DE102023136628A1 - Method for the adaptive design of an interactive, auditory game in a speech-controlled game system - Google Patents

Abstract

The invention relates to a method for the adaptive design of an interactive, auditory game in a voice-controlled game system, carried out by the voice-controlled game system. First, at least one voice command is received by a speech recognition system of the voice-controlled game system, which is connected to a speech model, wherein the speech model is trained to conduct a voice dialogue with the at least one user. The voice command describes game parameters to be generated, wherein game parameters define characters, game objectives, game scenarios, and/or game rules of a predefined persistent virtual world. Predefined building blocks that correlate with the game parameters are then retrieved from a database of the game system. The predefined building blocks are subsequently linked by incorporation into the persistent virtual world of the game system based on the game parameters, thereby generating auditory game content of the auditory game. Finally, a voice dialogue is carried out to provide the auditory game to the at least one user.

Description

The invention relates to a method for the adaptive design of an interactive, auditory game in a voice-controlled game system.

An auditory game represents a category of video game that relies on the use of language as an interaction medium. By integrating a language model, such as a "Generative Pre-trained Transformer," such an auditory game can include a dialogue system capable of responding to user input in the form of so-called natural spoken language. Another key contribution of such a language model lies in the generation of content. Such content can also be output to the user in the form of natural spoken language by the dialogue system in order to present game content to which the user must respond with their user input. In particular, it enables the automatic generation of stories, dialogues, and/or scenarios, which improves the scalability and/or diversity of the auditory game. A user can thus make a wide range of decisions, and the auditory game can react dynamically to these to provide a customized gaming experience.

The DE 10 2019 201 900 A1 discloses a method and apparatus for conducting group activities in vehicles.

The US 2017/0349184 A1 describes a system for determining actions of an autonomous vehicle in conjunction with a group of passengers.

The WO 2005067574 A2 discloses a vehicle entertainment system with integrated gaming functionality. Game content for the entertainment system is generated on-board.

None of the existing solutions offers users the option of creating their own game content. Instead, existing solutions are "interactive audiobooks" rather than interactive auditory games. While users can select from several possible narrative paths through user input, user input does not allow for freely selectable mobility within a game scenario ("I want to go back to the last room"), and the programmatic management of dynamic content within such game scenarios is not possible ("The angry wizard you tied up is still ranting in the last room"). The free, dynamic arrangement of such game content according to user specifications cannot be implemented with interactive audiobooks.

The invention is based on the object of creating an individually dynamically generated, auditory game for a user.

The object is achieved by the subject matter of the independent patent claims. Advantageous developments of the invention are described by the dependent patent claims, the following description, and the figures.

The invention provides a method for interactively creating an auditory game in a voice-controlled game system. An auditory game refers to an interactive application in which the primary focus is on acoustic elements. "Simple" animations, such as the presentation of a character and/or a map, may be displayed on a display device of the game system. However, the gaming experience is preferably designed through the use of voice content. The visual components found in the auditory game system play a secondary or supporting role in the realization of the auditory game and are simple in nature (e.g., a single image and/or 360-degree animation of the character or game piece), which merely serve to present basic information, while the gaming experience is conveyed through the user's sense of hearing. An auditory game system is therefore preferably fully functional or playable without the visual game content. Unlike visual games, which focus on graphics and animations, an auditory game relies on sounds, noises, and/or, in particular, voice commands and/or voice content for its actual game function in order to entertain a user or at least one user and/or enable an immersive experience. This is particularly advantageous in a motor vehicle, allowing the user to continue to observe traffic or drive the vehicle without distraction. "Adaptive design" means that at least one user has the ability to interact with the game system, for example, to change their location in the game scenario and/or to influence dynamic content (e.g., virtual characters and/or objects). A voice-controlled game system refers to a system and/or application in which the interaction between the at least one user and the system takes place at least partially via spoken language, i.e., via a voice input from the user and a voice output from the game system. To implement the method, the voice-controlled, auditory game system performs the following steps:

First, at least one voice command is processed by a speech recognition system of the controlled game system. According to the invention, a "voice command" means an orally spoken instruction or request that serves to control or operate the voice-controlled game system. Alternatively, it can be provided that a manual input is made, for example, via a control element of a display device, such as a screen, of the game system. The speech recognition system is connected to one or at least one language model, wherein the language model is trained to conduct a voice dialogue with the at least one user. The language model can be designed, for example, as a GPT (Generative Pretrained Transformer) and/or BERT (Bidirectional Encoder Representations from Transformers). The language model can be trained using machine learning. The language model can be trained on data in order to learn patterns and/or relationships between a voice command and/or user input on the one hand and desired model responses or feedback on the other.

