Path generation method and device, electronic equipment, storage medium and product

Abstract

The invention provides a path generation method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: in response to user interaction operation, obtaining current target behavior intention and game state data of a user; based on the target behavior intention and the game state data, determining at least one target area conforming to the target behavior intention from a game scene feature library; and according to the current position of the user in the game environment and the position of the target area, generating visual guidance information containing path guidance, and pushing the visual guidance information to a user terminal for display.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a path generation method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] In related path generation schemes, static analysis is usually performed based on preset rules or the historical behavioral characteristics of target users to determine the target path to be recommended for the target users. However, this approach cannot respond to the real-time changes in users' needs during the game, resulting in low real-time performance and personalization of the generated strategy paths. Summary of the Invention

[0003] This disclosure provides a path generation method, apparatus, electronic device, storage medium, and product to solve problems in the related art.

[0004] A first aspect of this disclosure provides a path generation method, the method comprising: In response to user interaction, obtain the user's current target behavior intention and game status data; Based on the target behavioral intention and the game state data, at least one target area that matches the target behavioral intention is determined from the game scene feature library; Based on the user's current location in the game environment and the location of the target area, visual guidance information containing path directions is generated and pushed to the user's terminal for display.

[0005] In one embodiment, in response to a user interaction, acquiring the user's current target behavior intention and game state data includes: In response to user interaction, obtain the user's task description information and game status data; The task description information is used to identify the user's target behavior intention, which includes combat, collection, or exploration.

[0006] In one embodiment, before determining at least one target region matching the target behavioral intention from a game scene feature library based on the target behavioral intention and the game state data, the method provided in this disclosure includes: Obtain spatial and visual attribute information of the game's virtual scene; Based on the spatial attribute information and visual attribute information, the game virtual scene is divided into regions to obtain multiple scene regions; Feature extraction is performed on each scene region to generate corresponding regional feature data for each scene region, thus obtaining a game scene feature library.

[0007] In one embodiment, based on the target behavioral intention and the game state data, determining at least one target region from a game scene feature library that matches the target behavioral intention includes: Based on the target behavioral intention and the game state data, user characteristic data is generated; Determine the matching degree between the user feature data and the regional feature data of each scene region; Based on the matching degree from high to low, at least one target region that matches the target behavior intention is determined from the game scene feature library.

[0008] In one embodiment, based on the user's current location in the game environment and the location of the target area, visual guidance information including path guidance is generated, including: The guidance path is determined based on the user's current location in the game environment and the location of the target area; Based on the guide path and the style data of the game screen, visual guidance information containing path guidance is generated, and the visual guidance information is a small map image with path arrows.

[0009] In one embodiment, the method provided in this disclosure further includes: Receive user feedback data regarding the visual guidance information; Based on the feedback data, the weight parameters for matching the target region are adjusted.

[0010] A second aspect of this disclosure provides a path generation apparatus, comprising: The acquisition unit is used to respond to user interaction operations and acquire the user's current target behavior intention and game state data; The determining unit is configured to determine at least one target region that matches the target behavior intention from a game scene feature library based on the target behavior intention and the game state data. The generation unit is used to generate visual guidance information containing path guidance based on the user's current position in the game environment and the position of the target area, and push the visual guidance information to the user terminal for display.

[0011] A third aspect of this disclosure provides an electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods described in the first aspect of this disclosure.

[0012] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0013] A fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the methods described in the first aspect of this disclosure.

[0014] In summary, this disclosure proposes a path generation method, which includes: in response to user interaction operations, acquiring the user's current target behavior intention and game state data; based on the target behavior intention and the game state data, determining at least one target area that matches the target behavior intention from a game scene feature library; generating visual guidance information containing path guidance according to the user's current position in the game environment and the position of the target area, and pushing the visual guidance information to the user terminal for display.

