Game strategy generation method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a game strategy generation method and device, equipment and a storage medium. The game strategy generation method provided by the embodiment of the invention comprises the steps that user demand information and a style selection instruction are received, a strategy style template is determined according to the style selection instruction, and the user demand information comprises one or more of a game name, a game version, a game role, a strategy direction and a target audience; performing knowledge graph construction based on a set knowledge base according to the user demand information to obtain key cue words; and generating an executable strategy generation instruction according to the key cue word and the strategy style template, and executing the strategy generation instruction to generate a game strategy of a corresponding style. According to the scheme, the technical problem that the game strategy generation efficiency is low can be solved, the game strategy of the corresponding style can be automatically generated based on the user demand information and the style selection instruction, and the game strategy generation efficiency is remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of game technology, and in particular to a game strategy generation method, apparatus, device, and storage medium. Background Art

[0002] With the booming development of the video game industry, the mechanics of large-scale open-world games, highly complex MMORPGs (Massively Multiplayer Online Role-Playing Games), and strategy games have become increasingly complex, significantly increasing players' reliance on game guides. As a core information carrier for players to understand game rules, master character skills, and optimize tactical strategies, game guides not only help new players quickly get started, but also provide veteran players with cutting-edge gameplay analysis as new versions of the game evolve, directly impacting their gaming experience and competitive level.

[0003] The current generation of game guides relies heavily on manual authoring, but manual writing has significant limitations. Game guides must integrate multi-dimensional information such as term definitions, skill values, combat strategies, and version dynamics. Professional guide writers must invest a considerable amount of time to sort out the complex in-game mechanics, resulting in a long production cycle for game guides. For example, guide writers must manually comb through official game documentation, community discussions, and real-world data. For games with frequent updates, gathering data for version preview guides alone can take days. Therefore, the existing method of manually authoring game guides is relatively inefficient in generating game guides and cannot adapt to the rapidly iterating technical demands of the gaming industry. Summary of the Invention The embodiments of the present application provide a game strategy generation method, apparatus, device and storage medium, which can solve the technical problem of low game strategy generation efficiency. Based on user demand information and style selection instructions, a game strategy of corresponding style can be automatically generated, which significantly improves the efficiency of game strategy generation.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a game strategy, comprising: receiving user demand information and a style selection instruction, and determining a strategy style template according to the style selection instruction, wherein the user demand information includes one or more of a game name, a game version, a game character, a strategy direction, and a target audience; According to user demand information, a knowledge graph is constructed based on the set knowledge base to obtain key prompt words; Generate executable strategy generation instructions based on key prompt words and strategy style templates, and execute the strategy generation instructions to generate a game strategy of the corresponding style.

[0005] Furthermore, before constructing the knowledge graph based on the set knowledge base according to the user demand information, it also includes: Receiving game reference materials, wherein the reference materials include one or more of game standard definitions, game encyclopedia data, cost guides for the game, pan-game finished product guides, and restriction rules; The game reference materials are parsed to obtain metadata, and the metadata is annotated to generate the corresponding knowledge base.

[0006] Furthermore, a knowledge graph is constructed based on the set knowledge base according to the user demand information to obtain key prompt words, including: Determine the retrieval index based on user demand information; According to the retrieval index, metadata is retrieved based on the set knowledge base to obtain the target triple data; A knowledge graph is constructed based on the target triple data, and key prompt words are extracted from the constructed knowledge graph.

[0007] Furthermore, executing the strategy generation instruction to generate a game strategy of a corresponding style includes: Determine the text generation sub-command, image acquisition sub-command, and image-text integration sub-command in the strategy generation command; Execute the text generation sub-command to generate the game strategy text of the corresponding style; Execute the image acquisition sub-command to obtain the corresponding game screenshots from the set knowledge base according to the game strategy text to obtain the target image; Execute the image-text integration sub-command to perform image-text fusion processing on the game strategy text and the target image to obtain the first target game strategy.

[0008] Furthermore, executing the strategy generation instruction to generate a game strategy of a corresponding style includes: Determine the text generation sub-command, video acquisition sub-command, video synthesis sub-command, and video text fusion sub-command in the strategy generation command; Execute the text generation sub-command to generate the game strategy text of the corresponding style; Execute the video acquisition sub-command to obtain the corresponding target game video from the set knowledge base according to the user's demand information, and edit the target game video according to the key prompt words to obtain the target video clip; Execute the video synthesis sub-command to dynamically synthesize the target video clip according to the game strategy text to obtain the initial strategy video; Execute the video-text fusion sub-command to embed the game strategy text into the initial strategy video to obtain the second target game strategy.

[0009] Furthermore, after executing the strategy generation instruction to generate a game strategy of a corresponding style, the method further includes: Display the game strategy and its corresponding style index and professionalism index on the interactive interface; receiving an adjustment instruction based on the style index and the professionalism index, and obtaining a target style index and a target professionalism index according to the adjustment instruction; A new game strategy is regenerated based on the target style index and the target professionalism index based on user demand information and style selection instructions.

[0010] Furthermore, user demand information is received, including: Receive voice information, text descriptions or pictures input by users; Perform text analysis on the received voice information to obtain the corresponding user demand information; Alternatively, semantic analysis is performed on the received text description to obtain corresponding user demand information; Alternatively, intelligent recognition processing is performed on the received images to obtain corresponding user demand information.

[0011] In a second aspect, an embodiment of the present application provides a game strategy generating device, comprising: An information receiving module, used for receiving user demand information and style selection instructions; A template determination module is used to determine a strategy style template according to the style selection instruction, wherein the user requirement information includes one or more of the game name, game version, game character, strategy direction, and target audience; The prompt word determination module is used to construct a knowledge graph based on the set knowledge base according to user demand information to obtain key prompt words; The strategy generation module is used to generate executable strategy generation instructions based on key prompt words and strategy style templates, and execute the strategy generation instructions to generate a game strategy of the corresponding style.

[0012] In a third aspect, an embodiment of the present application provides a game strategy generation device, comprising: memory and one or more processors; a memory for storing one or more programs; When one or more programs are executed by one or more processors, the one or more processors implement the game strategy generation method of the first aspect.

[0013] In a fourth aspect, an embodiment of the present application provides a storage medium storing computer-executable instructions, which, when executed by a computer processor, are used to execute the game strategy generation method of the first aspect.

[0014] In the embodiment of the present application, when generating a game strategy, a strategy style template is determined based on a received style selection instruction, a knowledge graph is constructed based on a set knowledge base according to the received user demand information to obtain key prompt words, an executable strategy generation instruction is generated based on the key prompt words and the strategy style template, and the strategy generation instruction is executed to generate a game strategy of the corresponding style. Using the above technical means, a game strategy of the corresponding style can be automatically generated based on user demand information and style selection instructions. This avoids the technical problem of low game strategy generation efficiency caused by manually writing game strategies, improves the degree of automation and intelligence of game strategy generation, and significantly improves the efficiency of game strategy generation.

