Game information determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a game information determination method and device, a storage medium and electronic equipment, and relates to the technical field of cloud games, and the game information determination method comprises the following steps: obtaining operation information of a user based on a target game and configuration information of the target game; based on the operation information and the configuration information, determining a demand type of the user for the game strategy; under the condition that the demand type is an instant demand, determining target strategy information matched with the operation information and the configuration information from the multi-dimensional strategy information; and outputting the target strategy information to the user according to the target multimedia form. According to the method and the device, the demand type of the user for the game strategy can be determined based on the operation information and the configuration information of the user in the target game, and when the demand type is an instant demand, the response can be immediately performed, and the target strategy information matched with the current operation information and the configuration information is provided for the user; the game strategy and help can be provided for the instant user based on the target strategy information, and the game experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of cloud gaming technology, and in particular to a method, apparatus, storage medium, and electronic device for determining game information. Background Technology

[0002] Providing interactive content based on user needs is the core capability of intelligent systems to achieve personalized, contextualized, and proactive services. It can generate or push interactive content by sensing and understanding users' current or potential needs.

[0003] Currently, the system primarily works by determining the necessary strategy information from standardized content based on user instructions before or after the game starts, and then sending that information to the user.

[0004] However, game strategy information obtained in this way can only be obtained based on user commands before or after the game starts, and cannot provide users with game strategies and help in a timely manner. This results in users lacking necessary guidance at critical moments in the game, which in turn affects the user's gaming experience. Summary of the Invention

[0005] In view of this, this application provides a method, apparatus, storage medium and electronic device for determining game information. The main purpose is to improve the technical problem that the existing technology can only obtain strategy information based on user instructions before or after the start of the game, and cannot provide game strategies and help to users in a timely manner, resulting in users lacking necessary guidance at critical moments in the game, thus affecting the user's game experience.

[0006] Firstly, this application provides a method for determining game information, including: Obtain user operation information based on the target game and the configuration information of the target game; Based on the operation information and the configuration information, the user's need type for game strategies is determined; When the demand type is an immediate demand, target strategy information that matches the operation information and the configuration information is determined from multi-dimensional strategy information; The target strategy information is output to the user in the form of a target multimedia presentation.

[0007] Secondly, this application provides a device for determining game information, comprising: The acquisition module is configured to acquire user operation information based on the target game and the configuration information of the target game; The determination module is configured to determine the user's need type for game strategies based on the operation information and the configuration information; The determination module is also configured to, when the demand type is an immediate demand, determine the target strategy information that matches the operation information and the configuration information from the multi-dimensional strategy information; The output module is configured to output the target strategy information to the user in the target multimedia format.

[0008] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for determining game information as described in the first aspect.

[0009] Fourthly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the method for determining game information as described in the first aspect.

[0010] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the method for determining game information as described in the first aspect.

[0011] By employing the above technical solutions, this application provides a method, apparatus, storage medium, and electronic device for determining game information. Compared with existing technologies, this application obtains user operation information and configuration information of the target game; determines the user's need type for game strategies based on the operation and configuration information; when the need type is an immediate need, determines the target strategy information matching the operation and configuration information from multi-dimensional strategy information; and outputs the target strategy information to the user in a target multimedia format. This allows the application to determine the user's need type for game strategies in the target game based on the user's operation and configuration information. When the need type is an immediate need, it can respond immediately and provide the user with target strategy information matching the current operation and configuration information. This enables the application to provide game strategies and assistance to users immediately based on the target strategy information, thereby improving the user's gaming experience. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating a method for determining game information provided in an embodiment of this application is shown. Figure 2 A flowchart illustrating a method for determining game information provided in an embodiment of this application is shown. Figure 3 A schematic diagram illustrating an example provided in an embodiment of this application is shown; Figure 4 A schematic diagram illustrating an example provided in an embodiment of this application is shown; Figure 5 This illustration shows a schematic diagram of a device for determining game information according to an embodiment of this application; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0015] The embodiments of this application will now be described in more detail with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0016] To address the technical problem that existing technologies only display basic information at the time the user finishes reading, forcing users to reread previously read content to review it and thus impacting the reading experience, this embodiment provides a method for determining game information, such as... Figure 1 As shown, the method includes: Step 101: Obtain the user's operation information and the target game's configuration information based on the target game.

[0017] In this embodiment of the application, the target game can be the game that the user is currently playing; correspondingly, the user operation information can be the instruction information and behavior data issued by the user to the game during the game, specifically, it can be the game operation behavior data of the user in the current level of the current game; correspondingly, the user operation information can reflect the user's real-time behavior status in the game.

