System

Abstract

A system in accordance with an embodiment is directed to adjusting the speech synthesis datum based on the persona of the character.SOLUTION: A system includes an input unit, a setting unit, and an adjustment unit. The input unit performs input of a knowledge database. The setting unit sets the persona of the character on the basis of the data input by the input unit. The adjustment unit adjusts the speech synthesis date based on the persona set by the setting unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that adjusting voice synthesis data is time-consuming and it is difficult to synthesize voice based on a character's persona.

[0005] The system according to the embodiment aims to adjust the voice synthesis data based on the persona of the character. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a setting unit, and an adjustment unit. The input unit inputs data to a knowledge database. The setting unit sets a persona for a character based on the data input by the input unit. The adjustment unit adjusts the voice synthesis data based on the persona set by the setting unit. [Effects of the Invention]

[0007] The system according to the embodiment can adjust the voice synthesis data based on the character's persona. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A conversation experience providing system according to an embodiment of the present invention uses voice synthesis and generation AI to provide the experience of conversing with a real person or a fictional character. The conversation experience providing system inputs data into a knowledge database, sets a character's persona, and adjusts voice synthesis data. For example, the conversation experience providing system inputs knowledge and information that a character should have into a knowledge database. Next, the conversation experience providing system sets the character's personality, speaking style, and behavioral patterns. Furthermore, the conversation experience providing system adjusts the character's voice characteristics and speaking patterns. This allows the conversation experience providing system to provide a character that converses with a user in a natural voice. The conversation experience providing system also has a function for hosting time-limited events. For example, it may provide a character that can only be spoken to during a specific period of time, or conversation content related to a specific event. Furthermore, the conversation experience providing system has a call log function for checking whether any inappropriate remarks have been made, and an operator reporting function for preventing fraudulent use. For example, the conversation experience providing system may record the content of a conversation between a user and a character and review it later. If fraudulent use is discovered, an operator may receive a report and take appropriate action. This allows the conversation experience providing system to offer users the experience of conversing with real people or fictional characters. For example, users can enjoy natural conversations with characters. In addition, time-limited events and safety measures can be implemented to provide a more fulfilling experience.

[0029] A conversation experience providing system according to an embodiment includes an input unit, a setting unit, and an adjustment unit. The input unit inputs data to a knowledge database. The knowledge database includes, for example, knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit, for example, inputs text data to the knowledge database. The input unit can also input voice data and image data to the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs the text data into the knowledge database. The setting unit sets a persona for the character based on the data input by the input unit. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. Furthermore, the setting unit can also set the character's behavior patterns. The adjustment unit adjusts voice synthesis data based on the persona set by the setting unit. The voice synthesis data includes the character's voice characteristics and speaking patterns. For example, the adjustment unit adjusts the character's voice tone. The adjustment unit can also adjust the rhythm of the character's speech. Furthermore, the adjustment unit can also adjust the pitch of the character's voice. This makes it possible for the conversation experience providing system according to the embodiment to input knowledge databases, set character personas, and adjust voice synthesis data.

[0030] Furthermore, the conversation experience providing system includes an event unit that holds time-limited events. The event unit holds time-limited events. For example, it provides characters that can only be conversed during a specific period of time. The event unit can also provide conversation content related to a specific event. For example, it provides conversation content based on a specific theme. Furthermore, the event unit can also hold events in which users can participate. For example, it holds online events in which users can participate together with characters. This makes it possible to hold time-limited events.

[0031] Furthermore, the conversation experience providing system includes a log unit that records a call log. The log unit records the call log. The call log includes, for example, the content of the conversation between the user and the character. For example, the log unit records the content of the conversation as text data. The log unit can also record the content of the conversation as audio data. Furthermore, the log unit provides a function for checking the content of the conversation later. For example, the log unit provides a function for searching the recorded call log. This makes it possible to record the call log.

[0032] Furthermore, the conversation experience providing system includes a reporting unit that reports fraudulent use to an operator. The reporting unit reports fraudulent use to an operator. Fraudulent use includes, for example, inappropriate remarks and fraudulent acts. For example, the reporting unit provides an interface that allows a user to report fraudulent use. The reporting unit can also provide a function that notifies an operator when fraudulent use is discovered. Furthermore, the reporting unit provides information that allows the operator to take appropriate action. For example, the reporting unit displays the content of the report to the operator. This makes it possible to report fraudulent use to the operator.

[0033] The input unit can input knowledge and information that a character should have into the knowledge database. The knowledge database includes, for example, knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit, for example, inputs text data into the knowledge database. The input unit can also input voice data and image data into the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs it into the knowledge database. This makes it possible to input knowledge and information that a character should have into the knowledge database.

[0034] The setting unit can set the character's personality, speaking style, and behavior patterns. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. The setting unit can also set the character's behavior patterns. For example, the setting unit can set the character's personality to be gentle. The setting unit can also set the character's speaking style to be polite. The setting unit can also set the character's behavior patterns to be friendly. This makes it possible to set the character's personality, speaking style, and behavior patterns.

[0035] The adjustment unit can adjust the voice characteristics and speaking pattern of the character. The voice synthesis data includes the voice characteristics and speaking pattern of the character. For example, the adjustment unit adjusts the tone of the character's voice. The adjustment unit can also adjust the rhythm of the character's speaking. Furthermore, the adjustment unit can adjust the pitch of the character's voice. For example, the adjustment unit adjusts the character's voice to be higher. The adjustment unit can also adjust the character's speaking to be slower. Furthermore, the adjustment unit can adjust the character's voice to be lower. This makes it possible to adjust the voice characteristics and speaking pattern of the character.

[0036] The input unit can input the user's past conversation history into the character's knowledge database. The input unit can add related knowledge to the database based on, for example, the content of questions the user has asked in the past. The input unit can also update the knowledge database to reflect topics in which the user has shown interest in the past. Furthermore, the input unit can also modify the contents of the knowledge database based on feedback the user has given in the past. This makes it possible to update the knowledge database to reflect the user's past conversation history.

[0037] The input unit can filter the knowledge database based on the user's current areas of interest when inputting information into the knowledge database. For example, the input unit inputs only information related to topics in which the user is currently interested. The input unit can also select the contents of the knowledge database based on the user's current areas of interest. Furthermore, the input unit can add related knowledge to the database based on the user's current search history. This makes it possible to select the contents of the knowledge database based on the user's current areas of interest.