[0015] The beneficial effects of the game strategy generation device, game strategy generation equipment, and storage medium provided above can refer to the beneficial effects of the game strategy generation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of a method for generating a game strategy provided by an embodiment of the present application; Figure 2 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application; Figure 3 This is a first schematic diagram of a game strategy generation interactive interface provided by an embodiment of the present application; Figure 4 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application; Figure 5 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application; Figure 6 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application; Figure 7 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application; Figure 8 This is a second schematic diagram of a game strategy generation interactive interface provided by an embodiment of the present application; Figure 9 This is a structural diagram of a game strategy generating device provided by an embodiment of the present application; Figure 10 This is a structural diagram of a game strategy generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] To further clarify the objectives, technical solutions, and advantages of this application, specific embodiments of the present application are described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are intended only to illustrate this application and are not intended to limit it. It should also be noted that, for ease of description, the drawings only illustrate portions relevant to this application, not all of them. Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts depict the various operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process may terminate upon completion of its operations, but may also include additional steps not shown in the accompanying drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, or the like.

[0018] The current generation of game guides relies heavily on manual authoring, but manual writing has significant limitations. Game guides must integrate multi-dimensional information such as term definitions, skill values, combat strategies, and version dynamics. Professional guide writers must invest a considerable amount of time to sort out the complex in-game mechanics, resulting in a long production cycle for game guides. For example, guide writers must manually comb through official game documentation, community discussions, and real-world data. For games with frequent updates, gathering data for version preview guides alone can take days. Therefore, the existing method of manually authoring game guides is relatively inefficient in generating game guides and cannot adapt to the rapidly iterating technical demands of the gaming industry.

[0019] Based on this, the game strategy generation method, apparatus, device, and storage medium of the embodiment of the present application are provided. The purpose is to determine the strategy style template according to the received style selection instruction when generating the game strategy, construct a knowledge graph based on the set knowledge base according to the received user demand information to obtain key prompt words, generate executable strategy generation instructions based on the key prompt words and the strategy style template, and execute the strategy generation instructions to generate a game strategy of the corresponding style. Using the above technical means, compared with the method of manually writing game strategies, this embodiment can automatically generate a game strategy of the corresponding style through user demand information and style selection instructions, thereby improving the automation and intelligence of game strategy generation and significantly improving the efficiency of game strategy generation.

[0020] Figure 1 A flowchart of a game strategy generation method provided in an embodiment of the present application is provided. The game strategy generation method provided in this embodiment can be executed by a game strategy generation device. The game strategy generation device can be implemented through software and / or hardware. The game strategy generation device can be composed of two or more physical entities, or a single physical entity. Generally speaking, the game strategy generation device can be a computer device.

[0021] The following description is made by taking a computer device as an example to execute the method for generating a game strategy. Figure 1 , the game strategy generation method specifically includes: S11. Receive user demand information and a style selection instruction, and determine a strategy style template according to the style selection instruction, wherein the user demand information includes one or more of a game name, a game version, a game character, a strategy direction, and a target audience.

[0022] A user can input user requirement information and a style selection instruction based on a preset interactive interface, and a computer device receives the user requirement information and the style selection instruction. The user requirement information includes one or more of the following: game name, game version, game character, strategy direction, and target audience. The system can have preset styles, such as "humorous," "serious," and "academic," and the user can select from the preset styles using the preset interactive interface. A style selection instruction is generated based on the user's selection, and a target style is determined based on the style selection instruction. A strategy style template corresponding to the target style is determined based on a mapping relationship between the preset styles and strategy style templates. For example, keyword extraction can be performed based on the text description input by the user, and the target style with the closest semantics is selected from the preset styles based on the extracted keywords. A style selection instruction is generated based on the determined target style, and a strategy style template corresponding to the target style is determined based on the style selection instruction based on the mapping relationship between the preset styles and strategy style templates. For example, if the text description entered by the user is "a relaxing and funny strategy", keyword extraction is performed on the text description, and the extracted keywords are "relaxed" and "funny". After calculation, it is determined that the semantic similarity between these keywords and the preset style is closest to "humorous style", and a style selection instruction for selecting "humorous style" is generated, and the corresponding "humorous style" strategy style template is matched according to the style selection instruction.

[0023] In one embodiment, user requirement information can be input via voice, text, or images. Style selection instructions can be selected through pre-set controls or input via corresponding voice, text, or images. If there is ambiguity between the received user requirement information and the style selection instruction, further information can be supplemented by asking questions to clarify the corresponding user requirement information and style selection instruction.

[0024] In one embodiment, user demand information includes one or more of the following: game title, game version, game character, strategy guide, and target audience. Strategy guides include beginners, advanced techniques, and specific level breakthroughs, and target audiences include novice players, experienced players, and casual players. Additionally, user demand information may include game platform information, specific game element focus, desired strategy depth, and preferred presentation format. Different gaming platforms vary in their operating methods and hardware performance, resulting in different corresponding game guides. Specific game element focus refers to the varying levels of interest players place on different elements in the game. Some players prioritize character development and desire guides detailing character upgrades, skill bonuses, and equipment builds. Others, who enjoy exploring the game map, require information on map resource distribution and hidden location locations. Still others, focused on the game's plot, desire guides to unravel the storyline and interpret the background and foreshadowing. Therefore, game guides can be determined based on their focus on specific game elements. Expected guide depth refers to the significant differences in user needs. New players may only require superficial content such as basic gameplay introductions and game flow guidance, while experienced players seek in-depth guides that offer challenging techniques, in-depth analysis of game mechanics, and extreme numerical calculations. Therefore, different game guides can be developed based on players' desired depth. Preferred presentation format refers to the presentation format of game guides. Some prefer concise, clear text descriptions; others prefer a combination of text and images to help understand game scenes and steps; and still others find video guides more intuitive, allowing a clearer understanding of the actual gameplay process. Therefore, different game guide formats can be developed based on players' preferred presentation format.

[0025] As described above, through the use of style selection commands and corresponding strategy style templates, game strategy styles can be customized to meet the preferences of different players, thereby enhancing the personalization of game strategy and ultimately improving the user experience. Furthermore, by using style selection commands to match strategy styles across game guides, the time required for manual strategy creation is reduced, thereby improving the efficiency of game strategy generation and further enhancing the user experience.

[0026] In one embodiment, users can also dynamically add custom strategy style templates. Users can upload multiple sample texts of a new style, and style features are extracted from the sample texts to generate initial feature tags, such as "Tech + Cyberpunk," to create a custom style. Furthermore, users can manually adjust the initial feature tags using the interactive interface to obtain personalized feature tags, which are then stored and used to create new strategy style templates for subsequent game strategy generation. By adding custom strategy style templates, the scalability of game strategy generation is improved.

