Game data processing method and device, electronic equipment and storage medium
By integrating game data into structure formats and processing them using natural language prompt words, the problem of low interaction efficiency between AI models and game applications is solved, and more efficient data interaction and processing is achieved.
Patent Information
- Application Number
- CN202311735721.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-15
- Publication Date
- 2025-01-10
AI Technical Summary
The existing game data processing methods lead to low interaction efficiency between AI models and game applications, requiring a large number of labels and cumbersome string matching and splitting processes.
By integrating game data into structure formats, inputting preset prompt words from natural language into artificial intelligence models, outputting task processing results in structure formats, and converting them into formats supported by game applications, reducing tag addition and improving interaction efficiency .
It improves the interaction efficiency between AI models and game applications, reduces the burden of understanding and processing of artificial intelligence models, and simplifies the splitting and conversion process of task processing results.
Smart Images
Figure CN119293105A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of game development technology, and in particular to a game data processing method, device, electronic device and storage medium. Background Art
[0002] In the process of game development, using artificial intelligence (AI) models to improve game quality and gaming experience has always been a cutting-edge research field. Today, AI models have strong logical reasoning capabilities, text comprehension capabilities, and natural sentence comprehension capabilities, such as ChatGPT in generative AI. The common application of AI models in games is to analyze and process the game data generated by game applications and then give it to the game application to convert it into actual game performance. For example, when choosing a game character to fight against the enemy, you can use the AI model to select a character with strong combat power from our side and give it to the game application, and then the game application controls the character to fight against the enemy character.
[0003] However, the existing game data processing method usually adds labels to the original game data generated by the game application and directly inputs it into the AI model, and then splits the data output by the AI model by string matching and gives it to the game application. Since the game data input to the AI model is relatively complex, more labels need to be added, which will bring a greater understanding and processing burden to the AI model; in addition, the use of string matching to split the output data of the AI model is also relatively cumbersome, which makes the interaction efficiency between the AI model and the game application low. Summary of the invention
[0004] The present application provides a game data processing method, device, electronic device and storage medium to solve the problem that the existing game data processing method makes the interaction efficiency between AI models and game applications low.
[0005] In a first aspect, an embodiment of the present application provides a method for processing game data, the method comprising:
[0006] Receiving game data generated during the running of the game application, and integrating the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of a virtual character in the game;
[0007] Inputting the input data in the structure format and the preset prompt words into a preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, wherein the preset prompt words are natural language, used to prompt the artificial intelligence model to process the task included in the natural language, and outputting the task processing result in a preset output format, and the preset output format includes the structure format;
[0008] Receive the task processing result, and split the task processing result to obtain the task processing result in the structure format;
[0009] The task processing result in the structure format is converted into a task processing result in a target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0010] Optionally, the step of inputting the input data in the structure format and the preset prompt words into a preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, includes:
[0011] Inputting the input data in the structure format and the preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and the preset output format;
[0012] Through the preset prompt words, the artificial intelligence model is prompted to infer the input data in the structure format according to the preset task processing rules to obtain task processing results in multiple data formats;
[0013] Through the preset prompt word, the artificial intelligence model is prompted to add label information and output the task processing results that conform to the preset output format.
[0014] Optionally, the preset prompt word also includes attribute information of a preset character string;
[0015] Before prompting the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules through the preset prompt words to obtain task processing results in multiple data formats, the method also includes:
[0016] By using the preset prompt word, the artificial intelligence model is prompted to convert the input data in the structure format according to the attribute information of the preset character string to obtain the converted input data;
[0017] The preset prompt word prompts the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules to obtain task processing results in multiple data formats, including:
[0018] Through the preset prompt words, the artificial intelligence model is prompted to infer the converted input data according to the preset task processing rules to obtain task processing results in multiple data formats.
[0019] Optionally, splitting the task processing result to obtain the task processing result in the structure format includes:
[0020] Acquire the label information carried in the task processing result, wherein the type of the label information corresponds to the type of the preset output format specified in the preset prompt word;
[0021] The task processing result is split according to the tag information to obtain the task processing result in the structure format.
