Immersive script killing sound effect generation method and system based on deep learning

Abstract

The application relates to the field of sound effect control and discloses an immersive script killing sound effect generation method and system based on deep learning, which comprises the following steps: acquiring environment space information corresponding to a target environment, and acquiring a plurality of sound unit position information and a plurality of player position information in the target environment; through a sound field control unit, determining sound unit control information of each sound unit according to the environment space information, the plurality of sound unit position information and the plurality of player position information; acquiring sound effect optimization information fed back by players corresponding to the plurality of player position information respectively; and through the sound field control unit, determining sound unit control information of each sound unit according to the environment space information, the plurality of sound unit position information, the plurality of player position information and the sound effect optimization information corresponding to the plurality of player position information respectively. The application can adjust sound effects output by each sound unit according to real-time physical positions of players and efficiently optimize a sound field.

Description

Technical Field

[0001] This application relates to the field of sound effect control technology, and more specifically, to a method and system for generating immersive script murder sound effects based on deep learning. Background Technology

[0002] Currently, the most common way to implement sound effects in murder mystery games is based on a pre-set script flow. At specific plot points or time points, staff or a central control system trigger and play fixed audio files. This is a linear playback mode that is highly dependent on the predetermined structure of the script. In this sound effect mode, the sound effects (such as ambient sounds, clue sounds, ambient music, character-specific voices, etc.) and their playback order, volume, and duration are set before the game starts and are strictly executed according to the script requirements and fixed steps throughout the game, lacking the ability to respond in real time to the actual dynamic changes in the game environment. This working method is essentially a "playlist-style" execution, lacking intelligent audio environment adaptation.

[0003] The sound effects modes in the above-mentioned murder mystery games suffer from a flaw: they cannot automatically adjust the volume of each speaker's output based on the player's real-time physical location. Regardless of the player's location in the room or distance from the speakers, a preset volume is consistently played. This easily leads to excessively loud sound when the player is close to the speakers, or unclear key sound effects when far away, severely impacting game immersion and comfort. Furthermore, existing systems generally lack sufficient optimization of the sound field, lacking the fine-tuning capabilities for multi-speaker collaboration, making it difficult to construct a uniform, clear, and accurately directional three-dimensional sound field environment. Sounds from different speakers may interfere with, overlap, or create dead zones, preventing players from accurately perceiving the direction and distance of sound sources. These deficiencies severely restrict the highly immersive experience and realistic interactivity that murder mystery games strive for. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for generating sound effects in immersive script murder mystery games based on deep learning. This method solves the technical problems of not being able to adjust the sound output of each speaker according to the player's real-time physical position and insufficient optimization of the sound field. It achieves the technical effect of adjusting the sound output of each speaker according to the player's real-time physical position and efficiently optimizing the sound field.

[0005] This application provides a method for generating immersive script-based murder mystery game sound effects based on deep learning. The method includes: acquiring environmental spatial information corresponding to a target environment, and acquiring the position information of multiple sound units and multiple player positions within the target environment; wherein, the environmental spatial information includes three-dimensional spatial information corresponding to the target environment, and one sound unit corresponds to one sound unit position information; through a sound field control unit, determining the sound unit control information of each sound unit based on the environmental spatial information, the position information of multiple sound units, and the position information of multiple player positions; and controlling the working state of each sound unit according to the sound unit control information of each sound unit.

[0006] In one possible implementation, the method further includes: acquiring sound effect optimization information from player feedback corresponding to multiple player location information; wherein the sound effect optimization information includes volume adjustment suggestions; determining the sound unit control information for each sound unit through a sound field control unit based on environmental space information, multiple speaker unit location information, multiple player location information, and the sound effect optimization information corresponding to each player location information; and controlling the working state of each sound unit based on the sound unit control information of each sound unit.

[0007] In another possible implementation, the method further includes: using a script parsing model to determine the scene information and scene transition information corresponding to the immersive murder mystery game based on the script information, where the scene transition information corresponds to the transition information between different scene information; using a sound field adjustment unit to determine the sound unit adjustment information for each sound unit based on environmental space information, multiple sound unit position information, multiple player position information, scene information, and scene transition information; and adjusting the working state of each sound unit based on the sound unit adjustment information for each sound unit; wherein, the sound unit adjustment information includes volume adjustment information and surround sound effect adjustment information.

[0008] In another possible implementation, the method further includes: acquiring sound effect preference information from player feedback corresponding to multiple player location information; wherein, the sound effect preference information includes volume change preference value, horror preference value, and low frequency tolerance value, the volume change preference value representing the player's liking for volume changes, the horror preference value representing the player's liking for horror sound effects, and the low frequency tolerance value representing the player's tolerance for low frequency sound effects; determining a limiting threshold for the sound unit adjustment information based on the sound effect preference information from player feedback corresponding to multiple player location information through a sound field adjustment unit; and adjusting the sound unit adjustment information of each sound unit according to the limiting threshold of the sound unit adjustment information.