[0027] S12. Construct a knowledge graph based on the set knowledge base according to user demand information to obtain key prompt words.

[0028] Based on the received user demand information and a pre-set knowledge base, a knowledge search is performed to search for materials related to the user demand. A knowledge graph is constructed based on the searched materials to obtain associated prompt words. For example, when the user demand information is input based on a text description, word segmentation, part-of-speech annotation, and named entity recognition are performed on the user demand information to extract entities such as the game name, game character, game skills / game mechanics, and strategy type. For example, if the user demand information is "a shield team strategy for character B in "Game A", suitable for beginners", word segmentation, part-of-speech annotation, and named entity recognition can be performed to obtain the game name: "Game A", the game character: "Game Character B", the game skill: "Shield", and the strategy type: "Team Strategy". A shield is a temporary defensive measure in the game that protects the character / unit by absorbing or offsetting damage, and usually exists in the form of an energy field or special skill. The implementation of shields in different games varies, but the core functions are similar. Shield teaming refers to building a shield-centric team strategy through specific character or equipment combinations in the game, primarily to achieve damage reduction, anti-interruption, and buff linkage. Damage reduction offsets damage from enemy attacks, anti-interruption maintains the stability of character skill releases, and buff linkage triggers shield-related damage / healing bonuses. When user request information is input based on an image, image recognition technology is used to identify entities such as the game name, game character, game skills / game mechanics, and strategy type. Based on these identified entities, a knowledge graph is constructed based on the pre-set knowledge base to generate key prompts. For example, the key prompts associated with game character B are "game character B," "shield," "teaming," and "equipment 1." "Equipment 1" is associated with the "shield" skill of "game character B," and "equipment 1" can enhance the "shield" effect.

[0029] As described above, by using a knowledge base to retrieve and fuse multi-source data, the reliability of the data sources used in game strategy generation is improved, thereby increasing the accuracy of game strategy generation. Furthermore, the corresponding entity data in the knowledge base can be automatically matched based on user demand information, generating corresponding key prompts without the need for manual retrieval and matching. This greatly improves the automation and intelligence of strategy retrieval and matching, thereby improving the overall efficiency of game strategy generation. Furthermore, the knowledge base supports incremental updates. When adding new characters or new game versions, only the corresponding nodes and relationships need to be added, without the need to restructure the architecture, thereby improving the scalability and maintainability of game strategy generation.

[0030] In one embodiment, before constructing a knowledge graph, a knowledge base must be established. Game reference materials can be received, including one or more of standard game definitions, game encyclopedia data, cost guides for this game, pan-game finished game guides, and restriction rules. Reference materials can be manually uploaded by the user or retrieved from a database on the internet or cloud. Standard game definitions are used to interpret various in-game terms, game encyclopedia data is used to explain fixed information such as skills and values, cost guides for this game are used to record existing guides for this game, pan-game finished game guides are used to record guides for games that are not part of this game but can be used as references, and restriction rules are used to record custom rules. The received game reference materials may be in various formats, such as text, data, images, and video, and the system supports receiving game reference materials in various formats. The received game reference materials are parsed to generate metadata. Metadata includes corresponding game terms, video screenshots, or video files. Game terms include character terms, skill terms, equipment terms, and proprietary terminology. The parsed metadata is annotated to generate a corresponding knowledge base. For example, metadata can be annotated with multiple tags, such as the game name, version, character, skill, and value. For example, if the game reference material describes "Character B's E skill's shield absorption is linked to the health limit," the corresponding annotation would be: [Character: Character B]'s [Skill: E skill] [Mechanic: Shield absorption] and [Attribute: Health limit] [Relationship: Linked]. Deeper semantic annotation can also be performed, such as annotating "Skill → Effect" and "Character → Counter relationship," and stored in a graph database to generate the corresponding knowledge base. When constructing the knowledge base, five core entities can be defined: game (name), character, skill, mechanic, and value. Multiple relationship types, such as "belongs to," "counters," "increases," and "trigger," can be defined between these entities. Based on these defined entities and relationship types, triples are constructed. For example, the triples might be: (Character B, belongs to, "Game A" character), (shield absorption, increase, health limit, +40%), (E skill, trigger, shield generation, 100%). Based on the constructed triple data, a knowledge base is generated, and the corresponding triple data can be subsequently retrieved by searching the knowledge base. By integrating game reference materials from multiple sources, the knowledge base is enriched, providing rich reference materials for subsequent game guides generated based on the knowledge base, thereby improving the richness and accuracy of the generated game guides.

[0031] In one embodiment, knowledge base updates can be processed asynchronously through a message queue. When a new document is added, it is first written into the memory cache. Then, based on the analysis of the new document, the corresponding metadata is obtained, and the metadata is annotated and added to the knowledge base.

[0032] S13. Generate an executable strategy generation instruction based on the key prompt words and the strategy style template, and execute the strategy generation instruction to generate a game strategy of the corresponding style.

[0033] According to the key prompt words obtained above and the strategy style template determined above, the key prompt words and the strategy style template are semantically spliced ​​to form structured prompt words. According to the structured prompt words, corresponding executable strategy generation instructions are generated, wherein the strategy generation instructions include text generation sub-instructions, picture acquisition sub-instructions, picture and text integration sub-instructions, video acquisition sub-instructions, video synthesis sub-instructions and video and text fusion sub-instructions, etc. The strategy generation instructions are executed to generate a game strategy of the corresponding style. Among them, the game strategy includes a pure text type game strategy, a game strategy combining pictures and text, or a game strategy combining video and text. As described above, the game strategy of the corresponding style is automatically generated through keyword prompts and strategy style templates, without the need for manual writing, which significantly improves the efficiency of game strategy generation.

[0034] As described above, when generating a game guide, a guide style template is determined based on the received style selection instructions. A knowledge graph is constructed based on the received user requirement information and a pre-set knowledge base to obtain key prompts. An executable guide generation instruction is generated based on the key prompts and the guide style template. The guide generation instruction is then executed to generate a game guide of the corresponding style. Using the above technical means, compared to manually writing a game guide, this embodiment can automatically generate a game guide of the corresponding style based on user requirement information and style selection instructions, thereby increasing the automation and intelligence of game guide generation and significantly improving the efficiency of game guide generation.

[0035] Figure 2 This is a flow chart of another method for generating a game strategy provided by an embodiment of the present application, referring to Figure 2 , the game strategy generation method specifically includes: S111: Receive voice information, text description or picture input by the user.

