training device provided in this specification;
[0039] Figure 4 A schematic diagram of a task generation device provided in this specification;
[0040] Figure 5 A method corresponding to the Figure 1 or Figure 2 Schematic block diagram of an electronic device. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.
[0042] In existing simulation games, role-playing games, and other games, various game tasks (such as resource collection tasks, confrontation tasks, etc.) are often fixed, so users can only perform these fixed game tasks in sequence when operating the game. In addition, the game tasks generated in existing games do not take into account the differences in game levels between different users, which will lead to higher complexity when users with poor game levels operate the game.
[0043] Therefore, this specification provides a model training method, which can effectively solve the problems in the prior art.
[0044] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.
[0045] Figure 1 A flow chart of a model training method provided in this specification includes the following steps:
[0046] S101: Obtain the historical behavior data of the user, where the historical behavior data is used to characterize the user's historical gaming behavior in the target game.
[0047] The execution subject of the model training method involved in this specification can be a terminal device such as a desktop computer or a laptop, or a client installed in the terminal device, or a server. Hereinafter, only the server as the execution subject is taken as an example to illustrate the model training method in the embodiments of this specification.
[0048] In this specification, the target model can be trained in a reinforcement learning manner. Furthermore, the trained target model can generate a corresponding target configuration file, and the target configuration file can be parsed by the client where the target game is located, so that corresponding target game tasks (such as: resource collection tasks, confrontation tasks, etc.) can be generated in the corresponding interface according to the parsed data.
[0049] For this purpose, the server can first obtain the historical behavior data of the user. Among them, the historical behavior data can characterize the user's historical gaming behavior in the target game. For example, data such as the login time when the user logs in to the target game, the duration of each game task executed in the target game, the completion status of each game task in the target game, and the interaction information with other users during the execution of the game task can be obtained. Furthermore, the target model to be trained can be trained based on the obtained historical behavior data to obtain the trained target model.
[0050] S102: Input the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays target game tasks in a preset interface according to the parsed data.
[0051] The server can input the historical behavior data into the target model to be trained (such as: deep Q-network model). Furthermore, the target model can determine the user level information of the user according to the historical behavior data. Among them, the user level information can be used to measure the operation level of the user operating the target game. The higher the operation level of the user operating the target game, the higher the user level represented by the user level information.
[0052] After the target model determines the user level information of the user, it can generate a corresponding target configuration file based on the determined user level information. Among them, the target configuration file can be a JSON file, an XML file, etc. storing game task-related information.
[0053] For example, when the user level is high, that is, the user's operation level of the target game is high, then the target model can generate a target configuration file configured with game task information with a relatively high difficulty coefficient. On the contrary, when the user level is low, that is, the user's operation level of the target game is low, then the target model can generate a target configuration file configured with game task information with a relatively low difficulty coefficient.
[0054] It should be noted that in the actual application process, when parsing the target configuration file generated based on the user level information, the generated target game task may not have a good effect on the user experience. Therefore, the task level of the historical tasks executed by the user in the past can be referred to for corresponding adjustment of the configuration file, so that to a certain extent, the game task level corresponding to the adjusted configuration file can be matched with the task level of the historical tasks executed by the user in the past, thereby improving the user experience.
[0055] Specifically, after the server inputs the historical behavior data into the target model to be trained, the target model can determine the user level information of the user and the task level of the historical game tasks executed by the user in the past based on the historical behavior data. Furthermore, the target model can generate an initial task configuration file based on the user level information. And, the level deviation between the task level of the game task corresponding to the initial task configuration file and the task level of the historical game task can be determined, so that the initial task configuration file can be adjusted according to the determined level deviation, and thus the target configuration file can be obtained.
[0056] For example, the task level of the game task can be divided into five levels, from low to high are the first level, the second level, the third level, the fourth level, and the fifth level. The higher the level, the higher the difficulty coefficient of the game task. The task level of the game task corresponding to the initial task configuration file generated based on the user level information is the fourth level, and the task level of the historical game task executed by the user in the past is the second level. Then, based on the level deviation between the task level of the game task corresponding to the initial task configuration file (the fourth level) and the task level of the historical game task executed by the user in the past (the second level), the task level of the game task corresponding to the initial task configuration file can be adjusted 50% of the deviation in the direction of the task level of the historical game task executed by the user in the past, that is, the task level of the game task corresponding to the initial task configuration file is adjusted to the average value of the two (the third level). Correspondingly, a target configuration file configured with game task information with a task level of the third level can be obtained.