The voice command here does not refer to voice input during a game, but rather to the creation of a game scenario. The voice command is intended to (at least partially) describe game parameters to be generated, with game parameters defining characters, game objectives, game scenarios, and/or game rules of a predefined persistent virtual world. The at least one user can therefore specify game parameters via the at least one voice command. For example, the at least one user can describe what their "character" (self-guided game figure) looks like and/or what properties it has. A "persistent virtual world" can be implemented by a digital environment and/or a digital game world, which, for example, contains a data structure for managing location- and/or time-related properties of the world and a management program for modifying this data structure depending on user input. Essentially, it forms the basis or basic structure for the virtual experience or for the persistent virtual world. This persistent virtual world can then be expanded, for example, by integrating pre-made or real maps.

• Der zumindest eine Nutzer gibt z. B folgenden Sprachbefehl ab:
  • Für den Charakter: „Erstelle einen mutigen Krieger mit einem roten Umhang und einem Schwert.“

A concrete example of this is the following:

• At least one user gives the following voice command:
  • For the character: “Create a brave warrior with a red cape and a sword.”

To set the game goal: "Set the goal to find a lost treasure in the cave and return safely to the village."

For the game scenario: "Change the in-game weather to a starry sky and add a mysterious fog bank."

To define the rules of the game: "Change the rules so that players have to collect more resources to create more powerful weapons."

To create a game scenario: "Incorporate a sudden dragon attack into the auditory game to increase the tension."

Next, the method retrieves or requests predefined building blocks or assets from a database of the game system, wherein the predefined building blocks correlate with or are assigned to the game parameters. In other words, a database can be implemented which provides correspondingly linked predefined building blocks if the game parameters to be generated in the voice command at least partially match the game parameters from the database. “Predefined building blocks” refers to digital resources, in particular audio files. These digital resources can additionally or alternatively be programming resources for implementing the game logic of the auditory game and/or include textual and/or linguistic content. It can be provided that such a digital resource comprises a decision tree or is implemented as a decision tree. It can be provided that by detecting user input, for example via voice input, the corresponding branch in the decision tree is activated and an audio file or linguistic content is provided that is relevant based on the decision made by the user.

• Der zumindest eine Nutzer übernimmt z. B. die Rolle eines Detektivs, der vor einem ungelösten Fall steht. Der Entscheidungsbaum verzweigt sich:
  • Option A: Untersuche den Tatort gründlich nach Spuren.
  • Option B: Befrage Zeugen in der Umgebung des Tatorts.

A concrete example of this is the following:

• At least one user assumes the role of a detective facing an unsolved case. The decision tree branches out:
  • Option A: Examine the crime scene thoroughly for evidence.
  • Option B: Interview witnesses in the area surrounding the crime scene.

At least one user gives a voice command: “Investigate the crime scene” or “Interview witnesses.”

• Option A1: Analysiere Fingerabdrücke auf einem verdächtigen Gegenstand.
• Option A2: Befrage Zeugen in der Nähe des Tatorts erneut.

If at least one user chooses “Investigate the crime scene,” the decision tree could branch further:

• Option A1: Analyze fingerprints on a suspicious object.
• Option A2: Re-interview witnesses near the crime scene.

Each decision can be accompanied by a corresponding audio file that provides at least one user with information about new clues or, for example, witness statements. For example, after investigating the crime scene, the audio file can provide at least one user with details about a suspicious object. Each decision thus leads to a unique path, ensuring variety in the gaming experience. Such an auditory game can be easily scaled by adding additional branches to the decision tree and thus new audio files. This allows developers to expand the gaming experience without having to make fundamental changes to the game code. This enables the adaptive design of the interactive, auditory game.