[0036] In the aforementioned S11, when receiving the user demand information, the user demand information may be determined by receiving language information, text description or pictures input by the user. Figure 3 This is a first schematic diagram of a game strategy generation interactive interface provided by an embodiment of the present application, referring to Figure 3In the game strategy generation interactive interface 1, a voice input control 11, a text input control 12, and an image input control 13 are displayed. Users can trigger the corresponding controls to input corresponding information. For example, triggering the voice input control 11 allows voice input, triggering the text input control 12 allows text input, and triggering the image input control 13 allows image input. Entering user requirement information through multiple interactive forms increases the diversity of interaction, facilitates users to input requirements in different ways, and thus improves the user experience.

[0037] S112: Perform text analysis on the received voice information to obtain corresponding user demand information.

[0038] When a user inputs user requirement information via voice, the system receives the user's voice input and performs text parsing on the received voice information to obtain the corresponding user requirement information. For example, the received voice information undergoes format unification and noise reduction processing to obtain standardized voice information. The standardized voice information is then framed and windowed to divide the audio into voice frames of a preset size (e.g., 20-30ms). A Hamming window is added to reduce spectral leakage, preparing for subsequent feature extraction. Acoustic feature extraction and text conversion are performed on the aforementioned voice frames to obtain a corresponding text description. The text description is semantically adjusted and contextually supplemented to obtain the corresponding user requirement information. For example, the obtained user requirement information may be "a shield teaming guide for character B in Game A, suitable for beginners." As described above, voice input significantly improves input efficiency compared to text input, thereby improving the efficiency of subsequent generation of the corresponding game guide.

[0039] S113: Perform semantic analysis on the received text description to obtain corresponding user demand information.

[0040] When a user inputs user demand information through text, the text description input by the user is received, and semantic analysis is performed on the received text description to identify entities and key information in the text description. For example, entities include game names, character names, mechanism terms, version numbers, strategy directions, and target audiences; key information includes relationships between entities. For example, if the input is: "Abyss team strategy for character B in version 3.8", the corresponding relationship can be: "Character B-belongs-Team, 3.8 version-limited-Abyss". Semantic expansion and context completion are performed based on the entities and the relationships between entities in the text description to obtain the corresponding user demand information. As described above, by performing text parsing on the received text description to obtain the corresponding user demand information, automatic expansion and semantic understanding of text input are achieved, and the accuracy of determining user demand information is improved, thereby improving the accuracy of subsequent game strategies generated based on user demand information.

[0041] S114: Perform intelligent recognition processing on the received image to obtain corresponding user demand information.

[0042] When a user inputs user requirement information via an image, the image input by the user is received. The image can be a screenshot of the corresponding game interface. The received image is then intelligently recognized to identify game elements and text information. Game elements include character portraits, skill icons, and equipment interfaces. Semantic association analysis is performed based on the identified game elements and text information. Text integration is performed based on the analysis results, and the corresponding user requirement information is output. For example, if the identified game elements are character B, skill a, and equipment 1, and the corresponding identified text information is "character B," "shield enhancement," and "20%," the game elements and text information are integrated, and the corresponding user requirement information output is "shield team strategy for character B in "Game A"." As described above, determining user requirement information through image input is faster than obtaining user requirement information through text descriptions, thereby improving the efficiency of determining user requirement information and, in turn, improving the efficiency of subsequently generating corresponding game strategies based on the user requirement information.

[0043] In one embodiment, when determining the user demand information based on the received voice information, text description or picture, if the user demand information cannot be accurately determined, follow-up questions can be asked to the user to remind the user to supplement the missing information. Subsequently, the complete user demand information can be generated based on the answer to the follow-up question combined with the aforementioned voice information, text description or picture.

[0044] In one embodiment, the user can also input voice information, text descriptions, and images simultaneously. The user's voice information, text descriptions, and images are received, and the received voice information is subjected to text parsing to obtain first demand information; the received text description is subjected to semantic analysis to obtain second demand information; and the received image is subjected to intelligent recognition to obtain third demand information. The first, second, and third demand information are integrated to obtain the corresponding user demand information.

[0045] As described above, three input interaction methods, namely voice information, text description and picture, are provided, which makes it easy for users to input their own needs using multiple interaction methods, improves the interaction flexibility, and thus improves the user experience.

[0046] Figure 4 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application, referring to Figure 4 , the game strategy generation method includes: S121. Determine a search index based on user demand information.

[0047] After receiving the user requirement information in S11, a search index is determined based on the user requirement information. For example, the search index may be an entity in the user requirement information, such as a game name, character name, skill name, etc. For example, if the user requirement information is "a shield team strategy for character B in Game A, suitable for beginners," the corresponding index information includes Game A, Character B, Shield, and Team.

[0048] S122: Search metadata based on the set knowledge base according to the search index to obtain target triple data.

[0049] Based on the search index, metadata is retrieved from the set knowledge base to determine target triple data. Since the corresponding triple data was semantically annotated when the knowledge base was created, metadata can be retrieved from the knowledge base using the search index to retrieve the corresponding semantically annotated target triple data. For example, if the search index is Game A and Character B, target triple data for Game A and Character B can be retrieved from the knowledge base. Exemplarily, the retrieved metadata is parsed to extract the relationships between entities, and target triple data is formed based on these relationships. For example, if the retrieved metadata is "In version 3.8 of Game A, Character B's shield mechanic is related to Equipment 1," the target triple data extracted would be (Character B, uses, Equipment 1), (Character B, belongs to, Game A), and (Shield mechanic, is, Character B's skill), etc. Since the retrieved target triple data may come from different data sources, the target triple data can be fused to combine target triple data from different data sources.

[0050] S123. Construct a knowledge graph based on the target triple data, and extract key prompt words from the constructed knowledge graph.

[0051] The knowledge graph is stored and constructed based on a pre-configured graph database. By importing the target triple data into the graph database, nodes and edges are created to generate the final knowledge graph. The nodes in the constructed knowledge graph are ranked by importance, and the top-ranked nodes are selected as candidate key prompts. For example, in the knowledge graph for character B in game A, nodes such as "character B," "equipment 1," and "shield mechanism" rank highly. Based on the semantics and context of the user's needs, candidate key prompts are screened and adjusted. For example, if the user's needs emphasize a beginner's guide, prompts such as "beginner's guide" and "basic" are added. The key prompts ultimately extracted are "Abyss team building guide for character B in version 3.8 of "Game A," with a detailed explanation of the shield mechanism for equipment 1."

[0052] As described above, by determining the search index based on user demand information and efficiently searching metadata based on the established knowledge base using a precise search index, data retrieval time is greatly shortened, metadata retrieval efficiency is improved, and thus the efficiency of game guide generation is enhanced. Keyword prompts extracted based on the knowledge graph and user demand information accurately reflect the core content of user needs, allowing the subsequently generated game guides to better meet user needs, improve the accuracy of game guide generation, and ultimately enhance the user experience.