[0038] The input unit can select the optimum input means depending on the user's input method when inputting data into the knowledge database. For example, if the user uses voice input, the input unit inputs data into the knowledge database using voice recognition technology. Also, if the user uses text input, the input unit can input data into the knowledge database using text analysis technology. Furthermore, if the user uses image input, the input unit can input data into the knowledge database using image recognition technology. This makes it possible to select the optimum input means depending on the user's input method.

[0039] When inputting data into the knowledge database, the input unit can prioritize inputting highly relevant data in consideration of the user's geographical location information. For example, the input unit prioritizes inputting information related to the user's current location. The input unit can also prioritize inputting information related to places the user has visited in the past. Furthermore, the input unit can also prioritize inputting information related to places the user plans to visit in the future. This makes it possible to prioritize inputting highly relevant data based on the user's geographical location information.

[0040] The input unit can analyze the user's social media activities and input related data when inputting information into the knowledge database. The input unit can update the knowledge database based on, for example, information shared by the user on social media. The input unit can also analyze the content posted by the user on social media and add related knowledge to the database. Furthermore, the input unit can input related information by referring to the activities of the user's friends on social media. This makes it possible to input related data based on the user's social media activities.

[0041] The input unit can customize the input method by reflecting the user's past feedback when inputting data into the knowledge database. The input unit can optimize the input method based on, for example, the user's past feedback. The input unit can also simplify the input procedure by reflecting the user's past feedback. Furthermore, the input unit can improve the input interface based on the user's past feedback. This makes it possible to customize the input method based on the user's past feedback.

[0042] When setting a character's persona, the setting unit can improve the accuracy of the setting by referring to the user's past conversation history. The setting unit sets the persona based on, for example, the personality of characters that the user has previously preferred. The setting unit can also analyze the user's past conversation history and set an optimal persona. Furthermore, the setting unit can adjust the persona settings based on feedback provided by the user in the past. This makes it possible to improve the accuracy of the character's persona setting by referring to the user's past conversation history.

[0043] When setting a persona for a character, the setting unit can apply different setting algorithms depending on the character category. For example, in the case of a historical figure, the setting unit sets a persona based on the life and achievements of that person. In addition, in the case of a fictional character, the setting unit can also set a persona based on the setting of that character. Furthermore, in the case of a real person, the setting unit can also set a persona based on the personality and speaking style of that person. This makes it possible to apply different setting algorithms depending on the character category.

[0044] The setting unit can improve the setting content by reflecting user feedback when setting a character's persona. For example, the setting unit adjusts the persona's personality based on the user's feedback. The setting unit can also improve the persona's speaking style by reflecting user feedback. Furthermore, the setting unit can also modify the persona's behavior pattern based on user feedback. This makes it possible to improve the character's persona setting content based on user feedback.

[0045] When setting personas for characters, the setting unit can adjust the order of setting based on the relevance of the characters. For example, if the relevance of the character is high, the setting unit can prioritize persona setting. Also, if the relevance of the character is low, the setting unit can postpone persona setting. Furthermore, the setting unit can dynamically adjust the order of setting based on the relevance of the character. This makes it possible to adjust the order of setting based on the relevance of the character.

[0046] When setting a persona for a character, the setting unit can adjust the use of technical terms in the setting according to the user's level of expertise. For example, if the user has technical expertise, the setting unit sets the persona using a lot of technical terms. Also, if the user is a beginner, the setting unit can set the persona without using technical terms. Furthermore, the setting unit can adjust the frequency of use of technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the setting according to the user's level of expertise.

[0047] The setting unit can customize the setting method by reflecting the user's past feedback when setting a character's persona. For example, the setting unit can optimize the persona setting procedure based on the user's past feedback. The setting unit can also simplify the setting method by reflecting the user's past feedback. Furthermore, the setting unit can improve the setting interface based on the user's past feedback. This makes it possible to customize the setting method based on the user's past feedback.

[0048] When adjusting the voice synthesis data, the adjustment unit can determine the level of detail of the adjustment based on the characteristics of the character's voice. For example, if the character's voice is high, the adjustment unit can adjust the high-pitched range in detail. Also, if the character's voice is low, the adjustment unit can adjust the low-pitched range in detail. Furthermore, the adjustment unit can dynamically determine the level of detail of the adjustment according to the characteristics of the character's voice. This makes it possible to determine the level of detail of the adjustment based on the characteristics of the character's voice.

[0049] When adjusting the speech synthesis data, the adjustment unit can apply different adjustment algorithms depending on the character category. For example, in the case of a historical figure, the adjustment unit applies an adjustment algorithm based on the voice characteristics of that person. In addition, in the case of a fictional character, the adjustment unit can also apply an adjustment algorithm based on the character's settings. Furthermore, in the case of a real person, the adjustment unit can also apply an adjustment algorithm based on the voice characteristics of that person. This makes it possible to apply different adjustment algorithms depending on the character category.

[0050] The adjustment unit can improve the adjustment content by reflecting user feedback when adjusting the speech synthesis data. The adjustment unit adjusts the speech synthesis data based on, for example, feedback provided by the user. The adjustment unit can also adjust the tone and pitch of the voice by reflecting user feedback. Furthermore, the adjustment unit can also make adjustments to improve the naturalness of the voice based on user feedback. This makes it possible to improve the adjustment content of the speech synthesis data based on user feedback.

[0051] When adjusting the voice synthesis data, the adjustment unit can adjust the order of adjustment based on the relevance of the characters. For example, when the relevance of the characters is high, the adjustment unit prioritizes adjusting the voice synthesis data. Also, when the relevance of the characters is low, the adjustment unit can postpone adjusting the voice synthesis data. Furthermore, the adjustment unit can dynamically adjust the order of adjustment according to the relevance of the characters. This makes it possible to adjust the order of adjustment based on the relevance of the characters.

[0052] When adjusting the speech synthesis data, the adjustment unit can adjust the use of technical terms in the adjustment according to the user's level of expertise. For example, if the user has technical knowledge, the adjustment unit adjusts the speech synthesis data to make heavy use of technical terms. In addition, if the user is a beginner, the adjustment unit can also adjust the speech synthesis data to avoid technical terms. Furthermore, the adjustment unit can adjust the frequency of use of technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the adjustment according to the user's level of expertise.