The predefined building blocks are then linked by integration into the persistent virtual world of the game system based on the game parameters, thereby generating auditory game content for the game. This integration gives the predefined building blocks a spatial and/or temporal and/or mutually interactive relationship. For example, if at least one user enters a forest in the auditory game, a predefined building block can automatically change the background music to a nature-related melody. Additionally or alternatively, it can be provided that, for example, at one or more specific locations in the persistent virtual world, information in the form of voice output or audio content can be provided by a predefined building block. Furthermore, it can be provided that, as already described, a predefined building block requires at least one user in the auditory game to make decisions, whereby a corresponding dialogue can be triggered depending on the decision made. For example, if the at least one user chooses a peaceful solution to a problem, a dialogue for a diplomatic conversation can be played.

According to the invention, a voice dialogue is conducted to provide the auditory game for the at least one user. The method allows individual preferences and/or personal tastes to be incorporated into the design of the auditory game. The at least one user can therefore dynamically generate an auditory game or auditory game content, at least in part, themselves. Since the method can additionally or alternatively be provided to multiple users, this has the advantage of creating a shared experience. Since the game is purely auditory, it is conceivable that, for example, the driver of a motor vehicle could participate in the game as a user without being distracted.

The invention also includes further developments which result in additional advantages.

A further development provides that the game parameters refer to information or settings provided by the voice command and that influence the course or conditions of the auditory game in the voice-controlled game system. Thus, at least one user can define the framework within which the gameplay of the auditory game takes place. This allows the user a high degree of creative freedom when creating the auditory game.

A further development provides for the auditory game content to be saved and made available for sharing with other users on a server of the game system. Additionally or alternatively, the saved game content can be made available for future plays of the auditory game. Furthermore, it can be provided that the saved game content is integrated into another auditory game. The saved game content can thus be shared by different users, thereby implementing a social component in the game. For example, users can work together on the game content, which promotes collaboration and/or interaction between users.

By storing the game content, the state of the auditory game can be maintained across different gaming sessions, allowing users to pick up where they left off at a later time, thus contributing to long-term motivation. The use of a server makes it possible to provide extensive resources for the auditory game. This allows for larger game worlds, i.e., a larger persistent virtual world, and/or complex calculations that might not be possible on a local device. Furthermore, storing the game on a server makes it easy to implement updates and/or patches. To integrate the game content into an auditory game, the skilled person can provide an appropriate interface and/or logic.

A further development provides that a topographical condition or topographical map of the real environment is recorded depending on the location of the game system and integrated or transferred into the persistent virtual world, so that a relationship between the building blocks and real objects in the environment is provided. This means that elements in the persistent virtual world, such as buildings, roads and/or other geographical features, are assigned to corresponding real objects in the environment of at least one user. Topographical features of the actual environment are therefore recorded at the respective location of the game system, for example by at least one sensor device, e.g. by means of a global navigation satellite system and/or camera system and/or a LIDAR (Light Detection and Ranging) sensor of the game system or e.g. a motor vehicle that comprises the game system. These topographical features and/or information are then integrated into the persistent virtual world in order to establish a relationship between the virtual building blocks and the real objects in the environment. The recorded topographical features or data can, for example: B. "SLAM algorithm" (Simultaneous Localization and Mapping), can be integrated into the persistent virtual world, creating a constantly updated representation of the real environment in the auditory game. The advantage of this is that a close connection can be established between the persistent virtual world of the game system and the real environment. This can create an immersive gaming experience in which the virtual world is directly aligned with the real environment. This can also enhance the authenticity and/or immersion of the auditory game, as the user can interact with their actual environment.

For this purpose, it may be provided that a geographic information system is used and/or geolocation is performed to track the position of the game system in the real environment. Furthermore, it is possible that augmented reality technologies are used to enhance the immersive gaming experience. For example, various types of sensors can be used, such as accelerometers and/or gyroscopes, to detect movements and/or orientation of the at least one user or the game system and/or, for example, the motor vehicle comprising the game system. This information can then be used to adapt the persistent virtual world accordingly.