[0015] According to the solution provided in this disclosure, by responding to user interaction operations, the user's current target behavior intention and game state data are obtained; based on the target behavior intention and the game state data, at least one target area that matches the target behavior intention is determined from the game scene feature library, thereby ensuring that the recommendation results are consistent with the user's current needs; by generating visual guidance information containing path guidance based on the user's current location in the game environment and the location of the target area, the visual guidance information is pushed to the user terminal for display, thereby improving the real-time nature and personalization of the game guide.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 A flowchart illustrating the path generation method provided in this embodiment of the disclosure; Figure 2 A schematic diagram of the floating window of the QuickPlay client provided in this embodiment of the disclosure; Figure 3 A schematic diagram of a pop-up dialog window in a fast-play client provided in an embodiment of this disclosure; Figure 4 A schematic diagram of multiple scene areas provided in the embodiments of this disclosure; Figure 5A flowchart illustrating the process of quantifying scene features provided in this embodiment of the disclosure; Figure 6 A schematic diagram illustrating visual guidance information including path directions provided in an embodiment of this disclosure; Figure 7 A schematic diagram illustrating the addition of directional guidance in the QuickPlay client provided in this embodiment of the disclosure; Figure 8 A schematic diagram illustrating visual guidance information including path directions after changing the strategy path according to an embodiment of this disclosure; Figure 9 A schematic diagram illustrating the generation of game guides provided in this embodiment of the disclosure; Figure 10 This is a schematic diagram of the path generation device provided in an embodiment of the present disclosure; Figure 11 This is a schematic diagram of the hardware composition structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0019] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0020] To facilitate a better understanding of the technical solutions described in the embodiments of this disclosure by those skilled in the art, the technical terms in the embodiments of this disclosure are explained as follows before introducing the embodiments of this disclosure.

[0021] Artificial Intelligence Generated Content (AIGC): This refers to content that is automatically generated in various forms, such as text, images, audio, video, and 3D models, using artificial intelligence technology.

[0022] The following is a brief introduction to one approach for path generation in related technologies: This solution proposes a path recommendation method in games. It acquires the behavioral features of target players, which characterize their gameplay within a pre-defined game scenario. A pre-defined path recommendation model is then used to process these behavioral features, yielding the target player's target path features. This model is trained using sample data from multiple players within the pre-defined game scenario. Each player's sample data includes their sample behavioral features and the corresponding path features. Based on these target path features, a recommended target path is determined from the pre-defined game scenario. This method improves the flexibility of path recommendation by determining the target path based on the player's behavioral features. The pre-defined path recommendation model is trained using sample behavioral features from multiple players and the corresponding path features, and the target path is determined based on the target path features output by the model.

[0023] The above solution has the following drawbacks: While existing technical solutions provide instructions for subsequent actions based on the game, they do not consider the user's operational difficulty. This makes them insufficient for players with low operational skills. Furthermore, they cannot personalize and adjust paths in real time according to the game's situation, and the process of processing guidance information is cumbersome, making it difficult to generate the corresponding guidance information quickly and easily.

[0024] To address the shortcomings of related technologies, this disclosure obtains the user's current target behavior intention and game state data in response to user interaction operations; based on the target behavior intention and the game state data, it determines at least one target area from the game scene feature library that matches the target behavior intention, thereby ensuring that the recommendation results are consistent with the user's current needs; and by generating visual guidance information containing path guidance based on the user's current location in the game environment and the location of the target area, it pushes the visual guidance information to the user's terminal for display, thereby improving the real-time nature and personalization of game guides.

[0025] The present disclosure will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0026] The path generation method provided in this disclosure can be applied to various games and interactive scenarios, such as open-world games and multiplayer online tactical arena games. The method can be executed by user terminal devices, cloud server clusters, edge computing nodes, etc.

[0027] like Figure 1 As shown, Figure 1 This is a flowchart illustrating the path generation method provided in this embodiment of the disclosure. The path generation method provided in this embodiment includes the following steps: Step 101: In response to user interaction, obtain the user's current target behavior intention and game state data; In one embodiment, user interaction operations are operations performed by the user through the game client interface, such as text input, voice input, or button selection via a floating window or input box.

[0028] In one embodiment, the target behavior intention refers to the type of behavior that the user currently wishes to perform in the game, including but not limited to combat, collection, and exploration. Combat refers to actively attacking enemies, collection refers to focusing on items, resources, or treasures, and exploration refers to going to unlocked or hidden areas.

[0029] In one embodiment, the game status data reflects quantitative information about the user's current game ability and progress, including but not limited to user level (R) and historical win rate (W), where user level represents the character's growth level and historical win rate represents the user's historical success rate in battles, characterizing operational proficiency.

[0030] In one embodiment, the system monitors the user's active input during gameplay and simultaneously collects their static or dynamic game state data, such as... Figure 2 , Figure 3 As shown, Figure 2 This is a schematic diagram of the floating window of the QuickPlay client provided in an embodiment of this disclosure. Figure 3 This is a schematic diagram of a pop-up dialog window in the Quick Game client provided in this embodiment. The user enters text, such as "I don't have enough supplies, take me to the collection point" or a voice command in the pop-up dialog window of the floating window embedded in the cloud gaming client interface. Natural Language Processing (NLP) can be used to identify the user's behavioral intent indicated by the input text or voice command, or keyword matching can be used to determine the user's behavioral intent. The user's game status data can be read from the game software development kit (SDK), or obtained from local storage or cloud user profile service.

