A game value generation and verification method, device and system

Abstract

The application relates to a game value generation and verification method, device and system, which acquires user input information, judges an intention, and identifies the operation intention of the user; determines a target work flow based on the operation intention and executes the target work flow; performs executability verification on game value data obtained after the target work flow is executed; executes simulation by using the verified game value data after the verification is passed, and outputs a simulation result; the device comprises an intention judgment module, a work flow execution module, a verification module and a simulation module; and the system is realized based on the method. The application significantly reduces the professional threshold of game value design, shortens the development cycle, reduces the error risk caused by manual conversion, has intelligent balancing and optimizing capabilities, improves the naturalness and convenience of human-computer interaction, and has good universality and long-term application value.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing, and in particular to a method, apparatus and system for generating and verifying game numerical values. Background Technology

[0002] In the field of video game development, the design and balancing of game numerical systems are crucial factors determining a game's playability, replayability, and commercial success. Traditional game numerical design relies on the personal experience of professional numerical designers. This is especially true for combat games, which require manually configuring game attribute systems, combat formulas, growth curves, and monster stats. This process typically begins with designers creating a configuration based on the game's core gameplay, world-building, and expected experience. After completing the configuration, significant effort is often required for manual table filling, configuration, and repeated calculations to verify the balance between numerical values, ultimately resulting in a complete numerical configuration table.

[0003] This traditional design pattern has many insurmountable technical drawbacks. In addition to being highly dependent on manual processes and inefficient, making it prone to human error, it also presents difficulties in balancing and optimizing, and lacks a global perspective. It is difficult to predict and evaluate the impact of a single modification on the overall balance from a global perspective, thus increasing the workload of repeated testing and iteration.

[0004] Currently, there are also some spreadsheet software or dedicated calculators on the market that can assist in simple numerical calculations or formula derivations. However, these tools are mostly auxiliary calculations or local optimizations, lacking end-to-end automated generation and simulation verification capabilities, making it difficult to achieve automated construction and optimization of multi-system coordination and multi-parameter balance. Summary of the Invention

[0005] This invention solves the problems existing in the prior art and provides a method, apparatus and system for generating and verifying game values.

[0006] The technical solution adopted in this invention is a method for generating and verifying game values, which involves acquiring user input information, judging its intent, identifying the user's operational intent, determining the target workflow based on the operational intent, and executing it. Perform executability verification on the game numerical data obtained after executing the target workflow; Once the verification is successful, the game numerical data that has been verified is used to perform a simulation, and the simulation results are output.

[0007] Preferably, the target workflow is extracted from multiple candidate workflows, including at least: The first workflow is used to generate a new game numerical system based on user input information; The second workflow is used to update the generated game numerical data based on user input information.

[0008] Preferably, the first workflow uses a pre-trained artificial intelligence model to analyze user input information and extract game design features; Based on game design features, executable numerical code is generated through a preset numerical engine.

[0009] Preferably, the preset numerical engine includes: The unary parameter layer is used to define and manage the uniqueness and standardization of all basic attribute parameters; A macro command library is used to store logic judgment code modules; the logic judgment code modules include pre-encapsulated general logic judgment code, as well as macro commands dynamically generated by an artificial intelligence model based on user input information; A computation layer is used to implement the calculation relationships between various attributes and the nested calls of the corresponding game formulas; An output layer is used to bind the attributes and formulas calculated by the computation layer to a preset instance object and generate structured executable numerical code.

[0010] Preferably, the second workflow parses the modification object and corresponding modification content indicated in the user input information, and adjusts the game value data corresponding to the modification object according to the modification content.

[0011] Preferably, the object to be modified includes one or more of the following: the value of a basic attribute parameter, a game formula, or the number of game systems.

[0012] Preferably, the executability verification of the game numerical data obtained after executing the target workflow includes: Verify that the basic attribute parameters called in the game's numerical data have unique and valid definitions; Verify that the enemy attributes called in the game's numerical data are correctly identified; Verify whether the logic judgment module called in the game's numerical data exists in the preset macro command library; Verify whether the game formulas defined by the game's numerical data conform to the preset logical rules.