[0053] Figure 5 This is a flow chart of another method for generating a game strategy provided by an embodiment of the present application, referring to Figure 5 , the game strategy generation method specifically includes: S131 , determining the text generation sub-instruction, the image acquisition sub-instruction, and the image-text integration sub-instruction in the strategy generation instruction.

[0054] The type of game guide generated can be determined based on user needs. It can be a pure text type, a combination of text and images, or a combination of video and text. When the game guide required by the user is a combination of text and images, the text generation sub-instruction, image acquisition sub-instruction, and image and text integration sub-instruction in the aforementioned executable guide generation instruction are determined. Among them, the text generation sub-instruction is used to generate the game guide text, the image acquisition sub-instruction is used to obtain the corresponding game interface screenshots, and the image and text integration sub-instruction is used to achieve the fusion of text and images to generate the final image and text type game guide.

[0055] In one embodiment, when the game strategy required by the user is of a pure text type, the aforementioned strategy generation instruction is executed, and the strategy style template (text type template) and the key prompt words generated by the knowledge graph are combined to generate a game strategy text of the corresponding style.

[0056] S132: Execute the text generation sub-instruction to generate a game strategy text of a corresponding style.

[0057] Execute a text generation sub-command, combining the strategy style template (a text-based template) with key prompts generated from the knowledge graph to generate a strategy text for the corresponding style. Exemplarily, dynamic parameters are determined within the key prompts. Dynamic parameters refer to replaceable variable portions (i.e., template variables) within the key prompts, such as entities like the game name, game character, and version. For example, a "humorous" style template might read: "Family, who understands! {{character}}'s {{mechanism}} is too {{adjective}}! Newbies should just use {{verb}}, which is simply {{noun}}~." Character, mechanism, adjective, verb, and noun are template variables, and a mapping relationship is established between template variables and dynamic parameters. For example, character maps to "Character B," mechanism maps to "shield," adjective maps to "thick," verb maps to "open E," and noun maps to "escape artifact." The key prompts corresponding to the dynamic parameters are entered into the strategy style template to generate an executable text generation sub-command. Exemplarily, the variable placeholders in the strategy style template can be parsed, and the value corresponding to each variable placeholder, such as "Character B", can be obtained from the aforementioned mapping relationship. The string corresponding to the strategy style template is executed to generate a complete executable text generation sub-instruction. The text generation sub-instruction is executed to generate and output the game strategy text of the corresponding style. Exemplarily, the text generation sub-instruction is converted into an executable API call, and the corresponding text generation model is called to generate the corresponding game strategy text. For example, the generated game strategy text is "Who understands it, family members! Character B's shield is too thick! It is recommended that novices directly open E, it is simply an escape artifact~".

[0058] As described above, the game strategy text of the corresponding style is automatically generated through the text generation sub-instruction, which greatly improves the efficiency of game strategy text generation compared to the manual writing method.

[0059] S133: Execute the picture acquisition sub-instruction to obtain the corresponding game screenshot from the set knowledge base according to the game strategy text to obtain the target picture.

[0060] The aforementioned image acquisition sub-instruction is executed to extract and parse keywords from the generated game guide text to obtain the corresponding target keywords. For example, text semantic analysis and keyword recognition are performed on the game guide text to identify key entities, distinguish between categories such as characters, equipment, and mechanics, and extract attribute terms such as "shield enhancement" and "health bonus." Each game screenshot in the pre-set knowledge base has been annotated with metadata. Therefore, the metadata annotations can be used to search for the target keywords identified above to obtain the corresponding target images. For example, images containing all target keywords are prioritized. Next, a semantic matching model is used to calculate the cross-modal similarity between the game guide text and the images, obtaining images with a similarity greater than a preset threshold. An image recognition model is then used to detect the characters and equipment in the images, filtering out irrelevant images (i.e., screenshots) to obtain the final target image.

[0061] As described above, the automatic acquisition of game screenshots related to the game guide text through the image acquisition sub-instruction greatly improves the efficiency of image acquisition in the graphic type game guide compared to manual retrieval or manual screenshot methods, thereby improving the efficiency of the final game guide generation.

[0062] S134 , executing the image-text integration sub-command to perform image-text fusion processing on the game strategy text and the target image to obtain the first target game strategy.

[0063] Execute the previously obtained image-text integration sub-command to obtain text keywords from the game guide text, calculate the semantic similarity between the text keywords and the image, and determine the strength of the image-text association. For example, the text keyword "Equipment 1's shield special effect" and the image feature "Equipment 1 interface and shield generation animation" have a calculated semantic similarity of 0.92. Assuming a preset threshold of 0.7, the calculated semantic similarity exceeds the preset threshold, indicating a strong image-text association. An association mapping relationship is established between the image and the text keyword with the strongest image-text association. A corresponding image anchor is generated for each text keyword in the game guide text. For example, clicking "Equipment 1's effect" automatically jumps to the image location displaying that attribute. The game guide text and the target image are then subjected to image-text fusion processing, and the target image is fused with the corresponding text keyword with the associated mapping relationship. Image-text fusion can be performed based on preset layout templates, such as tutorial templates, display templates, and data templates. The tutorial template displays an image on the left and a game guide on the right; the presentation template displays an image at the top and a game guide at the bottom; and the data template displays both images and game guide text simultaneously in a table. After the image and text fusion process is complete, the first target game guide is output, combining both images and text.

[0064] As described above, the automatic generation of a corresponding first-target game guide with both text and images through the guide generation command significantly improves the efficiency of game guide generation compared to manual writing. Furthermore, presenting the game guide in a combined text and image format allows users to better understand and retain key information, improving information delivery efficiency and ultimately enhancing the user experience.

[0065] Figure 6 This is a flowchart of another method for generating a game strategy provided by an embodiment of the present application, referring to Figure 6 , the game strategy generation method specifically includes: S135 , determining the text generation sub-instruction, video acquisition sub-instruction, video synthesis sub-instruction, and video text fusion sub-instruction in the strategy generation instruction.

[0066] The type of game strategy generated can be determined based on user needs. It can be a pure text type, a text and image combination type, or a video and text combination type. When the game strategy required by the user is a video and text combination type, the text generation sub-instruction, video acquisition sub-instruction, video synthesis sub-instruction, and video and text fusion sub-instruction in the aforementioned strategy generation instruction are determined. Among them, the text generation sub-instruction is used to generate the game strategy text, the video acquisition sub-instruction is used to obtain the corresponding game video, the video synthesis sub-instruction is used to perform corresponding cutting and synthesis processing on the obtained game video, and the video and text fusion sub-instruction is used to fuse the game strategy text and the synthesized video to generate the final video and text combination type game strategy.

[0067] S136: Execute the text generation sub-instruction to generate a game strategy text of a corresponding style.