[0022] Optionally, the integrating the game data in a structure format to obtain input data in a structure format includes:
[0023] Extracting a plurality of field information associated with the task to be processed from the game data;
[0024] The multiple field information are integrated according to the structure format to obtain input data in the structure format, wherein the field information in the input data in the structure format is combined according to the association relationship between the multiple field information, and the field information in the input data in the structure format is named in a way that is easy for the artificial intelligence model to understand.
[0025] Optionally, before inputting the input data in the structure format and the preset prompt words into a preset artificial intelligence model and outputting the task processing result through the artificial intelligence model, the method further includes:
[0026] Constructing the structure format based on the field information required by the task to be processed; and
[0027] The preset prompt words are constructed based on the processing rules required for the task to be processed and the output format requirements of the task processing results.
[0028] In a second aspect, an embodiment of the present application further provides a game data processing device, the device comprising:
[0029] A receiving and integrating module, used to receive game data generated during the running of the game application, and integrate the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of a virtual character in the game;
[0030] An input module, used to input the input data in the structure format and preset prompt words into a preset artificial intelligence model, and output the task processing result through the artificial intelligence model, wherein the preset prompt words are natural language, used to prompt the artificial intelligence model to process the task included in the natural language, and output the task processing result in a preset output format, and the preset output format includes the structure format;
[0031] A receiving and splitting module, used for receiving the task processing result and splitting the task processing result to obtain the task processing result in the structure format;
[0032] The conversion module is used to convert the task processing result in the structure format into the task processing result in the target format supported during the operation of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0033] Optionally, the input module includes:
[0034] An input submodule, used to input the input data in the structure format and the preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and the preset output format;
[0035] The reasoning submodule is used to prompt the artificial intelligence model to reason the input data in the structure format according to the preset task processing rules through the preset prompt words to obtain task processing results in multiple data formats;
[0036] The output submodule is used to prompt the artificial intelligence model to add label information and output the task processing results that are consistent with the preset output format through the preset prompt words.
[0037] In a third aspect, an embodiment of the present application further provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;
[0038] Memory, used to store computer programs;
[0039] The processor is used to implement the steps of the game data processing method described in any one of the first aspects when executing the program stored in the memory.
[0040] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the game data processing method described in any one of the first aspects are implemented.
[0041] The above-mentioned technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application receives the game data generated during the operation of the game application, and integrates the game data in a structure format to obtain input data in a structure format, wherein the game data includes status information data and behavior data of the virtual character in the game; the input data in the structure format and the preset prompt words are input into a preset artificial intelligence model, and the task processing result is output through the artificial intelligence model, wherein the preset prompt words are natural language, which are used to prompt the artificial intelligence model to process the task included in the natural language, and output the task processing result in a preset output format, and the preset output format includes the structure format; the task processing result is received, and the task processing result is split to obtain the task processing result in the structure format; the task processing result in the structure format is converted into a task processing result in a target format supported during the operation of the game application, so that the game application generates a game performance corresponding to the task processing result. Through the above method, different types of game data can be input into the artificial intelligence model in a structure format, so that the artificial intelligence model can better understand the meaning of each game data without adding labels to different game data. This not only reduces the understanding and processing burden of the artificial intelligence model, but also improves the interaction efficiency between the artificial intelligence model and the game application. In addition, the output format of the task processing results output from the artificial intelligence model is standardized by presetting prompt words, which facilitates the subsequent splitting and conversion of the task processing results, thereby replacing the more cumbersome splitting method using string matching, thereby further improving the interaction efficiency between the artificial intelligence model and the game application. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0044] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0045] Figure 1A flowchart of a method for processing game data provided by an embodiment of the present application;
[0046] Figure 2 A flowchart of another method for processing game data provided by an embodiment of the present application;
[0047] Figure 3 A schematic diagram of the structure of a game data processing device provided in an embodiment of the present application;
[0048] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0050] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0051] In order to solve the technical problem in the prior art that the game data processing method results in low interaction efficiency between AI models and game applications, the present application provides a game data processing method, device, electronic device and storage medium, which can improve the interaction efficiency between AI models and game applications.