[0018] For example, user operation information may include basic operation data, such as keyboard key sequence, mouse movement trajectory and clicks, gamepad input, etc.; it may also include data related to in-game behavior, such as the current level's game time, the player character's combat status (such as attack, defense, stealth), health value, stamina value and other specific ability values, the number of deaths in the current level, item usage, skill cooldown status, etc.

[0019] In some examples, the configuration information of the target game can be the configuration information of the game that the user is currently playing. Specifically, the configuration information can include, but is not limited to, the current level information, the level difficulty, and the abilities required for the level. The abilities required for the level can include abilities in multiple directions in the game, and different game abilities in different directions can correspond to different gameplay in the game.

[0020] Step 102: Based on the operation information and configuration information, determine the type of user's need for game guides.

[0021] In this application embodiment, the user's demand for game guides can include immediate demand, non-immediate demand, and non-existent demand. Immediate demand can be the user's need to immediately obtain the game guide information while playing the target game; non-immediate demand can be the user's need to obtain the game guide information after the game ends; and non-existent demand can be the user's need to obtain the game guide information without needing it while playing the target game.

[0022] For example, if a user is playing a game based on Game 1, the user's need for strategy information for Game 1 can be determined based on the operation and configuration information of Game 1. For instance, if the user needs to obtain strategy information for Game 1 immediately while playing Game 1, the user's need type can be determined as an immediate need; if the user can obtain strategy information for Game 1 after the game ends while playing Game 1, the user's need type can be determined as a non-immediate need; if the user does not need to obtain strategy information for Game 1 while playing Game 1, the user's need type can be determined as a non-existent need.

[0023] Step 103: When the demand type is immediate demand, determine the target strategy information that matches the operation information and configuration information from the multi-dimensional strategy information.

[0024] In this application embodiment, multi-dimensional strategy information may include, but is not limited to, strategy information for different game states, different game levels, different game progress, and different game character types.

[0025] In some examples, when the demand type is immediate, it is necessary to match the strategy information from multiple dimensions with the strategy information that best matches the user's current operation information and the game's current configuration information, and use this as the target strategy information.

[0026] For example, when the demand type is an immediate demand, strategy information that matches the user's current game status, game level, game progress, game character type, etc., can be matched from multi-dimensional strategy information as the target strategy information in this application embodiment.

[0027] Step 104: Output the target strategy information to the user in the target multimedia format.

[0028] In the embodiments of this application, the target multimedia format may include, but is not limited to, voice format, text format, still image format, moving image format, video format, etc.

[0029] For example, in this embodiment of the application, target multimedia formats that match the user's current state can be selected to output target strategy information to the user.

[0030] Compared with existing technologies, this embodiment obtains user operation information and configuration information of the target game; determines the user's need type for game strategies based on the operation and configuration information; when the need type is an immediate need, it determines the target strategy information that matches the operation and configuration information from multi-dimensional strategy information; and outputs the target strategy information to the user in the target multimedia format. This embodiment can determine the user's need type for game strategies in the target game based on the user's operation and configuration information. When the need type is an immediate need, it can respond immediately and provide the user with target strategy information that matches the current operation and configuration information. This allows for providing game strategies and assistance to users immediately based on the target strategy information, thereby improving the user's gaming experience.

[0031] As a refinement and extension of the above embodiments, this embodiment provides a method for determining game information, such as... Figure 2 As shown, the method includes: Step 201: Obtain the user's operation information and the target game's configuration information based on the target game.

[0032] In some examples, the configuration information of the target game can be the configuration information of the game that the user is currently playing. Specifically, the configuration information can include, but is not limited to, the current level information, the level difficulty, and the abilities required for the level. The abilities required for the level can include abilities in multiple directions in the game, and different game abilities in different directions can correspond to different gameplay in the game.

[0033] For example, user operation information based on the target game can be obtained by extracting user game information. Specifically, operation information can be the game operation behavior of the player in the current level of the current game. Operation information may include, but is not limited to: the current level game duration, the current player's combat status, the current player's health value, the current player's first ability direction, second ability direction, third ability direction and other specific ability values, the number of times the player has died in the current level, etc.

[0034] As an alternative approach, the user's real-time game parameter weighted fusion vector (i.e., the operation information in this embodiment) can be extracted using Formula 1, as shown below: (Formula 1) In Formula 1, p represents the user's real-time game parameter weighted fusion vector (i.e., the operation information in this application embodiment), L represents the level number, T represents the game duration, D represents the number of deaths, and w represents the weight of the corresponding game parameter.