[0013] Preferably, the game numerical data is used to perform execution simulation, instantiate game units, load game numerical data for game units, automatically execute multiple rounds or multiple game cycles according to the preset game execution method, and record key data in the process; Based on the recorded key data, visual analysis charts are generated to characterize numerical balance.

[0014] A device for generating and verifying game numerical values, comprising: The intent determination module is used to respond to received user input information, determine the intent of the user input information, and identify the user's operation intent. The workflow execution module is used to determine the corresponding target workflow from multiple preset workflows and execute it based on the identified operation intent; The verification module is used to verify the executability of the game numerical data obtained after executing the target workflow; The simulation module is used to perform simulations using the verified game numerical data after successful verification, and output the simulation results.

[0015] A system for generating and verifying game values ​​includes a processor and a memory; the memory is used to store program code and transmit the program code to the processor. The processor is used to execute the game value generation and verification method according to the instructions in the program code.

[0016] This invention relates to a method, apparatus, and system for generating and verifying game numerical values. The method acquires user input information, determines its intent, and identifies the user's operational intent; based on the operational intent, it determines and executes a target workflow; it verifies the executability of the game numerical data obtained after executing the target workflow; after successful verification, it uses the verified game numerical data to perform an execution simulation and outputs the simulation results; the apparatus includes an intent determination module, a workflow execution module, a verification module, and a simulation module; and the system is implemented based on the method.

[0017] The beneficial effects of this invention are as follows: (1) By introducing artificial intelligence models to understand user input intent and extract features, non-professional users can automatically generate a complete, self-consistent, and professional game numerical system simply by inputting natural language descriptions or reference images, which significantly reduces the professional threshold for game numerical design. (2) Construct an end-to-end automated pipeline. Starting from user input, the pipeline is divided into different workflows after intent judgment. From system design, formula generation, numerical construction to simulation verification, the entire link does not require manual coding, realizing full-process automation from design to verification, significantly shortening the development cycle and reducing the risk of errors caused by manual conversion. (3) By automatically conducting large-scale, multi-round battle simulations after generating numerical codes, and adjusting attributes, balancing difficulty, and optimizing battle rhythm based on simulation data, it provides an objective quantitative evaluation basis for numerical balance and has intelligent balance optimization capabilities. (4) It is compatible with multimodal input of text and / or images. Users can describe their design intent in text or upload reference images. The flexible input method better adapts to the usage habits of different users and the diverse design scenario requirements, further reducing the threshold for use and improving the naturalness and convenience of human-computer interaction. (5) The built-in meta-parameter layer, macro command library, formula template library and system rule library involved in the system are all designed as scalable architectures. Developers can adjust or add or remove them according to their own needs, so that the system can better adapt to the numerical design needs of different game types and has good versatility and long-term application value. Attached Figure Description

[0018] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a flowchart illustrating the implementation process of the present invention; Figure 3 This is a schematic diagram of the device structure of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] This invention relates to a method for generating and verifying game numerical values, comprising the following steps: (1) Obtain user input information, determine its intent, and identify the user's operational intent; (2) Based on the stated operational intent, determine the target workflow and execute it; (3) Verify the executability of the game numerical data obtained after executing the target workflow; (4) After verification, use the verified game numerical data to perform the simulation and output the simulation results.

[0021] The method will be described below with reference to specific embodiments.

[0022] Example 1

[0023] (1) Obtain user input information, determine its intent, and identify the user's operational intent; For example, if a user enters the text "Help me generate an RPG game formula" through the front-end interactive interface of a device or system, the intent recognition engine will analyze the input and identify the operation intent as "system Design", that is, to create a new system.

[0024] (2) Based on the stated operational intent, determine the target workflow and execute it; The target workflow is extracted from multiple candidate workflows, including at least: The first workflow is used to generate a new game numerical system based on user input information; The second workflow is used to update the generated game numerical data based on user input information.

