System and method for labyrinth game based on Dijkstra algorithm and GAN model

Abstract

The invention belongs to the technical field of Dijkstra algorithms, and discloses a Dijkstra algorithm and GAN model-based labyrinth game system, which consists of a labyrinth generation module, a path search module, a difficulty adjustment module, a personalized experience module, a feedback prompt module and a self-adaptive dynamic scheduling module. The dynamic generation of the maze map is realized by combining the generative adversarial network (GAN) and the Dijkstra algorithm, and the GAN can intelligently generate the maze layout adaptive to the style of the player according to the behavior data, historical performance and preference of the player, so that the repeatability of the map is avoided, the map can be dynamically adjusted according to the response of the player, the freshness and diversity are provided, and the user experience is improved. Meanwhile, through an intelligent difficulty adjusting mechanism, the performance of players is monitored and analyzed in real time, the difficulty of the maze is automatically adjusted, a Dijkstra algorithm is used for searching and optimizing a maze path in real time, and the Dijkstra algorithm can find the shortest path from the starting point to the end point in the maze.

Description

Technical Field

[0001] The present invention belongs to the technical field of Dijkstra algorithm, and specifically relates to a system and method based on Dijkstra algorithm and GAN model maze game. Background Art

[0002] As a classic puzzle game, maze games have a long history and a rich player base. Traditional maze games usually use fixed map designs and difficulty levels, and the player experience is often limited by these fixed patterns. With the development of game technology, especially the advancement of artificial intelligence technology, the design of maze games has gradually shown more room for innovation.

[0003] However, in traditional maze games, the level and map designs are often preset and fixed, which to some extent limits the diversity of the game and the long-term interest of players. When players play repeatedly, they easily feel fatigued and lack freshness and challenge due to the unchanging map and level layout. This preset game mode is difficult to satisfy players' pursuit of novel experiences and continuous self-breakthrough, which limits the appeal and continued appeal of maze games, so it needs to be improved and optimized. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for a maze game based on the Dijkstra algorithm and the GAN model to solve the problems raised in the above background technology.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a system based on Dijkstra algorithm and GAN model maze game, the system is composed of: a maze generation module, a path search module, a difficulty adjustment module, a personalized experience module, a feedback prompt module and an adaptive dynamic scheduling module;

[0006] Adaptive dynamic scheduling module: As the core linkage part of maze generation and path search, this module collects players' behavior data in real time when they are playing the game, dynamically adjusts the maze generation logic, and optimizes the path guidance strategy, thus forming an intelligent and personalized maze game ecosystem, realizing real-time feedback and continuous optimization of the game.

[0007] Preferably, the maze generation module: uses the Dijkstra algorithm to construct a path search basis, combines the adversarial network model to intelligently generate a maze map, and dynamically adjusts the maze difficulty according to the player's game performance to achieve adaptive game challenges;

[0008] Path search module: Use Dijkstra algorithm to search for the shortest path for players in the maze and give optimized route selection suggestions;

[0009] Difficulty adjustment module: dynamically adjust the difficulty of the maze according to the player's skill proficiency and the current stage of the game to keep the game moderately challenging at all times;

[0010] Personalized experience module: Analyze players’ behavior patterns and preferences, and customize personalized maze elements to enhance the game’s sense of involvement and immersion;

[0011] Feedback and prompt module: When players encounter difficulties, the system can intelligently provide maze clues or path guidance to help players smoothly advance the game process.

[0012] Preferably, the steps of the method are:

[0013] A1, maze map generation, using the GAN model to generate diversified and personalized maze maps;

[0014] A2, path search and guidance, applies Dijkstra algorithm to search for paths and provide players with the shortest path or optimized path selection;

[0015] A3, dynamic difficulty adjustment, real-time adjustment of maze difficulty based on player skill level and game progress;

[0016] A4, integration of personalized elements, analyzing player behavior and preferences, and customizing personalized maze elements for players;

[0017] A5, player feedback and continuous optimization, collect and analyze player feedback, and iteratively optimize maze design, algorithm application and difficulty adjustment.