[0035] Step 202: Based on operation information and configuration information, determine the user's game state characteristics.

[0036] In this embodiment of the application, the game state feature can be the user's current game state in the target game. For example, the game state feature can include, but is not limited to, the user's real-time game parameter weighted fusion vector P, game category (after encoding), the player's current level, the ability vector required for the current level, the current player's corresponding ability vector, the enemy's state vector, the player's health status, the player's game time, the number of times the player has died, etc.

[0037] Step 203: Based on the characteristics of the game state, determine the type of user's need for game strategies.

[0038] The types of demand include immediate demand, non-immediate demand, and non-existent demand.

[0039] Optionally, when performing the task of "determining the user's need type for game strategies based on game state characteristics", the following methods can be used, but are not limited to these: when the need type is an immediate need or a non-immediate need, extract features from the multi-dimensional strategy information in the strategy information database to obtain a strategy feature set; and determine multiple strategy features that meet the similarity conditions from the strategy feature set based on the similarity data between each strategy feature in the strategy feature set and the user's game features.

[0040] For example, in this embodiment of the application, a neural network architecture can be used to identify whether a player currently needs an immediate or non-immediate strategy. A multilayer perceptron (MLP) is employed, taking the player's game data features as input and outputting a game state classification: urgent or normal. Urgent corresponds to an immediate need, and normal corresponds to a non-immediate need.

[0041] For example, such as Figure 3 As shown, in Figure 3 In this context, m represents the number of game state categories. The following symbols are also used to represent matrices and vectors in the neural network: X represents the input feature vector with shape (1, 2, ..., n, P); W represents the weight matrix; b represents the bias vector; Z represents the weighted sum; and A represents the output after activation.

[0042] As an alternative approach, preprocessed game data features can be accepted in the input layer of the neural network architecture. Based on the example in step 202, the game data features may include, but are not limited to, the user's real-time game parameter weighted fusion vector P, game category, player's current level, the ability required for the current level (multiple values, one value for each ability), the current player's corresponding ability (multiple values, one value for each ability), enemy status (multiple values, one value for each enemy), player's health status (one value), player's game time (one value), and player's number of deaths (one value), for a total of n features.

[0043] For example, a neural network architecture can use two to three hidden layers, each containing several neurons and employing the ReLU activation function. The number of neurons in the output layer of the neural network architecture is equal to the number of categories of the game state, and a softmax activation function is used for classification. The activation value A4 of the output layer is the final result of the classification task, which is transformed into a probability distribution by the linear transformation Z4 through the softmax function. A4 can contain two values, representing the probability that the input data belongs to each category. For example, these two categories could be "urgent" and "normal".

[0044] As an alternative approach, the weighted sum from the input layer to the first fully connected layer can be calculated using Formula 2 to obtain the linear transformation result Z1, as shown in Formula 2 below: (Formula 2) For example, the weight matrix W1 and bias vector b1 in Formula 2 can be adjusted according to the gradient descent algorithm shown in Formulas 3 and 4. The algorithm requires calculation of user game behavior data and basic game information, necessitating higher computational efficiency. Gradient descent is more suitable for this task and exhibits better convergence, often finding the global optimum. Formulas 3 and 4 are detailed below: (Formula 3) (Formula 4) In Equations 3 and 4, L represents the loss function, where and This represents the partial derivative of the loss function L with respect to the parameters W1 and b1. The partial derivatives determine how the loss function L changes if W1 and b1 are slightly altered. The parameters that the gradient descent algorithm needs to adjust include the learning rate. Batch size m, momentum v; recommended parameters are learning rate 0.001, batch size 128, momentum 0.9.

[0045] As an alternative, the activation function (ReLU) can be determined using Equation 5, which is shown below: (Formula 5) In some examples, using the ReLU activation function can ensure that gradients propagate effectively and reduce overfitting; furthermore, the weighted sum from the first fully connected layer to the second fully connected layer can be calculated using Equation 6 to obtain the linear transformation result Z2, as shown in Equation 6 below: (Formula 6) In Equation 6, the weight matrix W2 and the bias vector b2 can be adjusted according to the gradient descent algorithm; specific recommended parameters may include a learning rate of 0.01, a batch size of 256, and a momentum of 0.9.

[0046] In some examples, the activation function (ReLU) can also be determined using Equation 7, which is shown below: (Formula 7) Furthermore, the weighted sum from the second fully connected layer to the third fully connected layer can be calculated using Formula 8 to obtain the linear transformation result Z3, as shown in Formula 8 below: (Formula 8) In Formula 8, the weight matrix W3 and the bias vector b3 can be adjusted according to the gradient descent algorithm; specifically, recommended parameters may include a learning rate of 0.001, a batch size of 256, and a momentum of 0.9.