[0025] In this embodiment, based on the operational intent, this falls under the category of the first workflow; The first workflow uses a pre-trained artificial intelligence model to analyze user input information and extract game design features; Based on game design features, executable numerical code is generated through a preset numerical engine.

[0026] In this embodiment, the intent recognition engine has determined that the current operation intent is "create a new system". At this time, the first workflow is triggered, and the game system generation engine (based on a large language model or multimodal model) performs in-depth analysis on the input content and extracts the game design features corresponding to the following type rules, including: The system rules set the game's formulas, specifying whether they are subtraction, multiplication, or other types of formulas. Taking a combat game as an example, the rule for a subtraction formula is attack - enemy defense, and the rule for a multiplication formula is attack * (parameter / enemy defense + parameter). Other rules include attack * parameter. The rules are not limited to the types set internally and are compatible with publicly available game formulas on the web. The combat formulas call internally set game attributes such as health, attack, defense, hit rate, and critical hit rate, while also being compatible with attribute names based on publicly available web pages. The logical judgment rules for formula calls, taking combat games as an example, include hit judgment, critical hit judgment, block judgment, and internally defined logical hit judgment, which judges the difference between our hit value and the enemy's evasion value. This difference is compared with a random number between 0 and 1. If the difference between hit and enemy evasion is a random number between 0 and 1, the system outputs 1 if it hits and 0 if it misses. Critical hit judgment and block judgment are similar, and they are all called according to internally set rules. When the game combat formula generated by the basic AI agent has a hit or critical hit judgment, it will call the internally defined judgment rules. Class rules, such as setting high defense, high health, and high survivability for warriors, will be set to give warriors higher attribute growth parameters in health and defense when generating internal values. Other classes, such as mages and assassins, will be set to have similar class-specific attribute parameters to reflect their class characteristics. Growth formula type rules include designing linear growth formulas, exponential growth formulas, logarithmic growth formulas, square root growth functions, probabilistic composite growth formulas, piecewise function growth formulas, etc.; formula type rules, such as the piecewise function growth formula is "when level ≤ N, attribute value = parameter 1 × level, otherwise attribute value = parameter 2 × level + C", where C is a preset parameter; Each game system has its own attribute bonus rules. System bonuses are applied through addition and multiplication, and attribute growth rules are set, such as "Total Attack = Equipment Attack + Level Growth Attack + Pet Bonus Attack", "Equipment Attack = Equipment Base Attack + Equipment Growth Attack * Equipment Level * Equipment Quality Coefficient", "Level Growth Attack = Level Growth Parameter * Level * Class Parameter", "Pet Bonus Attack = Pet Level * Bonus Parameter", etc. In the growth formula level cap setting and round design, the level cap is the highest level that can be reached by leveling up in the game. All formulas and attributes cannot exceed this level. By limiting the value of this level, the upper limit of formulas and values ​​is constrained. The round setting is set for both sides. It is the record value used from the start of the game until one side loses. This record value can be time or the number of attacks by a certain side. The unit of output round is determined by the internally set logic.

[0027] Based on the generated system and formula rules, as well as custom numerical specifications, a numerical engine (a tool for simulation and transformation) identifies underlying parameter rules, calculation rules, and code execution rules to generate executable numerical code, preferably in JSON format, including meta-parameters, macros, computation layers, and tables. Specifically, the numerical engine collaborates with a pre-trained artificial intelligence model. As the underlying implementation tool, the numerical engine receives game design features from the pre-trained AI model and converts them into structured, executable numerical code. The interface between the two uses a standardized data format (such as JSON) to ensure that the AI-generated content can be accurately parsed by the numerical engine.