[0031] Step 102: Based on the target behavior intention and the game state data, determine at least one target area that matches the target behavior intention from the game scene feature library; In one embodiment, the game scene feature library is a structured database constructed after preprocessing the game virtual map, containing multiple regions and their corresponding environmental features.

[0032] In one embodiment, the target area is one or more areas in the aforementioned game virtual map that match the user's current behavioral intention, such as areas with high enemy density, locations with many treasure chests, unexplored caves, etc.

[0033] In one embodiment, user feature data is constructed based on the target behavioral intention and the game state data. The user feature data is then matched and calculated with pre-constructed scene block feature data to select the most suitable region as the target region.

[0034] Step 103: Based on the user's current location in the game environment and the location of the target area, generate visual guidance information containing path guidance, and push the visual guidance information to the user terminal for display.

[0035] In one embodiment, the path guidance refers to a recommended route from the user's current location to the center point of the target area.

[0036] In one embodiment, the path guide can be a straight path, a polyline path, or a multi-node path.

[0037] In one embodiment, visual guidance information refers to path guidance content presented in a graphical manner, such as a small map with arrows, an augmented reality (AR) overlay path, or a three-dimensional (3D) directional marker.

[0038] In one embodiment, the user terminal is a device running cloud gaming or fast-play clients, such as a mobile phone, tablet, computer, or smart TV.

[0039] In one embodiment, relative coordinates are determined based on the user's current position in the game environment and the position of the target area, and visual guidance information containing path guidance is generated using an AIGC diffusion model or a real-time rendering engine.

[0040] In one embodiment, the visual guidance information can be pushed to the user terminal for display via a floating window, or it can be pushed to the user terminal for display via a WebSocket stream.

[0041] By responding to user interaction, the system acquires the user's current target behavior intention and game state data; based on the target behavior intention and game state data, it determines at least one target area from the game scene feature library that matches the target behavior intention, thereby ensuring that the recommendation results are consistent with the user's current needs; by generating visual guidance information containing path guidance based on the user's current location in the game environment and the location of the target area, the system pushes the visual guidance information to the user's terminal for display, thereby improving the real-time nature and personalization of the game guide.

[0042] In one embodiment, in response to a user interaction, acquiring the user's current target behavior intention and game state data includes: In response to user interaction, obtain the user's task description information and game status data; The task description information is used to identify the user's target behavior intention, which includes combat, collection, or exploration.

[0043] In one embodiment, the user's task description information can be a specific game request in the form of text or in the form of voice, such as "Take me to fight the BOSS" or "Take me to find the nearby treasure chest".

[0044] In one embodiment, an NLP model can be used to identify semantic intent in task description information and determine the user's target behavioral intention. The NLP model can be a bidirectional encoder representation transformer (BERT) model or a knowledge integration-based enhanced representation (ERNIE) model.

[0045] In one embodiment, keyword matching can also be used to identify semantic intent in task description information to determine the user's target behavior intention, such as fighting for combat and treasure chests for collection.

[0046] In one embodiment, before determining at least one target region matching the target behavior intention from a game scene feature library based on the target behavior intention and the game state data, the path generation method includes: Obtain spatial and visual attribute information of the game's virtual scene; In one embodiment, the game virtual scene is a three-dimensional or two-dimensional interactive map environment in the game, such as an open world or a dungeon. The spatial attribute information of the game virtual scene is used to describe its geometric structure, including at least height differences, which can be represented by Z-axis values ​​to indicate differences in terrain undulation, coordinate positions (X, Y), and path reachability. The visual attribute information is data used to describe the appearance style of the game virtual scene, including at least red, green, and blue (RGB) color parameters and texture complexity.