[0052] See also Figure 1 , Figure 1 A flowchart of a method for processing game data provided in an embodiment of the present application.
[0053] like Figure 1 As shown, the game data processing method may include the following steps:
[0054] Step 101: Receive game data generated during the running of the game application, and integrate the game data in a structure format to obtain input data in a structure format, wherein the game data includes status information data and behavior data of a virtual character in the game.
[0055] Specifically, the game application can be any stand-alone game, networked game or online game client, which is used to interact with game players to realize the performance of game logic. It can be a simulated business game client, or a game client with simulated business gameplay, etc. The game client type and game gameplay type are not specifically limited here. The game data includes the state information data and behavior data of the virtual character generated during the operation of the game application. The state information data here is used to characterize the relevant data of the current state of the virtual character, including but not limited to the equipment currently worn, attack power, defense power, blood volume and other data. The behavior data here is used to characterize the relevant data of the current behavior of the virtual character, including but not limited to defense, offense and other data. The above structure format refers to a structured format such as JS key-value pair data (JavaScript Object Notation, referred to as JSON), Hypertext Markup Language (Hyper Text MarkupLanguage, referred to as HTML).
[0056] In this step, the game data generated during the operation of the game application can be received in real time or at a fixed time, and when the game application triggers a certain game task, the received game data is integrated according to the structure format to obtain input data in the structure format, and then the input data in the structure format is input into the artificial intelligence model corresponding to the game task for analysis and processing. It should be noted that the input data in the structure format can put multiple different types of game data in one structure, and the position of each game data in the structure can be set according to the association relationship between the game data.
[0057] Step 102: input the input data in the structure format and the preset prompt words into the preset artificial intelligence model, and output the task processing results through the artificial intelligence model, wherein the preset prompt words are natural language, which are used to prompt the artificial intelligence model to process the tasks included in the natural language, and output the task processing results according to the preset output format, and the preset output format includes the structure format.
[0058] Specifically, the preset prompt words are the pre-set prompts. The prompts here are inputs provided to a generative artificial intelligence model (such as ChatGPT, etc.) to guide and inspire the artificial intelligence model to generate specific responses or content. Based on the provided prompts, the artificial intelligence model will combine its training data and built-in algorithms to generate corresponding answers, details or other relevant information.
[0059] In this step, the task processing rules corresponding to the game task can be determined first according to the game task, and then the output format of the task processing rules and the task processing results can be preset in the preset prompt words. After the input data in the structure format is obtained, the input data in the structure format and the preset prompt words can be input into the preset artificial intelligence model. At this time, the artificial intelligence model can perform task processing according to the input data in the structure format and the preset prompt words, obtain the task processing results, and output the task processing results according to the preset output format. For example, when the preset output format includes natural language format and structure format, the artificial intelligence model will output the task processing results in natural language format and structure format.
[0060] Step 103: Receive the task processing result, and split the task processing result to obtain the task processing result in a structure format.
[0061] In this step, after receiving the task processing results output by the artificial intelligence model, the task processing results can be split according to the type of preset output format, or split according to the output time sequence of the task processing results, or split in other ways, so as to obtain the task processing results in a structure format. It should be noted that the task processing results in the structure format contain the data required for the subsequent game application, so there is no need to process the task processing results in other formats here, and only the task processing results in the structure format need to be processed later.