[0018] Preferably, the process of the maze generation module is:

[0019] B1, input information, enter the player's difficulty level, game history and success rate;

[0020] B2, layout evaluation, the generator analyzes the player data and generates a maze layout, and the discriminator evaluates the generated maze layout;

[0021] B3, Level Adjustment, the discriminator adjusts the generation strategy of the generator according to the player’s level.

[0022] Preferably, the process of the path search module is:

[0023] C1, information input, the player inputs the starting point information and the end point information;

[0024] C2, path calculation, uses the Dijkstra algorithm to determine and output the shortest travel route from the starting point to the end point;

[0025] C3, assists players by displaying path guidance in real time during maze games to assist players in directional navigation.

[0026] Preferably, the process of the difficulty adjustment module is:

[0027] D1, player monitoring, monitors the game progress and game behavior of players;

[0028] D2, difficulty calculation, analyzes the data and calculates the current difficulty of the game;

[0029] D3, difficulty adjustment, automatically adjusts the difficulty parameters of the maze.

[0030] Preferably, the process of the personalized experience module is:

[0031] E1, data collection, collects players’ historical behavior data;

[0032] E2, element customization, generates corresponding personalized maze elements according to player data;

[0033] E3, real-time adjustment, dynamically modify the maze layout during the game process.

[0034] Preferably, the process of the feedback prompt module is:

[0035] F1, detect the stuck position, and perform real-time detection of the player’s stuck position;

[0036] F2, provides guidance, guiding and prompting players according to the structure of path search;

[0037] F3, give feedback, give feedback to players in the maze through graphics and sounds.

[0038] Preferably, the steps of the adaptive dynamic adjustment module are:

[0039] G1, collects and analyzes data, and collects players’ gaming behavior data in real time;

[0040] G2, data interaction and feedback linkage, adjusts maze complexity according to player performance, and optimizes path search algorithms to guide players;

[0041] G3, adaptive adjustment and optimization, dynamically adjusts the maze structure to adapt to player performance, and optimizes Dijkstra algorithm path prompts to improve player navigation experience.

[0042] The beneficial effects of the present invention are as follows:

[0043] 1. The present invention realizes the dynamic generation of maze maps by combining generative adversarial networks (GAN) with Dijkstra algorithm. GAN can intelligently generate maze layouts that adapt to the player's style based on the player's behavior data, historical performance and preferences. This not only avoids the repetitiveness of the map, but also dynamically adjusts the map according to the player's response to provide freshness and diversity. At the same time, through the intelligent difficulty adjustment mechanism, the player's performance is monitored and analyzed in real time, and the difficulty of the maze is automatically adjusted. By using Dijkstra algorithm to perform real-time search and optimization of maze paths, Dijkstra algorithm can find the shortest path from the starting point to the end point in the maze, and during the player's game process, the system will automatically optimize the path according to the maze structure, provide intelligent path guidance, and avoid players giving up the game because the maze path is too complicated.

[0044] 2. The present invention realizes personalized generation of mazes through intelligent analysis of players' historical behaviors, skill levels and game preference data. Based on players' past game performance and preferences, the system can customize the maze layout and obstacle design that suits the player's style. This personalized maze design enables players to have a unique challenge experience in each game. At the same time, through the intelligent feedback and prompt module, the system can analyze the player's current position and behavior based on real-time data and provide customized path guidance or prompts. In this way, the game is more in line with the needs of players, improving the player's immersion and game retention rate, through the combination of GAN and Dijkstra algorithms.

