Information processing device, program, and information processing method

Abstract

To efficiently generate script data. [Solution] The information processing device 2 includes an acquisition unit 100 that acquires speech data relating to a character's speech, a determination unit 102 that determines target emotion data relating to the emotion corresponding to the speech data based on the speech data, a determination unit 104 that identifies target performance data relating to the character's performance based on the target emotion data, and a generation unit 106 that generates script data associating the target performance data with the speech data.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, a program, and an information processing method.

Background Art

[0002] Conventionally, techniques related to game scripts (hereinafter simply referred to as "scripts") are known. For example, in Patent Document 1, control data included in a pre-created game script is converted into control explanatory text which is natural language data, a processed script sentence including the explanatory text and the control explanatory text corresponding to the explanatory text is created, and a learned model is generated by causing a natural language pre-trained model to learn the processed script sentence.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technique described in Patent Document 1, script data cannot be generated efficiently enough.

[0005] The present disclosure provides an information processing apparatus, a program, and an information processing method for efficiently generating script data.

Means for Solving the Problems

[0006] An information processing device according to one aspect of the present disclosure includes: an acquisition unit that acquires speech data relating to a character's speech; a determination unit that determines target emotion data relating to an emotion corresponding to the speech data based on the speech data; an identification unit that identifies target performance data relating to a character's performance based on the target emotion data; and a generation unit that generates script data associating the target performance data with the speech data.

[0007] A program relating to another aspect of this disclosure causes a computer to function as: an acquisition unit that acquires speech data relating to a character's speech; a determination unit that determines target emotion data relating to an emotion corresponding to the speech data based on the speech data; an identification unit that identifies target performance data relating to a character's performance based on the target emotion data; and a generation unit that generates script data associating the target performance data with the speech data.

[0008] An information processing method relating to another aspect of the present disclosure causes a computer to perform the following actions: acquire speech data relating to a character's speech; determine target emotion data relating to an emotion corresponding to the speech data based on the speech data; identify target performance data relating to a character's performance based on the target emotion data; and generate script data associating the target performance data with the speech data. [Effects of the Invention]

[0009] According to this disclosure, script data can be generated efficiently. [Brief explanation of the drawing]

[0010] [Figure 1] This is a conceptual diagram showing an example of the operation of System 1 in this embodiment. [Figure 2] This is a conceptual diagram showing an example of the operation of System 1 in this embodiment. [Figure 3] This is a diagram illustrating an example of the functional configuration of System 1 in this embodiment. [Figure 4]This is a diagram illustrating an example of the structural data of this embodiment. [Figure 5] This figure illustrates another example of the structural data of this embodiment. [Figure 6] This is a diagram illustrating an example of the operation of the information processing device 2 of this embodiment. [Figure 7] This diagram illustrates an example of the hardware configuration of each device included in System 1 of this embodiment. [Modes for carrying out the invention]

[0011] 1. Overview For example, in adventure games (ADV games), a technique is known in which the game program controls character speech and its accompanying animation by reading pre-created script data. The script data may include, for example, speech data indicating the content of the character's speech, and animation data indicating the character's animation corresponding to that speech. As an example, the speech data for a certain character may include the line, "Princess, it's time to study. Stop being lazy and have more dignity and spirit befitting a princess!" The animation data corresponding to that speech may include identification information for image data corresponding to the character's angry face. The game program reads such script data. This makes it possible to output the line, "Princess, it's time to study. Stop being lazy and have more dignity and spirit befitting a princess!" along with image data of the character's angry face on the game screen.

[0012] Traditionally, game program developers had to create script data for each line of dialogue of each character in the game, associating speech data with visual data such as image data. However, this development method sometimes made efficient development difficult as the number of script data to be created became enormous as the number of lines of dialogue for each character and the number of character types increased.

[0013] According to System 1 of this embodiment (hereinafter simply referred to as "System 1"), the problems related to this example can be solved. The overview of the operation of System 1 will be explained with reference to Figures 1 and 2.