[0047] In one embodiment, the game engine provides a terrain editor, allowing developers to create and edit terrain in the game scene. The terrain is represented as a 3D mesh, with a height value stored at each mesh point. When the game is cloud-based or launched, the game engine uses a rendering algorithm to present the terrain model on the screen. During rendering, the engine traverses each vertex of the terrain and calculates the actual 3D position based on its height value. This allows us to derive the Z-axis difference for each object, i.e., the height difference between the object's position (here, the top of the object is used to represent its Z-axis position) and a reference plane (such as the ground). Similarly, the game engine renders the scene using the rendering pipeline based on information such as light sources, object positions, and material properties. During this process, the final color and brightness values ​​of each pixel are calculated. We can then use techniques such as screenshots or screen recording to save the rendered scene as a two-dimensional image. This image contains the overall scene presentation, including the color and brightness information of various objects. This allows us to collect the RGB parameters δ, ε, and ζ (δ, ε, and ζ represent the red, green, and blue components, respectively) of each pixel in the scene.

[0048] Based on the spatial attribute information and visual attribute information, the game virtual scene is divided into regions to obtain multiple scene regions; In one embodiment, the map is clustered according to spatial and visual similarity to form multiple scene regions that are homogeneous internally and heterogeneous externally. Each scene region has relatively consistent environmental characteristics, such as forest areas, castle interiors, and desert edges.

[0049] In one embodiment, the multiple scene regions can be regular grid graphics or irregular polygons.

[0050] In one embodiment, the game virtual scene is divided into multiple scene regions based on the spatial attribute information and visual attribute information. The specific implementation steps are as follows: (1) Since the size of the partition and the size of the known game scene are defined in the above process, the number of partitions k to be generated can be obtained.

[0051] (2) Since the RGB data δ, ε, ζ are known, a numerical expression for the RGB parameters can be defined based on these parameters as follows:

[0052] r is the calculated RGB parameter. These are custom weight values ​​based on the three primary color components: red, green, and blue.

[0053] The above process yielded the height and RGB values ​​of each point in the scene. Using these two features as the x and y axes respectively, the coordinate coefficients (r, y) of all points can be obtained. h).

[0054] (3) Randomly select k block centers and denot them as Assuming these k points are the proposed centers of the blocks, and drawing on the K-means clustering algorithm, it is found that by selecting the proposed center point with the shortest distance among all points and dividing the blocks into partitions, and then selecting the most suitable center point within each partition to re-partition, the optimal partition can be obtained. The mathematical expression of the loss function is:

[0055] in For any point, express The partition to which it belongs To determine the center point, M represents the total number of points. The optimal values ​​for the k partitions can be obtained by minimizing the loss function, as detailed below: <1> Set an iteration step t = 0, 1, 2, ..., and repeatedly calculate each point. Assign it to the nearest center, satisfying the following constraints:

[0056] <II> After the initial partitioning, the most suitable center point within each partition is reselected, based on the following selection criteria:

[0057] Where b is the partition The total number of midpoints is used to reselect the center point. Then, repeat the above steps. <1> Re-partition the scene until all iterations are exhausted, and obtain each optimal partition and its contained points. The block enclosed by all the points is taken as a separate partition, and each partition is a scene area.

[0058] Feature extraction is performed on each scene region to generate corresponding regional feature data for each scene region, thus obtaining a game scene feature library.

[0059] In one embodiment, regional feature data refers to the numerical values ​​extracted from each scene region, such as average height feature value, average color feature value, etc.

[0060] In one embodiment, different scene areas, due to their different characteristics, can be adapted to different user intention behaviors such as combat, collection, and exploration.

[0061] In one embodiment, the block data is quantified and stored: Since the optimal partition and the point data contained therein were obtained in the above steps, in order to more intuitively represent the partition characteristics, the bit data is averaged to obtain the average color feature value of the partition data. Average height characteristic value The mathematical expressions are as follows:

[0062]

[0063] Where 'c' represents the partition, and 'b' is the total number of points contained in partition 'c'. This represents the height of the point. These are the color feature values ​​for the location. Finally, all feature data for this area is obtained: average color feature value. Average height characteristic value RGB data of feature points , , After storing the data, to facilitate subsequent steps, the coordinates of the block's center point are recorded for easy navigation and information collection. Figure 4 As shown, Figure 4 A schematic diagram of multiple scene areas provided in the embodiments of this disclosure.

[0064] In one embodiment, the game scene feature library can be built offline when the game version is updated, or it can be built online by scanning upon first launch, or it can be built uniformly in the cloud in advance.

[0065] In one embodiment, game scene information is evaluated and classified according to game characteristics to obtain the category corresponding to each game scene. The categories include combat scene, collection scene and exploration scene.