[0047] In some examples, the activation function (softmax) can be represented by Equation 9, which is shown below: (Formula Nine) In Equation 9, the softmax function can be defined using Equation 10, which is shown below: (Formula 10) It's important to note that the Softmax function converts the output into a probability distribution, ensuring that the result of A4 is distributed as [a, b], where a is the probability of being urgent and b is the probability of being normal. Softmax is used to expand the model further, adding an extension of [a, b, c...]. Otherwise, the Sigmoid function would suffice.

[0048] As an optional approach, labeled training data is required to train the aforementioned neural network. The training data should include the following: 1. Input features: Game and user data features for each sample, such as player level information, score, item status, enemy status, required abilities for the current level, game category, health status, and the weights w of the game parameters. 2. Results: The activation value A4 of the output layer is the final result of the classification task. It is transformed into a probability distribution using the softmax function through a linear transformation Z4. A4 contains two values, representing the probability that the input data belongs to each category. These two categories are "urgent" and "normal".

[0049] It should be noted that the above neural network architecture design and implementation example can analyze player game data and accurately identify the player's current game state. This neural network model can improve the accuracy of its game state predictions through continuous training and adjustment, thus providing a reliable basis for subsequent strategy recommendations.

[0050] Step 204: When the demand type is immediate demand, determine the target strategy information that matches the operation information and configuration information from the multi-dimensional strategy information.

[0051] Optionally, when performing the task of "determining the target strategy information that matches the operation information and configuration information from multi-dimensional strategy information when the demand type is immediate demand", the following methods can be used, but are not limited to these: when the demand type is immediate demand, merging multiple strategy features with operation information and configuration information to obtain fused features; determining the immediate relevance probability of multiple strategy features based on the fused features; generating immediate relevance content corresponding to operation information and configuration information based on the immediate relevance probability; and performing clustering processing on the immediate relevance content to obtain the target strategy information.

[0052] In this embodiment, feature extraction is performed on various types of guides, and relevant guide content is selected. Feature extraction can be performed first, including: for text-based guides, the TF-IDF method is used to convert the text content into feature vectors, which facilitates subsequent similarity calculation; for non-text-based guides, they are first converted into text form, and then their content is converted into feature vectors. The following describes the method of converting non-text-based guides into text; for image guides, deep learning models, such as convolutional neural networks (CNNs), are used to perform in-depth analysis of images, such as edges, textures, and shapes, to identify objects and scenes in the images. Based on the identified objects, scenes, and context, recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or more modern Transformer architectures are used to convert the image content into coherent sentences; for video guides, keyframes are extracted from the video, and computer vision techniques, such as convolutional neural networks (CNNs), are used to analyze the keyframes to identify objects, scenes, and activities within them. The identified information is converted into natural language descriptions, forming a textual summary of the video's visual content. For audio guides, Automatic Speech Recognition (ASR) technology is applied to convert the audio stream in the video into text. Furthermore, similarity calculations are performed using the cosine similarity algorithm to calculate the similarity between the user's feature vector and the feature vectors of various types of guides. Based on the similarity scores, all guides are ranked, and thresholds and rules are set to filter out the most relevant and user-preferred guides. m This information is provided for subsequent refinement and extraction of strategic features.

[0053] Furthermore, regarding the strategy text C matched above... m The analysis and extraction process is performed to extract the real-time strategy section that matches the current game state (i.e., game-related parameters and user game information); specifically, the strategy text C is processed using Formula 11. m Word segmentation yields a series of sentences W i Formula 11 is shown below: (Formula Eleven) Furthermore, each sentence W can be processed using Formula Twelve. i Feature extraction is performed to obtain the feature vector V. Wi Formula 12 is shown below: (Formula 12) Furthermore, the feature vector V of each sentence can be obtained using Formula Thirteen. Wi Combined with the user feature vector P, a fused input feature vector V is formed. 1Ni， Formula thirteen is shown below: (Formula Thirteen) It's important to note that game users may require different types of strategy guides in different scenarios. For example, some users might need quest guides, some might need equipment upgrade guides, while others might need boss guides. Therefore, combining the user feature vector P with the game strategy guide content feature vector V... Wi This can help the model better understand user preferences, thereby extracting and recommending more personalized strategy content.