A further development provides for the integration of a pre-fabricated map into the persistent virtual world, thereby determining the possibility of arranging the pre-defined building blocks. In other words, any map can be integrated into the persistent virtual world. Such a map could be, for example, a self-created map, i.e. one created individually by a user, and/or a real topographical map, such as of Munich, Berlin and/or New York. The spatial information and/or structures of the map thus become part of the persistent virtual world. At least one user can therefore design and/or adapt an environment in the persistent virtual world themselves, but the pre-defined building blocks to be arranged are based on the basic structure of the pre-fabricated map.

In the auditory game, at least one user moves around in a virtual environment that corresponds or can correspond to real geographical features. A user who is familiar with the real environment can therefore identify with the auditory game more easily. The recognition value of the map can increase immersion and/or increase the interest of at least one user. In addition, the use of a pre-made map can be advantageous in the technical development of the auditory game, as this already provides a basic framework for the persistent virtual world. This can shorten development time and/or save resources. For example, if changes occur in the real environment, these can simply be transferred to the persistent virtual world.

A further development provides for at least one user to be identified by voice recognition, and for user-specific game parameters to be created using the recognized user identity. This can be achieved using state-of-the-art voice recognition. The game system can then, for example, prompt each user participating in the auditory game to issue a voice command, so that user-specific game parameters are created for each user. However, it can also be provided that at least one user issues or submits voice commands without being asked, thereby creating game parameters. The user-specific game parameters can adapt the persistent virtual world of the auditory game by integrating elements, characters, and/or game scenarios that are of interest to the respective user. In an auditory game with multiple users, individual player profiles can be created so that each user can maintain their own game parameters when logging in. This can help the at least one user feel more connected to the auditory game.

A further development provides that the game system proactively prompts at least one user to issue a voice command. The proactive prompt can promote the user's engagement with the game. The game system therefore encourages at least one user to actively interact with the auditory game and can thus improve the overall experience for the at least one user. This can lead to a dynamic and/or personal gaming experience. The prompt to issue a voice command can vary depending on the context of the auditory game. For example, in an action game of the auditory game, the prompt can encourage the at least one user to issue a tactical command, while in an exploration game the prompt aims to interact with the environment.

A further development provides that the predefined building blocks comprise a concrete representation of the at least one game parameter, in particular a character, an environment, a task and/or an event. These predefined building blocks thus specifically represent various aspects or objects in the world of the auditory game that can be interacted with and/or influenced or controlled. For example, characters could represent various playable figures, environments could be game locations, tasks could represent the user's goals, and events could be actions or turning points in the auditory game. The predefined building block can be a speech building block that comprises media content and/or a voice message that is, for example, located at a geographical feature in the real environment or in the persistent virtual world. If the at least one user walks or drives past this geographical feature, for example, this voice message can then be automatically output or lead to an interaction with the respective user.

A further development provides for a filter system to be implemented in the gaming system to detect and prevent inappropriate or potentially harmful game content that could be created via a voice command. This can ensure a safe and/or appropriate gaming experience for the user. The filter system can, for example, include a pattern recognition algorithm that searches for specific words, expressions, and/or patterns that are considered problematic. Additionally or alternatively, a machine learning model can be used to train the filter system. By providing training data representing inappropriate or harmful content, the filter system can learn to detect and/or block such content. Additionally or alternatively, a blacklist can be included that contains inappropriate terms or phrases; if these terms or phrases appear, they are blocked.

For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and/or a request to enter user feedback is issued and/or a default setting and/or a predetermined initial state is set.

The invention also includes the control device for the game system. The control device can have a data processing device or a processor device configured to carry out an embodiment of the method according to the invention. For this purpose, the processor device can have at least one microprocessor and/or at least one microcontroller and/or at least one FPGA (Field Programmable Gate Array) and/or at least one DSP (Digital Signal Processor). In particular, a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), or an NPU (Neural Processing Unit) can be used as the microprocessor. Furthermore, the processor device can have program code configured to carry out the embodiment of the method according to the invention when executed by the processor device. The program code can be stored in a data memory of the processor device. The processor device can be based, for example, on at least one circuit board and/or on at least one SoC (System on Chip).