[0066] After defining the extraction parameters for game features, the recommended features for specific game scenes are numericalized based on these parameters. First, a certain number of game scene sample data are pre-set. Then, by extracting their feature parameters, the corresponding feature classification Y and average color feature value are recorded. Average height characteristic value Secondly, manual evaluation of the pre-built models' strategy features is required, defining corresponding feature values ​​based on different scene characteristics. Using collected scene data, a machine learning model is built and trained. Through learning from the training data, the model can learn the correlation between scene features and recommended values, allowing for intelligent evaluation of recommended values ​​based on strategy parameters. Finally, a large number of models are imported to ensure a sufficient number of scene samples across various numerical feature ranges. Figure 5 As shown, Figure 5 This is a flowchart illustrating the scene feature quantification process provided in this embodiment of the disclosure. The specific implementation method is as follows: (1) Feature extraction: Numerical feature quantization is performed on one of the scene samples, and its feature classification numerical simulation is as follows: The average color feature value is simulated as The average height characteristic value is simulated as Define a controllable function to obtain the total quantized value of a scene feature.

[0067]

[0068] Where r is the calculated feature value. Custom weight values.

[0069] (2) Function Model Construction: To intelligently evaluate the features of game strategies, this project trains a Convolutional Neural Network (CNN). By reading the parameter features and difficulty evaluation results of existing samples, the scene features and recommended values ​​are implicitly encoded in the neural network, thus enabling modeling. A proposed function model for scene feature parameters and recommended values ​​can be derived, and open parameters can be used... Determine the function model with the characteristic parameter r:

[0070] in, These are scene feature values. For controllable weight parameters (their influence value is...) ), For characteristic values, To assess the numerical differences, The proposed loss function model is as follows.

[0071] During the training process, it is necessary to simulate the process to address uncertainties. By making optimal numerical adjustments, the final CNN model can be obtained.

[0072] (3) Model Training: In the above process, we obtained the initial relationship function model between scene feature parameters and feature values. Next, we need to adjust the uncertain parameters through model training to obtain the optimal model, that is, the final CNN. Since the pre-set strategy samples have been processed in advance, we first divide the training set. When there is enough data, we use 50% of the dataset as the training set and 50% as the test set. When the dataset is not large, we use 80% of the dataset as the training set and 20% as the test set.

[0073] After the data preparation is complete, the initial CNN model is used to analyze the feature parameters of the training set. The parameters are adjusted by comparing the numerical results to minimize the difference in evaluation values. Training ends when the difference is equal to or less than our expected value, and the final strategy evaluation model is obtained. Finally, the performance of the established strategy evaluation model is verified by the test set.

[0074] (4) After obtaining the ability to analyze the difficulty of the strategy, we can use a large number of model outputs to pre-set the scene information with corresponding values ​​for each recommendation category interval as much as possible, so as to facilitate subsequent intelligent strategy recommendations in response to different user choices.

[0075] In one embodiment, based on the target behavioral intention and the game state data, determining at least one target region from a game scene feature library that matches the target behavioral intention includes: Based on the target behavioral intention and the game state data, user characteristic data is generated; Determine the matching degree between the user feature data and the regional feature data of each scene region; Based on the matching degree from high to low, at least one target region that matches the target behavior intention is determined from the game scene feature library.

[0076] In one embodiment, user feature data is generated based on the target behavioral intention and the game state data. The discrete target behavioral intention and game state data can be uniformly encoded into fixed-dimensional user feature data, such as intention_combat, intention_collection, intention_exploration, R_norm, W_norm, for use as input to the model.

[0077] In one embodiment, user feature data can be generated using one-hot encoding based on the target behavioral intention and the game state data.

[0078] For example, a pre-trained natural language processing model can be used to perform natural language recognition on text or voice information input by the user through an interactive interface to obtain the user's intent.

[0079] If a user enters the text "I'm running out of supplies, take me to collect some supplies" through the input window of the game's interactive interface, the pre-trained natural language processing model will perform natural language recognition on the text, determining that the user's intent is "collect supplies," and then compare it with the expected feature values ​​corresponding to "collect supplies." Perform a match.

[0080] Simultaneously, based on the aforementioned collected user levels and win rates, quantification is performed. Assuming that a numerical feature quantification is performed on one user's information, its level value is... Its win rate The user's expected feature values ​​are obtained through a natural language processing model. At this point, we can define a controllable function to obtain a quantified total value of a user feature.

[0081]

[0082] in, For the calculated characteristic values, Custom weight values.

[0083] (1) Let the user be represented as v, and the model numerical sample be denoted as v. We can obtain a relevant loss function:

[0084] in For different users, N is the total number of matched samples.