[0014] System 1 first obtains speech data me related to a character's utterance. The speech data me exemplified in Figure 1 is, "Princess, it's time to study. Don't be so lazy, show more princess-like grace and spirit!" Next, based on the speech data me, System 1 determines emotion data em related to the emotion corresponding to the speech data me (S1). In the example in Figure 1, the emotion data em for "anger" is determined. Then, based on the emotion data em, System 1 identifies performance data ex related to the character's performance (S2). In the example in Figure 1, the performance data ex for "angry face" is identified.

[0015] Next, System 1 generates script data sc by associating performance data ex with speech data me (S3). Based on the script data sc, System 1 makes the character's speech and performance available as audio and / or images on the terminal device 3 used by the game player (S4).

[0016] Figure 2 shows an example of the display screen of terminal device 3 based on the script data sc generated by the flow in Figure 1. The example display screen in Figure 2 shows image im1 and dialog di1. Image im1 is displayed based on the performance data ex from the script data sc. Dialog di1 is displayed based on the utterance data me from the script data sc.

[0017] System 1 determines emotion data based on utterance data and specifies production data based on the emotion data. That is, System 1 can also treat the emotion data as intermediate data between the utterance data and the production data. Thereby, System 1 can efficiently specify production data that matches the utterance data. As a result, the man-hours for manually creating script data are reduced.

[0018] Hereinafter, referring to FIG. 2 and subsequent figures, various configurations that System 1 may include will be exemplarily described.

[0019] 2 Functional Configuration Referring to FIG. 3, the functional configuration of System 1 will be described. System 1 includes an information processing device 2, a terminal device 3, a game server device 4, and a communication network 5. The information processing device 2, the terminal device 3, and the game server device 4 are configured to be communicable via the communication network 5.

[0020] 2.1 Information Processing Device 2 The information processing device 2 executes a process for improving the efficiency of script generation. The information processing device 2 may be a cloud server device. The information processing device 2 may be a device including one or more virtual or physical web server devices and one or more virtual or physical database server devices.

[0021] The information processing device 2 includes a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16.

[0022] 2.1.1 Control Unit 10 The control unit 10 can function as an acquisition unit 100, a determination unit 102, a specification unit 104, a generation unit 106, an output control unit 108, a reception unit 110, and an update unit 112 by executing various programs stored in the storage unit 12 described later. Various configurations that can be realized based on these functions will be described later.

[0023] 2.1.2 Storage section 12 The storage unit 12 stores various information necessary for the operation of the information processing device 2. In one embodiment, the storage unit 12 stores the program to be executed by the control unit 10.

[0024] 2.1.3 Network Interface Unit 14 The network interface unit 14 enables communication with other devices via the communication network 5.

[0025] 2.2 Terminal device 3 Terminal device 3 is a communication device used by the game player. Terminal device 3 may be a device designed and manufactured exclusively for the player to play games, or it may be a general-purpose device that can also play games. Examples of terminal device 3 include smartphones, personal computers, tablet devices, and wearable devices.

[0026] Terminal device 3 includes an input interface, an output interface, and a communication interface. The input interface is an interface for terminal device 3 to receive input from the user. The input interface may be a touch panel, microphone, camera, keyboard, mouse, etc. The output interface is an interface for transmitting information to the user via images, sound, etc. The output interface may be a display (which may also function as a touch panel) and speaker, etc. The communication interface is an interface for enabling communication with other devices via the communication network 5. The communication interface may be a wireless communication interface or a wired communication interface. Terminal device 3 may access services provided by the information processing device 2, for example, via a web browser, or it may access such services by installing dedicated software.

[0027] 2.3 Game Server Device 4 The game server device 4 is a device that enables a game program to be executed on the terminal device 3. The game server device 4 can distribute the game program to the terminal device 3. Note that the game related to the distributed game program may be an online game or an offline game. Also, the game related to the distributed game program may be a single-player game or a multiplayer game. The genre of the game related to the distributed game program may be any game that involves character dialogue, for example, an adventure game, a role-playing game, a simulation game, a breeding game, a quiz game, etc.

[0028] The game server device 4 is configured to be able to access the script data generated by the information processing device 2. The game server device 4 can distribute a game program based on the script data to the terminal device 3. In one example, the game server device 4 can build a game program related to an offline game using the script data generated by the information processing device 2 and distribute the game program to the terminal device 3. In another example, while distributing a game program that is an online game to the terminal device 3, the game server device 4 can appropriately access the script data stored in a database (in one example, the storage unit 12) or generated as needed in response to a request from the terminal device 3, and control to output an image / audio based on the script data on the terminal device 3.

