Information processing system, information processing method, and program

Abstract

To enable a user to utter conversation contents that interest him / her. [Solution] A response data generation unit generates response data to which a character responds in response to conversation data from a user to a character, and is characterized by comprising: a generation unit that generates the response data by quoting lines contained in a work in which the character appears; and an output unit that outputs the response data to the user.

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] A dialogue is taking place between a user and a computer (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6719747 Summary of the Invention [Problem to be solved by the invention]

[0004] Scenario-based interactions may not keep users engaged.

[0005] The present invention has been made in view of the above background, and has an object to provide a technique that enables a user to utter a conversation content that interests the user. [Means for solving the problem]

[0006] The main invention of the present invention for solving the above problem is a response data generation unit that generates response data to which a character responds in response to conversation data from a user to a character, the response data being generated by quoting lines contained in a work in which the character appears, and an output unit that outputs the response data to the user.

[0007] Other problems and solutions disclosed in this application will be made clear in the description of the preferred embodiments of the invention and the drawings. Effect of the Invention

[0008] According to the present invention, it is possible to generate conversation content that interests the user. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of an overall configuration of an information processing system. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of a management server 2. FIG. [Diagram 3] 2 illustrates an example of the software configuration of a management server 2. FIG. [Figure 4] FIG. 13 is a diagram illustrating the operation of the management server 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] <System Overview> An information processing system according to one embodiment of the present invention will be described below. The information processing system of this embodiment is intended to have a conversation between a user and the system, in which characters appearing in a particular work (e.g., manga, anime, movies, novels, games, etc.) have a conversation and quote lines from the work (which may be the lines of the character in question or lines of other characters) during the conversation.

[0011] In this embodiment, a conversation using a text is mainly described as an example, but the present invention is not limited to this. For example, conversations in various formats such as those below are also included in the scope of the present invention. (1) Voice conversation: Accepts the user's voice input and uses voice synthesis technology to output a response in the character's voice. (2) Conversations including images: Analyzes images and emojis sent by users and generates responses accordingly. Responses can also include images showing the character's facial expressions and postures. (3) Conversation using video: By combining character animation and live-action footage, conversations can be made more realistic. (4) Conversation using AR (Augmented Reality) or VR (Virtual Reality): Characters are projected into real or virtual spaces to provide a more immersive conversation environment. (5) Multimodal conversation: Combining multiple formats such as text, audio, images, and video to enable richer expression.

[0012] These various formats can be used alone or in combination, and while the following description focuses primarily on text-based conversations, it goes without saying that the techniques of the present invention can also be applied to the other formats mentioned above.

[0013] 1 is a diagram showing an example of the overall configuration of an information processing system. The information processing system of this embodiment is configured to include a management server 2. The management server 2 is communicably connected to a user terminal 1 via a communication network. The communication network is, for example, the Internet, and is constructed by a public telephone line network, a mobile phone line network, a wireless communication path, Ethernet (registered trademark), etc.

[0014] The user terminal 1 is a computer operated by a user. The user terminal 1 may be, for example, a smartphone, a tablet computer, or a personal computer.

[0015] The management server 2 may be a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing.

[0016] <Administration Server> FIG. 2 is a diagram showing an example of the hardware configuration of the management server 2. Note that the illustrated configuration is an example, and other configurations may be used. The management server 2 includes a CPU 201, a memory 202, a storage device 203, a communication interface 204, an input device 205, and an output device 206. The storage device 203 is, for example, a hard disk drive, a solid state drive, or a flash memory that stores various data and programs. The communication interface 204 is an interface for connecting to a communication network, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 205 is, for example, a keyboard, a mouse, a touch panel, a button, a microphone, etc. that input data. The output device 206 is, for example, a display, a printer, a speaker, etc. that output data. Each functional unit of the management server 2 described below is realized by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it, and each storage unit of the management server 2 is realized as part of the storage area provided by the memory 202 and the storage device 203.

[0017] 3 is a diagram showing an example of the software configuration of the management server 2. The management server 2 includes a work storage unit 231, an acquisition unit 211, a search unit 212, a generation unit 213, and an output unit 214.

[0018] The work storage unit 231 stores lines included in works of various formats. The works referred to here are not limited to manga, but include any creative work in which characters appear and lines or dialogue are included, such as novels, anime, movies, television dramas, plays, games, poems, and lyrics. The work storage unit 231 can store scenes of a work and lines included in the scenes. In this embodiment, it is assumed that a scene of a work is image data for displaying a page of a manga, and lines are text data. A scene may be image data for displaying a frame of a manga.