[0045] 3. The present invention can generate personalized mazes according to the real-time feedback of players and can dynamically adjust the difficulty of the maze, so that each player can play the game at a difficulty and rhythm that suits him or her. Whether it is the complexity of the maze layout or the optimization of the path design, it can be adjusted in real time according to the player's skill level, game history and performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the overall process of the present invention;

[0047] Figure 2 This is a schematic diagram of the maze generation module flow of the present invention;

[0048] Figure 3 This is a schematic diagram of the path search module flow of the present invention;

[0049] Figure 4 This is a schematic diagram of the path search module flow of the present invention;

[0050] Figure 5 This is a personalized experience module diagram of the present invention;

[0051] Figure 6This is a flow chart of the feedback prompt module of the present invention;

[0052] Figure 7 This is a flow chart of the adaptive dynamic adjustment module of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] like Figures 1 to 7 As shown, an embodiment of the present invention provides a system for maze games based on Dijkstra algorithm and GAN model, which is composed of: a maze generation module, a path search module, a difficulty adjustment module, a personalized experience module, a feedback prompt module and an adaptive dynamic scheduling module;

[0055] Adaptive dynamic scheduling module: As the core linkage part of maze generation and path search, this module collects players' behavior data in real time when they are playing the game, dynamically adjusts the maze generation logic, and optimizes the path guidance strategy, thus forming an intelligent and personalized maze game ecosystem, realizing real-time feedback and continuous optimization of the game.

[0056] By combining the generative adversarial network (GAN) with the Dijkstra algorithm, the dynamic generation of maze maps is realized. GAN can intelligently generate maze layouts that adapt to the player's style based on the player's behavioral data, historical performance and preferences. This not only avoids the repetitiveness of the map, but also dynamically adjusts the map according to the player's response to provide freshness and diversity. At the same time, through the intelligent difficulty adjustment mechanism, the player's performance is monitored and analyzed in real time, and the difficulty of the maze is automatically adjusted. By using the Dijkstra algorithm to search and optimize the maze path in real time, the Dijkstra algorithm can find the shortest path from the starting point to the end point in the maze. In addition, during the player's game process, the system will automatically optimize the path according to the maze structure and provide intelligent path guidance, avoiding players from giving up the game due to the maze path being too complicated.

[0057] Through intelligent analysis of players' historical behaviors, skill levels, and game preference data, personalized maze generation is achieved. Based on players' past game performance and preferences, the system can customize maze layouts and obstacle designs that suit players' styles. This personalized maze design allows players to have a unique challenge experience in every game. At the same time, through the intelligent feedback and prompt module, the system can analyze the player's current position and behavior based on real-time data and provide customized path guidance or prompts. In this way, the game is more in line with the needs of players, improving the player's immersion and game retention rate. Through the combination of GAN and Dijkstra algorithms;

[0058] By being able to generate personalized mazes based on players' real-time feedback and dynamically adjust the difficulty of the maze, each player can play the game at a difficulty and rhythm that suits them. Whether it is the complexity of the maze layout or the optimization of the path design, it can be adjusted in real time according to the player's skill level, game history and performance.

[0059] Among them: Maze generation module: uses Dijkstra algorithm to build a path search basis, combines the adversarial network model to intelligently generate maze maps, and dynamically adjusts the maze difficulty according to the player's game performance to achieve adaptive game challenges;

[0060] Path search module: Use Dijkstra algorithm to search for the shortest path for players in the maze and give optimized route selection suggestions;

[0061] Difficulty adjustment module: dynamically adjust the difficulty of the maze according to the player's skill proficiency and the current stage of the game to keep the game moderately challenging at all times;

[0062] Personalized experience module: Analyze players’ behavior patterns and preferences, and customize personalized maze elements to enhance the game’s sense of involvement and immersion;

[0063] Feedback and prompt module: When players encounter difficulties, the system can intelligently provide maze clues or path guidance to help players smoothly advance the game process.

[0064] By intelligently generating personalized maze maps, dynamically adjusting the difficulty to maintain the challenge, using the Dijkstra algorithm to search for the shortest path and provide optimization suggestions, analyzing player behavior and customizing elements to enhance immersion, intelligent feedback and prompts help players overcome difficulties and advance the game process.