[0054] In some examples, embodiments of this application may be based on a neural network model, with the input being the fused feature vector V. 1Ni The output is the instantaneous correlation probability P. oi The input layer is the fused feature vector V. 1Ni， There are two hidden layers, H and H respectively. 1i and H 2i Hidden layer H 1i The input layer receives the fused feature vector V. 1Ni Output a new feature vector H 1i， The first-level output can be determined using Formula Fourteen, which is shown below: (Formula Fourteen) Furthermore, the weight matrix W1 and bias vector b1 can be adjusted using the Adam optimization algorithm. Game strategy recommendation systems involve large amounts of user behavior data and article content data; the Adam optimization algorithm is more advantageous when handling large-scale data and complex models. Parameters that need to be adjusted when using the Adam optimization algorithm include: learning rate. Momentum parameters , Batch size m; The recommended parameter can be set to a learning rate of 0.001. =0.9, =0.999, batch size 128; hidden layer H 2i Receive first hidden layer H 1i The output is used as input, and these features are further processed. The Adam optimization algorithm is also used to adjust the weight matrix W2 and the bias vector b2. The recommendation parameters can be determined using a learning rate of 0.01. =0.9, =0.999, batch size 64; the second-level output can be determined using Formula Fifteen, as shown below: (Formula Fifteen) Furthermore, the instantaneous correlation probability Poi is determined, and without using an activation function, the linear result Z is directly obtained through Equation Sixteen. i Formula sixteen is shown below: (Formula Sixteen) In some examples, the Adam optimization algorithm is also used to adjust the weight matrix W3 and the bias vector b3, and the recommended parameters can be determined using a learning rate of 0.01. =0.9, =0.999, batch size 32; Formula 17 determines that the model output is the instantaneous correlation probability Poi, therefore the sigmoid activation function is needed for Z. i Binary classification is performed to compress the output to the range [0, 1]. Formula 17 is shown below: (Formula 17) In Formula 17, W1, W2, and W3 are weight matrices, and b1, b2, and b3 are bias vectors. It is the activation function (ReLU).

[0055] In this embodiment, real-time relevant content extraction can extract text content in Cm that is real-time relevant to the user vector P based on the real-time relevant probability Poi of each word or sentence. Assume the threshold is... ,if If Wi is considered to be instantaneously relevant, then Wi is considered to be instantaneously relevant.

[0056] For example, after extracting all highly relevant content, this content can be further aggregated to ensure there is no duplicate information and a clear logical order. Common methods include text clustering and summary generation; specifically, text clustering can be performed, that is, clustering the extracted real-time strategy content to eliminate redundant information. Common text clustering algorithms include K-means and hierarchical clustering. K-means clustering can represent the real-time strategy content as a vector V. TF-IDF Choose the number of clusters k; use the K-means algorithm to cluster the vectors to obtain k clusters, integrate the contents within each cluster, and generate strategy content representing that cluster.

[0057] For example, hierarchical clustering can also be performed, which involves calculating the similarity between each pair of instant strategy content (e.g., using cosine similarity); using a hierarchical clustering algorithm (such as single-link, fully-link, or average-link hierarchical clustering) to cluster the data; selecting appropriate clustering tree cut points based on a similarity threshold to generate several clusters; and integrating the content within each cluster.

[0058] Furthermore, text summarization is performed. Specifically, a summary is generated for the content of each cluster, and key information is extracted. Extractive summarization can use algorithms (such as TextRank) to extract key sentences in each cluster and combine these key sentences into the final summary. Generative summarization can use pre-trained generative models (such as BERT or GPT) to generate a summary for each cluster. These generated summaries are combined into the final summary, which can then output the guide content. Real-time guides are output primarily through a combination of audio and in-vehicle screens; non-real-time guides are output in text and image format through in-vehicle screens and / or mobile terminal screens.

[0059] Optionally, after performing "determining the target strategy information that matches the operation information and configuration information from multi-dimensional strategy information when the demand type is an immediate demand", the following methods can be used, but are not limited to them, including: when the demand type is a non-immediate demand, generating the target strategy information based on multiple strategy features; and outputting the target strategy information to the user in the form of text and images through the in-vehicle screen of the user's vehicle and / or the device screen of the user's mobile device.

[0060] Step 205: Output the target strategy information to the user in the target multimedia format.

[0061] Optionally, when performing the "outputting target strategy information to the user in the form of target multimedia", the following methods may be used, but are not limited to: in response to the user's vehicle being in motion, outputting target strategy information to the user in the form of voice broadcast, and outputting target strategy information to the user in the form of text and images through the vehicle's in-vehicle screen; in response to the user's vehicle being parked, outputting target strategy information to the user in the form of text and images through the vehicle's in-vehicle screen and / or the device screen of the user's mobile device.