[0009] In another possible implementation, the method further includes: determining the number of player location information as player quantity information; determining the sudden sound effect rise rate and soundscape switching speed corresponding to the sound unit adjustment information through the sound field transition adjustment unit based on the player quantity information; adjusting the working state of each sound unit according to the sound unit adjustment information of each sound unit; wherein, the larger the player quantity information, the greater the sudden sound effect rise rate and soundscape switching speed.

[0010] In another possible implementation, the method further includes: obtaining the player's in-game communication volume preference value, which represents the player's preferred sound effect volume for communication in the game; determining the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information through a sound field transition adjustment unit, based on the player number information and the in-game communication volume preference value; adjusting the working state of each sound unit according to the sound unit adjustment information of each sound unit; wherein, the larger the in-game communication volume preference value, the greater the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude.

[0011] In another possible implementation, the method further includes: acquiring player interaction information in an immersive script-based murder mystery game, including communication information between multiple players; determining the player interaction activity factor based on the number of players and player interaction information using an activity monitoring model; wherein the interaction activity factor is between 0.8 and 1.5; determining the product of the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information with the interaction activity factor, so as to adjust the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information.

[0012] In another possible implementation, the method further includes: obtaining the volume value of the game NPC in the immersive murder mystery game, and obtaining the voice clarity evaluation value of the players in the immersive murder mystery game for the game NPC; and determining the volume adjustment value of the game NPC based on the volume value, interaction activity factor and voice clarity evaluation value of the game NPC through the game NPC voice adjustment unit.

[0013] In another possible implementation, the method further includes: obtaining the interval duration of the same clue sound effects when played repeatedly in the immersive script murder mystery game, as the sound effect repetition interval duration; determining the product of the sound effect repetition interval duration and the interaction activity factor, as the sound effect repetition interval adjustment duration; and adjusting the interval duration of the same clue sound effects when played repeatedly in the immersive script murder mystery game according to the sound effect repetition interval adjustment duration.

[0014] This application also provides an immersive script murder mystery sound effect generation system based on deep learning, including a unit for performing the method described in any of the preceding claims.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are:

[0016] This application provides a method for generating immersive sound effects in a murder mystery game based on deep learning. The method includes: acquiring environmental spatial information corresponding to a target environment, and acquiring the position information of multiple speaker units and multiple player positions within the target environment; wherein the environmental spatial information includes three-dimensional spatial information corresponding to the target environment, and one speaker unit corresponds to one speaker unit position information; through a sound field control unit, determining the speaker unit control information for each speaker unit based on the environmental spatial information, the position information of multiple speaker units, and the position information of multiple player positions; and controlling the working state of each speaker unit according to the speaker unit control information. This application can avoid the problem of excessively loud sound when players are close to the speakers, or inability to hear key sound effects when they are far away from the speakers, while improving the personalized user experience and enhancing the effectiveness of immersive murder mystery game sound effects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the first deep learning-based immersive script murder sound effect generation method provided in this application embodiment;

[0019] Figure 2 A schematic diagram illustrating the working process of the first deep learning-based immersive script murder sound effect generation method provided in the embodiments of this application;

[0020] Figure 3 A flowchart illustrating the second deep learning-based immersive script murder sound effect generation method provided in this application embodiment;

[0021] Figure 4 A flowchart illustrating the third deep learning-based immersive script murder sound effect generation method provided in this application embodiment;

[0022] Figure 5 This is a schematic diagram of the logical structure of an immersive script murder sound effect generation system based on deep learning, provided in an embodiment of this application. Detailed Implementation

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0028] The sound effects modes in the above-mentioned murder mystery games suffer from a flaw: they cannot automatically adjust the volume of each speaker's output based on the player's real-time physical location. Regardless of the player's location in the room or distance from the speakers, a preset volume is consistently played. This easily leads to excessively loud sound when the player is close to the speakers, or unclear key sound effects when far away, severely impacting game immersion and comfort. Furthermore, existing systems generally lack sufficient optimization of the sound field, lacking the fine-tuning capabilities for multi-speaker collaboration, making it difficult to construct a uniform, clear, and accurately directional three-dimensional sound field environment. Sounds from different speakers may interfere with, overlap, or create dead zones, preventing players from accurately perceiving the direction and distance of sound sources. These deficiencies severely restrict the highly immersive experience and realistic interactivity that murder mystery games strive for.

[0029] Based on the above reasons, this application provides a method for generating immersive script-based murder mystery sound effects based on deep learning. This method includes: acquiring environmental spatial information corresponding to the target environment, and acquiring the position information of multiple speaker units and multiple player positions within the target environment; wherein the environmental spatial information includes the three-dimensional spatial information corresponding to the target environment, and one speaker unit corresponds to one speaker unit position information; through a sound field control unit, determining the speaker unit control information for each speaker unit based on the environmental spatial information, the position information of multiple speaker units, and the position information of multiple player positions; and controlling the working state of each speaker unit according to the speaker unit control information. This application can avoid the problem of excessively loud sound when players are close to the speakers, or inability to hear key sound effects when they are far away from the speakers, while improving the personalized user experience and enhancing the working effect of immersive script-based murder mystery sound effects.