[0062] Step 104: Convert the task processing result in the structure format into a task processing result in the target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0063] In this step, a preset conversion function can be used to convert the task processing result in the structure format into the task processing result in the target format, and then the task processing result in the target format is transmitted to the game application, and the game application performs logical processing according to the task processing result to generate the game performance corresponding to the task processing result. For example, the game application is a turn-based game, and the triggered game task is to calculate which virtual character of our side will go into battle in this battle, and the game data related to the known enemy includes {name: "enemy1", atk: 10, HP: 10, type: "fire"}, and the game data related to our side includes {name: "NPC1", atk: 10, HP: 100, type: "fire"} {name: "NPC2", atk: 1, HP: 100, type: "water"}, and the task processing rules are turn-based, with attribute restraint, water restrains fire, and only one character can go into battle. At this time, the artificial intelligence model can first analyze the values and attributes of the enemy and our characters, and then analyze the best character NPC2 according to the task processing rules, and output the task processing results of {name: "NPC2", atk: 1, HP: 100, type: "water"} and other formats. Then, the task processing results in the structure format corresponding to {name: "NPC2", atk: 1, HP: 100, type: "water"} are separated from the task processing results, and converted into the task processing results in the target format supported during the running of the game application. Finally, the game application selects the NPC2 character to fight against the enemy character.
[0064] For another example, in a massively multiplayer online role-playing game (MMORPG) with a simulated business gameplay, there are usually multiple intelligent non-player characters (NPCs) in the area provided. When multiple intelligent NPCs have a dialogue or a virtual character controlled by a player has a dialogue with an NPC, the game application can first analyze the game data of the members of the communication participants, which may include: attribute values, status values, character settings, game memory learned in the game application, etc. Then, these game data are integrated in a structure format, and the input data in the structure format is input into the artificial intelligence model. The artificial intelligence model then analyzes the plot direction, dialogue direction, output dialogue content or task processing results corresponding to the behavior control instructions according to the task processing rules, and outputs these task processing results to the game application in a preset output format, so that the NPC performs the corresponding dialogue or behavior in the game application.
[0065] In this embodiment, different types of game data can be input into the artificial intelligence model in a structure format, so that the artificial intelligence model can better understand the meaning of each game data without adding labels to different game data. This not only reduces the understanding and processing burden of the artificial intelligence model, but also improves the interaction efficiency between the artificial intelligence model and the game application. In addition, the output format of the task processing results output from the artificial intelligence model is standardized by presetting prompt words, which facilitates the subsequent splitting and conversion of the task processing results, thereby replacing the more cumbersome splitting method using string matching, thereby further improving the interaction efficiency between the artificial intelligence model and the game application.
[0066] Furthermore, the above step 102, inputting the input data in the structure format and the preset prompt words into the preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, specifically includes:
[0067] Inputting the input data in the structure format and the preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and preset output formats;
[0068] By using preset prompt words, the artificial intelligence model is prompted to infer the input data in the structure format according to the preset task processing rules, and the task processing results in various data formats are obtained;
[0069] By presetting prompt words, the artificial intelligence model is prompted to add label information and output the task processing results that conform to the preset output format.
[0070] Specifically, the preset task processing rules refer to the task processing rules pre-set in the prompt words for prompting the artificial intelligence model to process a certain game task. The preset output format refers to the task processing results pre-set in the prompt words for prompting the artificial intelligence model to output the format of the task processing results. For ease of understanding, continue to explain based on the above example. Assume that the game task triggered by the game application is to calculate which virtual character of our side will go into battle in this battle, and the game data related to the known enemy is {name: "enemy1", atk: 10, HP: 10, type: "fire"}, and the game data related to our side is {name: "NPC1", atk: 10, HP: 100, type: "fire"} {name: "NPC2", atk: 1, HP: 100, type: "water"}. At this time, the preset task processing rules in the prompt can be "first analyze the values and attributes of the enemy character, then analyze the values and attributes of our character, the battle rules are turn-based, there are attribute restraints, water restrains fire, and only one character can go on the field", and the preset output format in the prompt can be "output the character on the field in the original format of our character". Of course, in actual application, the prompt can be other natural languages with the same semantics, as long as the artificial intelligence model can understand it.
[0071] In one embodiment, input data in a structure format and preset prompt words can be input into an artificial intelligence model. Since the preset prompt words include preset task processing rules and preset output formats, the preset prompt words can be used to prompt the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules, so as to obtain task processing results in multiple data formats. The preset prompt words can also be used to prompt the artificial intelligence model to add label information and output the task processing results that are consistent with the preset output format.