[0053] The adjustment unit can customize the adjustment method by reflecting the user's past feedback when adjusting the synthesized speech data. The adjustment unit can optimize the adjustment method for the synthesized speech data, for example, based on the user's past feedback. The adjustment unit can also simplify the adjustment procedure by reflecting the user's past feedback. Furthermore, the adjustment unit can improve the adjustment interface based on the user's past feedback. This makes it possible to customize the adjustment method based on the user's past feedback.

[0054] When an event is held, the event unit can select the optimal event content by referring to the user's past participation history. For example, the event unit selects related events based on the content of events the user has previously participated in. The event unit can also analyze the user's past participation history and suggest the optimal event content. Furthermore, the event unit can adjust the event content based on feedback provided by the user in the past. This makes it possible to select the optimal event content by referring to the user's past participation history.

[0055] The event module can customize the event content based on the user's current areas of interest when an event is held. For example, the event module can provide event content related to topics that the user is currently interested in. The event module can also select event content based on the user's current areas of interest. Furthermore, the event module can provide related event content based on the user's current search history. This makes it possible to customize the event content based on the user's current areas of interest.

[0056] When holding an event, the event unit can prioritize holding highly relevant events taking into account the user's geographical location information. For example, the event unit prioritizes holding events related to the user's current location. The event unit can also prioritize holding events related to places the user has visited in the past. Furthermore, the event unit can also prioritize holding events related to places the user plans to visit in the future. This makes it possible to prioritize holding highly relevant events based on the user's geographical location information.

[0057] When an event is held, the event module can analyze the user's social media activity and suggest related events. For example, the event module can suggest related events based on information shared by the user on social media. The event module can also analyze the content posted by the user on social media and suggest related events. Furthermore, the event module can also suggest related events based on the activity of the user's friends on social media. This makes it possible to suggest related events based on the user's social media activity.

[0058] When recording a call log, the log unit can determine the level of detail of the recording by referring to the user's past conversation history. The log unit records a detailed call log based on, for example, the content of conversations the user has had in the past. The log unit can also analyze the user's past conversation history and select the optimal recording method. Furthermore, the log unit can adjust the call log recording method based on feedback the user has provided in the past. This makes it possible to determine the level of detail of the call log recording by referring to the user's past conversation history.

[0059] When recording a call log, the log unit can customize the recording content based on the user's current areas of interest. For example, the log unit records call logs in detail related to topics in which the user is currently interested. The log unit can also select the contents of the call log based on the areas in which the user is currently interested. Furthermore, the log unit can record related call logs based on the user's current search history. This makes it possible to customize the recording content of the call log based on the user's current areas of interest.

[0060] When recording a call log, the log unit can prioritize recording highly relevant logs by taking into account the user's geographical location information. For example, the log unit prioritizes recording call logs related to the user's current location. The log unit can also prioritize recording call logs related to places the user has visited in the past. Furthermore, the log unit can also prioritize recording call logs related to places the user plans to visit in the future. This makes it possible to prioritize recording highly relevant logs based on the user's geographical location information.

[0061] The log unit can analyze the user's social media activities and record related logs when recording call logs. For example, the log unit records related call logs based on information shared by the user on social media. The log unit can also analyze the content of the user's posts on social media and record related call logs. Furthermore, the log unit can also record related call logs by referring to the activities of the user's friends on social media. This makes it possible to record related logs based on the user's social media activities.

[0062] When reporting fraudulent use, the reporting unit can determine the level of detail of the report by referring to the user's past reporting history. The reporting unit can provide a detailed reporting method based on the content of reports made by the user in the past, for example. The reporting unit can also analyze the user's past reporting history and select the optimal reporting method. Furthermore, the reporting unit can adjust the reporting method based on feedback made by the user in the past. This makes it possible to determine the level of detail of the report by referring to the user's past reporting history.

[0063] When reporting fraudulent use, the reporting unit can customize the report content based on the user's current areas of interest. For example, the reporting unit provides report content related to topics that the user is currently interested in. The reporting unit can also select report content based on the user's current areas of interest. Furthermore, the reporting unit can also provide related report content based on the user's current search history. This makes it possible to customize the report content based on the user's current areas of interest.

[0064] When reporting fraudulent use, the reporting unit can prioritize highly relevant reports taking into account the user's geographical location information. For example, the reporting unit prioritizes reporting fraudulent use related to the user's current location. The reporting unit can also prioritize reporting fraudulent use related to places the user has visited in the past. Furthermore, the reporting unit can also prioritize reporting fraudulent use related to places the user plans to visit in the future. This makes it possible to prioritize highly relevant reports based on the user's geographical location information.

[0065] When reporting fraudulent use, the reporting unit can analyze the user's social media activity and make a related report. The reporting unit can report related fraudulent use, for example, based on information shared by the user on social media. The reporting unit can also analyze the content posted by the user on social media and make a related report. Furthermore, the reporting unit can also report related fraudulent use by referring to the activity of the user's friends on social media. This makes it possible to make a related report based on the user's social media activity.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] The conversation experience providing system can analyze the user's past conversation history and customize the character's responses based on the user's interests and concerns. For example, if the user has frequently talked about a particular topic in the past, the character can provide information related to that topic. Also, if the user has repeatedly asked a particular question in the past, the character can prepare a detailed answer to that question. Furthermore, the character's responses can be adjusted based on feedback provided by the user in the past. This makes it possible to provide responses based on the user's interests and concerns.

[0068] The conversation experience providing system can customize the character's response content by taking into account the user's geographical location information. For example, it can provide information related to the user's current location. It can also provide topics related to places the user has visited in the past. It can also provide information related to places the user plans to visit in the future. This makes it possible to provide responses based on the user's geographical location information.

[0069] The conversation experience providing system can analyze a user's social media activity and customize the character's response content. For example, the character can provide related topics based on information shared by the user on social media. The character can also analyze the content of the user's social media posts and provide a response based on that content. Furthermore, the character can provide related information based on the activity of the user's friends on social media. This makes it possible to provide responses based on the user's social media activity.