[0030] In some scenarios, the deep learning-based immersive script murder mystery game sound effect generation method of this application embodiment can be applied to short-duration (1-2 hours) immersive script murder mystery games that combine AR / VR technology, which can improve the player's experience in existing immersive script murder mystery games.

[0031] The following specific examples illustrate a method for generating immersive script murder sound effects based on deep learning, as provided in the embodiments of this application.

[0032] Figure 1 A flowchart illustrating the first deep learning-based immersive script murder mystery sound effect generation method provided in this application embodiment is shown below. Figure 1 As shown, the existing deep learning-based immersive script murder sound effect generation methods include S110 to S120, and S110 to S120 will be explained in detail below.

[0033] S110. Obtain the environmental spatial information corresponding to the target environment, and obtain the location information of multiple speaker units and multiple player positions within the target environment. The environmental spatial information includes the three-dimensional spatial information corresponding to the target environment, and one speaker unit corresponds to one speaker unit position.

[0034] In this implementation, the environmental spatial information corresponding to the target environment can be obtained, as well as the position information of multiple sound units and multiple player positions within the target environment. The environmental spatial information includes the three-dimensional spatial information corresponding to the target environment, which can accurately describe the spatial structural features of the game field.

[0035] In this implementation, each speaker unit has corresponding speaker unit position information. The speaker unit position information can be entered into the system when the target environment is arranged in three-dimensional space. The target environment's three-dimensional space information can be stored together with the speaker unit position information.

[0036] For example, in immersive murder mystery games, laser scanners can be used to acquire 3D point cloud data of the game room to track the position coordinates of each player in real time, and databases can be used to obtain 3D spatial information of the target environment and the position information of the sound units. These data together constitute the basic information for sound effect control.

[0037] S120: Through the sound field control unit, based on environmental spatial information, the position information of multiple speaker units, and the position information of multiple players, the control information for each speaker unit is determined. The operating state of each speaker unit is controlled according to this control information.

[0038] Figure 2 A schematic diagram illustrating the working process of the first deep learning-based immersive script murder mystery sound effect generation method provided in this application embodiment is shown below. Figure 2 As shown, after obtaining the above information, the sound field control unit can determine the sound unit control information of each sound unit based on the environmental space information, the position information of multiple sound units, and the position information of multiple players.

[0039] In this implementation, the sound field control unit can analyze the spatial relationship between the player and each speaker unit and calculate the optimal sound propagation path.

[0040] For example, the sound field control unit can be a deep learning model based on convolutional neural networks. The sound field control unit is trained with a large amount of acoustic propagation sample data in game scenarios, and can accurately predict the optimal sound parameters in different spatial positions. By inputting environmental spatial information, multiple speaker unit position information and multiple player position information into the sound field control unit, it can output the speaker unit control information for each speaker unit.

[0041] For example, the sound field control unit can also be a Transformer-based deep learning model that takes environmental spatial information, speaker unit position information, and player position information as input, and learns the spatial dependencies (distance, relative orientation) between them through a self-attention mechanism to obtain the speaker unit control information for each speaker unit.

[0042] After determining the control information of the audio units, the working state of each audio unit can be controlled based on this information. Furthermore, by adjusting the sound output parameters of each audio unit, the reasonable distribution of sound effects in the space can be ensured.

[0043] For example, when a player approaches a speaker unit, the volume of that speaker unit can be appropriately reduced to avoid the sound being too loud; when a player moves away from a speaker unit, the volume of that speaker unit can be appropriately increased and sound delay compensation can be added to ensure that the sound is clearly distinguishable. This dynamic adjustment can achieve balanced sound propagation in space.

[0044] The beneficial effect of the above implementation method is that by controlling the working state of each speaker unit through environmental spatial information, player position, and speaker unit position, it can avoid the problem of excessive sound when the player is close to the speaker or unclear sound effects when the player is far away from the speaker, thereby improving the user's immersion and experience comfort in the game.

[0045] The beneficial effects of the above implementation method are also that, compared with the traditional fixed sound effect control method, by controlling the working state of each sound unit through the player's position, the sound effects are dynamically adjusted according to the player's position, which improves the personalized experience of the user and enhances the working effect of the immersive script murder sound effects.

[0046] In some implementations, the above method also includes S130 to S140, which are described in detail below.

[0047] S130. Obtain sound effect optimization information from player feedback corresponding to multiple player location information. This sound effect optimization information includes volume adjustment suggestions.

[0048] In this implementation, in an immersive murder mystery game, sound effect optimization information can be continuously obtained from the player feedback corresponding to the location information of multiple players. The sound effect optimization information can include parameters such as volume adjustment suggestions, reflecting the subjective feelings and optimization needs of players in different locations regarding the current sound effects.

[0049] For example, during a murder mystery game, a player in a corner of the room might complain that the volume is too low, while a player near the speakers might complain that the volume is too high. By collecting this sound optimization information, the auditory experience of each player in each position can be adjusted accordingly.

[0050] S140: Through the sound field control unit, based on environmental space information, multiple speaker unit position information, multiple player position information, and sound effect optimization information corresponding to each player position information, determine the speaker unit control information for each speaker unit. Control the operating state of each speaker unit according to the speaker unit control information for each speaker unit.