[0072] In this way, the game data can be organized and classified in a structured format and then input into the artificial intelligence model, making it easier for the artificial intelligence model to understand and reason. The artificial intelligence model can also be standardized to output task processing results in a preset output format, making the output format of the artificial intelligence model more stable and easy to convert into content that can be read by game applications, greatly improving programming efficiency while also improving the interaction efficiency between game applications and artificial intelligence models.
[0073] Furthermore, the preset prompt word also includes attribute information of the preset character string;
[0074] Before the above steps of prompting the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules by using the preset prompt words to obtain the task processing results in multiple data formats, the method further includes:
[0075] By using preset prompt words, the artificial intelligence model is prompted to convert the input data in the structure format according to the attribute information of the preset character string to obtain the converted input data;
[0076] The above steps, through the preset prompt words, prompt the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules, and obtain task processing results in multiple data formats, including:
[0077] Through preset prompt words, the artificial intelligence model is prompted to infer the converted input data according to the preset task processing rules to obtain task processing results in multiple data formats.
[0078] Specifically, the attribute information of the above-mentioned preset character string refers to a natural language for interpreting certain specific character strings (such as enumeration information searched by a game application, abbreviations of certain names, etc.).
[0079] In one embodiment, the attribute information of a preset character string can be configured in a preset prompt word and input into an artificial intelligence model, so that the artificial intelligence model can convert the input data in the input structure format according to the attribute information of the preset character string to obtain the converted input data that is easy for the artificial intelligence model to understand, and then reason the converted input data according to the preset task processing rules to obtain task processing results in multiple data formats, and select the task processing results that match the preset output format from the task processing results in multiple data formats, add label information and output them.
[0080] Because the artificial intelligence model has a stronger understanding of natural language, in this embodiment, string attributes can be established for the game data to explain the meaning of the data, some enumeration information originally used for game application searches can be changed to natural language, and different data fields can be converted into a format that is easy for the artificial intelligence model to understand, thereby facilitating the artificial intelligence model to perform task processing and logical reasoning.
[0081] Furthermore, in the above step 103, the task processing result is split to obtain the task processing result in a structure format, including:
[0082] Obtaining label information carried in the task processing result, wherein the type of the label information corresponds to the type of the preset output format specified in the preset prompt word;
[0083] According to the tag information, the task processing results are split to obtain the task processing results in structure format.
[0084] In one embodiment, the artificial intelligence model can label the task processing results according to the output format of the task processing results. For example, if the task processing results are in natural language format, the label information of "natural language" is marked, and if the task processing results are in structure format, the label information of "structure" is marked, etc. In practical applications, the label information can be in any other form as long as it can distinguish different output formats. After the artificial intelligence model inputs the task processing results, it can obtain the label information carried in the task processing results, and then split the task processing results according to the label information to obtain the task processing results in structure format and the task processing results in other formats.
[0085] In this way, the splitting can be achieved by simply setting different label information for the task processing results according to the type of preset output format. Compared with the splitting method using string matching in the prior art, the method in this implementation does not need to write splitting logic for the output results of each artificial intelligence model separately, which improves the efficiency and scalability of game development. At the same time, it also makes the output structure more stable and greatly enhances the logic of the output results.
[0086] Furthermore, the above step 101, integrating the game data in a structure format to obtain input data in a structure format, includes:
[0087] Extract multiple field information associated with the tasks to be processed from the game data;
[0088] Multiple field information are integrated according to the structure format to obtain input data in the structure format, wherein the field information in the input data in the structure format is combined according to the association relationship between the multiple field information, and the field information in the input data in the structure format is named in a way that is easy for the artificial intelligence model to understand.