[0029] 2.4 Communication Network 5 The communication network 5 realizes communication between each device included in the system 1. The communication network 5 realizes communication between each device based on, for example, the TCP / IP protocol.

[0030] 3 Configuration Examples that the Control Unit 10 Can Realize Hereinafter, each configuration that can be realized by the control unit 10 functioning as the acquisition unit 100, the determination unit 102, the specification unit 104, the generation unit 106, the output control unit 108, the reception unit 110, and the update unit 112 will be exemplarily described.

[0031] In one embodiment, the acquisition unit 100 acquires speech data relating to a character's speech. The determination unit 102 determines target emotion data relating to the emotion corresponding to the acquired speech data based on the speech data. The identification unit 104 identifies target performance data relating to the character's performance based on the determined target emotion data. The generation unit 106 generates script data that associates the identified target performance data with the speech data. With this configuration, it is possible to generate script data for performing character actions that are in line with the content of the speech by determining emotion data from a character's speech data and associating performance data based on that emotion data.

[0032] A character can be a virtual being represented within a game. A character can interact with the player and other characters in the game through speech, emotional expression, actions, and other means. A character may be a non-player character or a player character.

[0033] Speech data can be data that expresses the intentions, emotions, and information that a character expresses. Speech data may be text data, or it may be audio data, i.e., waveform data. Speech data may be pre-set by, for example, the game program developer, or it may be input by the game player. Speech data may also include identification data of the character that makes the speech related to the speech data (for example, character name and character ID).

[0034] Emotional data can be data that virtually represents a character's psychological state. For example, emotional data may include classification data relating to the character's emotions, such as joy, anger, sadness, surprise, calmness, and excitement. In another example, emotional data may include intensity data relating to the strength of the character's emotions.

[0035] The performance data may be data for controlling the output of images and / or sounds accompanying a character's speech. In one embodiment, the performance data may be data relating to expressive elements that allow the player to perceive the character's intentions and emotions, etc. The performance data may include, for example, character appearance data, character movement data, character voice data, visual effect data, and auditory effect data.

[0036] Character appearance data may include facial expression data showing the character's facial expressions, or overall appearance data showing the character's overall posture, etc. Character motion data may include, for example, data showing the character's walking, running, jumping, gestures and movements according to emotions, and changes in body posture. Character voice data may include, for example, data showing changes in voice tone, pitch, volume, and voice quality.

[0037] In one example, visual effects data may include camera work data relating to the position of the camera that displays the character in the game space. In another example, visual effects data may include font size data relating to the size of the characters displayed in dialogue, which is a display element used to express the content of a character's speech. In yet another example, visual effects data may include font position data relating to the position of the characters displayed in dialogue. In yet another example, visual effects data may include effect data relating to effects such as auras, flashes, smoke, and flames that appear around a character. In yet another example, visual effects data may include background effect data relating to background effects such as changes in brightness, color tones, and blurring. Auditory effects data may include, for example, data relating to changes in background music, ambient sounds, and special sound effects that emphasize a character's emotions and intentions.

[0038] Furthermore, the speech data and performance data may both be tangible data for outputting images and / or sounds in the game (for example, the text data itself, the image data itself, and the sound data itself), and may be identification data for identifying such tangible data (for example, the ID of the text data, the file name of the image data, and the file path of the sound data).

[0039] Script data may be data that associates at least speech data and performance data. According to such script data, dialogue based on speech data and images and / or sounds based on performance data may be output in the game. Script data may further include character identification data, etc. In script data, multiple performance data may be associated with a single speech data.

[0040] Target emotion data may be emotion data determined based on a certain utterance data of a character. Target performance data may be performance data identified based on certain emotion data. A person skilled in the art can understand that one utterance data arbitrarily selected from a plurality of utterance data is "utterance data" acquired by the acquisition unit 100, the emotion data determined based on that utterance data is "target emotion data", and the performance data identified based on that target emotion data is "target performance data".