[0051] After obtaining the sound effect optimization information, the sound field control unit can determine the sound unit control information of each sound unit based on the environmental space information, the position information of multiple sound units, the position information of multiple players, and the sound effect optimization information corresponding to the position information of multiple players. This allows the sound field control unit to comprehensively consider the spatial layout and player feedback, and calculate the optimal sound adjustment scheme.

[0052] For example, the sound field control unit can analyze the reflection characteristics of sound waves in the environmental space and calculate the sound field distribution by combining the player's position information. The sound field control unit can be trained and optimized by historical sound effect data and player feedback data.

[0053] After determining the audio unit control information for each speaker unit, the operating status of each speaker unit can be precisely controlled based on this control information. The audio unit control information can further include volume, equalizer settings, delay parameters, etc., to ensure that each player position can obtain the best listening effect.

[0054] For example, for players whose feedback volume is too low, the output power of the corresponding speaker unit can be increased; for players whose feedback volume is too high, the volume of the corresponding speaker can be appropriately reduced. This precise control can ensure that players in every position can have a comfortable listening experience.

[0055] The beneficial effect of the above implementation method is that it obtains sound effect optimization information corresponding to multiple player location information, so as to obtain the specific sound effect optimization requirements of the player corresponding to each player location information, and further optimizes the user experience of the player corresponding to each player location information.

[0056] Figure 3 A flowchart illustrating the second deep learning-based immersive script murder mystery sound effect generation method provided in this application embodiment is shown below. Figure 3 As shown, the above method also includes S210 to S220, which will be described in detail below.

[0057] S210. Using the script analysis model, determine the scene information and scene transition information corresponding to the immersive murder mystery game based on the script information. The scene transition information corresponds to the transition information between different scene information.

[0058] In this implementation, during the immersive script murder mystery game, the script information can be intelligently analyzed through the script analysis model to further improve the control effect of game sound effects. The script analysis model can identify scene descriptions and scene transition nodes in the script, extract key scene information and transition relationships between scenes. Scene information includes the environmental features and plot elements of the current scene, and scene transition information includes the transition method, transition time point and transition duration when switching scenes.

[0059] For example, the script parsing model can be a deep learning model built using natural language processing technology. The script parsing model is trained with a large number of script samples and can accurately identify scene division markers and transition prompts in the script. The scene information output by the script parsing model can include features such as scene type and environmental atmosphere, while the scene transition information can include parameters such as transition method, transition time point, and transition duration.

[0060] S220: Through the sound field adjustment unit, based on environmental spatial information, the position information of multiple speaker units, the position information of multiple players, scene information, and scene transition information, the sound unit adjustment information for each speaker unit is determined. The operating state of each speaker unit is adjusted according to this sound unit adjustment information. This sound unit adjustment information includes volume adjustment information and surround sound effect adjustment information.

[0061] In this implementation, the sound field adjustment unit can generate sound unit adjustment information for each sound unit position and player position based on the scene information and scene transition information output by the script parsing model, combined with environmental space information, multiple sound unit position information, and multiple player position information. The sound unit adjustment information includes parameters such as volume adjustment and surround sound configuration.

[0062] For example, in the castle detective scene, the sound field adjustment unit can automatically lower the background music volume according to the scene information to enhance the surround sound effect. When the scene changes to an outdoor chase scene, it can smoothly transition the sound effects and gradually increase the volume of the main speaker unit to create a tense atmosphere. Each speaker unit will receive specific adjustment parameters according to the environmental space information, the position information of multiple speaker units, and the position information of multiple players to achieve precise sound field control.

[0063] The beneficial effect of the above implementation method is that it can analyze scene information and scene transition information based on the script information of immersive murder mystery games, and automatically adjust the sound effect information in the scene based on environmental space information, multiple sound unit position information, multiple player position information, scene information and scene transition information, so as to optimize the sound effect in the murder mystery game.

[0064] The beneficial effect of the above implementation method is that when controlling the working state of each speaker unit according to the speaker unit control information, the sound effect can be further adjusted according to the speaker unit adjustment information, thereby improving the personalization of the sound system during operation.

[0065] In some implementations, the above method also includes S230 to S240, which will be described in detail below.

[0066] S230. Obtain sound effect preference information from players corresponding to multiple player location information. This sound effect preference information includes volume change preference value, horror preference value, and low-frequency tolerance value. The volume change preference value represents the player's liking for volume changes, the horror preference value represents the player's liking for horror sound effects, and the low-frequency tolerance value represents the player's tolerance for low-frequency sound effects.

[0067] In this implementation, during the immersive murder mystery game, the sound effect preference information corresponding to each player's position can be obtained. The volume change preference value can reflect the player's acceptance of sudden volume changes, the horror preference value can measure the player's liking for horror sound effects, and the low frequency tolerance value can assess the player's physiological tolerance to low frequency sound effects. The sound effects of the immersive murder mystery game can be further optimized through the volume change preference value, horror preference value, and low frequency tolerance value.

