System

Abstract

An object of a system according to an embodiment is to objectively evaluate a degree of impression of a story and improve a story generation AI on the basis of the degree of impression.SOLUTION: A system includes a story generation part, a biological information collection part, an impression degree evaluation part, and a learning part. The story generating unit generates a story using the generated AI. The biological information collection unit collects biological information such as the facial expression, the pulse, and the amount of sweat of the reader. An impression degree evaluation part evaluates the impression degree of the story based on the biological information collected by the biological information collection part. The learning unit learns the generative AI based on a result of the degree of sensitivity evaluated by the sensitivity degree evaluating 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] Previous technology had the problem of not being able to objectively evaluate the emotional impact of a story and use that information to improve the story generation AI.

[0005] The system according to the embodiment aims to objectively evaluate the emotional impact of a story and use this to improve the story generation AI. [Means for solving the problem]

[0006] The system according to the embodiment includes a story generation unit, a biometric information collection unit, an emotional impact evaluation unit, and a learning unit. The story generation unit generates a story using a generation AI. The biometric information collection unit collects biometric information such as the reader's facial expression, pulse rate, and amount of sweat. The emotional impact evaluation unit evaluates the emotional impact of the story based on the biometric information collected by the biometric information collection unit. The learning unit trains the generation AI based on the emotional impact results evaluated by the emotional impact evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can objectively evaluate the emotional impact of a story and improve the story generation AI based on that evaluation. [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 story generation evaluation system according to an embodiment of the present invention uses a generation AI to create a story and evaluates how much that story moves people's hearts. This story generation evaluation system has a generation AI create a story and have multiple people read that story. During this process, biometric information such as the reader's facial expression, pulse rate, and amount of sweat is collected, and machine learning is used to evaluate the emotional impact of the story. Based on the evaluation results, the generation AI is trained to create an interesting story. This enables the story generation evaluation system to use the generation AI to create an interesting story that moves people's hearts.

[0029] A story generation and evaluation system according to an embodiment includes a story generation unit, a biometric information collection unit, an emotional impact evaluation unit, and a learning unit. The story generation unit generates a story using a generation AI. For example, the generation AI receives a prompt containing instructions from a user as input and generates a story based on the prompt. The generation AI can use a text generation AI such as GPT-3 or BERT. The biometric information collection unit collects biometric information such as the reader's facial expression, pulse rate, and sweat amount. For example, the facial expression is analyzed using a camera, the pulse rate is measured using a heart rate sensor, and the sweat amount is measured using an electrodermal activity sensor. The emotional impact evaluation unit evaluates the emotional impact of the story based on the biometric information collected by the biometric information collection unit. For example, a machine learning model is used to estimate the reader's emotions from changes in facial expression, pulse rate, sweat amount, etc., and evaluate the emotional impact of the story. The learning unit trains the generation AI based on the emotional impact evaluation results obtained by the emotional impact evaluation unit. For example, the learning unit extracts characteristics of stories that are highly emotional and trains the generation AI to learn these characteristics. As a result, the story generation evaluation system according to the embodiment can use the generation AI to create interesting stories that move people's hearts. For example, it is possible to generate stories that move readers to tears or stories that are so funny they can't stop laughing.

[0030] The story generation unit can input a prompt to elicit a specific emotion and generate scenes that induce emotional changes. For example, the story generation unit inputs a prompt to the generation AI such as "Please create a story that includes a moving scene," causing it to generate a story that includes a moving scene. For example, it generates a story that includes scenes depicting family reunions and friendship bonds. The story generation unit can also input a prompt to the generation AI such as "Please create a story that includes a tense scene," causing it to generate a story that includes a tense scene. For example, it can generate a story that incorporates elements of suspense or mystery. The story generation unit can also input a prompt to the generation AI such as "Please create a story that includes a humorous scene," causing it to generate a story that includes a humorous scene. For example, it can generate a story that incorporates comedic elements. In this way, by inputting a prompt to elicit a specific emotion and generating scenes that induce emotional changes, it is possible to increase the emotional impact of the story.