[0019] The information stored in the work storage unit 231 can be structured according to the type of work as follows:

[0020] (1) In the case of manga Dialogue: Text data Scene: Image data for displaying a page or frame Context information: information about the chapter or volume in which the line appears (2) In the case of novels Dialogue: Text data Context: The text before and after the dialogue Scene: A block of text that includes dialogue and narrative text. Metadata: chapters, page numbers, etc. (3) In the case of anime and movies Dialogue: Text data (subtitles and scripts) Audio data: Dialogue audio files Scene: A still image or a short video clip of the scene Timestamp: The time the line appears in the work (4) In the case of games Dialogue: Text data Scene: Description of the in-game situation or event in which the dialogue appears, or a captured video Character Status: The character's status when the line is spoken (e.g. stamina, emotions, etc.) (5) In the case of stage plays or dramas: Dialogue: Text data Scene: Description of the scene in which the dialogue appears, capture video Stage directions: acting instructions that accompany lines Act information: information about the act or scene in which the line appears

[0021] The work storage unit 231 can store the vector data in which the dialogue has been embedded in association with the dialogue. This embedding process can be applied regardless of the form of the work, and enables efficient dialogue search and similarity calculation.

[0022] The work storage unit 231 can also store additional information related to the work and characters. For example, the work storage unit 231 can store information related to the genre of the work, the year of production, author information, the characteristics, personality, background setting, important events and turning points in the work, information related to the world view and setting of the work, etc. This additional information can be used to select appropriate lines that are more in line with the context and to generate responses that reflect the characteristics of the characters.

[0023] The acquisition unit 211 acquires conversation data for a character from a user. In this embodiment, the conversation data is text data input by the user to the user terminal 1. The acquisition unit 211 can receive the conversation data from the user terminal 1.

[0024] The search unit 212 searches for lines related to the acquired conversation data. The search unit 212 can search for lines related to the conversation data from the work storage unit 231. As a method of searching for lines, the following multiple methods can be adopted.

[0025] (1) Cosine similarity: The cosine distance between the vector data in which the conversation data has been embedded and the vector data stored in the work storage unit 231 is calculated, and lines that are close in distance are determined to be highly related.

[0026] (2) Euclidean distance: Calculate the straight-line distance in vector space and select the lines that are close.

[0027] (3) Manhattan distance: Calculate the sum of the absolute values ​​of the differences in each dimension of the vector and select the lines that are close in distance.

[0028] (4) Jaccard Similarity: Treats the conversation data and lines as a set of words, and determines the similarity by calculating the percentage of common words.

[0029] (5) Edit distance (Levenshtein distance): Calculate the minimum number of string edit operations between the conversation data and the lines, and select the lines with the closest distance.

[0030] (6) Latent Semantic Analysis (LSA): Calculates the similarity between the conversation data and the lines by taking into account the latent semantic relationships between the lines.

[0031] (7) BM25 Algorithm: This applies a ranking algorithm widely used in information retrieval to select highly relevant lines.

[0032] The search unit 212 can use these methods alone or in combination with a plurality of methods, and can dynamically select an appropriate method depending on the conversation context and the required accuracy.

[0033] The generation unit 213 generates text (hereinafter, response data) that responds to the conversation data. The generation unit 213 can generate the response data so as to quote lines included in a work in which the character appears. Note that the generation unit 213 does not use the lines themselves as response data, but generates response data so that the lines are included as quotes along with the main text. As a method of generating response data, the following multiple methods can be adopted.

[0034] (1) Large-scale language models (LLMs): LLMs such as GPT-3, GPT-4, PaLM, and LLaMA are used to generate responses using conversational data and prompts containing dialogue.

[0035] (2) Rule-based system: Generates responses by combining conversation data and lines based on predefined response patterns and rules.

[0036] (3) Retrieval-based systems: Search for examples of dialogue similar to the conversation data from a large dialogue corpus, and generate new responses based on those responses.

[0037] (4) Template-based generation: Responses are generated by embedding conversation data and dialogue information into pre-prepared templates.

[0038] (5) Machine translation approach: Responses are generated by converting conversation data into an intermediate representation and then “translating” it to match the character’s tone and setting.