[0068] For example, this preference information can be obtained through pre-game questionnaires or real-time interactive interfaces. This preference information helps to understand each player's personalized needs for sound effects and provides a data basis for subsequent sound effect adjustments.

[0069] S240: Using the sound field adjustment unit, based on the sound effect preference information fed back by players corresponding to the position information of multiple players, determine the limiting threshold for the sound unit adjustment information. Adjust the sound unit adjustment information of each sound unit according to the limiting threshold.

[0070] After obtaining the sound effect preference information, the sound field adjustment unit can further determine the limit threshold of the sound unit adjustment information based on each player's sound effect preference information.

[0071] For example, the sound field adjustment unit can be a rule engine-based decision system. The sound field adjustment unit can calculate the optimal sound effect parameter limits suitable for the current player group by analyzing the combination relationship of each player's volume change preference value, horror preference value and low frequency tolerance value. The sound field adjustment unit can comprehensively consider the preference information of all players and avoid extreme sound effect settings.

[0072] Once the limit thresholds are determined, the volume, frequency, and other parameters of each speaker unit can be adjusted based on these thresholds. This adjustment can be made in real time to ensure that each player can obtain a sound effect experience that matches their own preferences.

[0073] For example, in horror-themed murder mystery games, the intensity of horror sound effects in the area can be reduced for players with lower horror preference values, and the output power of low-frequency sound effects can be reduced for players with lower low-frequency tolerance values.

[0074] The beneficial effect of the above implementation method is that by using the sound effect preference information fed back by players corresponding to multiple player location information, the limit threshold for adjusting the sound unit is determined, so as to ensure that the sound effects in the script murder game meet the user's usage preferences and improve the user experience.

[0075] The beneficial effect of the above implementation method is that by adjusting the audio unit adjustment information of each audio unit according to the limit threshold of the audio unit adjustment information, the working effect of the audio can be optimized based on the audio unit adjustment information, thereby improving the user experience.

[0076] Figure 4 A flowchart illustrating the third deep learning-based immersive script murder mystery sound effect generation method provided in this application embodiment is shown below. Figure 4 As shown, the above method also includes S310 to S320, which will be described in detail below.

[0077] S310. Determine the number of player location information as player quantity information.

[0078] In this implementation, the number of player location information can be determined as player quantity information. This player quantity information reflects the total number of players currently participating in the game. Player quantity information can be used to initially assess the ambient noise level and provide a basis for subsequent sound system adjustments.

[0079] S320: Through the sound field transition adjustment unit, based on the number of players, the sudden sound effect rise rate and soundscape switching speed corresponding to the speaker unit adjustment information are determined. The operating state of each speaker unit is adjusted according to its adjustment information. Specifically, the larger the number of players, the greater the sudden sound effect rise rate and soundscape switching speed.

[0080] After determining the number of players, the sound field transition adjustment unit can be used to determine the sudden sound effect rise rate and sound scene switching speed corresponding to the sound unit adjustment information based on the number of players. The sudden sound effect rise rate represents the response time of the sound unit from a silent state to the maximum sound effect intensity, and the sound scene switching speed represents the transition time between different scene sound effects.

[0081] It should be noted that when determining the rise rate of sudden sound effects and the speed of sound scene transition, the larger the number of players, the greater the rise rate of sudden sound effects and the speed of sound scene transition. This adjustment method can adapt to changes in environmental noise under different numbers of players and ensure that the sound effects can effectively penetrate environmental noise.

[0082] For example, the sound field transition adjustment unit can be a deep learning model based on neural networks, which can be trained using historical player count information and corresponding optimal sound effect parameters.

[0083] In this implementation, after obtaining the sudden sound effect rise rate and sound scene switching speed, the working state of each speaker unit can be adjusted according to the speaker unit adjustment information of each speaker unit. By adjusting the working state of each speaker unit in real time, precise sound field control can be achieved.

[0084] For example, in a murder mystery game with 10 players, the system will automatically increase the speed of sudden sound effects and the speed of sound scene transitions because the players' conversations are loud, so that key sound effects can be highlighted quickly; while in a 3-player game, the system will reduce these parameters to maintain a smooth transition of sound effects.

[0085] The beneficial effect of the above implementation method is that it can adjust the switching speed of sound effects according to the number of players. When the number of players is large, which leads to an increase in average ambient noise, the sudden sound effect rise speed and sound scene switching speed can be increased, and a faster transient response can be used to break through the environmental noise threshold. This avoids the ambient sound effect time being too long, which increases the noise level of the scene, and can improve the user experience in scenarios with a large number of players.

[0086] The beneficial effect of the above implementation method is that when the number of players is small, by reducing the speed of sudden sound effects and the speed of sound scene switching, it is possible to maintain the sense of immersion in the atmosphere and to smooth the transition of sound effects to maintain a delicate feel, thereby improving the user experience.

[0087] In some implementations, the above method also includes S330 to S340, which will be described in detail below.

[0088] S330: Obtain the player's preferred in-game communication volume value. The in-game communication volume preference value represents the player's preferred volume of sound effects for communication in the game.