[0031] The story generation unit can study scenes from classic literature and movies of the past and generate stories that incorporate those elements. For example, the story generation unit could have the generation AI study classic literature of the past (such as the works of Shakespeare) and generate stories that incorporate those elements. For example, it could generate stories that depict tragic endings or deep human relationships. The story generation unit could also have the generation AI study classic movies of the past (such as "The Godfather") and generate stories that incorporate those elements. For example, it could generate stories with themes of family ties and betrayal. The story generation unit could also have the generation AI study classic anime of the past (such as "My Neighbor Totoro") and generate stories that incorporate those elements. For example, it could generate stories that include fantasy elements and heartwarming scenes. In this way, by learning scenes from classic literature and movies of the past and generating stories that incorporate those elements, the quality of the story can be improved.

[0032] The biometric information collection unit can additionally measure the dilation and constriction of the reader's pupils, allowing for a more detailed capture of emotional changes. For example, the biometric information collection unit measures the dilation and constriction of the reader's pupils in real time using a camera and analyzes emotional changes based on that data. For example, pupil dilation indicates excitement or surprise. The biometric information collection unit also uses a dedicated pupil measurement device to measure pupil changes and capture emotional changes in detail. For example, pupil constriction indicates a relaxed state. The biometric information collection unit also integrates pupil change data with other biometric information (e.g., pulse rate and sweat volume) to analyze emotional changes from multiple angles. For example, pupil dilation and an increase in pulse rate simultaneously indicate excitement. This allows for the additional measurement of the reader's pupil dilation and constriction to capture emotional changes in more detail, allowing for a more accurate assessment of the impact of a story.

[0033] The biometric information collection unit collects changes in the reader's voice tone and speaking style, and is able to evaluate changes in emotions from multiple angles. For example, the biometric information collection unit uses a microphone to collect the voice tone when the reader reads a story aloud, and analyzes changes in emotions based on that data. For example, a higher voice tone indicates excitement. The biometric information collection unit also analyzes changes in the reader's speaking style (for example, speaking speed and rhythm) to evaluate changes in emotions. For example, a faster speaking speed indicates nervousness. The biometric information collection unit also integrates data on voice tone and speaking style with other biometric information (for example, facial expression and pulse rate) to evaluate changes in emotions from multiple angles. For example, emotions can be identified by matching changes in voice tone with changes in facial expression. In this way, by collecting changes in the reader's voice tone and speaking style and evaluating changes in emotions from multiple angles, it is possible to more accurately evaluate the impact of a story.

[0034] The biometric information collection unit can additionally measure changes in the reader's sitting position and posture to capture changes in emotions. For example, the biometric information collection unit measures changes in the reader's sitting position and posture in real time using a camera and analyzes changes in emotions based on that data. For example, leaning forward indicates interest. The biometric information collection unit also uses a dedicated posture sensor to measure changes in sitting position and posture, capturing changes in emotions in detail. For example, a relaxed posture indicates a sense of security. The biometric information collection unit also integrates data on changes in sitting position and posture with other biometric information (e.g., pulse rate and amount of sweat) to analyze changes in emotions from multiple angles. For example, a simultaneous change in posture and an increase in pulse rate indicates excitement. In this way, by additionally measuring changes in the reader's sitting position and posture and capturing changes in emotions, the impact of a story can be more accurately evaluated.

[0035] The biometric information collection unit can collect biometric information from different devices to increase the diversity of data. For example, the biometric information collection unit uses a smartwatch to collect the reader's pulse rate and sweat rate in real time and analyze changes in emotion based on that data. For example, an increase in pulse rate indicates excitement. The biometric information collection unit also uses smartglasses to collect changes in the reader's pupils and eye movements in real time and analyze changes in emotion based on that data. For example, a fixed gaze indicates concentration. The biometric information collection unit also integrates biometric information collected from different devices to build a system that analyzes changes in emotion from multiple angles. For example, emotions can be identified by combining data from a smartwatch and smartglasses. In this way, biometric information can be collected from different devices to increase the diversity of data, making it possible to more accurately evaluate the impact of a story.