[0068] Execute a text generation sub-command, combining the strategy style template (a text-based template) with key prompts generated from the knowledge graph to generate a strategy text for the corresponding style. Exemplarily, dynamic parameters are determined within the key prompts. Dynamic parameters refer to replaceable variable portions (i.e., template variables) within the key prompts, such as entities like the game name, game character, and version. For example, a "humorous" style template might read: "Family, who understands! {{character}}'s {{mechanism}} is too {{adjective}}! Newbies should just use {{verb}}, which is simply {{noun}}~." Character, mechanism, adjective, verb, and noun are template variables, and a mapping relationship is established between template variables and dynamic parameters. For example, character maps to "Character B," mechanism maps to "shield," adjective maps to "thick," verb maps to "open E," and noun maps to "escape artifact." The key prompts corresponding to the dynamic parameters are entered into the strategy style template to generate an executable text generation sub-command. Exemplarily, the variable placeholders in the strategy style template can be parsed, and the value corresponding to each variable placeholder, such as "Character B", can be obtained from the aforementioned mapping relationship. The string corresponding to the strategy style template is executed to generate a complete executable text generation sub-instruction. The text generation sub-instruction is executed to generate and output the game strategy text of the corresponding style. Exemplarily, the text generation sub-instruction is converted into an executable API call, and the corresponding text generation model is called to generate the corresponding game strategy text. For example, the generated game strategy text is "Who understands it, family members! Character B's shield is too thick! It is recommended that novices directly open E, it is simply an escape artifact~".

[0069] As described above, the game strategy text of the corresponding style is automatically generated through the text generation sub-instruction, which greatly improves the efficiency of game strategy text generation compared to the manual writing method.

[0070] S137, executing the video acquisition sub-instruction, acquiring the corresponding target game video from the set knowledge base according to the user demand information, and editing the target game video according to the key prompt words to obtain the target video clip.

[0071] The video acquisition sub-command is executed to extract entities from the user's requested information, including game names, characters, mechanics, and versions. Game videos are retrieved from a pre-defined knowledge base based on the entities, and videos matching the entities are retrieved. The cosine similarity between the entity and the video features is then calculated, and videos with a cosine similarity greater than a preset threshold are identified. The visual detection model is then used to detect characters and equipment in the video keyframes, identifying videos with characters and equipment matching the entities in the keyframes, thereby obtaining the final target game video. The target game video is then matched against the timestamps in the metadata of the target game video based on the key prompts determined in S12. For example, if the key prompt is "Character B's Equipment 1 shield generation timing," the timestamp of the corresponding target game video is "Equipment 1 Special Effect_00:01:10-00:01:30." A clipping script is generated based on the key prompts and the corresponding timestamps, and the target game video is edited based on the clipping script to obtain the corresponding target video segment.

[0072] As described above, the target game video is automatically acquired through the video acquisition sub-instruction and the target game video is automatically edited into a target video clip that matches the key prompt words corresponding to the user's demand information. Compared with the manual acquisition and manual editing method, the efficiency of video acquisition and video editing is greatly improved.

[0073] S138. Execute the video synthesis sub-instruction to dynamically synthesize the target video clip according to the game strategy text to obtain an initial strategy video.

[0074] Execute the video synthesis sub-command to semantically segment the game guide text into chunks, assigning timelines to the chunks based on the guide's textual logic. Extract dynamic parameters (such as character, skills, and equipment) from the guide text and associate them with target video segments. Based on the assigned timelines, seamlessly splice the corresponding target video segments together to produce the initial guide video. For example, corresponding transition effects, such as hard cuts, fade-ins, and fade-outs, can be added to each target video segment.

[0075] As described above, the target video clips are automatically synthesized into an initial strategy video that is compatible with the game strategy text through the video synthesis sub-instruction. Compared with the manual synthesis method, the efficiency of strategy video synthesis is greatly improved.

[0076] S139. Execute the video-text fusion sub-instruction to embed the game strategy text into the initial strategy video to obtain the second target game strategy.

[0077] Execute the video-text fusion sub-instruction to semantically segment the game guide text into blocks, generating block text. Calculate the semantic similarity between the text keywords in the block text and the video frames in the initial guide video. Determine the associated video frames for the corresponding text keywords based on the semantic similarity greater than a preset threshold, thereby determining the display timing of the text keywords. Based on the text display timing, embed the corresponding block text into the initial guide video to form video subtitles, resulting in a second target game guide combining video and text.

[0078] The aforementioned second-target game guide, which automatically combines video and text with guide generation instructions, significantly improves the efficiency of game guide generation compared to manually editing video guides. Furthermore, presenting game guides through a combination of video and text allows users to better understand and retain key information, improving information delivery efficiency and ultimately enhancing the user experience.

[0079] Figure 7 This is a flow chart of another method for generating a game strategy provided by an embodiment of the present application, referring to Figure 7 , the game strategy generation method specifically includes: S21. Display the game strategy and the style index and professionalism index corresponding to the game strategy on the interactive interface.

[0080] After generating a game guide of a corresponding style in S13, the game guide and its corresponding style index and professionalism index can be displayed on an interactive interface. For example, language feature extraction is performed on the game guide to extract style-related features. For example, for a "humorous" style, corresponding style-related features include emoticon density and the proportion of internet buzzwords; for an "academic" style, corresponding style-related features include professional terminology density and the proportion of long sentences. Based on the extracted style-related features, a style index is calculated using a predefined calculation model, and the corresponding style index is output. The style index ranges from 0% to 100%. The values ​​in the game guide are factually verified based on a predefined knowledge base to determine the numerical accuracy coefficient. The game guide's hierarchy is analyzed to determine the hierarchy coefficient. The game guide's professional terminology is analyzed to determine the terminology consistency coefficient. The professionalism index is calculated based on the numerical accuracy coefficient, hierarchy coefficient, and terminology consistency coefficient to obtain the professionalism index. For example, the professionalism index = numerical accuracy coefficient × weight (e.g., 40%) + hierarchy coefficient × weight (e.g., 30%) + terminology consistency coefficient × weight (e.g., 30%).

[0081] Figure 8 This is a second schematic diagram of a game strategy generation interactive interface provided by an embodiment of the present application, referring to Figure 8,After obtaining the style index and the professional index, the game strategy and the ,corresponding style index and professional index are displayed on the ,interactive interface. Figure 8 As shown, the style index of this game strategy is 75%, and the corresponding professional index is 50%.

[0082] As described above, by displaying the style index and professionalism index of the generated game guide in the interactive interface, it is convenient for users to know whether the style index and professionalism index of the game guide meet their own needs. If not, they can adjust the style index and professionalism index of the game guide according to their own needs, thereby improving the user experience.

[0083] S22: Receive an adjustment instruction based on the style index and the professionalism index, and obtain a target style index and a target professionalism index according to the adjustment instruction.