[0089] In this implementation, the player's pre-set communication volume preference value in the game can be obtained through the game system interface. The communication volume preference value can reflect the player's personalized needs for the volume of communication sound effects during the game.

[0090] For example, the communication volume preference value in the game can be set to a continuous range of 1-10. The smaller the communication volume preference value in the game, the less the game sound effects may affect communication between players. The larger the communication volume preference value in the game, the more the game sound effects may affect communication between players.

[0091] S340: Through the sound field transition adjustment unit, based on player quantity information and in-game communication volume preference values, the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the speaker unit adjustment information are determined. The operating state of each speaker unit is adjusted according to its adjustment information. Specifically, the higher the in-game communication volume preference value, the greater the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude.

[0092] After obtaining the communication volume preference value in the game, the sound field transition adjustment unit can determine the sudden sound effect rise rate, sound scene switching speed, and sound effect change amplitude corresponding to the sound unit adjustment information based on the number of players and the communication volume preference value in the game. This allows for further adjustment of the sound parameters according to the number of players and the sound effect volume requirements in game communication.

[0093] For example, the sound field transition adjustment unit can adopt a sound effect control model based on deep learning. The sound field transition adjustment unit can be trained by analyzing the correspondence between the number of players, communication volume preference value and optimal sound effect parameters in historical game scenes. The sound field transition adjustment unit can intelligently calculate the sound unit adjustment information suitable for the current game atmosphere based on the current number of players and the communication volume preference value in the game.

[0094] It's important to note that the audio unit adjustment information includes three key parameters: the rate of increase in sudden sound effects, the speed of soundscape transitions, and the magnitude of sudden sound effect changes. When the preferred communication volume value in the game is high, the audio control system can increase the values ​​of these three parameters, making sound effect changes faster and more noticeable. For example, when a player sets a high preferred communication volume value, the system will speed up the transition from background music to dialogue scenes. In this case, a large increase in the rate of increase in sudden sound effects, the speed of soundscape transitions, and the magnitude of sudden sound effect changes may significantly impact communication between players.

[0095] After receiving the sound unit adjustment information, the working status of each sound unit can be adjusted in real time according to the calculated sound unit adjustment information. This allows for dynamic control of the sound intensity, frequency response, and spatial positioning effect of each sound unit, ensuring that the sound effect changes meet the communication needs of players in the current game.

[0096] For example, when a startling sound effect suddenly appears during the reasoning phase, the abrupt change in the sound effect will be controlled according to the parameter settings to ensure that the sound effect change meets the communication needs of the players in the current game.

[0097] The beneficial effect of the above implementation method is that by obtaining the game communication volume preference value, which represents the player's preference for sound effect volume in the game, a fast and strong sound effect pulse is generated when the game communication volume preference value is large. This makes the volume, sound effect switching speed and sound effect change amplitude more adaptable to the player's overall need to maintain a large sound effect volume when communicating in the game, which can better maintain the interactive atmosphere in the game and improve the player's user experience in the game.

[0098] The beneficial effect of the above implementation method is that when the communication volume preference value in the game is small, the volume, sound effect switching speed and sound effect change amplitude are smaller, which can better adapt to the communication needs of thinking and quiet players in the game. By maintaining the smooth transition of game sound effects, the user experience of players who prefer quiet is improved.

[0099] The beneficial effect of the above implementation method is that by obtaining the game communication volume preference value, which represents the player's preferred volume of sound effects in the game, and combining it with the number of players, the volume, sound effect switching speed and sound effect change amplitude are adjusted in a comprehensive manner, thereby improving the player's user experience in the game.

[0100] In some implementations, the above method also includes S410 to S420, which are described in detail below.

[0101] S410. Obtain player interaction information in the immersive murder mystery game, including communication information between multiple players. Using an activity monitoring model, determine the player interaction activity factor based on the number of players and their interaction information. The interaction activity factor should be between 0.8 and 1.5.

[0102] During immersive murder mystery games, player interaction information can be obtained, including communication information between multiple players. This communication information can reflect the frequency and depth of interaction between players. By analyzing this interaction information, we can understand the level of player participation in the game.

[0103] After obtaining communication information between multiple players, an activity monitoring model can be used to determine the player interaction activity factor based on player number information and player interaction information.

[0104] For example, the activity monitoring model can be a deep learning model based on neural networks. The activity monitoring model predicts the current game's interactive activity by analyzing features such as the number of players, interaction frequency, and interaction content in historical game data.

[0105] For example, the activity monitoring model can be trained using sample player number information, sample player interaction information, and sample interaction activity factor. The activity monitoring model can identify the activity level corresponding to different interaction modes, such as the impact of interaction forms like rapid dialogue, heated debate, or in-depth discussion on the activity factor.

[0106] It should be noted that the interaction activity factor is between 0.8 and 1.5, and the interaction activity factor can quantify the overall activity level of the player group.

[0107] S420. Determine the product of the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information and the interactive activity factor, so as to adjust the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information.

[0108] After determining the interaction activity factor, the product of the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information and the interaction activity factor can be calculated. Through this product calculation, the rate and intensity of sound effect changes can be dynamically adjusted according to the player's actual activity level. When the interaction activity factor is greater than 1, the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude can be amplified; when the interaction activity factor is less than 1, the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude can be reduced.