[0085] (2) Calculate the minimum loss value between each matched sample and the user sample:

[0086] Where d is the minimum loss value, i is a random number representing the i-th matched sample, and k is a fixed value representing a certain patient sample. Let be the variable threshold for sample i. When k remains constant, the sample i that minimizes d is the best-matching sample.

[0087] In one embodiment, based on the user's current location in the game environment and the location of the target area, visual guidance information including path guidance is generated, including: The guidance path is determined based on the user's current location in the game environment and the location of the target area; Based on the guide path and the style data of the game screen, visual guidance information containing path guidance is generated, and the visual guidance information is a small map image with path arrows.

[0088] In one embodiment, the user's current position in the game environment refers to the real-time coordinates of the user character in the game world coordinate system, which is usually provided by the game engine or client SDK, and the position of the target area usually refers to the coordinates of its center point.

[0089] In one embodiment, the style data of the game screen refers to visual feature information describing the art style of the game, which is used to ensure that the generated guide image is consistent with the style of the original game screen, including but not limited to color scheme, such as dark, cartoon, or realistic; and user interface element styles, such as icons, fonts, borders, etc.

[0090] In one embodiment, the small map image refers to a dynamic arrow superimposed on the background of the thumbnail map, pointing to the target direction or path.

[0091] For example, the current user orientation is obtained through the client SDK, and the user's current position is placed in the center of the minimap. The target scene position is calculated proportionally and placed in a relative position, as follows: Assuming the user's location is set as the origin (0,0) with its orientation in the positive y-axis direction, and the center coordinates of the target area are (x,y), we can obtain the horizontal distance x and vertical distance y from the user, thus obtaining the coordinates of the point (x / L, y / L), where L is a map scaling factor preset according to the actual map size.

[0092] A small map image generation model based on the AIGC algorithm is built. Using a diffusion model algorithm, a map pointing image is generated based on coordinate scale and a game image dataset. This image is then pushed to the user. Figure 6 As shown, Figure 6 This is a schematic diagram of visual guidance information including path guidance provided in an embodiment of this disclosure. The black arrow represents the route, and the user can go to the current scene area by pointing to the red arrow in the map image.

[0093] The map image generated from the user's location and the target location is loaded into the Quick Game client. While the user is playing the game, directional indicators can be provided to help them navigate the game path. Figure 7 As shown, Figure 7 This is a schematic diagram illustrating the addition of directional guidance to the QuickPlay client provided in this embodiment of the disclosure.

[0094] Furthermore, due to the characteristics of cloud gaming, given the target location and user location, automatic pathfinding can be achieved through a pre-defined instruction set, as follows: 1. Based on the user's current location and the associated block range, the data of the user's current block and other blocks that need to be matched can be derived; 2. Select a suitable block from the game scene information using a matching scheme and derive the location information of the central block; 3. Launch the cloud gaming instance and use the preset instruction set to log in to the target game and move the character to the matched optimal tile position, including map jump instructions, to generate control flow and send it to the cloud server, so that the target game in the cloud can be loaded into the scene that needs to be jumped to in the target game; 4. The video and audio streams returned by the cloud server are sent to the user's device. The game is launched through the QuickPlay client or SDK, and the target location is ultimately displayed directly on the user's terminal.

[0095] When players need to temporarily change their strategy route, they can click the floating window to bring up an input window. By inputting their needs in the input window, a new strategy route will be generated. After AIGC processing, the output image corresponding to the new strategy route will be as follows: Figure 8 As shown, Figure 8 This is a schematic diagram illustrating visual guidance information including path directions after changing the strategy path, as provided in an embodiment of this disclosure.

[0096] The red arrows represent the old strategy path before the strategy path is changed (such as the path corresponding to combat requirements), the dotted lines represent scenes that the user has not visited, and the purple arrows represent the strategy path after the strategy path is updated in real time according to new requirements (such as the path corresponding to collection requirements).

[0097] In one embodiment, the path generation method further includes: Receive user feedback data regarding the visual guidance information; Based on the feedback data, the weight parameters for matching the target region are adjusted.

[0098] In one embodiment, feedback data represents the user's behavioral response or explicit evaluation to the displayed visual guidance information, used to measure the quality of the recommendation. This may include implicit feedback, such as whether a click was made, whether the user reached the target as instructed, and the duration of the interaction; and explicit feedback, such as likes / dislikes, ratings, and textual reviews, such as "useless" or "very good."