[0028] The preset numerical engine includes: The unary parameter layer is used to define and manage the uniqueness and standardization of all basic attribute parameters. The standardization includes non-zero values, no undefined numbers, and the requirement to set the Chinese and English names for each meta-parameter. The Chinese name is used for interface display, and the English name is used for formula calculation. A macro command library is used to store logic judgment code modules. These logic judgment code modules include pre-encapsulated general logic judgment code and macro commands dynamically generated by an artificial intelligence model based on user input information. The encapsulated macro code includes, but is not limited to, general custom hit judgment, critical hit judgment, parry judgment, attribute restraint, maximum / minimum value, exponential / logarithmic functions, etc. This code can be executed in the self-developed numerical engine and strictly follows the internal engine calling format. It should be noted that although the numerical engine is preset, the content stored inside it is not completely fixed. The macro command library, as a code container, can dynamically store AI-generated macro commands to ensure the flexibility of the overall operation.

[0029] The first layer is used to realize the calculation relationship between various attributes and the nested call of the corresponding game formulas, realizing the calculation of game formulas, growth formulas, and attributes. Taking a combat game as an example, it can be set as "Character growth life attribute = growth life parameter * level parameter * class parameter" and "Combat formula = (attack - defense) * hit judgment * critical hit judgment". It also supports setting attribute identifiers for formulas and attributes, formula nesting, and parameter calls. By setting attribute identifiers, it can be distinguished whether the attribute is called from the enemy's attribute. For example, if attack - defense is the enemy's attribute, then an identifier needs to be set for the defense attribute. An output layer is used to bind the attributes and formulas calculated by the calculation layer to a preset instance object and generate structured executable numerical code. In specific implementation, by providing AI-generated code logic, code such as hit judgment, critical hit judgment, and block judgment is generated. The code can be executed in the numerical engine and strictly follows the internal engine calling format.

[0030] In fact, in addition to the above, it also includes: The table structure serves as the data storage medium, supporting the import and export of complex segmented growth, attribute tables, and numerical tables. For example, when the growth rule is a segmented function, the segmentation points and corresponding coefficients can be stored in a table format. When multiple professions or multiple level ranges of attribute values ​​are involved, the attribute table can provide efficient batch data management capabilities. The table data is included in the JSON code during output for subsequent reading by the simulation engine.

[0031] Folder structure: Meta-parameters and computation layers are stored according to system categories for easy management and retrieval; Formula and property output structure: used to bind the designed formulas and properties to the instance objects. The instance is either a friendly (protagonist) instance or an enemy (monster) instance. Multiple instances can be generated at the same time, but at least one friendly instance and one enemy instance must be generated for the two sides to fight. View and modify instance parameters and formulas, create instance assignment rules, set instance health, combat formulas, etc., and combine the created formulas and attribute parameters to allow the large model to assign formulas and parameters to instances based on the above structure, generate instance attributes and combat formulas, such as setting the combat formula of our instance (the combat formula set through the calculation layer), setting the health of our instance to the total health (the total health set through the calculation layer), etc. The battle modes can be set, such as turn-based battle mode and free battle mode. In turn-based battle mode, the enemy attacks once for each turn, and there is a set number of turns. When there are multiple battle instances on our side, all our units attack once and all enemy units attack once, which counts as one turn. In free battle mode, the two sides fight based on the distance between them, and there is no concept of turns. The battle ends when all combat units on one side are killed. By combining the above underlying rules with the formulas, parameters, and attributes extracted by the generated system, a formula format that the engine can use is formed. Through the code logic embedded in the engine, JSON format code that the engine can execute is generated. That is, the generated JSON code can be directly parsed, and the meta-parameters, macro commands, operation layer rules, and table data in the JSON can be read, object units can be instantiated and executed, realizing the decoupling of numerical definition and game execution, so that the adjustment of the numerical system does not require modification of the simulation engine code.

[0032] (3) Verify the executability of the game numerical data obtained after executing the target workflow; Specifically, including: Verify that the basic attribute parameters called in the game's numerical data have unique and valid definitions; Verify that the enemy attributes called in the game's numerical data are correctly identified; Verify whether the logic judgment module called in the game's numerical data exists in the preset macro command library; Verify whether the game formulas defined by the game's numerical data conform to the preset logical rules.

