Content recommendation method and server for a game creativity workshop

Abstract

This invention discloses a content recommendation method and server for a game creative workshop. It acquires player client's in-game action data and a comprehensive score of creative content in the creative workshop database. Based on the action data and the comprehensive score, it calculates the match between the player client and the creative content, and then filters and displays creative content according to the match score. Therefore, it can combine player client's in-game action behavior for creative content matching and recommendation, thereby effectively improving the adaptability of content recommendations for player clients in the game creative workshop.

Description

Technical Field

[0001] This invention relates to the technical field of content recommendation, and in particular to a content recommendation method and server for a game creative workshop. Background Technology

[0002] Currently, game workshops typically allow players to customize, expand, and modify game content, and to upload and download their custom content. Furthermore, game workshop content is usually recommended based on player community voting results and popular rankings.

[0003] However, current game workshop content recommendations can only be based on players' browsing preferences and the popularity of the creative content itself, making it difficult to improve the personalization of recommendations. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a content recommendation method and server for the game creative workshop, which can effectively improve the adaptability of content recommendations for players in the game creative workshop.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for recommending content in the Game Workshop, including the following steps: S1. The server obtains the player client's operation behavior data in the game and the comprehensive score of each creative content in the game's creative workshop database, and calculates the matching degree between the player client and the creative content based on the operation behavior data and the comprehensive score of the creative content; S2. The server filters creative content with a matching degree greater than the matching threshold and displays the creative content in descending order according to the matching degree.

[0006] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is as follows: A content recommendation server for a game creative workshop includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps of the content recommendation method for a game creative workshop described above.

[0007] The beneficial effects of this invention are as follows: it acquires player client's in-game action data and a comprehensive score of creative content in the game's creative workshop database; it calculates the match between the player client and the creative content based on the action data and the comprehensive score; and it filters and displays creative content based on the match score. Therefore, it can combine player client's in-game action data for matching and recommending creative content, thereby effectively improving the adaptability of content recommendations for player clients in the game's creative workshop. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating a content recommendation method for a game creative workshop according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a content recommendation server for a game creative workshop according to an embodiment of the present invention; Label Explanation: 1. A content recommendation server for a game creative workshop; 2. Storage; 3. Processor. Detailed Implementation

[0009] To explain in detail the technical content, objectives, and effects of the present invention, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0010] Please refer to Figure 1 This invention provides a content recommendation method for a game creative workshop, including the following steps: S1. The server obtains the player client's operation behavior data in the game and the comprehensive score of each creative content in the game's creative workshop database, and calculates the matching degree between the player client and the creative content based on the operation behavior data and the comprehensive score of the creative content; S2. The server filters creative content with a matching degree greater than the matching threshold and displays the creative content in descending order according to the matching degree.

[0011] As described above, the beneficial effects of this invention are as follows: the server obtains the player's client's operational behavior data in the game and the comprehensive score of creative content in the game's creative workshop database; it calculates the matching degree between the player's client and the creative content based on the operational behavior data and the comprehensive score of the creative content; and it filters and displays creative content based on the matching degree. Therefore, it can combine the player's client's game operational behavior to match and recommend creative content, thereby effectively improving the adaptability of content recommendations for player clients in the game's creative workshop.

[0012] Furthermore, step S1 is preceded by: The server periodically retrieves the number of likes, comments, and downloads for each creative content from the game's Steam Workshop database, and calculates a comprehensive score using a weighted average method. Overall score = (Number of likes × Like weight + Number of comments × Comment weight + Number of downloads × Download weight) / (Like weight + Comment weight + Download weight).

[0013] As described above, by comprehensively scoring each creative content in the Creative Workshop database, it becomes easier to recommend more popular creative content.

[0014] Further, step S1 includes: The server acquires player client's operational behavior data in the game, including skill usage frequency, operation shortcut key usage frequency, and game element attention frequency. Based on the operational behavior data, the server analyzes the player client's game style and preferred content. The server matches creative content with the same game style and preferences based on the player's client's game style and preferences, and calculates the match degree between the player's client and the creative content based on the comprehensive score of the creative content.