[0039] (6) Reinforcement learning model: A reward function is defined and responses are generated using a reinforcement learning model trained to maximize character-likeness and naturalness of the conversation.

[0040] (7) Neural dialogue model: Responses are generated using a neural network model specialized for dialogue, such as a sequence-to-sequence model or a model with an attention mechanism.

[0041] The generator 213 can use these techniques alone or in combination. For example, a rule-based system can be used to generate basic response structures, and then the LLM can be used to refine the responses. It is also possible to dynamically select an appropriate technique depending on the characteristics of the character and the complexity of the conversation.

[0042] When the search unit 212 searches for lines related to the conversation data, the generation unit 213 generates response data to quote the lines, and when the lines are not searched for, the generation unit 213 can generate response data as a response to the conversation data without quoting the lines. When quoting lines, the generation unit 213 appropriately selects a quoting method and incorporates the lines into the response data in a natural way. Even when not quoting lines, an appropriate response is generated taking into account the characteristics of the character and the context of the conversation.

[0043] In this embodiment, the generation unit 213 can provide a prompt including conversation data and an instruction to create a response to the conversation data to the large-scale language model to generate response data that does not quote a line. Also, the generation unit 213 can provide a prompt including, for example, conversation data, a searched line, and an instruction to create a response to the conversation data so as to quote the line to the large-scale language model to generate response data that quotes the line.

[0044] The generation unit 213 can employ the following methods for quoting lines: (1) Direct quotation: The retrieved lines are inserted as is into the response data. (2) Partial quotation: A part of the retrieved lines is extracted and inserted into the response data. (3) Paraphrase: The meaning of the retrieved lines is preserved while incorporating them into the response data in a different expression. (4) Free translation: The essential meaning and emotion of the retrieved lines are captured, and the expression is changed to match the current conversation context before being incorporated into the response data. The generation unit 213 can appropriately select these quotation methods based on the flow of the conversation, the length of the retrieved lines, the user's preferences, and the like. In this embodiment, direct quotation is assumed as the method for quoting lines.

[0045] Furthermore, the generation unit 213 can use the following criteria as selection criteria for lines to be quoted: (1) Relevance: Lines whose semantic similarity exceeds a predetermined threshold are selected. (2) Emotion matching: Lines whose emotional expression matches the emotional state of the user estimated from the conversation data are preferentially selected. (3) Character matching: Lines uttered by characters in conversation are preferentially selected. (4) Importance: Lines whose importance or impression in the work is high are preferentially selected. (5) Diversity: Lines that have not been used in past conversations are preferentially selected to avoid excessive repetition of the same lines. The generation unit 213 can select more appropriate lines by using a combination of these criteria.

[0046] The generation unit 213 can perform the following processes to naturally incorporate the selected lines into the response data. (1) Preface generation: Generates an appropriate preface before quoting the lines (e.g., "Now that I think of it, there was a line like this"). (2) Post-explanation: After quoting the lines, generates a sentence that explains the intention and relevance of the quote. (3) Context adjustment: Generates sentences that match the flow of the conversation before and after the selected lines, incorporating the lines naturally. (4) Maintaining character: Generates sentences that reflect the character's tone and personality even in response data other than the quoted parts. Through these processes, the generation unit 213 can generate response data that is more natural and does not sound awkward.

[0047] The large-scale language model (LLM) used by the generation unit 213 can be, for example, GPT-3, GPT-4, PaLM, LLaMA, or a model with equivalent performance. The following procedure can be adopted as a method for using the LLM.

[0048] (1) Initialization of LLM: The LLM to be used is loaded and fine-tuned as necessary. In the fine-tuning, the model is trained using a related dataset to reflect the characteristics of the characters and the worldview of the work. In this embodiment, it is assumed that the trained LLM is used as is.

[0049] (2) Setting the context: Create a system prompt that includes background information for the conversation and character settings, and give it to the LLM. (3) Conversation history management: Maintain conversation history with the user and input it into the LLM for each turn. (4) Prompt Generation: Dynamically generate a prompt that includes the conversation data, the retrieved lines, and instructions for response generation. (5) Input to LLM: The generated prompt is input to the LLM and a response is obtained. The LLM may be provided in the management server 2, or the response may be obtained by calling the API of an external server that performs generation processing using the LLM. (6) Post-processing: The output of the LLM is adjusted as necessary to obtain the final response data.