[0065] The steps of the method are:

[0066] A1, maze map generation, using the GAN model to generate diversified and personalized maze maps;

[0067] A2, path search and guidance, applies Dijkstra algorithm to search for paths and provide players with the shortest path or optimized path selection;

[0068] A3, dynamic difficulty adjustment, real-time adjustment of maze difficulty based on player skill level and game progress;

[0069] A4, integration of personalized elements, analyzing player behavior and preferences, and customizing personalized maze elements for players;

[0070] A5, player feedback and continuous optimization, collect and analyze player feedback, and iteratively optimize maze design, algorithm application and difficulty adjustment.

[0071] Among them, the process of the maze generation module is:

[0072] B1, input information, enter the player's difficulty level, game history and success rate;

[0073] B2, layout evaluation, the generator analyzes the player data and generates a maze layout, and the discriminator evaluates the generated maze layout;

[0074] B3, Level Adjustment, the discriminator adjusts the generation strategy of the generator according to the player’s level.

[0075] The maze generation module analyzes the player's difficulty level, game history and success rate, intelligently generates the maze layout, and the discriminator evaluates the layout quality. At the same time, the generation strategy is dynamically adjusted according to the player's level to ensure that the maze is both challenging and adaptable to the player's ability, thereby improving the gaming experience.

[0076] Among them, the process of the path search module is:

[0077] C1, information input, the player inputs the starting point information and the end point information;

[0078] C2, path calculation, uses the Dijkstra algorithm to determine and output the shortest travel route from the starting point to the end point;

[0079] C3, assists players by displaying real-time path guidance in maze games to assist players in directional navigation.

[0080] The path search module receives the starting and ending point information input by the player, uses the Dijkstra algorithm to quickly calculate the shortest route, and displays path guidance in real time in the game to assist player navigation, ensuring that players can traverse the maze efficiently and accurately, and improving the fluency and experience of the game.

[0081] Among them, the process of the difficulty adjustment module is:

[0082] D1, player monitoring, monitors the game progress and game behavior of players;

[0083] D2, difficulty calculation, analyzes the data and calculates the current difficulty of the game;

[0084] D3, difficulty adjustment, automatically adjusts the difficulty parameters of the maze.

[0085] The difficulty adjustment module monitors the player's game progress and behavior in real time, accurately calculates the current game difficulty, and automatically adjusts the maze difficulty parameters accordingly, ensuring that the game challenge matches the player's ability and continuously stimulates the player's interest and desire for challenge.

[0086] Among them, the process of the personalized experience module is:

[0087] E1, data collection, collects players’ historical behavior data;

[0088] E2, element customization, generates corresponding personalized maze elements according to player data;

[0089] E3, real-time adjustment, dynamically modify the maze layout during the game process.

[0090] The personalized experience module collects players' historical behavior data, customizes personalized maze elements based on it, and adjusts the maze layout in real time during the game to create an exclusive gaming experience for players and enhance immersion and satisfaction.

[0091] Among them, the process of the feedback prompt module is:

[0092] F1, detect the stuck position, and perform real-time detection of the player’s stuck position;

[0093] F2, provides guidance, guiding and prompting players according to the structure of path search;

[0094] F3, give feedback, give feedback to players in the maze through graphics and sounds;

[0095] The feedback prompt module detects the player's stuck position in real time, provides intelligent guidance and prompts based on the path search results, and helps players overcome difficulties through multiple feedback methods such as graphics and sound, thereby improving game fluency and player satisfaction.

[0096] Among them, the steps of adaptively and dynamically adjusting the module are:

[0097] G1, collects and analyzes data, and collects players’ gaming behavior data in real time;

[0098] G2, data interaction and feedback linkage, adjusts maze complexity according to player performance, and optimizes path search algorithms to guide players;

[0099] G3, adaptive adjustment and optimization, dynamically adjusts the maze structure to adapt to player performance, and optimizes Dijkstra algorithm path prompts to improve player navigation experience.

[0100] By collecting and analyzing player data in real time, dynamically adjusting the maze complexity and path search algorithm, optimizing the Dijkstra algorithm path prompts, and achieving adaptive adjustment of the maze structure and navigation experience, we ensure that the game challenge matches the player's ability and improves the overall gaming experience.