[0089] In one embodiment, since a large amount of game data needs to be input for each game task processing, structuring the game data can improve the artificial intelligence model's ability to understand the data content, so that when a large amount of data is input, the artificial intelligence model still maintains the correct understanding and reasonable output of the requirements and rules; and the stable structure format input also makes it faster and more efficient when splicing the input data, and has great convenience in use. Therefore, in this embodiment, when the game data input to the artificial intelligence model is integrated, multiple field information that is associated with the task to be processed can be extracted from the game data, and then the multiple field information is integrated according to the association between the multiple field information in the structure format to obtain the input data in the structure format. For example, when the artificial intelligence model is required to analyze the virtual character and the equipment it wears, the equipment information of the virtual character can be used as a substructure of the character information of the virtual character, which is more conducive to the understanding of the artificial intelligence model. For another example, in the above example, there are multiple characters on our side, and each character on our side includes different data and attributes. At this time, the data and attributes of each character on our side can be used as a substructure under the character information of our character, as shown in the following code:
[0090]
[0091]
[0092] Among them, one {} represents a structure. In the input data of this structure format, there are 2 substructures of NPC and 1 substructure of enemy.
[0093] Through the above method, game data can be converted into structured data that is easy for artificial intelligence models to understand. Compared with the existing technology, there is no need to set different labels for different game data, which reduces the understanding and processing burden of artificial intelligence models and improves the interaction efficiency between game applications and artificial intelligence models.
[0094] Furthermore, in the above step 102, inputting the input data in the structure format and the preset prompt words into the preset artificial intelligence model, and before outputting the task processing result through the artificial intelligence model, the method also includes:
[0095] Constructing a structure format based on the field information required by the task to be processed; and,
[0096] Construct preset prompt words based on the processing rules required for the task to be processed and the output format requirements of the task processing results.
[0097] In one embodiment, before integrating the game data according to the structure format, it is necessary to pre-build the structure format based on the field information required for the task to be processed, and before inputting the preset prompt words into the artificial intelligence model, it is necessary to pre-build the preset prompt words based on the processing rules required for the task to be processed and the output format requirements of the task processing results. In this way, the game data can be processed based on the structure format and the preset prompt words to achieve structured input and output.
[0098] In one embodiment, the game data processing process provided by the embodiment of the present application is as follows: Figure 2 As shown, the specific steps include:
[0099] Step 201: Construct a structure format based on the field information required by the task to be processed.
[0100] Step 202: Construct preset prompt words based on the processing rules required for the task to be processed and the output format requirements of the task processing results.
[0101] Step 203: Receive game data generated during the running of the game application, and integrate the game data according to the structure format to obtain input data in the structure format.
[0102] Step 204: Input the input data in the structure format and the preset prompt words into the artificial intelligence model.
[0103] Step 205: Using a preset prompt word, prompt the artificial intelligence model to convert the input data in the structure format according to the attribute information of the preset character string to obtain the converted input data.
[0104] Step 206: Using preset prompt words, prompt the artificial intelligence model to infer the converted input data according to preset task processing rules to obtain task processing results in multiple data formats.
[0105] Step 207: Using preset prompt words, prompt the artificial intelligence model to add label information to the task processing results that conform to the preset output format and output them.
[0106] Step 208: Receive the task processing result, and split the task processing result to obtain the task processing result in a structure format.
[0107] Step 209: Convert the task processing result in the structure format into a task processing result in the target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0108] It should be noted that the specific implementation process of the above steps 201 to 209 has been described in the above embodiments and will not be repeated here. The execution order of the above steps does not constitute a limitation to this application, and the order of the above steps can be adjusted according to actual conditions.
[0109] In this embodiment, different types of game data can be input into the artificial intelligence model in a structure format, so that the artificial intelligence model can better understand the meaning of each game data without adding labels to different game data. This not only reduces the understanding and processing burden of the artificial intelligence model, but also improves the interaction efficiency between the artificial intelligence model and the game application. In addition, the output format of the task processing results output from the artificial intelligence model is standardized by presetting prompt words, which facilitates the subsequent splitting and conversion of the task processing results, thereby replacing the more cumbersome splitting method using string matching, thereby further improving the interaction efficiency between the artificial intelligence model and the game application.
[0110] See also Figure 3 , Figure 3 A schematic diagram of the structure of a game data processing device provided in an embodiment of the present application.