[0050] Examples of prompts include the following:

[0051] Example 1: Quoting lines System: You will act as [character name]. [brief character description]. Quote the given lines naturally in your conversation. User: [user's conversation data] Related lines: "[Lines from the work]" Instructions: Please respond to the user's conversation data in a natural way, quoting the lines above.

[0052] Example 2: If no lines were found System: You will act as [character name]. [brief character description]. User: [user's conversation data] Instructions: Respond to the user's conversation data in a way that is appropriate for [character name]. Please do not quote lines from the work, but generate an original response that reflects the character's personality and tone.

[0053] The generation unit 213 can use these prompts as templates and dynamically change the contents according to the actual conversation situation. For example, the character name, character description, user conversation data, related lines, etc. are replaced with appropriate values ​​each time and input to the LLM. It is also possible to flexibly change the structure and instruction contents of the prompt according to the flow of the conversation and the characteristics of the searched lines.

[0054] The generation unit 213 may include some of the lines in the prompt to perform learning by short-shot learning.

[0055] The output unit 214 outputs the generated response data to the user. The output unit 214 transmits the response data to the user terminal 1, which can display the response data. The output unit 214 can output a scene corresponding to the searched line, which is stored in the work storage unit 231, to the user. After outputting the response data, the output unit 214 can output a scene in response to a request from the user.

[0056] <Operation> FIG. 4 is a diagram illustrating the operation of the management server 2. As shown in FIG.

[0057] The management server 2 acquires conversation data (S301), searches for lines related to the conversation data (S302), and if the lines are found (S303: YES), generates response data quoting the lines (S304), and if the lines are not found (S303: NO), generates response data not quoting the lines (S305), and transmits the response data to the user terminal 1 (S306). In response to a request from the user terminal 1, the management server 2 can read out a scene corresponding to the lines from the work storage unit 231 and transmit the scene to the user terminal 1 (S307).

[0058] As described above, according to the information processing system of this embodiment, in a conversation between a user and the system, it is possible to respond by quoting lines from a work related to conversation data from a user.

[0059] Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention may be modified or improved without departing from the spirit of the present invention, and equivalents thereof are also included in the present invention.

[0060] For example, the processes performed by each of the functional units of the management server 2 described above may be executed by any of the functional units. Also, a different functional unit that executes part of the processes performed by each of the functional units described above may be added. Also, the functional units of the management server 2 may be provided in a distributed manner on multiple computers.

[0061] Furthermore, the information stored in each storage unit of the management server may be stored by any of the storage units. That is, the information stored in the above-mentioned multiple storage units may be stored by one storage unit, or part of the information stored in one of the above-mentioned storage units may be stored by another storage unit.

[0062] <Variation 1> In addition to the configuration of the above embodiment, the first modification has a function for handling multi-modal input. The following mainly describes the differences from the above embodiment.

[0063] The management server 2 of the first modification may include a voice recognition unit and an image recognition unit in addition to the configuration of the above embodiment.

[0064] The speech recognition unit analyzes the speech data input by the user and converts it into text data. The speech recognition unit performs highly accurate speech-to-text conversion using, for example, a speech recognition model based on deep learning. It also extracts prosodic information such as intonation and tone of the speech, which can be used to estimate the user's emotional state.

[0065] The image recognition unit analyzes image data input by the user and recognizes objects, facial expressions, situations, etc. in the image. The image recognition unit uses deep learning models such as convolutional neural networks (CNN) to extract image features. The recognition results are output as text data.

[0066] The acquisition unit 211 can accept not only text data, but also voice data and image data as input. When voice data is input, the acquisition unit 211 converts it into text using a voice recognition unit. When image data is input, the acquisition unit 211 converts the contents of the image into text using an image recognition unit.

[0067] The search unit 212 searches for related lines based on the contents of the voice data or image data converted into text. For example, if a user transmits an image of a sad expression, the search unit 212 can search preferentially for sad scenes or comforting lines in the work.

[0068] The generation unit 213 generates response data taking into consideration the characteristics of multimodal input. For example, it can estimate the emotion of the user from the voice input and quote lines in a tone that matches the emotion, or preferentially use lines related to the content of the image sent by the user.

[0069] The output unit 214 can not only output the generated response data as text, but also read the response in a character's voice using voice synthesis technology, and can simultaneously display images and videos related to the response.

[0070] <Variation 2> In addition to the configuration of the above embodiment, the second modification has a function for simultaneously conversing with multiple characters. The following mainly describes the differences from the above embodiment.