[0070] The conversation experience providing system can adjust the content of the character's responses depending on the user's level of expertise. For example, if the user has specialized knowledge, the character will respond using a lot of technical jargon. On the other hand, if the user is a beginner, the character can respond by avoiding technical jargon. Furthermore, the character's responses can be made more detailed depending on the user's level of expertise. This makes it possible to provide appropriate responses according to the user's level of expertise.

[0071] The conversation experience providing system can improve the content of the character's responses based on the user's past feedback. For example, the content of the character's responses can be optimized based on the user's past feedback. The system can also adjust the character's speaking style and behavior patterns by reflecting the user's past feedback. Furthermore, the system can customize the content of the character's responses based on the user's past feedback. This makes it possible to provide responses based on the user's past feedback.

[0072] The conversation experience providing system can customize the character's response content based on the user's current areas of interest. For example, it can provide information related to topics that the user is currently interested in. It can also select the character's response content based on the user's current areas of interest. It can also provide related information based on the user's current search history. This makes it possible to provide responses based on the user's current areas of interest.

[0073] The processing flow of the first embodiment will be briefly explained below.

[0074] Step 1: The input unit inputs data into the knowledge database. The knowledge database contains, for example, the knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit inputs, for example, text data into the knowledge database. The input unit can also input voice data and image data into the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs the text data into the knowledge database. Step 2: The setting unit sets the character's persona based on the data input by the input unit. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. Furthermore, the setting unit can also set the character's behavior patterns. Step 3: The adjustment unit adjusts the voice synthesis data based on the persona set by the setting unit. The voice synthesis data includes the character's voice characteristics and speaking pattern. For example, the adjustment unit adjusts the character's voice tone. The adjustment unit can also adjust the character's speaking rhythm. Furthermore, the adjustment unit can also adjust the character's voice pitch.

[0075] (Example 2) A conversation experience providing system according to an embodiment of the present invention uses voice synthesis and generation AI to provide the experience of conversing with a real person or a fictional character. The conversation experience providing system inputs data into a knowledge database, sets a character's persona, and adjusts voice synthesis data. For example, the conversation experience providing system inputs knowledge and information that a character should have into a knowledge database. Next, the conversation experience providing system sets the character's personality, speaking style, and behavioral patterns. Furthermore, the conversation experience providing system adjusts the character's voice characteristics and speaking patterns. This allows the conversation experience providing system to provide a character that converses with a user in a natural voice. The conversation experience providing system also has a function for hosting time-limited events. For example, it may provide a character that can only be spoken to during a specific period of time, or conversation content related to a specific event. Furthermore, the conversation experience providing system has a call log function for checking whether any inappropriate remarks have been made, and an operator reporting function for preventing fraudulent use. For example, the conversation experience providing system may record the content of a conversation between a user and a character and review it later. If fraudulent use is discovered, an operator may receive a report and take appropriate action. This allows the conversation experience providing system to offer users the experience of conversing with real people or fictional characters. For example, users can enjoy natural conversations with characters. In addition, time-limited events and safety measures can be implemented to provide a more fulfilling experience.

[0076] A conversation experience providing system according to an embodiment includes an input unit, a setting unit, and an adjustment unit. The input unit inputs data to a knowledge database. The knowledge database includes, for example, knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit, for example, inputs text data to the knowledge database. The input unit can also input voice data and image data to the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs the text data into the knowledge database. The setting unit sets a persona for the character based on the data input by the input unit. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. Furthermore, the setting unit can also set the character's behavior patterns. The adjustment unit adjusts voice synthesis data based on the persona set by the setting unit. The voice synthesis data includes the character's voice characteristics and speaking patterns. For example, the adjustment unit adjusts the character's voice tone. The adjustment unit can also adjust the rhythm of the character's speech. Furthermore, the adjustment unit can also adjust the pitch of the character's voice. This makes it possible for the conversation experience providing system according to the embodiment to input knowledge databases, set character personas, and adjust voice synthesis data.

[0077] Furthermore, the conversation experience providing system includes an event unit that holds time-limited events. The event unit holds time-limited events. For example, it provides characters that can only be conversed during a specific period of time. The event unit can also provide conversation content related to a specific event. For example, it provides conversation content based on a specific theme. Furthermore, the event unit can also hold events in which users can participate. For example, it holds online events in which users can participate together with characters. This makes it possible to hold time-limited events.

[0078] Furthermore, the conversation experience providing system includes a log unit that records a call log. The log unit records the call log. The call log includes, for example, the content of the conversation between the user and the character. For example, the log unit records the content of the conversation as text data. The log unit can also record the content of the conversation as audio data. Furthermore, the log unit provides a function for checking the content of the conversation later. For example, the log unit provides a function for searching the recorded call log. This makes it possible to record the call log.

[0079] Furthermore, the conversation experience providing system includes a reporting unit that reports fraudulent use to an operator. The reporting unit reports fraudulent use to an operator. Fraudulent use includes, for example, inappropriate remarks and fraudulent acts. For example, the reporting unit provides an interface that allows a user to report fraudulent use. The reporting unit can also provide a function that notifies an operator when fraudulent use is discovered. Furthermore, the reporting unit provides information that allows the operator to take appropriate action. For example, the reporting unit displays the content of the report to the operator. This makes it possible to report fraudulent use to the operator.

[0080] The input unit can input knowledge and information that a character should have into the knowledge database. The knowledge database includes, for example, knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit, for example, inputs text data into the knowledge database. The input unit can also input voice data and image data into the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs it into the knowledge database. This makes it possible to input knowledge and information that a character should have into the knowledge database.

[0081] The setting unit can set the character's personality, speaking style, and behavior patterns. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. The setting unit can also set the character's behavior patterns. For example, the setting unit can set the character's personality to be gentle. The setting unit can also set the character's speaking style to be polite. The setting unit can also set the character's behavior patterns to be friendly. This makes it possible to set the character's personality, speaking style, and behavior patterns.

[0082] The adjustment unit can adjust the voice characteristics and speaking pattern of the character. The voice synthesis data includes the voice characteristics and speaking pattern of the character. For example, the adjustment unit adjusts the tone of the character's voice. The adjustment unit can also adjust the rhythm of the character's speaking. Furthermore, the adjustment unit can adjust the pitch of the character's voice. For example, the adjustment unit adjusts the character's voice to be higher. The adjustment unit can also adjust the character's speaking to be slower. Furthermore, the adjustment unit can adjust the character's voice to be lower. This makes it possible to adjust the voice characteristics and speaking pattern of the character.