[0062] It should be noted that the system converts the generated real-time travel guide text into speech, using technologies such as seat sensors, facial recognition, and voice recognition to identify the user. It also detects the vehicle's driving status, in-car noise levels, and other environmental factors to determine whether the guide is output via the car speaker or the user's headphones. For example, while driving, the system prioritizes voice output via the car speaker or headphones, combined with the in-car screen, ensuring the driver's attention is not distracted. In non-driving scenarios, such as when passengers are viewing the guide or when the vehicle is parked, the guide content can be displayed as text via a mobile app or the in-car screen, providing a more detailed reading experience. In noisy environments, headphones are preferred; in quiet environments, the car speaker can be used.

[0063] As an optional approach, embodiments of this application also provide the following examples, such as... Figure 4As shown, it includes: 1) Determining whether a game guide is needed based on the player's current game status, and distinguishing whether the need is for an immediate guide or a non-immediate guide. Finding the guide content corresponding to the current game content in the guide library, extracting, parsing, and splitting the content by keywords, and defining the immediate and non-immediate content in each guide segment based on context matching and factors such as player preferences and level. Generating a summary for the immediate content, directly playing videos or images for the non-immediate content, outputting the immediate text using voice, and outputting the non-immediate content through the in-vehicle screen.

[0064] In some examples, existing technologies, within the target software's runtime environment, determine the unresolved needs corresponding to the target user identifier, determine the interactive content to satisfy those needs based on the unresolved needs and runtime status information, return the interactive content based on the target user identifier (which may include text, rich text, video, audio, or action execution logic), display interactive function controls in the runtime environment, acquire user input information, and interact with the user. Based on the above, the differences between this application's embodiments and existing technologies are: 1. Personalization and multi-dimensional analysis: While existing technologies can provide interactive content based on user needs, they lack multi-dimensional analysis of the player's current game state, such as comprehensive consideration of factors like player preferences and level. 2. Distinction between real-time and non-real-time content: In this application's embodiments, strategy content is subdivided into real-time and non-real-time content, outputting them via voice and screen display respectively, while existing technologies do not explicitly distinguish between these two types of content. 3. Safety-first design: This application's embodiments particularly emphasize safety in the in-vehicle environment, ensuring that strategy display does not interfere with driving, while existing technologies do not adequately consider this aspect. 4. Interactive experience: The embodiments of this application can provide a more personalized and interactive experience, and provide strategy content that is more in line with user needs by analyzing the player's game status and preferences in real time.

[0065] It should be noted that the main drawback of existing technical solutions lies in their lack of personalization and targeting. They cannot provide customized content based on the player's real-time status and preferences, and may lack necessary safety mechanisms in an in-vehicle environment. Furthermore, existing technical solutions may fail to effectively distinguish and process real-time and non-real-time information, resulting in a poor user experience. Specifically, this includes: 1. Lack of real-time information: Existing technologies often fail to provide real-time game guides and assistance, leaving players without necessary guidance at crucial moments. 2. Non-personalized experience: Guide content is usually standardized and not personalized based on the player's real-time game status, behavioral habits, and personal preferences. 3. Limited information format: Most systems only provide text or video guides, lacking differentiation and optimized display of real-time content (such as voice prompts) and non-real-time content (such as video demonstrations).

[0066] Based on the above, the embodiments of this application can achieve real-time content output, that is, develop a system that can immediately respond to the player's current game status and provide real-time text or voice strategy summaries; it can also provide non-real-time content display, that is, design the system to display non-critical strategy videos or images on the in-vehicle screen at appropriate times to avoid affecting driving; and it can also provide personalized strategy customization, that is, customize personalized strategy content according to the player's game behavior and preferences.

[0067] In some examples, embodiments of this application can intelligently distinguish and adaptively output real-time and non-real-time content. Specifically, by using deep learning models to predict the importance and urgency of in-game events, this proposal can intelligently distinguish between urgent information requiring immediate feedback (such as hints of missed tasks) and non-real-time content that can be postponed (such as game strategy analysis). Real-time content is delivered via voice broadcast, allowing players to quickly obtain assistance; non-real-time content is presented in text and image format, enhancing information richness and readability. This design transcends the single content output mode of existing technologies, improving the user experience.

[0068] In some examples, embodiments of this application can also integrate artificial intelligence, natural language processing, and machine learning technologies to not only analyze users' basic needs and operational status, but also comprehensively consider multiple dimensions of information such as players' personal preferences and game levels, thereby generating highly personalized strategy content suitable for the current context. This overcomes the limitations of existing technologies that rely on only a single or limited factor to determine interactive content, achieving more accurate personalized services.