[0036] The emotional impact evaluation unit can feed back changes in the reader's emotions to the machine learning model in real time, thereby continuously improving the accuracy of the model. For example, the emotional impact evaluation unit feeds back data on changes in the reader's emotions to the machine learning model in real time, thereby improving the accuracy of the model. For example, the model is trained based on data on the reader's smiles and tears. The emotional impact evaluation unit also uses the emotional data collected in real time to dynamically adjust the parameters of the machine learning model, thereby improving the accuracy of the emotional impact evaluation. For example, the model is optimized based on data on changes in pulse rate. The emotional impact evaluation unit also builds a system that analyzes data on changes in the reader's emotions in real time and feeds the results back to the machine learning model. For example, it focuses on learning data from emotional peaks. In this way, changes in the reader's emotions are fed back to the machine learning model in real time, thereby continuously improving the accuracy of the model, making it possible to more accurately evaluate the emotional impact of a story.

[0037] The emotional impact evaluation unit can refer to the reader's past emotional data and take into account individual emotional tendencies when evaluating the emotional impact. The emotional impact evaluation unit, for example, refers to the reader's past emotional data and evaluates the emotional impact by taking into account individual emotional tendencies. For example, the evaluation is made based on data on scenes that moved the reader in the past. The emotional impact evaluation unit also analyzes the reader's emotional history and builds a machine learning model that reflects individual emotional tendencies. For example, if a particular reader shows strong emotions toward a particular genre, this tendency is incorporated into the model. The emotional impact evaluation unit also uses the past emotional data to profile the emotional tendencies of each reader and builds a system that evaluates the emotional impact based on this profile. For example, the evaluation is made by taking into account the intensity and frequency of emotions. In this way, by referring to the reader's past emotional data and taking into account individual emotional tendencies when evaluating the emotional impact, the emotional impact of a story can be more accurately evaluated.

[0038] The impact assessment unit can assess emotional changes from multiple angles using reader data from different age groups and genders when assessing the impact. The impact assessment unit, for example, uses reader data from different age groups to assess the impact. For example, it analyzes differences in emotional responses between children and adults and reflects this in the assessment. The impact assessment unit also takes gender differences into account when assessing the impact. For example, it analyzes differences in emotional responses between men and women and reflects this in the assessment. The impact assessment unit also comprehensively analyzes data from age groups and genders to build a system that assesses emotional changes from multiple angles. For example, it incorporates emotional responses specific to specific age groups and genders into a model. This allows for a more accurate assessment of the impact of a story by assessing emotional changes from multiple angles using reader data from different age groups and genders.

[0039] The emotional impact evaluation unit can compare the evaluation result of the emotional impact with other entertainment content and relatively evaluate the emotional impact of the story. For example, the emotional impact evaluation unit compares the evaluation result of the emotional impact of the story with the evaluation result of the emotional impact of a movie to perform a relative evaluation. For example, it compares a movie and a story with the same emotional impact score. The emotional impact evaluation unit also compares the evaluation result of the emotional impact of music with the evaluation result of the emotional impact of a story to perform a relative evaluation. For example, it compares the emotional responses of emotional music with those of a story. The emotional impact evaluation unit also constructs a system that comprehensively analyzes the evaluation results of the emotional impact of other entertainment content (e.g., a play or a game) and the evaluation result of the emotional impact of a story to perform a relative evaluation. For example, it analyzes the differences in emotional responses between different content. In this way, the quality of the story can be improved by comparing the evaluation result of the emotional impact with other entertainment content and relatively evaluating the emotional impact of the story.

[0040] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0041] The story generation unit can generate individually customized stories based on the user's past reading history. For example, it can analyze the genres and themes of stories the user has read in the past and generate new stories based on those tendencies. Also, if the user has a preference for a particular author or style, it can generate a story that incorporates those elements. It can also extract moving scenes and character characteristics from the user's reading history and generate a story that reflects them. This can increase reader satisfaction by providing stories that match the user's preferences.