[0099] In one embodiment, the weight parameters for target region matching refer to the aforementioned To optimize the next matching result and improve user satisfaction.

[0100] In one embodiment, after a user sees a small map with a red arrow, if they successfully reach the target area and complete the task, such as defeating a boss, it is considered positive feedback; if they ignore the guidance, turn in another direction, or close the window, it is considered negative feedback; the context of the interaction, such as user ID, intent type, recommended area, and actual behavior, is recorded.

[0101] For example, displaying arrows indicating combat zones allows users to avoid combat zones and engage in monster hunting, thus reducing the weight of combat intent during target area matching.

[0102] For example, based on the textual requests (i.e., user interaction) entered by the player (user) through the interactive window, the player's interests in this game are categorized (e.g., combat-oriented, collection-oriented, exploration-oriented). Different strategy routes are generated for different types of players. For instance, for combat-oriented players, a strategy route filled with enemies is generated based on the game map information, guiding the player to areas filled with enemies. Enemies include non-player characters (NPCs) and real-time players; therefore, the generated strategy route will differ for each player and for each player's entry time into the game. For collection-oriented players, a strategy route passing through multiple collection points is generated based on the game map information. For exploration-oriented players, a route filled with unlocked map areas or hidden locations is generated based on the game map information.

[0103] Based on the player's temporary needs, the game strategy route can be switched in real time during the game based on map information.

[0104] After completing a portion of the combat missions, players can input their "treasure collection" request through the interaction window, and the system can generate a new collection route in real time based on the current location and map information.

[0105] like Figure 9 As shown, Figure 9This is a schematic diagram illustrating the generation of game guides provided in this embodiment. Through the interactive window provided by the cloud gaming client, users can input or select recommended behavior schemes. By combining user basic information with logical judgment services to select user feature analysis, we make a numerical judgment on the user's expected behavior. Due to the characteristic of cloud gaming placing the game in the cloud, we can combine SDK service capabilities to obtain scene information within a specific range of the user in real time, perform feature analysis on different scenes to generate estimated values, combine the user's expected value information, calculate the recommended path, and provide path prompts through the cloud gaming client.

[0106] In summary, the solution provided in this public disclosure is as follows: By responding to user interaction, the system acquires the user's current target behavior intention and game state data; based on the target behavior intention and game state data, it determines at least one target area from the game scene feature library that matches the target behavior intention, thereby ensuring that the recommendation results are consistent with the user's current needs; by generating visual guidance information containing path guidance based on the user's current location in the game environment and the location of the target area, the system pushes the visual guidance information to the user's terminal for display, thereby improving the real-time nature and personalization of the game guide.

[0107] To implement the path generation method provided in this disclosure, this disclosure also provides a path generation apparatus, such as... Figure 10 As shown. Figure 10 This is a schematic diagram of the path generation apparatus provided in an embodiment of the present disclosure. The path generation apparatus 1000 includes: The acquisition unit 1001 is used to acquire the user's current target behavior intention and game state data in response to user interaction operations; The determining unit 1002 is used to determine at least one target area that matches the target behavior intention from the game scene feature library based on the target behavior intention and the game state data; The generation unit 1003 is used to generate visual guidance information containing path guidance based on the user's current position in the game environment and the position of the target area, and push the visual guidance information to the user terminal for display.

[0108] In one embodiment, the acquisition unit 1001 is specifically used for: In response to user interaction, obtain the user's task description information and game status data; The task description information is used to identify the user's target behavior intention, which includes combat, collection, or exploration.

[0109] In one embodiment, the generation unit 1003 is specifically used for: Obtain spatial and visual attribute information of the game's virtual scene; Based on the spatial attribute information and visual attribute information, the game virtual scene is divided into regions to obtain multiple scene regions; Feature extraction is performed on each scene region to generate corresponding regional feature data for each scene region, thus obtaining a game scene feature library.

[0110] In one embodiment, the determining unit 1002 is specifically used for: Based on the target behavioral intention and the game state data, user characteristic data is generated; Determine the matching degree between the user feature data and the regional feature data of each scene region; Based on the matching degree from high to low, at least one target region that matches the target behavior intention is determined from the game scene feature library.

[0111] In one embodiment, the generation unit 1003 is specifically used for: The guidance path is determined based on the user's current location in the game environment and the location of the target area; Based on the guide path and the style data of the game screen, visual guidance information containing path guidance is generated, and the visual guidance information is a small map image with path arrows.