[0111] like Figure 3 As shown, the device 300 includes:
[0112] The receiving and integrating module 301 is used to receive the game data generated during the operation of the game application, and integrate the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of the virtual character in the game;
[0113] An input module 302, used to input input data in a structure format and preset prompt words into a preset artificial intelligence model, and output a task processing result through the artificial intelligence model, wherein the preset prompt words are natural languages, used to prompt the artificial intelligence model to process the tasks included in the natural languages, and output the task processing result in a preset output format, wherein the preset output format includes a structure format;
[0114] The receiving and splitting module 303 is used to receive the task processing result and split the task processing result to obtain the task processing result in a structure format;
[0115] The conversion module 304 is used to convert the task processing result in the structure format into the task processing result in the target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0116] Furthermore, the input module 302 includes:
[0117] An input submodule, used to input input data in a structure format and preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and preset output formats;
[0118] The reasoning submodule is used to prompt the artificial intelligence model to reason on the input data in the structure format according to the preset task processing rules through preset prompt words, and obtain the task processing results in multiple data formats;
[0119] The output submodule is used to prompt the artificial intelligence model to add label information and output the task processing results that conform to the preset output format through preset prompt words.
[0120] Furthermore, the preset prompt word also includes attribute information of a preset character string; the input module 302 also includes:
[0121] The conversion submodule is used to prompt the artificial intelligence model to convert the input data in the structure format according to the attribute information of the preset character string through the preset prompt word to obtain the converted input data;
[0122] The reasoning submodule is also used to prompt the artificial intelligence model to reason on the converted input data according to preset task processing rules through preset prompt words, and obtain task processing results in multiple data formats.
[0123] Further, the receiving and splitting module 303 includes:
[0124] An acquisition submodule is used to acquire label information carried in the task processing result, wherein the type of the label information corresponds to the type of the preset output format specified in the preset prompt word;
[0125] The splitting submodule is used to split the task processing results according to the label information to obtain the task processing results in the structure format.
[0126] Furthermore, the receiving and integrating module 301 includes:
[0127] An extraction submodule, used to extract multiple field information associated with the task to be processed from the game data;
[0128] The integration submodule is used to integrate multiple field information according to the structure format to obtain input data in the structure format, wherein the field information in the input data in the structure format is combined according to the association relationship between the multiple field information, and the naming method of the field information in the input data in the structure format is a naming method that is easy for the artificial intelligence model to understand.
[0129] Furthermore, the device 300 also includes:
[0130] A first building module is used to build a structure format based on field information required by the task to be processed; and
[0131] The second construction module is used to construct preset prompt words based on the processing rules required for the task to be processed and the output format requirements of the task processing results.
[0132] It should be noted that the device 300 can implement the steps of the game data processing method provided by any of the aforementioned method embodiments and can achieve the same technical effects, which will not be described one by one here.
[0133] like Figure 4 As shown, the embodiment of the present application further provides an electronic device, including a processor 411, a communication interface 412, a memory 413 and a communication bus 414, wherein the processor 411, the communication interface 412, and the memory 413 communicate with each other through the communication bus 414.
[0134] Memory 413, used for storing computer programs;
[0135] In one embodiment of the present application, the processor 411 is used to implement the game data processing method provided by any one of the aforementioned method embodiments when executing the program stored in the memory 413, including:
[0136] Receive game data generated during the running of the game application, and integrate the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of a virtual character in the game;
[0137] Inputting the input data in the structure format and the preset prompt words into the preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, wherein the preset prompt words are natural language, used to prompt the artificial intelligence model to process the task included in the natural language, and outputting the task processing result according to the preset output format, and the preset output format includes the structure format;
[0138] Receive the task processing results, split the task processing results, and obtain the task processing results in structure format;
[0139] The task processing result in the structure format is converted into a task processing result in a target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
[0140] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the game data processing method provided in any of the aforementioned method embodiments are implemented.