[0069] In some examples, embodiments of this application can also address the specific characteristics of the in-vehicle environment. These embodiments employ a dedicated safety-first design philosophy, dynamically adjusting content display strategies by analyzing driving conditions. For instance, during high-speed driving or complex road conditions, unnecessary visual information is automatically reduced or paused, retaining only voice guidance. This effectively avoids interfering with the driver and improves driving safety. Existing technologies do not fully consider the safety requirements of the in-vehicle environment; embodiments of this application have made targeted optimizations in this regard.

[0070] In some examples, embodiments of this application can also continuously monitor player gameplay and feedback, utilizing natural language understanding and generation technologies to adjust strategy suggestions in real time, making the interactive experience smoother and more personalized. This dynamic adjustment mechanism surpasses the relatively static interactive content generation methods of existing technologies, providing users with a more immersive and interactive gaming assistance experience.

[0071] Compared with existing technologies, this embodiment obtains user operation information and configuration information of the target game; determines the user's need type for game strategies based on the operation and configuration information; when the need type is an immediate need, it determines the target strategy information that matches the operation and configuration information from multi-dimensional strategy information; and outputs the target strategy information to the user in the target multimedia format. This embodiment can determine the user's need type for game strategies in the target game based on the user's operation and configuration information. When the need type is an immediate need, it can respond immediately and provide the user with target strategy information that matches the current operation and configuration information. This allows for providing game strategies and assistance to users immediately based on the target strategy information, thereby improving the user's gaming experience.

[0072] Furthermore, as Figure 1 and Figure 2 The specific implementation of the method shown in this embodiment provides a device for determining game information, such as... Figure 5 As shown, the device includes: an acquisition module 31, a determination module 32, and an output module 33.

[0073] The acquisition module 31 is configured to acquire user operation information based on the target game and configuration information of the target game; The determination module 32 is configured to determine the user's need type for game strategies based on the operation information and the configuration information; The determination module 32 is also configured to, when the demand type is an immediate demand, determine the target strategy information that matches the operation information and the configuration information from the multi-dimensional strategy information; Output module 33 is configured to output the target strategy information to the user in the form of target multimedia.

[0074] In some examples of this embodiment, the determining module 32 is specifically configured to determine the user's game state characteristics based on the operation information and the configuration information; and to determine the user's demand type for game strategies based on the game state characteristics, wherein the demand type includes immediate demand, non-immediate demand, and non-existent demand.

[0075] In some examples of this embodiment, the determining module 32 is further configured to, when the demand type is an immediate demand or a non-immediate demand, extract features from the multi-dimensional strategy information in the strategy information database to obtain a strategy feature set; and, based on the similarity data between each strategy feature in the strategy feature set and the user's game features, determine multiple strategy features that meet the similarity conditions from the strategy feature set.

[0076] In some examples of this embodiment, the determining module 32 is further configured to, when the demand type is an immediate demand, fuse the multiple strategy features with the operation information and the configuration information to obtain a fused feature; determine the immediate relevance probability of the multiple strategy features based on the fused feature; generate immediate relevance content corresponding to the operation information and the configuration information according to the immediate relevance probability; and perform clustering processing on the immediate relevance content to obtain the target strategy information.

[0077] In some examples of this embodiment, the determining module 32 is further configured to generate the target strategy information based on the multiple strategy features when the demand type is a non-immediate demand; and to output the target strategy information to the user in graphic form through the in-vehicle screen of the user's vehicle and / or the device screen of the user's mobile device.

[0078] In some examples of this embodiment, the output module 33 is specifically configured to output the target strategy information to the user in the form of voice broadcast when the user's vehicle is in motion, and to output the target strategy information to the user in the form of pictures and text through the vehicle's in-vehicle screen; and to output the target strategy information to the user in the form of pictures and text through the vehicle's in-vehicle screen and / or the device screen of the mobile device used by the user when the user's vehicle is parked.

[0079] It should be noted that other corresponding descriptions of the functional units involved in the game information determination device provided in this embodiment can be found in [reference]. Figure 1 and Figure 2 The corresponding description in [the document] will not be repeated here.

[0080] Based on the above, Figure 1 and Figure 2 Accordingly, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 and Figure 2 The method shown.

[0081] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0082] like Figure 6 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising: At least one processor 401; and, A memory 402 is communicatively connected to at least one of the processors 401; wherein, The memory 402 stores instructions that can be executed by at least one of the processors to enable at least one of the processors to perform the game information determination method as described above.