[0112] In one embodiment, the path generation device 1000 further includes an adjustment unit, which is used to: Receive user feedback data regarding the visual guidance information; Based on the feedback data, the weight parameters for matching the target region are adjusted.

[0113] It should be noted that the path generation device provided in the above embodiments is only illustrated by the division of the above program modules. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the path generation device can be divided into different program modules to complete all or part of the processing described above. In addition, the path generation device provided in the above embodiments and the path generation method provided in this disclosure belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0114] Figure 11 This is a schematic diagram of the hardware composition structure of the electronic device provided in the embodiments of this disclosure, such as... Figure 11As shown, the electronic device 1100 includes at least one processor 1102; and a memory 1101 communicatively connected to at least one processor 1102; wherein the memory 1101 stores instructions executable by at least one processor 1102, the instructions being executed by at least one processor 1102 to implement the steps of the path generation method of the present disclosure embodiments.

[0115] Optionally, the electronic device may specifically be a path generation device according to the embodiments of this application, and the electronic device may implement the corresponding processes implemented by the path generation device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0116] It is understood that the electronic device also includes a communication interface 1103. Various components in the electronic device are coupled together via a bus system 1104. It is understood that the bus system 1104 is used to implement communication between these components. In addition to a data bus, the bus system 1104 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 11 The general designated all buses as Bus System 1104.

[0117] It is understood that memory 1101 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 1101 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0118] The methods disclosed in the above embodiments can be applied to or implemented by processor 1102. Processor 1102 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the hardware of processor 1102 or by instructions in software form. Processor 1102 may be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 1102 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in memory 1101. Processor 1102 reads information from memory 1101 and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0119] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0120] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the steps of the path generation method of the present invention.

[0121] Optionally, the computer-readable storage medium can be applied to the path generation apparatus in the embodiments of this application, and the computer instructions cause the computer to execute the corresponding processes implemented by the path generation apparatus in the various methods of the embodiments of this application. For the sake of brevity, these will not be described in detail here.

[0122] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the path generation method provided in this embodiment of the invention.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0124] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0126] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0127] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0128] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A path generation method, characterized in that, include: In response to user interaction, obtain the user's current target behavior intention and game status data; Based on the target behavioral intention and the game state data, at least one target area that matches the target behavioral intention is determined from the game scene feature library; Based on the user's current location in the game environment and the location of the target area, visual guidance information containing path directions is generated and pushed to the user's terminal for display.

2. The method according to claim 1, characterized in that, The process of responding to user interaction and acquiring the user's current target behavior intention and game state data includes: In response to user interaction, obtain the user's task description information and game status data; The task description information is used to identify the user's target behavior intention, which includes combat, collection, or exploration.

3. The method according to claim 1, characterized in that, Before determining at least one target region matching the target behavioral intention from the game scene feature library based on the target behavioral intention and the game state data, the method includes: Obtain spatial and visual attribute information of the game's virtual scene; Based on the spatial attribute information and visual attribute information, the game virtual scene is divided into regions to obtain multiple scene regions; Feature extraction is performed on each scene region to generate corresponding regional feature data for each scene region, thus obtaining a game scene feature library.

4. The method according to claim 1, characterized in that, The step of determining at least one target region matching the target behavioral intention from the game scene feature library based on the target behavioral intention and the game state data includes: Based on the target behavioral intention and the game state data, user characteristic data is generated; Determine the matching degree between the user feature data and the regional feature data of each scene region; Based on the matching degree from high to low, at least one target region that matches the target behavior intention is determined from the game scene feature library.

5. The method according to claim 1, characterized in that, The step of generating visual guidance information containing path directions based on the user's current location in the game environment and the location of the target area includes: The guidance path is determined based on the user's current location in the game environment and the location of the target area; Based on the guide path and the style data of the game screen, visual guidance information containing path guidance is generated, and the visual guidance information is a small map image with path arrows.

6. The method according to claim 1, characterized in that, The method further includes: Receive user feedback data regarding the visual guidance information; Based on the feedback data, the weight parameters for matching the target region are adjusted.

7. A path generation device, characterized in that, include: The acquisition unit is used to respond to user interaction operations and acquire the user's current target behavior intention and game state data; The determining unit is configured to determine at least one target region that matches the target behavior intention from a game scene feature library based on the target behavior intention and the game state data. The generation unit is used to generate visual guidance information containing path guidance based on the user's current position in the game environment and the position of the target area, and push the visual guidance information to the user terminal for display.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images