[0033] Specifically, the executability verification involves validating the generated JSON code. For example, it simulates battles at levels 1, 10, 30, and 50, checking whether the number of battle rounds is within a preset reasonable range (e.g., 8-15 rounds). If the number of rounds is found to be too short or too long at certain levels, it may mean that the attribute growth curve is unreasonable or the formula has defects. If undefined parameters or macro commands are found to be called, errors are automatically marked. If a problem is found during verification, a regeneration mechanism is triggered. For example, if it is found that the enemy's defense is too high at a certain level, resulting in zero damage, the defense growth coefficient will be automatically adjusted, the JSON code will be regenerated, and verification will be performed again until all checks pass.

[0034] (4) After verification, use the verified game numerical data to perform the simulation and output the simulation results; The game numerical data is used to perform execution simulation, instantiate game units, load game numerical data for game units, automatically execute multiple rounds or multiple game cycles according to the preset game execution method, and record key data in the process; Based on the recorded key data, visual analysis charts are generated to characterize numerical balance.

[0035] In this embodiment, taking a combat game as an example, the game's numerical data is used to simulate combat. At least one friendly combat unit and at least one enemy combat unit are instantiated, and game numerical data is loaded for each combat unit. Finally, line graphs are drawn, such as the curve of remaining health changing with level, the curve of average number of rounds, etc., and complete numerical codes and simulation reports are output. Users can view the reports and initiate new modification commands as needed.

[0036] Example 2

[0037] Based on Example 1, the second workflow parses the modification object and corresponding modification content indicated in the user input information, and adjusts the game value data corresponding to the modification object according to the modification content.

[0038] The objects to be modified include one or more of the following: the numerical values ​​of basic attribute parameters, game formulas, or the number of game systems.

[0039] In this embodiment, after viewing the simulation report, if the user thinks the monster is too difficult, they can enter "The monster is too difficult, reduce the monster's attack power". The user's operation intention is recognized as modifying the game formula or attribute parameters, corresponding to the second workflow. Therefore, the object to be modified is "monster attack power", and the content to be modified is "reduce". The attack attribute value of the monster instance is automatically adjusted, and JSON is regenerated for verification and simulation again until the user is satisfied. Alternatively, after the user receives a simulation report showing 4 game systems, the user can further input "need 6 game systems" or "generate more systems," thus changing the output to generate 6 game systems or obtaining the number of systems and generating more systems than currently available.

[0040] Example 3

[0041] Users can upload a screenshot of a massively multiplayer online role-playing game, or enter the text "Generate MMORPG-style numerical system"; Intent determination: The system identifies the user's intent as "to generate a numerical system for a specified game type based on an image / text" and invokes the first workflow; Multimodal analysis and feature extraction: If the input is an image, the game interface features are extracted to identify the game type as MMORPG, and information such as class icons and attribute panel layout may be captured; if the input is text, the natural language model parses out keywords; combined with the internal knowledge base, the system confirms the core characteristics of the game. The game generation system includes: Combat formula: Damage = (Attack - Defense) * Hit chance * Critical hit chance * (1 + Skill bonus); Class settings: Three typical factions are automatically generated: high physical attack, magic damage, and healing / support. Growth System: Five major systems including equipment generation, cultivation, pets, magic weapons, and mounts; The activation level and attribute ratio of each system are automatically allocated; Generate executable numerical code: The numerical code generation engine converts the above system description into a JSON file, which includes battle formulas, numerical parameters, various system attributes and their proportions, system growth attributes, etc., and also includes the created friendly and enemy instance data, creating a matching battle pool (free battle, turn-based battle). Verify that all parameters in the JSON have been defined at the meta-parameter level, enemy attributes (such as monster defense) have been correctly identified, and the macro commands called are all in the macro command library; The combat simulation engine performs batch simulations: simulating players of different levels battling monsters and recording data; Output data simulation curve (output with level as the x-axis, including curves showing changes in remaining health, attack power, and battle round time).