[0083] The input unit can estimate the user's emotions and adjust the timing of input to the knowledge database based on the estimated user emotions. For example, if the user is relaxed, the input unit can immediately input data to the knowledge database. Furthermore, if the user is feeling stressed, the input unit can postpone input to the knowledge database. Furthermore, if the user is concentrating, the input unit can prioritize input to the knowledge database. This makes it possible to adjust the timing of input to the knowledge database based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0084] The input unit can input the user's past conversation history into the character's knowledge database. The input unit can add related knowledge to the database based on, for example, the content of questions the user has asked in the past. The input unit can also update the knowledge database to reflect topics in which the user has shown interest in the past. Furthermore, the input unit can also modify the contents of the knowledge database based on feedback the user has given in the past. This makes it possible to update the knowledge database to reflect the user's past conversation history.

[0085] The input unit can filter the knowledge database based on the user's current areas of interest when inputting information into the knowledge database. For example, the input unit inputs only information related to topics in which the user is currently interested. The input unit can also select the contents of the knowledge database based on the user's current areas of interest. Furthermore, the input unit can add related knowledge to the database based on the user's current search history. This makes it possible to select the contents of the knowledge database based on the user's current areas of interest.

[0086] The input unit can select the optimum input means depending on the user's input method when inputting data into the knowledge database. For example, if the user uses voice input, the input unit inputs data into the knowledge database using voice recognition technology. Also, if the user uses text input, the input unit can input data into the knowledge database using text analysis technology. Furthermore, if the user uses image input, the input unit can input data into the knowledge database using image recognition technology. This makes it possible to select the optimum input means depending on the user's input method.

[0087] The input unit can estimate the user's emotions and determine the priority of knowledge data to be input based on the estimated user emotions. For example, when the user is excited, the input unit prioritizes input of topics that interest the user. The input unit can also prioritize input of detailed information when the user is relaxed. Furthermore, when the user is in a hurry, the input unit can also prioritize input of information that focuses on the main points. This makes it possible to determine the priority of knowledge data to be input based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0088] When inputting data into the knowledge database, the input unit can prioritize inputting highly relevant data in consideration of the user's geographical location information. For example, the input unit prioritizes inputting information related to the user's current location. The input unit can also prioritize inputting information related to places the user has visited in the past. Furthermore, the input unit can also prioritize inputting information related to places the user plans to visit in the future. This makes it possible to prioritize inputting highly relevant data based on the user's geographical location information.

[0089] The input unit can analyze the user's social media activities and input related data when inputting information into the knowledge database. The input unit can update the knowledge database based on, for example, information shared by the user on social media. The input unit can also analyze the content posted by the user on social media and add related knowledge to the database. Furthermore, the input unit can input related information by referring to the activities of the user's friends on social media. This makes it possible to input related data based on the user's social media activities.

[0090] The input unit can customize the input method by reflecting the user's past feedback when inputting data into the knowledge database. The input unit can optimize the input method based on, for example, the user's past feedback. The input unit can also simplify the input procedure by reflecting the user's past feedback. Furthermore, the input unit can improve the input interface based on the user's past feedback. This makes it possible to customize the input method based on the user's past feedback.

[0091] The setting unit can estimate the user's emotions and adjust the character's persona settings based on the estimated user's emotions. For example, if the user is relaxed, the setting unit can set a persona with a calm personality. If the user is excited, the setting unit can also set a persona with a lively personality. Furthermore, if the user is stressed, the setting unit can also set a persona with a soothing personality. This makes it possible to adjust the character's persona settings based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0092] When setting a character's persona, the setting unit can improve the accuracy of the setting by referring to the user's past conversation history. The setting unit sets the persona based on, for example, the personality of characters that the user has previously preferred. The setting unit can also analyze the user's past conversation history and set an optimal persona. Furthermore, the setting unit can adjust the persona settings based on feedback provided by the user in the past. This makes it possible to improve the accuracy of the character's persona setting by referring to the user's past conversation history.

[0093] When setting a persona for a character, the setting unit can apply different setting algorithms depending on the character category. For example, in the case of a historical figure, the setting unit sets a persona based on the life and achievements of that person. In addition, in the case of a fictional character, the setting unit can also set a persona based on the setting of that character. Furthermore, in the case of a real person, the setting unit can also set a persona based on the personality and speaking style of that person. This makes it possible to apply different setting algorithms depending on the character category.

[0094] The setting unit can improve the setting content by reflecting user feedback when setting a character's persona. For example, the setting unit adjusts the persona's personality based on the user's feedback. The setting unit can also improve the persona's speaking style by reflecting user feedback. Furthermore, the setting unit can also modify the persona's behavior pattern based on user feedback. This makes it possible to improve the character's persona setting content based on user feedback.

[0095] The setting unit can estimate the user's emotions and adjust the level of detail of the persona setting based on the estimated user's emotions. For example, if the user is relaxed, the setting unit can set a detailed persona. If the user is in a hurry, the setting unit can also set a simplified persona. Furthermore, if the user is excited, the setting unit can also set a visually stimulating persona. This makes it possible to adjust the level of detail of the persona setting based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0096] When setting personas for characters, the setting unit can adjust the order of setting based on the relevance of the characters. For example, if the relevance of the character is high, the setting unit can prioritize persona setting. Also, if the relevance of the character is low, the setting unit can postpone persona setting. Furthermore, the setting unit can dynamically adjust the order of setting based on the relevance of the character. This makes it possible to adjust the order of setting based on the relevance of the character.

[0097] When setting a persona for a character, the setting unit can adjust the use of technical terms in the setting according to the user's level of expertise. For example, if the user has technical expertise, the setting unit sets the persona using a lot of technical terms. Also, if the user is a beginner, the setting unit can set the persona without using technical terms. Furthermore, the setting unit can adjust the frequency of use of technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the setting according to the user's level of expertise.

[0098] The setting unit can customize the setting method by reflecting the user's past feedback when setting a character's persona. For example, the setting unit can optimize the persona setting procedure based on the user's past feedback. The setting unit can also simplify the setting method by reflecting the user's past feedback. Furthermore, the setting unit can improve the setting interface based on the user's past feedback. This makes it possible to customize the setting method based on the user's past feedback.