The invention also includes further developments of the game system according to the invention that have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments are not described again here.

As already mentioned, the game system can be incorporated into a motor vehicle. The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

The invention also encompasses the auditory game content that can be generated using the method. As already explained, the auditory game content first requires the output of a voice command, which is then interpreted into game parameters. Subsequently, predefined building blocks stones are combined according to these game parameters. Due to this procedure, the generated auditory game content exhibits features that are also protectable as intermediate products of the process.

As a further solution, the invention also encompasses a computer-readable storage medium comprising program code which, when executed by a computer or computer network, causes the computer or computer network to execute an embodiment of the method according to the invention. The storage medium can be provided at least partially as a non-volatile data memory (e.g., as a flash memory and/or as an SSD - solid state drive) and/or at least partially as a volatile data memory (e.g., as a RAM - random access memory). The storage medium can be arranged in the computer or computer network. However, the storage medium can also be operated, for example, as a so-called app store server and/or cloud server on the Internet. The computer or computer network can provide a processor circuit with, for example, at least one microprocessor. The program code can be provided as binary code and/or as assembly code and/or as source code of a programming language (e.g., C) and/or as a program script (e.g., Python).

The invention also encompasses combinations of the features of the described embodiments. The invention therefore also encompasses implementations that each have a combination of the features of several of the described embodiments, unless the embodiments are described as mutually exclusive.

• 1 zeigt eine schematische Darstellung einer erfindungsgemäßen Ausführungsform der Idee.

Exemplary embodiments of the invention are described below. Shown are:

• 1 shows a schematic representation of an inventive embodiment of the idea.

The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention that can be considered independently of one another, each of which also develops the invention independently of one another. Therefore, the disclosure is intended to encompass combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

In the figures, the same reference symbols denote elements with the same function.

1 shows a schematic representation of an inventive embodiment of the idea.

Shown are a real environment 30, real objects 9 linked to a (digital) predefined building block 12 or asset, a server 20, and a motor vehicle 10 having a game system 7 and/or at least one sensor device 4, wherein the game system 7 has a speech recognition system 5 and/or a game engine. A user 2 is located in the motor vehicle 10, who issues or transmits a voice command 11 to the game system 7. Also symbolically represented are game parameters 13 and auditory game content 6.

At least one user 2 can be in the motor vehicle 10 and decide to use the game system 7, whereby it is irrelevant whether the user 2 is the driver or a passenger. First, at least one voice command 11 can be received by a speech recognition system 5 of the voice-controlled game system 7, which is connected to a speech model. The speech model can be trained to conduct a voice dialogue with the at least one user 2, whereby the voice command 11 describes game parameters 13 to be generated. Game parameters 13 can define characters, game objectives, game scenarios and/or game rules of a predefined persistent virtual world. The voice command 11 can be recognized by the speech recognition system 5 and forwarded to a game engine of the game system 7, which provides game parameters 13 therefrom.

Predefined building blocks 12 that correlate with the game parameters 13 can then be retrieved from a database of the game system 7. Next, the predefined building blocks 12 can be linked by embedding them into the persistent virtual world of the game system 7 based on the game parameters 13, thereby generating auditory game content 6 of the auditory game. A voice dialogue can then be performed to provide the auditory game to the at least one user 2.

The auditory game can be a classic table-top role-playing game, in which at least one user 2 makes their own decisions, and the auditory game adapts to them. A first prototype of the game system 7 is designed to be specifically suited for a situation in a cabin or motor vehicle 10. wherein the at least one user 2 interacts with the (LLM-controlled) game system 7 using at least one voice command 11 or a voice announcement and acts, for example, as a game master. In addition to the regular voice-controlled game, the at least one user 2 can create one or more auditory game contents 6, in particular by issuing at least one voice command 11 to, for example, the voice engine of the game system 7.