[0041] In one embodiment, the output control unit 108 enables the output of character speech and performance as audio and / or images on the terminal device 3 based on script data. With this configuration, the player can be provided with character speech and performance based on the generated script data.

[0042] Making character speech and performances output as audio and / or images on terminal device 3 based on script data (hereinafter referred to as "script output processing") may include making the game server device 4 able to distribute the game using said script data. In one example, script output processing may be processing that makes script data accessible when game server device 4 builds a game program. In another example, script output processing may include recording script data in a database accessible to game server device 4. In yet another example, script output processing may include writing a file containing script data in a manner that can be read by adventure game development software.

[0043] In one embodiment, the identification unit 104 further identifies target performance data based on structural data in which performance data is associated with each of a plurality of emotion data. With this configuration, since target performance data can be identified based on structural data in which emotion data and performance data are associated, it becomes possible to identify more appropriate and accurate performances that can respond to the diversity and complexity of emotions.

[0044] Structural data can be data that expresses the relationships between multiple data through a structure. Structural data can be, for example, tree-structured data, table-structured data, graph-structured data, and list-structured data. Structural data in which performance data is associated with each of multiple emotion data can be data that is configured in such a way that the performance data uniquely corresponding to each of those emotion data can be identified.

[0045] Table st1 in Figure 4 is an example of structured data. Table st1 includes columns for character name, emotion data, and performance data. In Table st1, "Character c1" is associated with the emotion data "laughing" as the performance data "Character c1's laughing face", with the emotion data "anger" as the performance data "Character c1's angry face", and with the emotion data "sadness" as the performance data "Character c1's crying face". Similarly, "Character c2" is associated with the emotion data "laughing" as the performance data "Character c2's laughing face", with the emotion data "anger" as the performance data "Character c2's angry face", and with the emotion data "sadness" as the performance data "Character c2's crying face".

[0046] According to table st1, if character c1's emotion is determined to be "laughing" based on character c1's speech data, then the performance data "character c1's laughing face" can be identified. Similarly, if character c2's emotion is determined to be "anger" based on character c2's speech data, then the performance data "character c2's angry face" can be identified.

[0047] Table st2 in Figure 5 is another example of structured data. Table st2 includes columns for character name, emotion data, facial expression data, camera work data, font size data, and font position data. As mentioned above, camera work data, font size data, and font position data are all examples of performance data. In Table st2, "Character c1" is associated with the emotion data "Anger [Small]" with facial expression data "Character c1's angry face", camera work data "Medium", font size data "12pt", and font position data "Left-aligned". Similarly, the emotion data "Anger [Large]" is associated with facial expression data "Character c1's angry face", camera work data "Close-up", font size data "20pt", and font position data "Center-aligned".

[0048] In one embodiment, structural data is generated based on an AI model configured and / or instructed to associate emotion data with performance data. This configuration allows for the efficient generation of structural data for generating effective performances that are in line with emotions.

[0049] The associations made by AI models can be considered a concept that establishes specific semantic correspondences between multiple data elements. Specifically, when an AI model associates emotion data with performance data, it may include the function of the AI ​​model learning the rules governing how a given emotion can be effectively expressed or evoked by certain performances, and internally associating them between the emotion data and the performance data.

[0050] In one embodiment, the AI ​​model may include a Large Language Model (LLM). In this case, the instructions, or prompts, given to the AI ​​model may be, for example, as follows: "Please select the performance data that corresponds to the following emotion data from the performance data list." Emotional data: anger List of animation data: (1) Angry face.gif (2) Smiling face.gif (3) Crying face.gif The information processing device 2 can input such prompts to the AI ​​model for each emotion data, thereby identifying the performance data that should be associated with each emotion data, and generating structured data.

[0051] In another embodiment, the AI ​​model may be a model capable of performing natural language processing, not limited to LLM. In this case, the AI ​​model may identify the performance data to be associated with the emotion data based on, for example, the relationship between the text corresponding to the emotion data and the text corresponding to each of the performance data, thereby generating structured data. For example, if the text corresponding to the emotion data is "anger," and the filenames of the performance data (an example of the text corresponding to the performance data) are "angry face.gif," "laughing face.gif," and "crying face.gif," the AI ​​model may determine that the performance data to be associated with the emotion data is "angry face.gif" because the string "anger" is contained in "angry face.gif." Alternatively, the AI ​​model may identify the performance data to be associated with the emotion data based on the cosine similarity between the text corresponding to the emotion data and the text corresponding to each of the performance data, etc.