[0084] After the game strategy and the style index and professionalism index corresponding to the game strategy are displayed on the interactive interface, if the displayed style index and professionalism index do not meet the user's needs, the user can adjust the style index and professionalism index accordingly based on the interactive interface. Figure 8 The user can drag the progress bar corresponding to the style index and professionalism index to enter the corresponding adjustment instructions. The adjustment instructions based on the style index and professionalism index are received, and the target style index and target professionalism index are determined based on the adjustment instructions. For example, if the original style index is 75%, and the user drags the style index progress bar to 85%, the target style index will be 85%; if the original professionalism index is 50%, and the user drags the professionalism index progress bar to 90%, the target professionalism index will be 90%.

[0085] As described above, the style index and professionalism index of the generated game guide are adjusted accordingly through adjustment commands, so that the adjusted target style index and target professionalism index can meet the user's needs, thereby improving the user experience. In addition, by simply adjusting the style index and professionalism index, new game guides can be automatically generated based on the target style index and target professionalism index, without the need for manual rewriting or adjustment, greatly improving the efficiency of game guide adjustment and further enhancing the user experience.

[0086] S23. Regenerate a new game strategy based on the target style index and the target professionalism index based on the user demand information and the style selection instruction.

[0087] Comparing the target style index with the original style index, if the target style index is greater than the original style index, the strategy is determined to include increasing slang, emoticons, and short sentence rhythm; if the target style index is less than the original style index, the strategy is determined to include reducing slang, emoticons, and short sentence rhythm. Comparing the target professionalism index with the original professionalism index, if the target professionalism index is greater than the original professionalism index, the strategy is determined to include adding mechanism decomposition and numerical formulas; if the target professionalism index is less than the original professionalism index, the strategy is determined to include reducing mechanism decomposition and numerical formulas. For example, based on the determined strategy, the target style index can be decomposed into executable language feature parameters, such as: 20 emoticons per 100 characters, 30% internet buzzwords, and 60% irony intensity. Based on the determined strategy, the target professionalism index can be decomposed into content depth parameters, such as: 25% professional terminology, 3 formulas, and version comparison analysis. Based on the decomposed language feature parameters and content depth parameters, key prompt words are reconstructed based on user demand information. For example, the original key prompt (Style Index 75% + Expertise Index 50): "Character B's Shield Strategy"; the new prompt: "Using memes like 'Internet buzzword XXX' (Style (Humor) Index 90%+), combined with a comparison of shield formulas in versions 3.8 and 4.0 (Expertise Index 85%+), a detailed analysis of Character B's shield threshold calculation (including three formulas)." Based on the new key prompt, a new game strategy of the corresponding style is regenerated, ensuring that the generated game strategy meets the target Style Index and Expertise Index.

[0088] As described above, regenerating new game strategies driven by the style index and professionalism index greatly improves the efficiency of game strategy adjustment compared to manual writing and adjustment. Furthermore, the corresponding style index and professionalism index can be adjusted according to the user's personalized needs. This allows the generated new game strategy based on the adjusted target style index and professionalism index to meet the user's personalized needs, significantly improving the user experience.

[0089] Based on the above embodiments, Figure 9 This is a schematic diagram of the structure of a game strategy generation device provided by an embodiment of the present application. Figure 9 The game strategy generating device provided in this embodiment specifically includes: an information receiving module 21, a template determining module 22, a prompt word determining module 23 and a strategy generating module 24.

[0090] The information receiving module 21 is used to receive user demand information and style selection instructions; A template determination module 22 is configured to determine a strategy style template according to the style selection instruction, wherein the user requirement information includes one or more of the game name, game version, game character, strategy direction, and target audience; The prompt word determination module 23 is used to construct a knowledge graph based on the user demand information and the set knowledge base to obtain key prompt words; The strategy generation module 24 is used to generate executable strategy generation instructions based on key prompt words and strategy style templates, and execute the strategy generation instructions to generate a game strategy of a corresponding style.

[0091] In one embodiment, the game strategy generating device further comprises: a reference material receiving module, a reference material parsing module and a knowledge base generating module; A reference material receiving module, configured to receive game reference materials, wherein the reference materials include one or more of game standard definitions, game encyclopedia data, cost strategies for the game, strategies for pan-game finished products, and restriction rules; Reference data parsing module, used to parse game reference data to obtain metadata; The knowledge base generation module is used to annotate metadata and generate the corresponding knowledge base.

[0092] In one embodiment, the prompt word determination module 23 includes: an index determination submodule, a retrieval submodule, a graph construction submodule, and a key prompt word determination submodule; The index determination submodule is used to determine the search index according to the user's demand information; The retrieval submodule is used to retrieve metadata based on the set knowledge base according to the retrieval index to obtain the target triple data; The graph construction submodule is used to construct a knowledge graph based on the target triple data; The key word determination submodule is used to extract key words from the constructed knowledge graph.

[0093] In one embodiment, the strategy generation module 24 includes: a sub-instruction determination sub-module, a text generation sub-module, a picture acquisition sub-module, and a picture-text fusion sub-module; The sub-command determination sub-module is used to determine the text generation sub-command, image acquisition sub-command, and image-text integration sub-command in the strategy generation command; The text generation submodule is used to execute the text generation sub-instruction to generate the game strategy text of the corresponding style; The image acquisition submodule is used to execute the image acquisition sub-command, obtain the corresponding game screenshots from the set knowledge base according to the game strategy text, and obtain the target image; The image-text fusion submodule is used to execute the image-text integration sub-instruction, perform image-text fusion processing on the game strategy text and the target image, and obtain the first target game strategy.

[0094] In one embodiment, the strategy generation module 24 further includes: a video acquisition submodule, a video editing submodule, a video synthesis submodule, and a subtitle fusion submodule; The sub-command determination sub-module is further used to determine the text generation sub-command, video acquisition sub-command, video synthesis sub-command, and video text fusion sub-command in the strategy generation command; The text generation submodule is also used to execute the text generation sub-instruction to generate the game strategy text of the corresponding style; The video acquisition submodule is used to execute the video acquisition sub-command and obtain the corresponding target game video from the set knowledge base according to the user's demand information; The video editing submodule is used to edit the target game video according to the key prompt words to obtain the target video clip; The video synthesis submodule is used to execute the video synthesis sub-instruction, dynamically synthesize the target video clip according to the game strategy text, and obtain the initial strategy video; The subtitle fusion submodule is used to execute the video text fusion sub-instruction to embed the game strategy text into the initial strategy video to obtain the second target game strategy.

[0095] In one embodiment, the game strategy generating device further includes: a display module, an adjustment module, and a strategy regeneration module; A display module is used to display the game strategy and the style index and professionalism index corresponding to the game strategy on the interactive interface; An adjustment module, configured to receive an adjustment instruction based on the style index and the professionalism index, and obtain a target style index and a target professionalism index according to the adjustment instruction; The strategy regeneration module is used to regenerate a new game strategy based on the target style index and target professionalism index based on user demand information and style selection instructions.