[0099] The adjustment unit can estimate the user's emotions and adjust the synthesized voice data based on the estimated user's emotions. For example, if the user is relaxed, the adjustment unit can adjust calm synthesized voice data. If the user is excited, the adjustment unit can also adjust active synthesized voice data. Furthermore, if the user is stressed, the adjustment unit can also adjust soothing synthesized voice data. This makes it possible to adjust the synthesized voice data based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0100] When adjusting the voice synthesis data, the adjustment unit can determine the level of detail of the adjustment based on the characteristics of the character's voice. For example, if the character's voice is high, the adjustment unit can adjust the high-pitched range in detail. Also, if the character's voice is low, the adjustment unit can adjust the low-pitched range in detail. Furthermore, the adjustment unit can dynamically determine the level of detail of the adjustment according to the characteristics of the character's voice. This makes it possible to determine the level of detail of the adjustment based on the characteristics of the character's voice.

[0101] When adjusting the speech synthesis data, the adjustment unit can apply different adjustment algorithms depending on the character category. For example, in the case of a historical figure, the adjustment unit applies an adjustment algorithm based on the voice characteristics of that person. In addition, in the case of a fictional character, the adjustment unit can also apply an adjustment algorithm based on the character's settings. Furthermore, in the case of a real person, the adjustment unit can also apply an adjustment algorithm based on the voice characteristics of that person. This makes it possible to apply different adjustment algorithms depending on the character category.

[0102] The adjustment unit can improve the adjustment content by reflecting user feedback when adjusting the speech synthesis data. The adjustment unit adjusts the speech synthesis data based on, for example, feedback provided by the user. The adjustment unit can also adjust the tone and pitch of the voice by reflecting user feedback. Furthermore, the adjustment unit can also make adjustments to improve the naturalness of the voice based on user feedback. This makes it possible to improve the adjustment content of the speech synthesis data based on user feedback.

[0103] The adjustment unit can estimate the user's emotions and prioritize the synthesized voice data based on the estimated user emotions. For example, if the user is excited, the adjustment unit prioritizes active synthesized voice data. The adjustment unit can also prioritize calm synthesized voice data if the user is relaxed. Furthermore, the adjustment unit can also prioritize soothing synthesized voice data if the user is stressed. This makes it possible to prioritize the synthesized voice data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0104] When adjusting the voice synthesis data, the adjustment unit can adjust the order of adjustment based on the relevance of the characters. For example, when the relevance of the characters is high, the adjustment unit prioritizes adjusting the voice synthesis data. Also, when the relevance of the characters is low, the adjustment unit can postpone adjusting the voice synthesis data. Furthermore, the adjustment unit can dynamically adjust the order of adjustment according to the relevance of the characters. This makes it possible to adjust the order of adjustment based on the relevance of the characters.

[0105] When adjusting the speech synthesis data, the adjustment unit can adjust the use of technical terms in the adjustment according to the user's level of expertise. For example, if the user has technical knowledge, the adjustment unit adjusts the speech synthesis data to make heavy use of technical terms. In addition, if the user is a beginner, the adjustment unit can also adjust the speech synthesis data to avoid technical terms. Furthermore, the adjustment unit can adjust the frequency of use of technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the adjustment according to the user's level of expertise.

[0106] The adjustment unit can customize the adjustment method by reflecting the user's past feedback when adjusting the synthesized speech data. The adjustment unit can optimize the adjustment method for the synthesized speech data, for example, based on the user's past feedback. The adjustment unit can also simplify the adjustment procedure by reflecting the user's past feedback. Furthermore, the adjustment unit can improve the adjustment interface based on the user's past feedback. This makes it possible to customize the adjustment method based on the user's past feedback.

[0107] The event unit can estimate the user's emotions and adjust the timing of an event based on the estimated user's emotions. For example, if the user is relaxed, the event unit can immediately hold an event. Furthermore, if the user is feeling stressed, the event unit can postpone holding an event. Furthermore, if the user is excited, the event unit can prioritize holding an event. This makes it possible to adjust the timing of an event based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0108] When an event is held, the event unit can select the optimal event content by referring to the user's past participation history. For example, the event unit selects related events based on the content of events the user has previously participated in. The event unit can also analyze the user's past participation history and suggest the optimal event content. Furthermore, the event unit can adjust the event content based on feedback provided by the user in the past. This makes it possible to select the optimal event content by referring to the user's past participation history.

[0109] The event module can customize the event content based on the user's current areas of interest when an event is held. For example, the event module can provide event content related to topics that the user is currently interested in. The event module can also select event content based on the user's current areas of interest. Furthermore, the event module can provide related event content based on the user's current search history. This makes it possible to customize the event content based on the user's current areas of interest.

[0110] The event unit can estimate the user's emotions and determine the priority of events based on the estimated user emotions. For example, if the user is excited, the event unit can prioritize stimulating events. Furthermore, if the user is relaxed, the event unit can prioritize calming events. Furthermore, if the user is stressed, the event unit can prioritize soothing events. This makes it possible to determine the priority of events based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0111] When holding an event, the event unit can prioritize holding highly relevant events taking into account the user's geographical location information. For example, the event unit prioritizes holding events related to the user's current location. The event unit can also prioritize holding events related to places the user has visited in the past. Furthermore, the event unit can also prioritize holding events related to places the user plans to visit in the future. This makes it possible to prioritize holding highly relevant events based on the user's geographical location information.

[0112] When an event is held, the event module can analyze the user's social media activity and suggest related events. For example, the event module can suggest related events based on information shared by the user on social media. The event module can also analyze the content posted by the user on social media and suggest related events. Furthermore, the event module can also suggest related events based on the activity of the user's friends on social media. This makes it possible to suggest related events based on the user's social media activity.

[0113] The log unit can estimate the user's emotions and adjust the call log recording method based on the estimated user's emotions. For example, if the user is relaxed, the log unit records a detailed call log. If the user is stressed, the log unit can also record a simplified call log. Furthermore, if the user is excited, the log unit can also record a call log that emphasizes important points. This makes it possible to adjust the call log recording method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0114] When recording a call log, the log unit can determine the level of detail of the recording by referring to the user's past conversation history. The log unit records a detailed call log based on, for example, the content of conversations the user has had in the past. The log unit can also analyze the user's past conversation history and select the optimal recording method. Furthermore, the log unit can adjust the call log recording method based on feedback the user has provided in the past. This makes it possible to determine the level of detail of the call log recording by referring to the user's past conversation history.