[0141] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0143] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0144] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for processing game data, characterized in that: The method comprises: Receiving game data generated during the running of the game application, and integrating the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of a virtual character in the game; Inputting the input data in the structure format and the preset prompt words into a preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, wherein the preset prompt words are natural language, used to prompt the artificial intelligence model to process the task included in the natural language, and outputting the task processing result in a preset output format, and the preset output format includes the structure format; Receive the task processing result, and split the task processing result to obtain the task processing result in the structure format; The task processing result in the structure format is converted into a task processing result in a target format supported during the running of the game application, so that the game application generates a game performance corresponding to the task processing result.
2. The method according to claim 1, characterized in that The step of inputting the input data in the structure format and the preset prompt words into a preset artificial intelligence model, and outputting the task processing result through the artificial intelligence model, includes: Inputting the input data in the structure format and the preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and the preset output format; Through the preset prompt words, the artificial intelligence model is prompted to infer the input data in the structure format according to the preset task processing rules to obtain task processing results in multiple data formats; Through the preset prompt word, the artificial intelligence model is prompted to add label information and output the task processing results that conform to the preset output format.
3. The method according to claim 2, characterized in that The preset prompt word also includes attribute information of the preset character string; Before prompting the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules through the preset prompt words to obtain task processing results in multiple data formats, the method also includes: By using the preset prompt word, the artificial intelligence model is prompted to convert the input data in the structure format according to the attribute information of the preset character string to obtain the converted input data; The preset prompt word prompts the artificial intelligence model to infer the input data in the structure format according to the preset task processing rules to obtain task processing results in multiple data formats, including: Through the preset prompt words, the artificial intelligence model is prompted to infer the converted input data according to the preset task processing rules to obtain task processing results in multiple data formats.
4. The method according to claim 2, characterized in that: The step of splitting the task processing result to obtain the task processing result in the structure format includes: Acquire the label information carried in the task processing result, wherein the type of the label information corresponds to the type of the preset output format specified in the preset prompt word; The task processing result is split according to the tag information to obtain the task processing result in the structure format.
5. The method according to claim 1, characterized in that The step of integrating the game data in a structure format to obtain input data in a structure format includes: Extracting a plurality of field information associated with the task to be processed from the game data; The multiple field information are integrated according to the structure format to obtain input data in the structure format, wherein the field information in the input data in the structure format is combined according to the association relationship between the multiple field information, and the field information in the input data in the structure format is named in a way that is easy for the artificial intelligence model to understand.
6. The method according to claim 5, characterized in that Before inputting the input data in the structure format and the preset prompt words into the preset artificial intelligence model and outputting the task processing result through the artificial intelligence model, the method further includes: Constructing the structure format based on the field information required by the task to be processed; and The preset prompt words are constructed based on the processing rules required for the task to be processed and the output format requirements of the task processing results.
7. A game data processing device, characterized in that: The device comprises: A receiving and integrating module, used to receive game data generated during the running of the game application, and integrate the game data in a structure format to obtain input data in a structure format, wherein the game data includes state information data and behavior data of a virtual character in the game; An input module, used to input the input data in the structure format and preset prompt words into a preset artificial intelligence model, and output the task processing result through the artificial intelligence model, wherein the preset prompt words are natural language, used to prompt the artificial intelligence model to process the task included in the natural language, and output the task processing result in a preset output format, and the preset output format includes the structure format; A receiving and splitting module, used for receiving the task processing result and splitting the task processing result to obtain the task processing result in the structure format; The conversion module is used to convert the task processing result in the structure format into the task processing result in the target format supported during the operation of the game application, so that the game application generates a game performance corresponding to the task processing result.
8. The device according to claim 7, characterized in that The input module comprises: An input submodule, used to input the input data in the structure format and the preset prompt words into the artificial intelligence model, wherein the preset prompt words include preset task processing rules and the preset output format; The reasoning submodule is used to prompt the artificial intelligence model to reason the input data in the structure format according to the preset task processing rules through the preset prompt words to obtain task processing results in multiple data formats; The output submodule is used to prompt the artificial intelligence model to add label information and output the task processing results that are consistent with the preset output format through the preset prompt words.
9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the game data processing method described in any one of claims 1-6 when executing the program stored in the memory.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the game data processing method according to any one of claims 1 to 6 are implemented.