[0052] In another embodiment, the AI ​​model may be a machine learning model, not limited to LLM, configured to take emotion data and a plurality of performance data as inputs and output performance data from among the plurality of performance data that should be associated with the emotion data. Such a machine learning model may include, for example, a neural network and may be composed of other machine learning algorithms.

[0053] In another embodiment, the AI ​​model may be a rule-based model configured to reference rule data concerning rules for identifying performance data that should be associated with a particular emotional data from among multiple performance data. Such rule data may be set, for example, by the developer of a game program.

[0054] In this embodiment, the “model” includes a program that outputs output data that at least partially reflects the characteristics of the model in response to input data, and its complexity is not particularly limited.

[0055] In one embodiment, the determination unit 102 generates speech data and instruction data relating to determining target emotion data based on the speech data, and determines the target emotion data by inputting the instruction data into the AI ​​model. The AI ​​model may be an LLM, or not limited to an LLM, may be a model capable of performing natural language processing, may be a machine learning model not limited to an LLM, or may be a rule-based model. The "instruction data" may be input data to the AI ​​model. When the AI ​​model is an LLM, it may be possible to determine the target emotion data from the speech data in a particularly flexible and convenient manner.

[0056] In one embodiment, the determination unit 102 determines the target emotion data based on the character's attributes. Depending on the character's attributes, different emotions may be expressed even if the content of the utterance is the same. For example, a sarcastic character or a shy character may have a difference between what they say and what they truly feel. This configuration makes it possible to determine emotion data that matches the character's personality and setting.

[0057] Character attributes can be data that defines a character's personality, nature, and state. Examples of character attributes include personality, preferences, dislikes, hobbies / thoughts, abilities, and physical / mental state. Character attributes are not limited to being constant throughout the game; for example, they may change as the game progresses. Furthermore, character attributes may be predetermined by the game program developer or determined by the game program itself.

[0058] In one embodiment, the target performance data includes appearance data relating to the character's appearance and additional performance data relating to dialogue and / or camera work when the character speaks, the target emotion data includes classification data relating to the classification of emotions corresponding to the speech data and intensity data relating to the strength of emotions corresponding to the speech data, and the identification unit 104 identifies the appearance data based on the classification data and includes additional performance data based on the intensity data. With this configuration, by identifying the appearance performance of the character based on the classification of emotions corresponding to the speech data and identifying additional performances relating to dialogue and camera work based on the strength of emotions, it becomes possible to perform expressive performances that correspond to the nuances of emotions.

[0059] Camera work data can be data that controls the camera's viewpoint and composition within the game space. Camera work data may include data that controls the camera's position, orientation, field of view, and focal length. For example, camera work data may include data that zooms in on a character's face when they speak, or shakes the camera according to the intensity of their emotions.

[0060] In one embodiment, the reception unit 110 receives changes to performance data associated with at least one of a plurality of emotion data in the structural data, and the update unit 112 updates the script data in accordance with the changes received by the reception unit 110. With this configuration, changes to the structural data can be quickly reflected in the script data.

[0061] Refer to Figure 6 to explain an example of operation with this configuration. In Figure 6, table st3, which is an example of structural data, includes columns for rule number, character name, emotion data, and performance data. In the row for rule number ru1 in table st3, the emotion data "laugh" for "character c1" is associated with the performance data "character c1's laughing face ver.1". Similarly, in the row for rule number ru2, the emotion data "anger" for "character c1" is associated with the performance data "character c1's angry face ver.1".

[0062] The information processing device 2 generates the script data table sc2 based on the table st3 (S10). The script data table sc2 includes columns for script number, character name, utterance data, performance data, and reference rule number. The reference rule number indicates which row of table st3 was referenced when generating the script data for that row.

[0063] Script data table sc2 indicates that in the script data for script number scr1, a certain utterance data of "character c1" is associated with the performance data "character c1's smiling face ver.1". Furthermore, script data table sc2 indicates that the script data in question was generated based on the row with rule number ru1 in table st3.