[0083] Figure 6 Take a processor 401 as an example.

[0084] The electronic device may also include an input device 403 and a display device 404.

[0085] The processor 401, memory 402, input device 403, and display device 404 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0086] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the game information determination method in this embodiment of the application. Figure 1 and Figure 2 The method flow is shown. The processor 401 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 402, thereby realizing the method for determining game information in the above embodiment.

[0087] The memory 402 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the method for determining game information. Furthermore, the memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 402 may optionally include memory remotely located relative to the processor 401, and these remote memories may be connected via a network to means of performing the method for determining game information. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0088] Input device 403 can receive user clicks and generate user settings and function control signals related to the method of determining game information. Display device 404 may include display devices such as a display screen.

[0089] When one or more modules are stored in the memory 402, and are run by one or more processors 401, the method for determining game information in any of the above method embodiments is executed.

[0090] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0091] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0092] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented using hardware. By applying the solution of this embodiment, compared with the prior art, this embodiment obtains the user's operation information and configuration information based on the target game; determines the user's need type for game strategies based on the operation information and configuration information; when the need type is an immediate need, determines the target strategy information matching the operation information and configuration information from multi-dimensional strategy information; and outputs the target strategy information to the user in a target multimedia format. This embodiment can determine the user's need type for game strategies in the target game based on the user's operation information and configuration information in the target game. When the need type is an immediate need, it can respond immediately and provide the user with target strategy information matching the current operation information and configuration information. This allows for providing game strategies and assistance to users immediately based on the target strategy information, improving the user's gaming experience.

[0094] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0095] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for determining game information, characterized in that, include: Obtain user operation information based on the target game and the configuration information of the target game; Based on the operation information and the configuration information, the user's need type for game strategies is determined; When the demand type is an immediate demand, target strategy information that matches the operation information and the configuration information is determined from multi-dimensional strategy information; The target strategy information is output to the user in the form of a target multimedia presentation.

2. The method according to claim 1, characterized in that, The process of determining the user's need type for game guides based on the operation information and the configuration information includes: Based on the operation information and the configuration information, the user's game state characteristics are determined; Based on the game state characteristics, the user's demand type for game strategies is determined, including immediate demand, non-immediate demand, and non-existent demand.

3. The method according to claim 2, characterized in that, After determining the user's need type for game strategies based on the game state characteristics, the method further includes: When the demand type is immediate or non-immediate, feature extraction is performed on the multi-dimensional strategy information in the strategy information database to obtain a strategy feature set. Based on the similarity data between each strategy feature in the strategy feature set and the user's game features, multiple strategy features that meet the similarity criteria are determined from the strategy feature set.

4. The method according to claim 3, characterized in that, When the demand type is an immediate demand, determining the target strategy information that matches the operation information and the configuration information from multi-dimensional strategy information includes: When the demand type is an immediate demand, the multiple strategy features are fused with the operation information and the configuration information to obtain a fused feature; The instantaneous relevance probability of the multiple strategy features is determined based on the fused features; Based on the real-time correlation probability, generate real-time correlation content corresponding to the operation information and the configuration information; The real-time relevant content is clustered to obtain the target strategy information.

5. The method according to claim 3, characterized in that, After determining multiple strategy features that meet the similarity criteria from the strategy feature set based on the similarity data between each strategy feature in the strategy feature set and the user's game features, the method further includes: When the demand type is a non-immediate demand, the target strategy information is generated based on the multiple strategy features; The target strategy information is displayed to the user in a graphic and textual format via the in-vehicle screen of the user's vehicle and / or the device screen of the user's mobile device.

6. The method according to claim 1, characterized in that, The step of outputting the target strategy information to the user in the target multimedia format includes: In response to the user's vehicle being in motion, the target strategy information is output to the user in the form of voice broadcast, and the target strategy information is output to the user in the form of pictures and text through the vehicle's in-vehicle screen; In response to the user's vehicle being parked, the target strategy information is output to the user in graphic and text form through the vehicle's in-vehicle screen and / or the screen of the user's mobile device.

7. A device for determining game information, characterized in that, include: The acquisition module is configured to acquire user operation information based on the target game and the configuration information of the target game; The determination module is configured to determine the user's need type for game strategies based on the operation information and the configuration information; The determination module is also configured to, when the demand type is an immediate demand, determine the target strategy information that matches the operation information and the configuration information from the multi-dimensional strategy information; The output module is configured to output the target strategy information to the user in the target multimedia format.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. An electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

10. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images