[0057] Of course, the above is only an embodiment of adjusting the initial task profile provided in this specification. During the actual training process, different task levels and adjustment ratios can be set according to actual needs, so as to adjust based on the level deviation between the task level of the game task corresponding to the initial task profile and the task level of the historical game task. For example, the task level of the game task corresponding to the initial task profile can be adjusted by 25% of the level deviation in the direction of the task level of the historical game task.
[0058] In addition, during the process of generating the target profile, in addition to referring to the user level information, user preference information can also be referred to.
[0059] Specifically, the server can input the historical behavior data into the target model to be trained, and then the target model can determine the user level information of the user and the user preference information of the user according to the historical behavior data. Among them, the user preference information can represent the degree of preference of the user for different types of game tasks. For example, compared with confrontation tasks, user A prefers to perform resource collection tasks. Another example is that compared with resource collection tasks, user B prefers to perform confrontation tasks, etc.
[0060] After determining the user level information and the user preference information, the target model can generate a corresponding target profile in the target game based on the user level information and the user preference information. For example, if user A has a relatively high user level and prefers to perform confrontation tasks, then the target model can generate a target profile configured with confrontation task information with a relatively high difficulty coefficient.
[0061] After the target model generates the target profile, the target profile can be transmitted to the client where the target game is located. Then, the client where the target game is located can parse the target profile and generate and display the target game task in the preset interface according to the parsed data.
[0062] In this specification, the above target model can have multiple deployment methods. For example, the target model can be deployed in the server. Then, when transmitting the target profile to the client where the target game is located, the file transmission can be completed by establishing a corresponding network communication protocol. Another example is that the target model can also be deployed in the terminal device. Then, when transmitting the target profile to the client where the target game is located, the file transmission can be directly realized inside the terminal device. This specification does not make a limitation here.
[0063] S103: In response to the user's execution operation on the target game task in the preset interface, determine the task execution information when the user executes the target game task.
[0064] S104: Determine a target reward value according to the task execution information, and adjust the parameters of the target model according to the target reward value to obtain a trained target model.
[0065] The server can determine the task execution information when the user executes the target game task in response to the user's execution operation on the target game task in the preset interface. Among them, the task execution information can characterize the execution situation of the user when executing the target game task.
[0066] Furthermore, the server can determine the target reward value according to the task execution information. For example, the server can determine the target reward value according to the task completion degree when the user executes the target game task. During the actual training process, a corresponding reward function can be set in advance, and then the corresponding reward can be given based on the task completion degree. Among them, the target reward values corresponding to different task completion degrees are different, and there is a positive correlation between the task completion degree and the target reward value, that is, the higher the task completion degree, the greater the target reward value.
[0067] Of course, in addition to determining the target reward value according to the task completion degree when the user executes the target game task, the target reward value can also be determined according to the time taken by the user to execute the target game task. Correspondingly, in the actual training process, a corresponding reward function can also be set, and then the corresponding reward can be given based on the time taken by the user to execute the target game task. Among them, the closer the time taken by the user to execute the target game task is to the preset standard time, the greater the target reward value.
[0068] Or, the target reward value can also be determined according to the score of the user's execution of the target game task, the interaction situation between the user and other users when the user executes the target game task, the number of times the user visits the target game task, etc. Correspondingly, in the actual training process, the corresponding reward function can be set according to the actual situation, which will not be elaborated in this specification.
[0069] In addition, in actual applications, the generated target game tasks are often multiple. Then when there are multiple generated target game tasks, different task weights can be set for different target game tasks. The task weight can characterize the importance of the game task in the entire target game. For example, the task weights of main game tasks (such as confrontation tasks and resource collection tasks) are often higher than those of side game tasks (such as daily check-in tasks and game sharing tasks).
[0070] Then, in the process of determining the target reward value, for each target game task, the reward value corresponding to the target game task can be determined according to the task execution information when executing the target game task. Furthermore, the target reward value can be determined according to the reward values corresponding to the target game tasks and the task weights of the target game tasks. The target reward value can specifically refer to the following formula:
[0071] M = m1 * n1 + m2 * n2
[0072] Among them, M can be used to represent the target reward value, m1 can be used to represent the reward value corresponding to target game task A, n1 can be used to represent the task weight corresponding to target game task A, m2 can be used to represent the reward value corresponding to target game task B, and n2 can be used to represent the task weight corresponding to target game task B.
[0073] Furthermore, the parameters of the target model can be adjusted according to the target reward value to obtain the trained target model. For example, the parameters of the target model can be adjusted with the goal of gradually increasing the target reward value, so as to obtain the trained target model.