[0064] Similarly, script data table sc2 indicates that in the script data for script number scr2, a certain utterance data of "character c1" is associated with the performance data "character c1's angry face ver.1". Furthermore, script data table sc2 indicates that the script data in question was generated based on the row with rule number ru2 in table st3.

[0065] Here, the reception unit 110 accepts an operation to change the performance data associated with the emotion data of "laughter" in table st3 from "character c1's smiling face ver.1" to "character c1's smiling face ver.2" (S12). In response, the update unit 112 identifies the rule number of the changed rule in table st3 (rule number ru1 in this example) and identifies the script data generated based on that rule number from the script data in script data table sc2 (script data with script number scr1 in this example). Subsequently, the update unit 112 changes the performance data of the script data with script number scr1 from "character c1's smiling face ver.1" to "character c1's smiling face ver.2".

[0066] 5 Hardware Configuration Referring to Figure 7, an example of a hardware configuration when the devices included in System 1 described above are implemented by computer 70 will be explained. Note that the functions of each device can also be implemented by dividing them among multiple devices.

[0067] As shown in Figure 7, the computer 70 includes a processor 700, a storage device 702, an input interface 704, a data interface 706, a communication interface 708, and a display device 710.

[0068] The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit of the control unit 10 of the information processing device 2 can be realized by the processor 700 executing programs stored in the storage device 702.

[0069] The storage device 702 is a storage medium such as RAM (Random Access Memory). RAM temporarily stores the program code of the program executed by the processor 700, as well as data required during program execution.

[0070] The storage device 702 can also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores the operating system and various programs for realizing the above configurations. The storage medium storing these various programs may be a non-transitory computer-readable medium. In addition, the storage device 702 can also store tables for registering various information and a database for managing those tables. Such programs and data are loaded into the storage device 702 as needed and accessed by the processor 700.

[0071] The input interface 704 is a device for receiving input from the user. Specific examples of the input interface 704 include cameras, buttons, microphones, keyboards, mice, touch panels, various sensors, and wearable devices. The input interface 704 may be connected to the computer 70 via an interface such as USB (Universal Serial Bus).

[0072] The data interface 706 is a device for inputting data from outside the computer 70. Specific examples of the data interface 706 include drive devices for reading data stored on various storage media. The data interface 706 may also be located outside the computer 70. In that case, the data interface 706 would be connected to the computer 70 via an interface such as USB.

[0073] The communication interface 708 is a device for performing data communication with external devices of the computer 70 via a communication network 5, either wired or wirelessly. The communication interface 708 may also be located outside the computer 70. In that case, the communication interface 708 would be connected to the computer 70 via an interface such as USB.

[0074] The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include liquid crystal displays, organic EL (Electro-Luminescence) displays, and displays for wearable devices. The display device 710 may be located outside the computer 70. In that case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, if a touch panel is used as the input I / F 704, the display device 710 can be configured as an integrated unit with the input I / F 704.

[0075] Furthermore, the components of the device included in the System 1 described above are such that a program stored in the storage device 702 is executed by the processor 700, thereby realizing a defined process in cooperation with other hardware. In other words, these components are conceived as both software or firmware, and as corresponding hardware, and in both concepts, they are also described and interpreted as "function," "means," "part," "processing circuit," "unit," or "module," etc.

[0076] 6. Variations The embodiments described above are provided to facilitate understanding of this disclosure and are not intended to limit it. The configurations that the embodiments may have are not limited to those exemplified and can be modified as appropriate. Furthermore, configurations shown in different embodiments can be partially substituted or combined.

[0077] In the above embodiment, the information processing device 2 was described as a separate device from the game server device 4, but this is not limited to that. The information processing device 2 may be a device that is integrated with the game server device 4.

[0078] In the above embodiment, the information processing device 2 may use an AI model it hosts, or it may use an AI model hosted by an AI model server device (not shown in Figure 2), for example, via an API.

[0079] In the above embodiment, the information processing device 2 can accept a setting for the format of the script data and generate script data based on that setting. For example, the information processing device 2 can generate script data in a format that can be accepted by a first script engine and script data in a format that can be accepted by a second script engine. The script engines are, for example, KiriKiri and TyranoScript.