[0101] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0102] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A system based on Dijkstra algorithm and GAN model maze game, characterized by: The system is composed of: maze generation module, path search module, difficulty adjustment module, personalized experience module, feedback prompt module and adaptive dynamic scheduling module; Adaptive dynamic scheduling module: As the core linkage part of maze generation and path search, this module collects players' behavior data in real time when they are playing the game, dynamically adjusts the maze generation logic, and optimizes the path guidance strategy, thus forming an intelligent and personalized maze game ecosystem, realizing real-time feedback and continuous optimization of the game.

2. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: Said: Maze generation module: Use Dijkstra algorithm to build a path search foundation, combine adversarial network model to intelligently generate maze map, and dynamically adjust maze difficulty according to the player's game performance to achieve adaptive game challenges; Path search module: Use Dijkstra algorithm to search for the shortest path for players in the maze and give optimized route selection suggestions; Difficulty adjustment module: dynamically adjust the difficulty of the maze according to the player's skill proficiency and the current stage of the game to keep the game moderately challenging at all times; Personalized experience module: Analyze players’ behavior patterns and preferences, and customize personalized maze elements to enhance the game’s sense of involvement and immersion; Feedback and prompt module: When players encounter difficulties, the system can intelligently provide maze clues or path guidance to help players smoothly advance the game process.

3. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: The process of the maze generation module is as follows: B1, input information, enter the player's difficulty level, game history and success rate; B2, layout evaluation, the generator analyzes the player data and generates a maze layout, and the discriminator evaluates the generated maze layout; B3, Level Adjustment, the discriminator adjusts the generation strategy of the generator according to the player’s level.

4. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: The process of the path search module is as follows: C1, information input, the player inputs the starting point information and the end point information; C2, path calculation, uses the Dijkstra algorithm to determine and output the shortest travel route from the starting point to the end point; C3, assists players by displaying real-time path guidance in maze games to assist players in directional navigation.

5. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: The process of the difficulty adjustment module is as follows: D1, player monitoring, monitors the game progress and game behavior of players; D2, difficulty calculation, analyzes the data and calculates the current difficulty of the game; D3, difficulty adjustment, automatically adjusts the difficulty parameters of the maze.

6. The system for maze game based on Dijkstra algorithm and GAN model according to claim 1, characterized in that: The process of the personalized experience module is: E1, data collection, collects players’ historical behavior data; E2, element customization, generates corresponding personalized maze elements according to player data; E3, real-time adjustment, dynamically modify the maze layout during the game process.

7. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: The process of the feedback prompt module is as follows: F1, detect the stuck position, and perform real-time detection of the player’s stuck position; F2, provides guidance, guiding and prompting players according to the structure of path search; F3, give feedback, give feedback to players in the maze through graphics and sounds.

8. The system based on Dijkstra algorithm and GAN model maze game according to claim 1, characterized in that: The steps of the adaptive dynamic adjustment module are: G1, collects and analyzes data, and collects players’ gaming behavior data in real time; G2, data interaction and feedback linkage, adjusts maze complexity according to player performance, and optimizes path search algorithms to guide players; G3, adaptive adjustment and optimization, dynamically adjusts the maze structure to adapt to player performance, and optimizes Dijkstra algorithm path prompts to improve player navigation experience.

9. A method for playing a maze game based on the Dijkstra algorithm and the GAN model, characterized in that: The steps of this method are: A1, maze map generation, using the GAN model to generate diversified and personalized maze maps; A2, path search and guidance, applies Dijkstra algorithm to search for paths and provide players with the shortest path or optimized path selection; A3, dynamic difficulty adjustment, real-time adjustment of maze difficulty based on player skill level and game progress; A4, integration of personalized elements, analyzing player behavior and preferences, and customizing personalized maze elements for players; A5, player feedback and continuous optimization, collect and analyze player feedback, and iteratively optimize maze design, algorithm application and difficulty adjustment.

Images