[0071] The management server 2 of the second modification may include a character management section and a dialogue control section in addition to the configuration of the above embodiment.

[0072] The character management unit manages information on multiple characters participating in a conversation. It stores information on each character's settings, personality, relationships with other characters, etc., and has the function of selecting an appropriate character depending on the context of the conversation.

[0073] The dialogue control section controls the flow of dialogue between multiple characters. It decides which character will respond to what the user says and what kind of dialogue will take place between the characters. It also manages the dialogue history between characters to keep the conversation natural and consistent.

[0074] In addition to the configuration of the above embodiment, the work storage unit 231 also stores scenes of dialogue between characters and scenes of group conversations. This makes it possible to quote appropriate lines and dialogue patterns even in situations involving multiple characters.

[0075] When searching for lines related to user conversation data, the search unit 212 searches not only lines of a single character but also dialogue scenes involving multiple characters.

[0076] The generation unit 213 has a function of simultaneously generating responses from multiple characters. It generates response data that takes into account the characteristics and relationships of each character and reproduces natural interactions. In addition, when generating dialogue between characters, the following elements are taken into consideration: (1) Relationships between characters (friendly, antagonistic, hierarchical, etc.) (2) Each character’s personality and speaking style (3) The context or situation of the conversation (4) The content and intent of the user’s comments (5) Past dialogue history

[0077] The output unit 214 presents the generated responses of the multiple characters to the user in a format that allows each character to be distinguished. For example, in the case of text chat, the remarks of each character can be displayed in a different color or speech bubble, or a character icon can be added.

[0078] In the second modification, the user directly converses with multiple characters, but a role-playing style dialogue is also possible in which the user operates a specific character and converses with other characters as that character. In this case, the generation unit 213 can have a function of suggesting appropriate response candidates in consideration of the characteristics of the character operated by the user.

[0079] <Variation 3> In addition to the configuration of the above embodiment, the third modification has a function of generating more appropriate quotes and responses by taking into account past conversation history. The following mainly describes the points that are different from the above embodiment.

[0080] The management server 2 of the third modification includes a conversation history storage unit and a context analysis unit in addition to the configuration of the above embodiment.

[0081] The conversation history storage unit stores the history of past conversations between the user and the system. It saves the user's comments, the system's responses, quoted lines, and conversation time information in each conversation session. It also records important information mentioned during the conversation (e.g., the user's preferences and experiences).

[0082] The context analysis unit has the function of analyzing the current conversation data and past conversation history to understand the context of the conversation. Specifically, it performs the following processes. (1) Tracking topic progression (2) Estimating the user’s emotional state (3) Understanding the long-term purpose and direction of the conversation (4) Analysis of the relationship between users and characters (5) Record previously quoted lines and avoid duplication

[0083] The search unit 212 uses the information obtained from the context analysis unit to search for lines that are more suitable for the context. For example, the following search criteria can be added: (1) Prioritize lines related to the current topic (2) Prioritize lines that have not been quoted before (3) Selecting lines that fit the user’s current emotional state (4) Choosing lines that fit the long-term purpose of the conversation

[0084] The generator 213 generates a more appropriate response by taking into account the information obtained from the context analyzer. Specifically, the generator 213 realizes the following functions. (1) Appropriate reference to information mentioned in previous conversations (2) Maintaining consistency in conversation (avoiding contradictory statements) (3) Developing topics based on users’ interests and reactions (4) Structuring long-term conversations (introduction, development, conclusion, etc.) (5) Adjusting response style according to the development of the relationship with the user

[0085] As described above, according to the third modification, it is possible to generate more appropriate quotes and responses by taking into account the past conversation history. This makes it possible to realize a more natural and contextual dialogue that is consistent over the long term.

[0086] In addition, in the third modification, it is important to appropriately set the retention period and scope of use of the conversation history and to take the user's privacy into consideration. For example, a function can be implemented that saves the conversation history with the user's consent and automatically deletes it after a certain period of time. It is also possible to provide a mechanism that clearly explains the purpose of use of the conversation history and allows the user to request deletion of the history or suspension of use.

[0087] The functions of this embodiment can also be implemented in combination with Modification 1 and Modification 2. For example, a more advanced dialogue experience can be provided by taking into account the history of multimodal inputs and tracking the development of relationships with multiple characters in conversations with each character.