[0042] Example 4

[0043] Users input the text "Help me generate a value for a billionaire" through the front-end interactive interface of the device or system. The intent recognition engine analyzes the input and identifies the operation intent as "system Design", that is, to create a new system, which belongs to the first workflow category. The first workflow is triggered, and the game system generation engine (based on a large language model or multimodal model) performs in-depth analysis of the input content, extracting the following types of game design features, including: System rules, setting numerical formulas for the game, determining how to acquire resources (such as currency resources), setting currency acquisition formulas, such as base click revenue * number of clicks, while also being compatible with attribute names publicly available on the webpage; Define the rules for the profession (agent), and the basic attributes of an agent are shown in Table 1. Table 1. Basic Attributes of Brokers 1 star 50% 1～5 Low 2 stars 55% 5～20 middle 3 stars 60% 20～100 Medium and high 4 stars 70% 100～500 high 5 stars 80% 500～2000 Extremely high The rules for growth formula types include linear growth formulas, exponential growth formulas, logarithmic growth formulas, square root growth functions, probabilistic composite growth formulas, and piecewise function growth formulas. Formula type rules, such as the piecewise function growth formula being "when level ≤ N, attribute value = parameter 1 × level; otherwise, attribute value = parameter 2 × level + C". The rules for attribute bonuses in each game system are also defined, with system bonuses applied through addition and multiplication, and attribute growth rules set accordingly. AgentIncomePerSec = Base × (1 + Level × StarMultiplier) × AllBoost Among them, Base is the basic production per second of star level, Level is 1 to 50, and the unit is level. StarMultiplier is the star level growth multiplier, which satisfies 5 stars > 4 stars > ... > 1 star. AllBoost is the bonus for 4 skills, office / decoration, global buff, etc.

[0044] Based on the generated system and formula rules and the custom numerical specifications, the numerical engine (a tool for simulation and transformation) identifies the underlying parameter rules, calculation rules and code execution rules, and generates executable numerical code, preferably in JSON format, including meta-parameters, macros, operation layers and tables. Perform executability verification on the game numerical data obtained after executing the target workflow; Execute and record key data to generate visual analysis charts that characterize numerical balance.

[0045] This invention also relates to a device for generating and verifying game values. To better realize its applicability, a front-end interactive interface is set up to support users to input their needs in the form of text and / or images. For example, users can input natural language descriptions through text boxes or upload reference images (such as game screenshots, attribute panels, growth curves, etc.). The front-end interface transmits the received multimodal information to subsequent modules for processing. Subsequent modules include: The intent determination module is used to respond to received user input information, determine the user's intent, and identify the user's operational intention. The intent determination module is built based on a large language model and has built-in multiple intent categories, such as "create a new game value system", "modify an existing game value", "add / delete a game system", etc. The recognition result will determine which workflow to call next.

[0046] The workflow execution module is used to determine and execute the corresponding target workflow from a set of preset workflows based on the identified operational intent; among them, The first workflow (system generation workflow) is used to generate a new game numerical system based on user input information; The second workflow (system modification workflow) is used to modify the generated game numerical data based on user input information; The workflow execution module can further call the numerical engine.

[0047] The verification module is used to verify the executability of game numerical data obtained after executing the target workflow; including whether the basic attribute parameters have unique and valid definitions in the meta-parameter layer, whether enemy attributes are correctly identified, whether the macro commands called exist in the macro command library, whether the formulas conform to the preset logical rules, and whether the AI-generated custom code is executable. If an error is found during verification, a regeneration mechanism is triggered to automatically correct the error and regenerate the numerical code until verification passes.

[0048] The simulation module is used to perform simulations using the verified game numerical data after successful verification, and output the simulation results. The engine instantiates game units and loads game numerical data, such as corresponding attributes and combat rules, for each unit. Taking a combat game as an example, it automatically executes multiple rounds or cycles of combat based on preset combat methods (such as turn-based combat or free combat), and records key data during the combat process, such as damage value, remaining health, number of combat rounds, and victory or defeat. It supports batch simulation (such as setting the number of combats or sampling at different levels) to obtain statistically significant balance indicators. Based on key data recorded in the battle simulation, visual analysis charts are generated, such as the remaining health curve with level as the horizontal axis, the attack power change curve, and the battle round distribution chart, to help users understand the current numerical status and meet the user's need to quickly input modification commands (such as "the monster difficulty is too high") through the front-end interactive interface, triggering a second workflow for targeted adjustments.