For example, as soon as sufficient voice commands 11 have been issued, e.g., 1, 2, 3, or 1 to 8, the language model can combine correspondingly predefined building blocks 12 by extracting or interpreting the game parameters 13 from the at least one voice command 11 in order to create the auditory game according to the at least one voice command 11 of the at least one user 2. This can be implemented in the form of a story, in particular, e.g., for character creation and/or for campaign creation of the auditory game. The auditory game can then be made accessible to other users 2. Each user 2 can be given the opportunity to actively create their own auditory game content 6 individually.

Each auditory game content 6 takes place in a persistent virtual world with real interaction. Geographical locations or maps can be integrated into the auditory game, for example, using location-based technologies, whereby audio content can be assigned to the geographical locations. The game system 7 and the virtual persistent world can be constructed such that the at least one user 2 can also play the auditory game outside of their motor vehicle 10. The motor vehicle 10 can also include triggers for the auditory game, for example, by enabling interactions and/or a voice dialogue, e.g., with other users 2 and/or NPCs (non-playable characters), which are not provided outside the motor vehicle 10.

According to the idea, a separate auditory game content 6 can be created for an auditory game of the voice-controlled game system 7.

The gaming system 7 can be implemented as a general mobile application. It is therefore not intended for use solely in a motor vehicle 10.

Overall, the examples show how a speech-based game system 7 with a persistent virtual world and the possibility of creating auditory game content 6 can be provided.

List of reference symbols

2

Users

4

Sensor device

5

Speech recognition system

6

auditory game content

7

Game system

9

real object

10

motor vehicle

11

Voice command

12

predefined building block

13

Game parameters

20

server

30

real environment

QUOTES CONTAINED IN THE DESCRIPTION

This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• DE 10 2019 201 900 A1 [0003]
• US 2017/0349184 A1 [0004]
• WO 2005067574 A2 [0005]

Claims (12)

A method for the adaptive design of an interactive, auditory game in a voice-controlled game system (7), carried out by the voice-controlled game system (7) through the following steps: - Receiving at least one voice command (11) by a speech recognition system (5) of the voice-controlled game system (7) that is connected to a speech model, wherein the speech model is trained to conduct a voice dialogue with the at least one user (2), wherein the voice command (11) describes game parameters (13) to be generated, wherein game parameters (13) define characters, game objectives, game scenarios, and/or game rules of a predefined persistent virtual world, - Retrieving predefined building blocks (12) from a database of the game system (7) that correlate with the game parameters (13), - Linking the predefined building blocks (12) by integrating them into the persistent virtual world of the game system (7) based on the game parameters (13), so that an auditory game content (6) of the auditory game is generated - Conducting a voice dialogue to provide the auditory game to the at least one user (2). Procedure according to Claim 1 , wherein the game parameters (13) refer to information or settings provided by the voice command (11) and which influence the course or conditions of the auditory game in the voice-controlled game system (7). Method according to one of the preceding claims, wherein the auditory game content (6) is stored, wherein the stored auditory game content (6) is provided for shared use with other users (2) on a server (20) of the game system (7). Method according to one of the preceding claims, wherein a topographical condition of the real environment (30) is detected as a function of the location of the game system (7) and integrated into the persistent virtual world, so that a relation of the predefined building blocks (12) to real objects (9) of the environment (30) is provided. Method according to one of the preceding claims, wherein an integration of a prefabricated map into the persistent virtual world takes place and thereby the possibility of arranging the predefined building blocks (12) is determined. Method according to one of the preceding claims, wherein the at least one user (2) is identified by voice recognition, and user-specific game parameters (13) are created with the recognized user identity. Method according to one of the preceding claims, wherein the game system (7) proactively requests the at least one user (2) to issue a voice command (11). Method according to one of the preceding claims, wherein the predefined building blocks (12) comprise a concrete representation of the at least one game parameter (13), in particular characters, environments, tasks and/or events. Method according to one of the preceding claims, wherein a filter system is implemented in the game system (7) to detect and prevent inappropriate or potentially harmful game content that could be created by a voice command (11). A game system (7), wherein the game system (7) comprises a processor device having program instructions which, when executed by the processor device, cause the processor device to carry out a method according to any one of the preceding method claims. Motor vehicle (10), comprising a game system (7) according to Claim 10 . Game content and/or storage medium with the game content, wherein the game content has been generated by a method according to one of the preceding method claims.

Images