[0115] When recording a call log, the log unit can customize the recording content based on the user's current areas of interest. For example, the log unit records call logs in detail related to topics in which the user is currently interested. The log unit can also select the contents of the call log based on the areas in which the user is currently interested. Furthermore, the log unit can record related call logs based on the user's current search history. This makes it possible to customize the recording content of the call log based on the user's current areas of interest.

[0116] The log unit can estimate the user's emotions and determine the priority of call logs based on the estimated user's emotions. For example, if the user is excited, the log unit can prioritize recording call logs that emphasize important points. Furthermore, if the user is relaxed, the log unit can prioritize recording detailed call logs. Furthermore, if the user is stressed, the log unit can prioritize recording simplified call logs. This makes it possible to determine the priority of call logs based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] When recording a call log, the log unit can prioritize recording highly relevant logs by taking into account the user's geographical location information. For example, the log unit prioritizes recording call logs related to the user's current location. The log unit can also prioritize recording call logs related to places the user has visited in the past. Furthermore, the log unit can also prioritize recording call logs related to places the user plans to visit in the future. This makes it possible to prioritize recording highly relevant logs based on the user's geographical location information.

[0118] The log unit can analyze the user's social media activities and record related logs when recording call logs. For example, the log unit records related call logs based on information shared by the user on social media. The log unit can also analyze the content of the user's posts on social media and record related call logs. Furthermore, the log unit can also record related call logs by referring to the activities of the user's friends on social media. This makes it possible to record related logs based on the user's social media activities.

[0119] The reporting unit can estimate the user's emotions and adjust the fraud reporting method based on the estimated user emotions. For example, the reporting unit can provide a detailed reporting method when the user is relaxed. The reporting unit can also provide a simplified reporting method when the user is stressed. Furthermore, the reporting unit can also provide a quick reporting method when the user is excited. This makes it possible to adjust the fraud reporting method based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0120] When reporting fraudulent use, the reporting unit can determine the level of detail of the report by referring to the user's past reporting history. The reporting unit can provide a detailed reporting method based on the content of reports made by the user in the past, for example. The reporting unit can also analyze the user's past reporting history and select the optimal reporting method. Furthermore, the reporting unit can adjust the reporting method based on feedback made by the user in the past. This makes it possible to determine the level of detail of the report by referring to the user's past reporting history.

[0121] When reporting fraudulent use, the reporting unit can customize the report content based on the user's current areas of interest. For example, the reporting unit provides report content related to topics that the user is currently interested in. The reporting unit can also select report content based on the user's current areas of interest. Furthermore, the reporting unit can also provide related report content based on the user's current search history. This makes it possible to customize the report content based on the user's current areas of interest.

[0122] The reporting unit can estimate the user's emotions and determine the priority of reports based on the estimated user emotions. For example, if the user is excited, the reporting unit can prioritize quick reports. Furthermore, if the user is relaxed, the reporting unit can also prioritize detailed reports. Furthermore, if the user is stressed, the reporting unit can also prioritize simplified reports. This makes it possible to determine the priority of reports based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0123] When reporting fraudulent use, the reporting unit can prioritize highly relevant reports taking into account the user's geographical location information. For example, the reporting unit prioritizes reporting fraudulent use related to the user's current location. The reporting unit can also prioritize reporting fraudulent use related to places the user has visited in the past. Furthermore, the reporting unit can also prioritize reporting fraudulent use related to places the user plans to visit in the future. This makes it possible to prioritize highly relevant reports based on the user's geographical location information.

[0124] When reporting fraudulent use, the reporting unit can analyze the user's social media activity and make a related report. The reporting unit can report related fraudulent use, for example, based on information shared by the user on social media. The reporting unit can also analyze the content posted by the user on social media and make a related report. Furthermore, the reporting unit can also report related fraudulent use by referring to the activity of the user's friends on social media. This makes it possible to make a related report based on the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements, including the input unit, setting unit, adjustment unit, event unit, log unit, and reporting unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit is realized by the control unit 46A of the smart device 14 and inputs knowledge and information that a character should have into a knowledge database. The setting unit is realized by the specific processing unit 290 of the data processing device 12 and sets the character's personality, speech style, and behavior pattern. The adjustment unit is realized by the control unit 46A of the smart device 14 and adjusts the character's voice characteristics and speech pattern. The event unit is realized by the specific processing unit 290 of the data processing device 12 and holds time-limited events. The log unit is realized by the control unit 46A of the smart device 14 and records call logs. The reporting unit is realized by the specific processing unit 290 of the data processing device 12 and reports fraudulent use to an operator. === Hard Collateral 1-2 === Each of the multiple elements, including the input unit, setting unit, adjustment unit, event unit, log unit, and reporting unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit is realized by the control unit 46A of the smart glasses 214 and inputs knowledge and information that a character should have into a knowledge database. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets the character's personality, speech style, and behavior pattern. The adjustment unit is realized, for example, by the control unit 46A of the smart glasses 214 and adjusts the character's voice characteristics and speech pattern. The event unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and holds time-limited events. The log unit is realized, for example, by the control unit 46A of the smart glasses 214 and records call logs. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports fraudulent use to an operator. === Hard Collateral 1-3 === Each of the multiple elements including the input unit, setting unit, adjustment unit, event unit, log unit, and reporting unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the input unit is realized by the control unit 46A of the headset terminal 314 and inputs knowledge and information that a character should have into a knowledge database. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets the character's personality, speech style, and behavior pattern. The adjustment unit is realized, for example, by the control unit 46A of the headset terminal 314 and adjusts the character's voice characteristics and speech pattern. The event unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and holds time-limited events. The log unit is realized, for example, by the control unit 46A of the headset terminal 314 and records call logs. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports fraudulent use to an operator. === Hard Collateral 1-4 === Each of the multiple elements including the input unit, setting unit, adjustment unit, event unit, log unit, and reporting unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit is realized by the control unit 46A of the robot 414 and inputs knowledge and information that the character should have into the knowledge database. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets the character's personality, speech style, and behavior pattern. The adjustment unit is realized, for example, by the control unit 46A of the robot 414 and adjusts the character's voice characteristics and speech pattern. The event unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and holds time-limited events. The log unit is realized, for example, by the control unit 46A of the robot 414 and records call logs. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports fraudulent use to an operator.