[0109] For example, in a detective-themed murder mystery game, when players are discussing clues enthusiastically, the interaction activity factor may reach 1.3. At this time, the speed of sound effect changes will increase by 30% to create a more tense atmosphere. Conversely, when players fall into deep thought and the interaction activity factor may reach 0.8, the speed of sudden sound effects, soundscape transitions, and sudden changes in sound effects will remain gradual, giving players ample time to think.

[0110] The beneficial effect of the above implementation method is that, based on the number of players and player interaction information, the player interaction activity factor is determined, and the sudden sound effect rise speed, sound scene switching speed and sound effect change amplitude corresponding to the sound unit adjustment information are adjusted according to the interaction activity factor. This can adjust the game rhythm according to the player's interaction activity in the actual game, and achieve a positive cycle where the more active the player team is, the more intense the challenge becomes.

[0111] In some implementations, the above method also includes S430 to S440, which are described in detail below.

[0112] S430: Obtain the volume value of the game NPC in the immersive murder mystery game, and obtain the player's evaluation value of the voice clarity of the game NPC in the immersive murder mystery game.

[0113] During an immersive murder mystery game, the volume of the game NPCs can be continuously acquired, and the subjective evaluation value of the players' voice clarity can be collected simultaneously. The volume of the game NPCs reflects the actual sound pressure level of the NPCs' voice output, while the voice clarity evaluation value quantifies the players' perception of whether the voice is clear.

[0114] S440: Through the game NPC voice adjustment unit, determine the volume adjustment value of the game NPC based on the volume value, interaction activity factor and voice clarity evaluation value of the game NPC.

[0115] After obtaining the volume value and speech clarity evaluation value of the game NPC, the game NPC speech adjustment unit can comprehensively analyze the three key parameters of volume value, interaction activity factor and speech clarity evaluation value, and determine the specific volume adjustment value based on these three input parameters.

[0116] For example, in horror-themed murder mystery games, when players' interaction activity level decreases due to tension, the NPC's volume can be automatically increased to ensure the transmission of key clues; conversely, when players are engaged in heated discussions during the deduction phase, the NPC's volume will be appropriately decreased to avoid interfering with player communication. This dynamic adjustment ensures sound balance across different game stages.

[0117] The beneficial effect of the above implementation method is that when the player's interaction activity factor is different in the game, the NPC's volume value may affect the effect of the immersive script murder game. By obtaining the user feedback on the voice clarity evaluation value of the game NPC, the NPC's volume value can be adjusted according to the interaction activity factor and the voice clarity evaluation value, so as to improve the control effect of the NPC's volume value, thereby avoiding the interruption of the player's interaction activity by the NPC's volume and improving the control effect of the NPC's volume.

[0118] The beneficial effects of the above implementation method are that, by taking into account both objective volume measurement values ​​and subjective clarity evaluation, the volume adjustment not only conforms to acoustic characteristics but also meets the player's perceptual needs, thereby improving the naturalness and realism of sound interaction.

[0119] The beneficial effects of the above implementation method are that the introduction of the interactive activity factor enables the system to perceive changes in the game situation, automatically reduce NPC interference when players are focused on discussion, and enhance the presence of NPCs when guidance is needed, thus achieving intelligent volume and situational adaptation.

[0120] In some implementations, the above method also includes S450 to S460, which are described in detail below.

[0121] S450: Obtain the interval duration of the same clue sound effects when they are played repeatedly in the immersive script murder mystery game, and use it as the sound effect repetition interval duration.

[0122] In immersive murder mystery games, the interval between repeated playback of the same clue sound effects can be obtained, i.e., the sound effect repetition interval. The sound effect repetition interval reflects the time interval between repeated playback of clue sound effects. By monitoring this parameter, the repetition frequency of clue sound effects in the current game process can be understood.

[0123] For example, when players explore a secret room scene, the ticking of a clock playing in the background serves as a key time clue. By recording the time difference between two playbacks of this sound effect as the duration of the sound effect repetition interval, this kind of timing data collection can be achieved through the game engine's built-in audio management system, providing basic data support for subsequent dynamic adjustments.

[0124] S460. Determine the product of the sound effect repetition interval duration and the interaction activity factor as the sound effect repetition interval adjustment duration. Adjust the interval duration of the same clue sound effects when they are played repeatedly in the immersive script murder mystery game based on the sound effect repetition interval adjustment duration.

[0125] After obtaining the duration of the sound effect repetition interval, the product of the sound effect repetition interval duration and the interaction activity factor can be determined to obtain the adjusted sound effect repetition interval duration. By combining the sound effect repetition interval duration with the interaction activity factor that reflects the player's level of participation, intelligent matching of the clue sound effect playback rhythm with the actual game progress is achieved. When the player interacts frequently, the repetition interval is appropriately shortened to maintain the continuity of clue prompts; when the player is focused on solving puzzles, the interval is appropriately lengthened to avoid interference.

[0126] For example, the interaction activity factor can be between 0.7 and 1.8, which can increase or decrease the duration of sound effect repetition intervals.