[0088] <Variation 4> In addition to the configuration of the above embodiment, the fourth modification has a function of learning the user's preferences and interests, and selecting lines and generating responses in accordance with them. The following mainly describes the differences from the above embodiment.

[0089] The management server 2 of the fourth modification includes a user profile storage unit, a preference learning unit, and a preference consideration unit in addition to the configuration of the above embodiment.

[0090] The user profile storage unit stores the preference information of each user. Specifically, the following information can be stored: (1) Favorite character (2) Genres and topics of interest (3) Frequently quoted lines and their characteristics (4) Conversation patterns that users responded well to (5) User frequency and time of use (6) Basic user attribute information (such as age group and gender, collected with the user's consent)

[0091] The preference learning unit has a function of learning the user's preferences from conversation data with the user and the user's actions. Specifically, it can perform the following processes. (1) Analysis of user comments (2) Tracking user responses (e.g., use of the "Like" button, duration of conversations) (3) Extraction of topics frequently mentioned by users (4) Analysis of users’ preferred language and expression styles (5) Measuring the level of interest that users have in particular characters or works

[0092] The preference learning unit periodically updates the information in the user profile storage unit based on the results of these analyses.

[0093] The preference consideration unit has a function of referring to the preference information stored in the user profile storage unit and reflecting it in the selection of lines and the generation of responses.

[0094] The search unit 212 uses the information obtained from the preference consideration unit to preferentially search for phrases that match the user's preferences. For example, the following search criteria can be added. (1) Prioritizing the lines of the user’s favorite character (2) Selection of lines related to the genre or topic of the user’s interest (3) Selecting lines that are similar to lines that users responded favorably to in the past

[0095] The generation unit 213 generates a response that matches the user's preferences, taking into account the information obtained from the preference consideration unit. Specifically, the generation unit 213 realizes the following functions. (1) Adopting the user's preferred language and style (2) Guiding users to topics of interest (3) Selection of characters according to the user's preferences (if multiple characters are supported) (4) Reproducing conversation patterns that users responded well to

[0096] As described above, according to the fourth modification, it is possible to learn the preferences and interests of the user and select lines and generate responses according to them, thereby providing the user with a more attractive and personalized conversation experience.

[0097] In addition, in Modification 4, it is necessary to pay sufficient attention to the handling of user preference information. For example, it is desirable to take the following measures. (1) Collect and use preference information with the explicit consent of the user (2) Clearly explain the scope of information to be collected and the purpose of its use (3) Provide users with the ability to confirm, modify, or delete their own preference information (4) Implement appropriate security measures, such as encrypting preference information and controlling access to it.

[0098] In addition, the functions of this embodiment can be implemented in combination with the other embodiments described above. For example, by combining this embodiment with Modification 3, a more advanced dialogue system that takes into account both past conversation history and user preferences can be realized.

[0099] <Variation 5> In addition to the configuration of the above embodiment, the fifth modification has a function of incorporating new works and added lines in real time and reflecting the latest information. The following mainly describes the points that are different from the above embodiment.

[0100] The management server 2 of the fifth modification includes an update monitor, a data acquisition unit, and an integration processing unit in addition to the configuration of the above embodiment.

[0101] The update monitoring unit has the function of periodically checking for new work information and additional lines. Specifically, it performs the following process. (1) Regular access to external data sources (publisher APIs, official websites, etc.) (2) Receive update notifications using RSS feeds, Webhooks, etc. (3) Monitoring the update date and time of the work database

[0102] The data acquisition unit has the function of acquiring new information detected by the update monitoring unit. Specifically, it performs the following processes. (1) Acquire metadata for new works (title, author, release date, etc.) (2) Downloading new dialogue data (3) Obtaining updated work information

[0103] The integration processing unit has a function of integrating new information acquired by the data acquisition unit with existing data. Specifically, it performs the following processes. (1) Addition of new work data to the work storage unit 231 (2) Adding or updating lines to existing works (3) Converting the format of new data (e.g. converting text data to embedding vectors) (4) Data integrity check and error handling

[0104] The work storage unit 231 is always kept up to date by the integration processing unit, so that the search unit 212 and the generation unit 213 can always use the latest work information and lines.

[0105] As described above, according to the fifth modification, new works and added lines can be incorporated in real time, making it possible to always have conversations that reflect the latest information.