[0125] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0126] The conversation experience providing system can estimate the user's emotions and dynamically change the character's responses based on the estimated emotions. For example, if the user is sad, the character can offer comforting words. If the user is excited, the character can respond by empathizing and sharing the user's excitement. Furthermore, if the user is tired, the character can offer topics to help the user relax. This makes it possible to provide appropriate responses according to the user's emotions.

[0127] The conversation experience providing system can analyze the user's past conversation history and customize the character's responses based on the user's interests and concerns. For example, if the user has frequently talked about a particular topic in the past, the character can provide information related to that topic. Also, if the user has repeatedly asked a particular question in the past, the character can prepare a detailed answer to that question. Furthermore, the character's responses can be adjusted based on feedback provided by the user in the past. This makes it possible to provide responses based on the user's interests and concerns.

[0128] The conversation experience providing system can customize the character's response content by taking into account the user's geographical location information. For example, it can provide information related to the user's current location. It can also provide topics related to places the user has visited in the past. It can also provide information related to places the user plans to visit in the future. This makes it possible to provide responses based on the user's geographical location information.

[0129] The conversation experience providing system can analyze a user's social media activity and customize the character's response content. For example, the character can provide related topics based on information shared by the user on social media. The character can also analyze the content of the user's social media posts and provide a response based on that content. Furthermore, the character can provide related information based on the activity of the user's friends on social media. This makes it possible to provide responses based on the user's social media activity.

[0130] The conversation experience providing system can estimate the user's emotions and adjust the character's tone of voice and speaking style based on the estimated emotions. For example, if the user is relaxed, the character can speak in a calm voice. If the user is excited, the character can speak in a lively voice. Furthermore, if the user is stressed, the character can speak in a soothing voice. This makes it possible to provide an appropriate tone of voice and speaking style according to the user's emotions.

[0131] The conversation experience providing system can adjust the content of the character's responses depending on the user's level of expertise. For example, if the user has specialized knowledge, the character will respond using a lot of technical jargon. On the other hand, if the user is a beginner, the character can respond by avoiding technical jargon. Furthermore, the character's responses can be made more detailed depending on the user's level of expertise. This makes it possible to provide appropriate responses according to the user's level of expertise.

[0132] The conversation experience providing system can estimate the user's emotions and adjust the character's behavior pattern based on the estimated emotions. For example, if the user is relaxed, the character will behave calmly. If the user is excited, the character can behave lively. Furthermore, if the user is stressed, the character can behave in a soothing manner. This makes it possible to provide an appropriate behavior pattern according to the user's emotions.

[0133] The conversation experience providing system can improve the content of the character's responses based on the user's past feedback. For example, the content of the character's responses can be optimized based on the user's past feedback. The system can also adjust the character's speaking style and behavior patterns by reflecting the user's past feedback. Furthermore, the system can customize the content of the character's responses based on the user's past feedback. This makes it possible to provide responses based on the user's past feedback.

[0134] The conversation experience providing system can estimate the user's emotions and prioritize the character's response content based on the estimated emotions. For example, if the user is excited, the character can prioritize stimulating topics. If the user is relaxed, the character can prioritize calming topics. Furthermore, if the user is stressed, the character can prioritize soothing topics. This makes it possible to prioritize the response content based on the user's emotions.

[0135] The conversation experience providing system can customize the character's response content based on the user's current areas of interest. For example, it can provide information related to topics that the user is currently interested in. It can also select the character's response content based on the user's current areas of interest. It can also provide related information based on the user's current search history. This makes it possible to provide responses based on the user's current areas of interest.

[0136] The processing flow of the second embodiment will be briefly explained below.

[0137] Step 1: The input unit inputs data into the knowledge database. The knowledge database contains, for example, the knowledge and information that a character should have. For example, in the case of a historical figure, information about the person's life and achievements is input. The input unit inputs, for example, text data into the knowledge database. The input unit can also input voice data and image data into the knowledge database. For example, the input unit converts voice data into text data using voice recognition technology and inputs the text data into the knowledge database. Step 2: The setting unit sets the character's persona based on the data input by the input unit. A persona defines the character's personality, speaking style, behavior patterns, etc. For example, the setting unit sets the character's personality. The setting unit can also set the character's speaking style. Furthermore, the setting unit can also set the character's behavior patterns. Step 3: The adjustment unit adjusts the voice synthesis data based on the persona set by the setting unit. The voice synthesis data includes the character's voice characteristics and speaking pattern. For example, the adjustment unit adjusts the character's voice tone. The adjustment unit can also adjust the character's speaking rhythm. Furthermore, the adjustment unit can also adjust the character's voice pitch.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0143] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0159] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0174] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0175] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0177] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0178] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0181] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0182] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0183] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0184] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0185] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0186] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0187] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0188] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0189] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0190] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0191] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0192] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0193] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0194] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0195] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0196] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0197] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0198] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0199] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0200] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0201] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0202] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0203] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0204] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0205] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0206] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0207] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0208] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0209] [Explanation of symbols]

[0210] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an input unit for inputting data into a knowledge database; a setting unit that sets a persona of a character based on the data input by the input unit; an adjustment unit that adjusts voice synthesis data based on the persona set by the setting unit; Equipped with A system characterized by:

2. Equipped with an event department that holds limited-time events 2. The system of claim 1.

3. Equipped with a logging section that records call logs 2. The system of claim 1.

4. Equipped with a reporting unit that reports fraudulent use to operators 2. The system of claim 1.

5. The input unit Enter the knowledge and information that the character should have into the knowledge database.

2. The system of claim 1.

6. The setting unit Set the character's personality, speech style, and behavior patterns 2. The system of claim 1.

7. The adjustment unit Adjust your character's voice characteristics and speaking patterns 2. The system of claim 1.

8. The input unit The system estimates the user's emotions and adjusts the timing of input to the knowledge database based on the estimated user emotions.

2. The system of claim 1.

Images