[0096] In one embodiment, the information receiving module 21 includes: an information receiving submodule, a speech analysis submodule, a text analysis submodule, and an image recognition submodule; The information receiving submodule is used to receive voice information, text descriptions or pictures input by the user; The voice analysis submodule is used to perform text analysis on the received voice information to obtain the corresponding user demand information; The text parsing submodule is used to perform semantic analysis on the received text description to obtain the corresponding user demand information; The picture recognition submodule is used to perform intelligent recognition processing on the received pictures to obtain the corresponding user demand information.

[0097] The game strategy generation device provided in the embodiment of the present application can be used to execute the game strategy generation method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0098] The present application embodiment provides a game strategy generating device, referring to Figure 10 The game strategy generation device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors in the game strategy generation device can be one or more, and the number of memories in the game strategy generation device can be one or more. The processor, memory, communication module, input device, and output device of the game strategy generation device can be connected via a bus or other means.

[0099] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the game strategy generation method of any embodiment of the present application (e.g., the information receiving module, template determination module, prompt word determination module, and strategy generation module in the game strategy generation device). The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on device usage, etc. Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the memory may further include memory remotely located relative to the processor, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0100] The communication module 33 is used for data transmission.

[0101] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory, that is, implements the above-mentioned game strategy generation method.

[0102] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0103] The game strategy generation device provided above can be used to execute the game strategy generation method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0104] An embodiment of the present application also provides a storage medium storing computer-executable instructions, which, when executed by a computer processor, are used to execute a game strategy generation method, the game strategy generation method comprising: receiving user demand information and a style selection instruction, and determining a strategy style template according to the style selection instruction, wherein the user demand information includes one or more of a game name, a game version, a game character, a strategy direction, and a target audience; constructing a knowledge graph based on a set knowledge base according to the user demand information to obtain key prompt words; generating an executable strategy generation instruction according to the key prompt words and the strategy style template, and executing the strategy generation instruction to generate a game strategy of a corresponding style.

[0105] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROMs, floppy disks, or tape drives; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or it may be located in a different second computer system that is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). The storage medium may store program instructions (e.g., embodied as a computer program) that can be executed by one or more processors.

[0106] Of course, the computer executable instructions of the storage medium storing computer executable instructions provided in the embodiment of the present application are not limited to the game strategy generation method described above, and can also execute related operations in the game strategy generation method provided in any embodiment of the present application.

[0107] The game strategy generation device, storage medium and game strategy generation equipment provided in the above embodiments can execute the game strategy generation method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the game strategy generation method provided in any embodiment of the present application.

[0108] The above are only preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that are possible for those skilled in the art will not depart from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include more other equivalent embodiments without departing from the concept of the present application. The scope of the present application is determined by the scope of the claims.

Claims

1. A method for generating a game strategy, characterized in that: include: receiving user demand information and a style selection instruction, and determining a strategy style template according to the style selection instruction, wherein the user demand information includes one or more of a game name, a game version, a game character, a strategy direction, and a target audience; According to the user demand information, a knowledge graph is constructed based on a set knowledge base to obtain key prompt words; An executable strategy generation instruction is generated according to the key prompt words and the strategy style template, and the strategy generation instruction is executed to generate a game strategy of a corresponding style.

2. The method according to claim 1, characterized in that Before constructing the knowledge graph based on the set knowledge base according to the user demand information, the method further includes: Receiving game reference materials, the reference materials including one or more of game standard definitions, game encyclopedia data, cost strategies for the game, pan-game finished product strategies, and restriction rules; The game reference material is parsed to obtain metadata, and the metadata is annotated to generate a corresponding knowledge base.

3. The method according to claim 2, characterized in that The knowledge graph is constructed based on the user demand information and the set knowledge base to obtain key prompt words, including: Determine a search index according to the user demand information; Perform metadata retrieval based on the set knowledge base according to the retrieval index to obtain target triple data; A knowledge graph is constructed based on the target triple data, and key prompt words are extracted from the constructed knowledge graph.

4. The method according to claim 1, wherein The step of executing the strategy generation instruction to generate a game strategy of a corresponding style includes: Determine the text generation sub-instruction, the image acquisition sub-instruction, and the image and text integration sub-instruction in the strategy generation instruction; Execute the text generation sub-instruction to generate a game strategy text of a corresponding style; Execute the picture acquisition sub-instruction to obtain the corresponding game screenshot from the set knowledge base according to the game strategy text to obtain the target picture; The image-text integration sub-instruction is executed to perform image-text fusion processing on the game strategy text and the target image to obtain a first target game strategy.

5. The method according to claim 1, wherein The step of executing the strategy generation instruction to generate a game strategy of a corresponding style includes: Determine the text generation sub-command, video acquisition sub-command, video synthesis sub-command, and video text fusion sub-command in the strategy generation command; Execute the text generation sub-instruction to generate a game strategy text of a corresponding style; Executing the video acquisition sub-instruction to acquire a corresponding target game video from a set knowledge base according to the user demand information, and editing the target game video according to the key prompt words to obtain a target video clip; Executing the video synthesis sub-instruction to dynamically synthesize the target video clip according to the game strategy text to obtain an initial strategy video; Execute the video-text fusion sub-instruction to embed the game strategy text into the initial strategy video to obtain a second target game strategy.

6. The method according to claim 1, characterized in that After executing the strategy generation instruction to generate a game strategy of a corresponding style, the method further includes: Displaying the game strategy and the style index and professionalism index corresponding to the game strategy on an interactive interface; receiving an adjustment instruction based on the style index and the professionalism index, and obtaining a target style index and a target professionalism index according to the adjustment instruction; A new game strategy is regenerated based on the target style index and the target professionalism index based on user demand information and style selection instructions.

7. The method according to claim 1, characterized in that The receiving of user demand information includes: Receive voice information, text descriptions or pictures input by users; Perform text analysis on the received voice information to obtain the corresponding user demand information; Alternatively, semantic analysis is performed on the received text description to obtain corresponding user demand information; Alternatively, intelligent recognition processing is performed on the received images to obtain corresponding user demand information.

8. A game strategy generating device, characterized in that: include: An information receiving module, used for receiving user demand information and style selection instructions; A template determination module, configured to determine a strategy style template according to the style selection instruction, wherein the user requirement information includes one or more of a game name, a game version, a game character, a strategy direction, and a target audience; A prompt word determination module is used to construct a knowledge graph based on the user demand information and a set knowledge base to obtain key prompt words; The strategy generation module is used to generate an executable strategy generation instruction according to the key prompt words and the strategy style template, and execute the strategy generation instruction to generate a game strategy of the corresponding style.

9. A game strategy generating device, characterized in that: include: memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the computer executable instructions are used to perform the method according to any one of claims 1 to 7.

Images