[0074] It can be seen from this that the target model trained by the above model training method can generate a target configuration file configured with game task information matching the user level based on the user level information. Furthermore, the client where the target game is located can generate target game tasks matching the user's own level information according to the data parsed from the target configuration file. That is, for users with a lower user level, there is no need to execute high-difficulty target game tasks that do not match their own level, greatly reducing the complexity of operating the game. Similarly, for users of other user levels, they can also execute target game tasks matching their own user level, greatly improving the user experience.
[0075] In addition, in the above method, for different users, game tasks matching their preference information can also be generated, further improving the user experience when operating the game.
[0076] The above mainly introduces the model training method. After the model is trained, it can be deployed to generate tasks. Next, a task generation method provided in this specification will be described.
[0077] Figure 2 It is a schematic flowchart of a task generation method provided in this specification, including the following steps:
[0078] S201: Obtain the historical behavior data of the user, and the historical behavior data is used to characterize the historical game behavior of the user in the target game.
[0079] For the task generation method provided in this specification, the execution entity can be a server or a terminal device such as a desktop computer or a laptop computer. Hereinafter, only the terminal device will be taken as an example to elaborate on the following content in detail.
[0080] In this specification, the generated target game tasks will not be fixed as in the prior art, but can generate target game tasks that match the historical behavior data of each user. The terminal device can obtain the historical behavior data of the user and input the historical behavior data of the user into a pre-trained target model, so that the target model generates a target configuration file configured with game task information that matches the historical behavior data of the user, facilitating subsequent parsing and generating target game tasks based on the parsed data.
[0081] S202: Input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user based on the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays a target game task in a preset interface according to the parsed data. The target model is trained by the model training method as described above.
[0082] During the generation process of the target configuration file, the target model can generate a target configuration file based on the user level information determined by the historical behavior data and transmit it to the client where the target game is located. Then, the client can generate a target game task according to the data obtained by parsing the target configuration file and display the target game task in the preset interface of the terminal device for the user to operate.
[0083] Of course, in the actual application process, when the user executes the target game task, the terminal device can also monitor the operation behavior of the user in real time and make corresponding adjustments to the task objectives of the target game task according to the monitored operation behavior of the user, so as to optimize the user experience.
[0084] It can be seen from this that in the above method, different target game tasks can be generated for users with different user levels. That is, for users with a lower user level, there is no need to execute high-difficulty target game tasks that do not match their own level, greatly reducing the complexity of operating the game. Similarly, for users with other user levels, they can also execute target game tasks that match their user levels, greatly improving the user experience. In addition, in the above method, for users with different user levels, target game tasks that match their preference information can also be generated, further improving the user experience.
[0085] The above are the methods of one or more implementations of this specification. Based on the same idea, this specification also provides corresponding model training devices and task generation devices, as Figure 3 , Figure 4 shown.
[0086] Figure 3 The figure is a schematic diagram of a model training device provided in this specification, including:
[0087] An acquisition module 301: configured to acquire historical behavior data of a user, where the historical behavior data is used to characterize the historical game behavior of the user in a target game;
[0088] A generation module 302: configured to input the historical behavior data into a target model to be trained, so that the target model determines user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to a client where the target game is located, so that the client parses the target configuration file and generates and displays a target game task in a preset interface according to the parsed data;
[0089] A determination module 303: configured to determine task execution information of the user when executing the target game task in response to an execution operation of the user on the target game task in the preset interface;
[0090] An adjustment module 304: configured to determine a target reward value according to the task execution information, and adjust parameters of the target model according to the target reward value to obtain a trained target model.
[0091] Optionally, the generation module 302 is specifically configured to:
[0092] Input the historical behavior data into a target model to be trained, so that the target model determines user level information of the user and user preference information of the user according to the historical behavior data, and generates a corresponding target configuration file based on the user level information and the user preference information.
[0093] Optionally, the adjustment module 304 is specifically configured to:
[0094] When there are multiple target game tasks, for each target game task, determine a reward value corresponding to the target game task according to the task execution information of the user when executing the target game task; determine a target reward value according to the reward value corresponding to each target game task and the task weight corresponding to each target game task.
[0095] Optionally, the adjustment module 304 is specifically configured to:
[0096] Determine a target reward value according to the task completion degree when the user executes the target game task, and there is a positive correlation between the task completion degree and the target reward value.
[0097] Optionally, the generation module 302 is specifically configured to:
[0098] Input the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user and the task levels of the historical game tasks executed by the user in history according to the historical behavior data, and generates an initial task configuration file based on the user level information, and determines the level deviation between the task level of the game task corresponding to the initial task configuration file and the task level of the historical game task, and adjusts the initial task configuration file according to the level deviation to obtain a target configuration file.