[0080] 7. Supplementary Information The wording in this embodiment may be understood as follows, to the extent that it does not cause any contradiction.

[0081] In this embodiment, "performing a predetermined process based on predetermined information" may mean performing the predetermined process based on at least a portion of the predetermined information, performing the predetermined process based on at least the predetermined information, or performing the predetermined process probabilistically based on the predetermined information. In other words, "performing a predetermined process based on predetermined information" is not limited to performing the predetermined process based solely on the predetermined information.

[0082] In this embodiment, "executing another process based on a predetermined process" may mean any of the following: executing the other process after the predetermined process has been executed; executing the predetermined process and the other process consecutively; executing the other process based on information determined by the predetermined process; executing the other process on the condition that the predetermined process has been executed; or executing the other process by means of the predetermined process. Furthermore, "executing another process by a predetermined process" may be understood in the same way as "executing another process based on a predetermined process."

[0083] In this embodiment, "the predetermined information includes other information" may mean either that at least a portion of the predetermined information is the other information, or that the other information can be obtained based on the predetermined information.

[0084] In this embodiment, "a predetermined process includes other processes" may mean either that at least a part of the predetermined process is the other process (i.e., the other process is performed in the process of obtaining the result of the predetermined process), or that one aspect of the predetermined process is the other process.

[0085] In this embodiment, "a predetermined object and another object correspond" may mean that there is a one-to-one relationship between the predetermined object and the other object, that the other object is included in a predetermined set identified based on the predetermined object, or that the other object can be identified based on the predetermined object. Furthermore, "a predetermined object and another object corresponding" is not limited to being managed, for example, in a database. Also, "a predetermined object and another object being associated" may be understood in the same way as "a predetermined object and another object corresponding."

[0086] In this embodiment, "acquiring information" includes making the information processable by the control unit 10. "Acquiring information" may include, for example, receiving the information from another device, obtaining the information through predetermined processing, and reading the information from the storage unit 12.

[0087] In this embodiment, "generating information" may mean either making the information obtained by a predetermined process processable in the control unit 10, or storing the information obtained by the predetermined process in the storage unit 12.

[0088] In this embodiment, "determining information" may mean either selecting at least one piece of information from one or more pieces of information, or generating new information.

[0089] In this embodiment, "outputting information" may mean either transmitting the information to another device or outputting the information as audio or video.

[0090] 8. Configuration Examples This disclosure includes the following technologies:

[0091] [Note 1] Information processing device 2 comprises: an acquisition unit 100 that acquires speech data relating to a character's speech; a determination unit 102 that determines target emotion data relating to the emotion corresponding to the speech data based on the speech data; an identification unit 104 that identifies target performance data relating to the character's performance based on the target emotion data; and a generation unit 106 that generates script data associating the target performance data with the speech data.

[0092] [Note 2] The identification unit 104 further identifies target performance data based on structural data in which performance data is associated with each of a plurality of emotion data, as described in Appendix 1, for the information processing device 2.

[0093] [Note 3] The information processing device 2 as described in Appendix 2 further comprises a receiving unit 110 that receives changes to performance data associated with at least one of a plurality of emotion data in structural data, and an updating unit 112 that updates script data in accordance with the changes received by the receiving unit 110.

[0094] [Note 4] The information processing device 2 according to Appendix 2 or 3 generates structural data based on an AI model configured and / or instructed to associate emotional data with performance data.

[0095] [Note 5] The information processing device 2 according to any one of the appendices 1 to 4 further comprises an output control unit 108 that enables the output of character speech and performance in the terminal device 3 as sound and / or images based on script data.

[0096] [Note 6] The information processing device 2 according to any one of the appendices 1 to 5, wherein the determination unit 102 generates speech data and instruction data relating to determining target emotion data based on the speech data, and determines the target emotion data by inputting the instruction data into the AI ​​model.

[0097] [Note 7] The AI ​​model is the information processing device 2 described in Appendix 6, which includes a large-scale language model.

[0098] [Note 8] The determination unit 102 determines target emotion data based on the character's attributes, as described in any one of the appendices 1 to 7.