[0106] In addition, in the fifth modification, it is necessary to appropriately set the data update frequency and acquisition timing. In order to avoid excessive system load due to the update process, it is possible to consider measures such as adjusting the update frequency or executing the update process during a time period when the system load is low.

[0107] Quality control of newly added data is also important. By implementing a function for checking the validity of new data and filtering inappropriate content in the integrated processing unit, the reliability and security of the system can be ensured.

[0108] The function of the modification example 5 can be implemented in combination with the other modifications described above. For example, by combining it with the modification example 4, a more attractive dialogue experience can be realized, such as preferentially providing the latest lines and work information that match the user's preferences.

[0109] <Disclosures> The present disclosure also includes the following configurations. [Item 1] a response data generation unit that generates response data in response to conversation data from a user to a character, the response data being generated so as to quote lines included in a work in which the character appears; an output unit that outputs the response data to the user; An information processing system comprising: [Item 2] The information processing system according to item 1, a work storage unit that stores the lines included in the work; a search unit that searches the work storage unit for the lines related to the conversation data; Equipped with the generation unit generates the response data by providing a prompt to a large-scale language model, the prompt including the conversation data, the searched lines, and an instruction to create a response to the conversation data so as to quote the lines; An information processing system comprising: [Item 3] The information processing system according to item 1, a work storage unit that stores scenes of the work and lines included in the scenes; a search unit that searches the work storage unit for the lines related to the conversation data; Equipped with the output unit acquires the scene corresponding to the line from the work storage unit, and outputs the acquired scene to the user; An information processing system comprising: [Item 4] The information processing system according to item 1, a search unit for searching the lines related to the conversation data; the generation unit generates the response data so as to quote the line when the line is found, and generates the response data as a response to the conversation data without quoting the line when the line is not found; An information processing system comprising: [Item 5] The information processing system according to item 1, the conversation data generating unit generates the second conversation data so as to quote the lines by a second character different from the first character; An information processing system comprising: [Item 6] generating response data for the character to respond to conversation data from the user; outputting the response data to the user; An information processing method executed by a computer, comprising: In the generating step, the computer generates the response data so as to quote lines included in a work in which the character appears; An information processing method comprising: [Item 7] generating response data for the character to respond to conversation data from the user; outputting the response data to the user; A program for causing a computer to execute the above, In the generating step, causing the computer to generate the response data so as to quote lines included in a work in which the character appears; A program characterized by. [Explanation of symbols]

[0110] 1 User terminal 2 Management Server

Claims

1. A response data generation unit that generates response data for a first character in response to conversation data from a user to the first character, the generation unit that generates the response data in such a way as to quote the lines of a second character, which is different from the first character, and is included in a work in which the first character appears, An output unit that outputs the response data to the user, An information processing system characterized by comprising the following features.

2. The information processing system according to claim 1, A work memory unit that stores the lines of the second character included in the aforementioned work, A search unit that searches the work memory unit for the lines of dialogue related to the conversation data, Equipped with, The generation unit generates the response data by providing a prompt to a large-scale language model that includes the conversation data, the retrieved line of dialogue, and an instruction to create a response to the conversation data that quotes the line of dialogue. An information processing system characterized by the following.

3. The information processing system according to claim 1, A work memory unit that stores scenes from the aforementioned work and the lines of the second character included in those scenes, A search unit that searches the work memory unit for the lines of dialogue related to the conversation data, Equipped with, The output unit retrieves the scene corresponding to the dialogue from the work storage unit and outputs the retrieved scene to the user. An information processing system characterized by the following.

4. The information processing system according to claim 1, The system includes a search unit that searches for the lines of dialogue related to the aforementioned conversation data, The generation unit generates the response data by quoting the dialogue if the dialogue is found, and generates the response data as a response to the conversation data without quoting the dialogue if the dialogue is not found. An information processing system characterized by the following.

5. The steps include generating response data for the first character in response to conversation data from the user to the first character, The steps include outputting the response data to the user, A computer-based information processing method, In the generation step, the computer generates the response data by quoting the lines of a second character, which is different from the first character, and which is included in a work in which the first character appears. An information processing method characterized by the following.

6. The steps include generating response data for the first character in response to conversation data from the user to the first character, The steps include outputting the response data to the user, A program that causes a computer to execute, In the generation step, the computer is instructed to generate the response data by quoting the lines of a second character, which is different from the first character, and which is included in a work in which the first character appears. A program characterized by the following.

Images