[0099] Figure 4 The figure is a schematic diagram of a task generation device provided in this specification, including:
[0100] An acquisition module 401: configured to acquire historical behavior data of a user, where the historical behavior data is used to characterize the historical game behavior of the user in a target game;
[0101] A generation module 402: configured to input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to a client where the target game is located, so that the client parses the target configuration file and generates and displays a target game task in a preset interface, and the target model is trained by the model training method as described above.
[0102] This specification also provides a computer-readable storage medium, which stores a computer program, and the computer program can be used to execute the above Figure 1 model training method shown or Figure 2 task generation method shown.
[0103] This specification also provides Figure 5 the schematic structural diagram of an electronic device corresponding to Figure 1 or Figure 2 . As shown in Figure 5As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above Figure 1 model training method shown or Figure 2 task generation method shown.
[0104] Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logical devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logical unit, and can also be hardware or logical devices.
[0105] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not only one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.
[0106] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.
[0107] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0108] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0109] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.
[0110] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks for implementing the specified functions.
[0111] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks.
[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks.
[0113] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.
[0114] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.
[0115] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0117] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0118] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0119] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the relevant parts of the method embodiments for the relevant content.
[0120] The above is only the embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various changes and modifications can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims of this specification.
Claims
1. A model training method, characterized in that, Including: Obtain the historical behavior data of the user, where the historical behavior data is used to characterize the historical game behavior of the user in the target game; Input the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays target game tasks in a preset interface according to the parsed data; In response to the user's execution operation on the target game task in the preset interface, determine the task execution information when the user executes the target game task; Determine a target reward value according to the task execution information, so as to adjust the parameters of the target model according to the target reward value to obtain the trained target model.
2. The method according to claim 1, characterized in that The step of inputting the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data and generates a corresponding target configuration file based on the user level information specifically includes: Input the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user and the user preference information of the user according to the historical behavior data, and generates a corresponding target configuration file based on the user level information and the user preference information.
3. The method according to claim 1, wherein The step of determining a target reward value according to the task execution information specifically includes: When there are multiple target game tasks, for each target game task, determine the reward value corresponding to the target game task according to the task execution information when the user executes the target game task; Determine the target reward value according to the reward value corresponding to each target game task and the task weight corresponding to each target game task.
4. The method according to claim 1, wherein The step of determining a target reward value according to the task execution information specifically includes: Determine the target reward value according to the task completion degree when the user executes the target game task, and the task completion degree has a positive correlation with the target reward value.
5. The method according to claim 1, characterized in that, The step of inputting the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data and generates a corresponding target configuration file based on the user level information specifically includes: Input the historical behavior data into the target model to be trained, so that the target model determines the user level information of the user and the task level of the historical game tasks executed by the user in the past according to the historical behavior data, generates an initial task configuration file based on the user level information, and determines the level deviation between the task level of the game tasks corresponding to the initial task configuration file and the task level of the historical game tasks, so as to adjust the initial task configuration file according to the level deviation to obtain the target configuration file.
6. A task generation method, characterized in that, Including: Obtain the historical behavior data of the user, where the historical behavior data is used to characterize the user's historical gaming behavior in the target game; Input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays target game tasks in a preset interface. The target model is trained by the method described in any one of claims 1 to 5 above.
7. A model training device, characterized in that, It includes: An acquisition module: used to obtain the historical behavior data of the user, where the historical behavior data is used to characterize the user's historical gaming behavior in the target game; A generation module: used to input the historical behavior data into a target model to be trained, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays target game tasks in a preset interface; A determination module: used to determine the task execution information when the user executes the target game task in response to the user's execution operation on the target game task in the preset interface; An adjustment module: used to determine a target reward value according to the task execution information, and adjust the parameters of the target model according to the target reward value to obtain a trained target model.
8. A task generation device, characterized in that, It includes: An acquisition module: used to obtain the historical behavior data of the user, where the historical behavior data is used to characterize the user's historical gaming behavior in the target game; A generation module: used to input the historical behavior data into a pre-trained target model, so that the target model determines the user level information of the user according to the historical behavior data, generates a corresponding target configuration file based on the user level information, and transmits the target configuration file to the client where the target game is located, so that the client parses the target configuration file and generates and displays target game tasks in a preset interface. The target model is trained by the method described in any one of claims 1 to 5 above.
9. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 6 above is implemented.
10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, the method described in any one of claims 1 to 6 above is implemented.
Citation Information
Cited By
Intelligent dynamic configuration management system and method
CN120856553A