[0015] As described above, by analyzing players' game operation behavior data to determine their game style, and then matching creative content with the game style and its corresponding preferences, the matching degree between players and creative content is calculated based on the comprehensive score of the creative content. This method can not only provide creative content that is highly compatible with players' game habits, but also prioritize recommending content based on its popularity, thereby improving the adaptability of the recommended content.

[0016] Furthermore, based on the aforementioned operational behavior data, the player client's game style and preferences are analyzed, including: The server calculates a weighted average of the frequency of skill usage and the frequency of operation shortcut key usage to obtain a first style score, and uses the frequency of attention to game elements as a second style score. If the first style score is greater than the second style score, the player client is determined to be of the first style, and the player client's preferred skill data and preferred operation shortcuts are determined based on the frequency of skill use and the frequency of operation shortcut use. If the first style score is less than or equal to the second style score, the player client is determined to be of the second style, and the player client's preferred game elements are determined based on the frequency of attention to the game elements.

[0017] As described above, the competitive game style score is calculated based on the frequency of skill usage and the frequency of operation shortcut key usage, while the event-based game style score is determined based on the frequency of attention to game elements. By comparing the two scores, the player's game style can be determined and the corresponding preferred content can be analyzed, thereby improving the accuracy of content recommendations.

[0018] Furthermore, based on the player's client's game style and preferred content, creative content with the same game style and similar preferences is matched, and the match degree between the player's client and the creative content is calculated by combining the comprehensive score of the creative content, including: The server calculates a player feature vector based on the player's client's game style and preferred content, calculates a content feature vector based on the matched creative content, and performs a similarity calculation on the player feature vector and the content feature vector. The server uses the overall score of the creative content as the weight for the similarity calculation result to calculate the matching degree between the player's client and the creative content.

[0019] As described above, the similarity between players and content is calculated by calculating player feature vectors and content feature vectors, and the comprehensive score of creative content is used as the weight of the similarity calculation result to improve the accuracy of matching.

[0020] Please refer to Figure 2 Another embodiment of the present invention provides a content recommendation server for a game creative workshop, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps of the above-described content recommendation method for a game creative workshop.

[0021] The content recommendation method and server for a game creative workshop described above are applicable to effectively improving the adaptability of content recommendations for players in the game creative workshop. The following is a detailed description of the implementation methods: Please refer to Figure 1 Embodiment 1 of the present invention is as follows: A method for recommending content in the Game Workshop, including the following steps: S1. The server obtains the player client's operation behavior data in the game and the comprehensive score of each creative content in the game's creative workshop database, and calculates the matching degree between the player client and the creative content based on the operation behavior data and the comprehensive score of the creative content.

[0022] In this embodiment, the creation interface of the Creative Workshop needs to be displayed first, allowing players to customize the game interface layout and gameplay settings. After completing the settings, the creation is uploaded and stored via the upload interface. For example, in the creation interface, players can arrange skill icons according to their preferred combat flow, adjust the transparency and size of the information display, and then upload the creation to the game's Creative Workshop database and name it. The Creative Workshop database can use category tags to categorize designs, such as "Skill Layout" and "Gameplay Rules," and provides a sorting function based on popularity, recent uploads, etc., and includes a search box to help players quickly find content of interest.

[0023] Before step S1, it is necessary to calculate the overall score of each creative content in the Game Workshop: periodically obtain metrics such as the number of likes, comments, and downloads for each creative content in the Game Workshop database. An overall score is calculated based on a preset algorithm to assess the popularity of the creative content.

[0024] Specifically, a weighted average method can be used to calculate the overall score: Overall score = (Number of likes × Like weight + Number of comments × Comment weight + Number of downloads × Download weight) / (Like weight + Comment weight + Download weight).

[0025] In step S1, the player's in-game action data is first acquired. This data includes skill usage frequency, shortcut key usage frequency, and game element attention frequency. Based on this action data, the player's gaming style and preferred content are analyzed. A weighted average of the skill usage frequency and the operation shortcut key usage frequency is calculated to obtain a first style score, and the game element attention frequency is used as a second style score. If the first style score is greater than the second style score, the player client is determined to be of the first style, and the player's preferred skill data and preferred operation shortcut keys are determined based on the skill usage frequency and the operation shortcut key usage frequency. If the first style score is less than or equal to the second style score, the player client is determined to be of the second style, and the player client's preferred game elements are determined based on the game element attention frequency.