[0099] [Note 9] The target performance data includes appearance data relating to the character's appearance and additional performance data relating to the dialogue and / or camera work when the character speaks; the target emotion data includes classification data relating to the classification of emotions corresponding to the speech data and intensity data relating to the strength of emotions corresponding to the speech data; and the identification unit 104 identifies the appearance data based on the classification data and includes the additional performance data based on the intensity data, as described in any one of the appendices 1 to 8.

[0100] [Note 10] Computer 70, A program that functions as: an acquisition unit 100 that acquires speech data related to a character's speech; a determination unit 102 that determines target emotion data related to the emotion corresponding to the speech data based on the speech data; an identification unit 104 that identifies target performance data related to the character's performance based on the target emotion data; and a generation unit 106 that generates script data that associates the target performance data with the speech data.

[0101] [Note 11] An information processing method that causes a computer 70 to perform the following actions: acquire speech data relating to a character's speech; determine target emotion data relating to the emotion corresponding to the speech data based on the speech data; identify target performance data relating to the character's performance based on the target emotion data; and generate script data associating the target performance data with the speech data. [Explanation of symbols]

[0102] 1...System, 2...Information Processing Device, 3...Terminal Device, 4...Game Server Device, 10...Control Unit, 12...Storage Unit, 70...Computer, 100...Acquisition Unit, 102...Decision Unit, 104...Specification Unit, 106...Generation Unit, 108...Output Control Unit, 110...Reception Unit, 112...Update Unit

Claims

1. An acquisition unit that acquires speech data related to the character's speech, A determination unit that determines target emotion data related to the emotion corresponding to the utterance data based on the utterance data, A structural data in which performance data is associated with each of multiple emotion data, and an identification unit that identifies target performance data related to the performance of the character based on the target emotion data, A generation unit that generates script data by associating the target performance data with the aforementioned speech data, After the generation unit generates the script data, the receiving unit accepts changes to the performance data in the structural data, If the change received by the reception unit is a change relating to the target performance data, the update unit reflects the change in the script data already generated by the generation unit. An information processing device equipped with the following features.

2. The information processing apparatus according to claim 1, wherein at least a portion of the structural data is generated based on an AI model configured and / or instructed to associate emotional data with performance data.

3. The information processing apparatus according to claim 1, further comprising an output control unit that enables the output of the character's speech and performance as sound and / or images on a terminal device based on the script data.

4. The information processing apparatus according to claim 1, wherein the determination unit generates the speech data and instruction data relating to determining the target emotion data based on the speech data, and determines the target emotion data by inputting the instruction data into an AI model.

5. The information processing apparatus according to claim 4, wherein the AI ​​model includes a large-scale language model.

6. The information processing apparatus according to claim 1, wherein the determination unit determines the target emotion data based on the attributes of the character.

7. The aforementioned target performance data includes appearance data relating to the appearance of the character and additional performance data relating to the dialogue and / or camera work when the character speaks. The aforementioned target emotion data includes classification data relating to the classification of emotions corresponding to the speech data, and intensity data relating to the strength of emotions corresponding to the speech data. The specified unit identifies the appearance data based on the classification data and identifies the additional effect data based on the intensity data. The information processing apparatus according to claim 1.

8. Computers, An acquisition unit that acquires speech data related to the character's speech, A determination unit that determines target emotion data related to the emotion corresponding to the utterance data based on the utterance data, A structural data in which performance data is associated with each of multiple emotion data, and an identification unit that identifies target performance data related to the performance of the character based on the target emotion data, A generation unit that generates script data by associating the target performance data with the aforementioned speech data, After the generation unit generates the script data, the receiving unit accepts changes to the performance data in the structural data, If the change received by the reception unit is a change relating to the target performance data, the update unit reflects the change in the script data already generated by the generation unit. A program that makes something function as such.

9. Computers To obtain speech data related to character speech, Based on the aforementioned speech data, the target emotion data relating to the emotion corresponding to the speech data is determined. Based on structural data in which performance data is associated with each of multiple emotion data, and the target emotion data, the target performance data relating to the performance of the character is identified. To generate script data that associates the target performance data with the aforementioned speech data, After generating the script data, the system accepts changes to the performance data in the structural data. If the accepted change concerns the aforementioned performance data, the change will be reflected in the script data that has already been generated. An information processing method that performs [this action].

Images