[0127] The beneficial effect of the above implementation method is that the repetition interval of clue sound effects in immersive script murder mystery games will affect the continuity of the game. By adjusting the repetition interval of clue sound effects through the interaction activity factor, the adaptability of game clue sound effects and player activity in the game is further improved, thus enhancing the player's gaming experience.

[0128] This application also provides an immersive script murder mystery sound effect generation system based on deep learning, including a unit for performing the method described in any of the preceding claims.

[0129] Figure 5 A schematic diagram of the logical structure of an immersive script murder mystery sound effect generation system based on deep learning, as provided in an embodiment of this application, is shown below. Figure 5As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0130] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0131] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0132] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0133] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0134] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0135] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0136] The units described 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 can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for generating immersive script-based murder mystery game sound effects based on deep learning, characterized in that, The method includes: The system acquires the environmental spatial information corresponding to the target environment, as well as the location information of multiple speaker units and multiple player positions within the target environment. The environmental spatial information includes the three-dimensional spatial information corresponding to the target environment, and one speaker unit corresponds to one speaker unit position information. The sound field control unit determines the sound unit control information for each sound unit based on environmental space information, the position information of multiple sound units, and the position information of multiple players; and controls the working status of each sound unit based on the sound unit control information of each sound unit. The method further includes: Determine the number of player location information as player quantity information; obtain the player's set in-game communication volume preference value, which represents the player's preferred sound effect volume for in-game communication; The sound field transition adjustment unit determines the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information based on the number of players and the communication volume preference value in the game. The working state of each sound unit is adjusted according to the sound unit adjustment information of each sound unit. The sound unit adjustment information includes volume adjustment information and surround sound effect adjustment information. When the communication volume preference value in the game is higher, the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude are greater. The system acquires player interaction information in immersive murder mystery games, including communication information between multiple players. Using an activity monitoring model, it determines the player interaction activity factor based on player count and interaction information; the interaction activity factor is between 0.8 and 1.

5. The product of the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information and the interaction activity factor is determined, so as to adjust the sudden sound effect rise rate, soundscape switching speed, and sound effect abrupt change amplitude corresponding to the sound unit adjustment information.

2. The method as described in claim 1, characterized in that, The method further includes: Obtain sound effect optimization information from player feedback corresponding to multiple player location information; the sound effect optimization information includes volume adjustment suggestions; The sound field control unit determines the sound unit control information for each sound unit based on environmental space information, multiple speaker unit position information, multiple player position information, and sound effect optimization information corresponding to each player position information; and controls the working state of each sound unit based on the sound unit control information of each sound unit.

3. The method as described in claim 2, characterized in that, The method further includes: Through the script analysis model, based on the script information of the immersive murder mystery game, the scene information and scene transition information corresponding to the immersive murder mystery game are determined. The scene transition information corresponds to the transition information between different scene information. The sound field adjustment unit determines the sound unit adjustment information for each sound unit based on environmental space information, the position information of multiple sound units, the position information of multiple players, scene information, and scene transition information; and adjusts the working state of each sound unit according to the sound unit adjustment information of each sound unit.

4. The method as described in claim 3, characterized in that, The method further includes: Obtain sound effect preference information from players corresponding to multiple player location information; among which, sound effect preference information includes volume change preference value, horror preference value, and low frequency tolerance value. The volume change preference value represents the player's liking for volume changes, the horror preference value represents the player's liking for horror sound effects, and the low frequency tolerance value represents the player's tolerance for low frequency sound effects. The sound field adjustment unit determines the limiting threshold for the sound unit adjustment information based on the sound effect preference information fed back by players corresponding to the position information of multiple players; and adjusts the sound unit adjustment information of each sound unit according to the limiting threshold.

5. The method as described in claim 4, characterized in that, The method further includes: The sound field transition adjustment unit determines the sudden sound effect rise rate and soundscape switching speed corresponding to the sound unit adjustment information based on the number of players; it also adjusts the working state of each sound unit according to the sound unit adjustment information of each sound unit; in particular, the greater the number of players, the greater the sudden sound effect rise rate and soundscape switching speed.

6. The method as described in claim 1, characterized in that, The method further includes: Get the volume value of the game NPCs in the immersive murder mystery game, and get the players' evaluation value of the voice clarity of the game NPCs in the immersive murder mystery game. The game NPC voice adjustment unit determines the volume adjustment value of the game NPC based on the game NPC's volume value, interaction activity factor, and voice clarity evaluation value.

7. The method as described in claim 6, characterized in that, The method further includes: Obtain the interval duration of the same clue sound effects when they are played repeatedly in the immersive script murder mystery game, and use it as the sound effect repetition interval duration. The product of the sound effect repetition interval duration and the interaction activity factor is determined as the sound effect repetition interval adjustment duration; the interval duration of the same clue sound effects when played repeatedly in immersive script murder mystery games is adjusted according to the sound effect repetition interval adjustment duration.

8. An immersive script-based murder mystery game sound effect generation system, characterized in that, Includes a unit for performing the method according to any one of claims 1 to 7.

Images