[0026] Then, based on the player's client's game style and preferred content, creative content with the same game style and similar preferences is matched, and the match degree between the player's client and the creative content is calculated by combining the comprehensive score of the creative content: Player feature vectors are calculated based on the game style and content preferences of the player's client, and content feature vectors are calculated based on the matched creative content. Similarity is calculated between the player feature vectors and the content feature vectors. The overall score of the creative content is used as the weight of the similarity calculation result to calculate the matching degree between the player's client and the creative content.

[0027] Therefore, in addition to analyzing conventional metrics such as likes, comments, and downloads of creative content, this embodiment further analyzes players' actual in-game behavioral data, such as the frequency of skill usage in different scenarios, attention paid to different information display elements, and usage habits of operation shortcuts. By analyzing this detailed behavioral data, a more accurate understanding of players' gaming styles and preferences can be achieved. That is, when players browse the Workshop, recommendations are not only made based on the overall rating of creative content, but also by considering the player's own behavioral characteristics to filter out designs that highly match the player's gaming style. This prioritizes recommending creative content with higher ratings that optimize the skill layout or incorporate gameplay settings related to the skill.

[0028] Because players of different playstyles may have different needs and preferences regarding game interface layout and gameplay settings. For example, players of competitive games may pay more attention to the layout of skill icons and the setting of operation hotkeys, while players of role-playing games may focus more on the way information is displayed and the integration of gameplay rules with the storyline. By making targeted recommendations to players of similar styles, the accuracy and effectiveness of the recommendations can be improved, making it easier for players to discover designs that interest them.

[0029] S2. Filter creative content with a matching degree greater than the matching threshold, and display the creative content in descending order of matching degree.

[0030] In some embodiments, players can select a creative content to try out and load it into their game environment. They can then adjust the creative content through a settings interface and save the adjusted version as a personalized creation. For example, players can adjust the skill hotkey settings according to their own operating habits.

[0031] In other embodiments, when a player hovers their mouse over a creative element, a virtual experience window automatically pops up. This window dynamically demonstrates the design's application in actual gameplay. For example, for a skill layout design, the virtual experience window simulates a player using that layout in-game, showcasing the smoothness of the skill icons and their synergy with other game elements. For gameplay rule-based designs, the virtual experience window demonstrates the player's experience following those rules, including quest flows and reward mechanisms. This allows players to more intuitively understand the design's actual effectiveness, improving the accuracy and efficiency of their choices.

[0032] Please refer to Figure 2 Embodiment two of the present invention is as follows: A content recommendation server 1 for a game creative workshop includes a memory 2, a processor 3, and a computer program stored on the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, it implements the various steps of a content recommendation method for a game creative workshop according to Embodiment 1.

[0033] In summary, the content recommendation method and server provided by this invention for a game creative workshop comprehensively scores each creative content in the workshop based on its number of likes, comments, and downloads. It acquires player action data in the game and the comprehensive score of creative content in the workshop, analyzes the player's gaming style and preferred content based on the action data, and then matches creative content with the same game style and preferred content. Furthermore, it calculates the match degree between the player and the creative content based on the comprehensive score of the creative content, and filters and displays creative content based on the match degree. Therefore, it can match and recommend creative content based on player action behavior, thereby effectively improving the adaptability of content recommendations to players in the game creative workshop.

[0034] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent modifications made based on the content of the present invention specification and drawings, or direct or indirect applications in related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A content recommendation method for a game creative workshop, characterized in that, Including the following steps: S1. The server obtains the player client's operation behavior data in the game and the comprehensive score of each creative content in the game's creative workshop database, and calculates the matching degree between the player client and the creative content based on the operation behavior data and the comprehensive score of the creative content; S2. The server filters creative content with a matching degree greater than the matching threshold and displays the creative content in descending order according to the matching degree.

2. The content recommendation method for a game creative workshop according to claim 1, characterized in that, Before step S1, the following are included: The server periodically retrieves the number of likes, comments, and downloads for each creative content from the game's Steam Workshop database, and calculates a comprehensive score using a weighted average method. Overall score = (Number of likes × Like weight + Number of comments × Comment weight + Number of downloads × Download weight) / (Like weight + Comment weight + Download weight).