[0049] The present invention also relates to a system for generating and verifying game values, including a processor and a memory; the memory is used to store program code and transmit the program code to the processor; The processor is used to execute the game value generation and verification method according to the instructions in the program code.

[0050] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0051] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0055] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for generating and verifying game numerical values, characterized in that: Obtain user input information, determine its intent, and identify the user's intended action. Based on the stated operational intent, determine and execute the target workflow; Perform executability verification on the game numerical data obtained after executing the target workflow; Once the verification is successful, the game numerical data that has been verified is used to perform a simulation, and the simulation results are output.

2. The method for generating and verifying game numerical values ​​according to claim 1, characterized in that: The target workflow is extracted from multiple candidate workflows, including at least: The first workflow is used to generate a new game numerical system based on user input information; The second workflow is used to update the generated game numerical data based on user input information.

3. The method for generating and verifying game numerical values ​​according to claim 2, characterized in that: The first workflow uses a pre-trained artificial intelligence model to analyze user input information and extract game design features; Based on game design features, executable numerical code is generated through a preset numerical engine.

4. The method for generating and verifying game numerical values ​​according to claim 3, characterized in that: The preset numerical engine includes: The unary parameter layer is used to define and manage the uniqueness and standardization of all basic attribute parameters; A macro command library is used to store logic judgment code modules; the logic judgment code modules include pre-encapsulated general logic judgment code, as well as macro commands dynamically generated by an artificial intelligence model based on user input information; A computation layer is used to implement the calculation relationships between various attributes and the nested calls of the corresponding game formulas; An output layer is used to bind the attributes and formulas calculated by the computation layer to a preset instance object and generate structured executable numerical code.

5. The method for generating and verifying game numerical values ​​according to claim 2, characterized in that: The second workflow parses the modification object and corresponding modification content indicated in the user input information, and adjusts the game value data corresponding to the modification object according to the modification content.

6. The method for generating and verifying game numerical values ​​according to claim 5, characterized in that: The objects to be modified include one or more of the following: the numerical values ​​of basic attribute parameters, game formulas, or the number of game systems.

7. The method for generating and verifying game numerical values ​​according to claim 1, characterized in that: Perform executability verification on the game numerical data obtained after executing the target workflow, including: Verify that the basic attribute parameters called in the game's numerical data have unique and valid definitions; Verify that the enemy attributes called in the game's numerical data are correctly identified; Verify whether the logic judgment module called in the game's numerical data exists in the preset macro command library; Verify whether the game formulas defined by the game's numerical data conform to the preset logical rules.

8. The method for generating and verifying game numerical values ​​according to claim 1, characterized in that: The game numerical data is used to perform execution simulation, instantiate game units, load game numerical data for game units, automatically execute multiple rounds or multiple game cycles according to the preset game execution method, and record key data in the process; Based on the recorded key data, visual analysis charts are generated to characterize numerical balance.

9. A device for generating and verifying game numerical values, characterized in that: include: The intent determination module is used to respond to received user input information, determine the intent of the user input information, and identify the user's operation intent. The workflow execution module is used to determine the corresponding target workflow from multiple preset workflows and execute it based on the identified operation intent; The verification module is used to verify the executability of the game numerical data obtained after executing the target workflow; The simulation module is used to perform simulations using the verified game numerical data after successful verification, and output the simulation results.

10. A system for generating and verifying game numerical values, characterized in that: It includes a processor and a memory; the memory is used to store program code and transfer the program code to the processor; The processor is used to execute the game value generation and verification method according to any one of claims 1 to 8 according to the instructions in the program code.

Images