3. The content recommendation method for a game creative workshop according to claim 1, characterized in that, Step S1 includes: The server acquires player client's operational behavior data in the game, including skill usage frequency, operation shortcut key usage frequency, and game element attention frequency. Based on the operational behavior data, the server analyzes the player client's game style and preferred content. The server matches creative content with the same game style and preferences based on the player's client's game style and preferences, and calculates the match degree between the player's client and the creative content based on the comprehensive score of the creative content.

4. The content recommendation method for a game creative workshop according to claim 3, characterized in that, Based on the aforementioned operational behavior data, the player client's game style and preferences are analyzed, including: The server calculates a weighted average of the frequency of skill usage and the frequency of operation shortcut key usage to obtain a first style score, and uses the frequency of attention to game elements as a second style score. If the first style score is greater than the second style score, the player client is determined to be of the first style, and the player client's preferred skill data and preferred operation shortcuts are determined based on the frequency of skill use and the frequency of operation shortcut use. If the first style score is less than or equal to the second style score, the player client is determined to be of the second style, and the player client's preferred game elements are determined based on the frequency of attention to the game elements.

5. The content recommendation method for a game creative workshop according to claim 3, characterized in that, Based on the player's client's game style and preferred content, creative content with the same game style and similar preferences is matched. The match degree between the player's client and the creative content is calculated by combining the overall score of the creative content, including: The server calculates a player feature vector based on the player's client's game style and preferred content, calculates a content feature vector based on the matched creative content, and performs a similarity calculation on the player feature vector and the content feature vector. The server uses the overall score of the creative content as the weight for the similarity calculation result to calculate the matching degree between the player's client and the creative content.

6. A content recommendation server for a game creative workshop, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it performs the following steps: S1. Obtain the player's client's operation behavior data in the game and the comprehensive score of each creative content in the game's creative workshop database, and calculate the matching degree between the player's client and the creative content based on the operation behavior data and the comprehensive score of the creative content; S2. Filter creative content with a matching degree greater than the matching threshold, and display the creative content in descending order of matching degree.

7. A content recommendation server for a game creative workshop according to claim 6, characterized in that, Before step S1, the following are included: Regularly retrieve the number of likes, comments, and downloads for each creative content in the Game Workshop database, and calculate the overall score using a weighted average method: Overall score = (Number of likes × Like weight + Number of comments × Comment weight + Number of downloads × Download weight) / (Like weight + Comment weight + Download weight).

8. A content recommendation server for a game creative workshop according to claim 6, characterized in that, Step S1 includes: Acquire player client's operational behavior data in the game, including skill usage frequency, operation shortcut key usage frequency, and game element attention frequency; analyze player client's game style and preferred content based on the operational behavior data. Based on the player's client's game style and preferred content, creative content with the same game style and similar preferences is matched, and the match degree between the player's client and the creative content is calculated by combining the comprehensive score of the creative content.

9. A content recommendation server for a game creative workshop according to claim 8, characterized in that, Based on the aforementioned operational behavior data, the player client's game style and preferences are analyzed, including: A weighted average of the frequency of use of the skill and the frequency of use of the operation shortcut is calculated to obtain a first style score, and the frequency of attention to the game element is used as a second style score. If the first style score is greater than the second style score, the player client is determined to be of the first style, and the player client's preferred skill data and preferred operation shortcuts are determined based on the frequency of skill use and the frequency of operation shortcut use. If the first style score is less than or equal to the second style score, the player client is determined to be of the second style, and the player client's preferred game elements are determined based on the frequency of attention to the game elements.

10. A content recommendation server for a game creative workshop according to claim 8, characterized in that, Based on the player's client's game style and preferred content, creative content with the same game style and similar preferences is matched. The match degree between the player's client and the creative content is calculated by combining the overall score of the creative content, including: Calculate player feature vectors based on the game style and content preferences of the player's client, calculate content feature vectors based on the matched creative content, and calculate the similarity between the player feature vectors and the content feature vectors; The overall score of the creative content is used as the weight in the similarity calculation result to calculate the matching degree between the player's client and the creative content.

Images