[0042] The story generation unit can generate stories that incorporate elements of different cultures and languages. For example, it can study folk tales and legends from different countries and generate stories based on them. It can also generate stories that incorporate expressions and phrases from different languages. It can also generate stories that include scenes that reflect the customs and habits of different cultures. This allows the system to provide readers with new perspectives and knowledge by providing stories that incorporate elements of different cultures and languages.

[0043] The story generation unit can generate a story based on information about the user's current environment. For example, it can acquire the user's current location and weather information and generate a story that includes scenes based on that information. It can also generate a story that incorporates information about the sound and light around the user. It can also generate a story that takes into account the user's device usage status and the time of day. This allows for a more immersive reading experience by providing a story that is tailored to the user's current environment.

[0044] The story generation unit can adjust the progress of the story according to the user's reading speed. For example, if the user reads quickly, the story can be accelerated. On the other hand, if the user reads slowly, the story can be slowed down. Furthermore, it is possible to add or omit detailed descriptions and explanations of the story according to the user's reading speed. This reduces the burden on the reader by providing a story that matches the user's reading speed, making it possible to provide a more comfortable reading experience.

[0045] The story generation unit can generate a story while playing music that the user likes in the background. For example, if the user wants to relax, the story can be generated while playing calm music in the background. If the user wants to get excited, the story can be generated while playing up-tempo music in the background. Furthermore, if the user wants to be moved, the story can be generated while playing moving music in the background. This makes it possible to provide a story while playing music that the user likes in the background, thereby enriching the reading experience.

[0046] The story generation unit can customize the visual elements of a story according to the user's visual preferences. For example, if a user has a preference for a particular color or style, the unit can generate visuals that incorporate those elements. Also, if a user has a preference for a particular art style or the work of an illustrator, the unit can generate visuals that reflect that style. Furthermore, the unit can customize the design of story scenes and characters according to the user's visual preferences. This can increase reader satisfaction by providing a story that matches the user's visual preferences.

[0047] The story generation unit can modify the story in real time based on user feedback. For example, if a user provides feedback on a specific scene or character, the story is modified based on that feedback. Also, if a user gives an opinion on the progression of the story, the story can be adjusted to reflect that opinion. Furthermore, it is also possible to change the ending of the story based on user feedback. In this way, by modifying the story in real time based on user feedback, it is possible to provide a story that reflects the reader's opinions.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The story generation unit generates a story using a generation AI. For example, the generation AI receives a prompt containing instructions from a user as input and generates a story based on the prompt. The generation AI can use a text generation AI such as GPT-3 or BERT. Step 2: The biometric information collection unit collects biometric information such as the reader's facial expression, pulse rate, and sweat rate. For example, facial expression is analyzed using a camera, pulse rate is measured using a heart rate sensor, and sweat rate is measured using an electrodermal activity sensor. Step 3: The emotional impact assessment unit assesses the emotional impact of the story based on the biometric information collected by the biometric information collection unit. For example, a machine learning model can be used to estimate the reader's emotions from changes in facial expressions, pulse rate, sweat volume, etc., and assess the emotional impact of the story. Step 4: The learning unit trains the generation AI based on the emotional impact assessment results from the emotional impact assessment unit. For example, it extracts the characteristics of stories that are highly emotional and trains the generation AI to learn those characteristics.

[0050] (Example 2) A story generation evaluation system according to an embodiment of the present invention uses a generation AI to create a story and evaluates how much that story moves people's hearts. This story generation evaluation system has a generation AI create a story and have multiple people read that story. During this process, biometric information such as the reader's facial expression, pulse rate, and amount of sweat is collected, and machine learning is used to evaluate the emotional impact of the story. Based on the evaluation results, the generation AI is trained to create an interesting story. This enables the story generation evaluation system to use the generation AI to create an interesting story that moves people's hearts.

[0051] A story generation and evaluation system according to an embodiment includes a story generation unit, a biometric information collection unit, an emotional impact evaluation unit, and a learning unit. The story generation unit generates a story using a generation AI. For example, the generation AI receives a prompt containing instructions from a user as input and generates a story based on the prompt. The generation AI can use a text generation AI such as GPT-3 or BERT. The biometric information collection unit collects biometric information such as the reader's facial expression, pulse rate, and sweat amount. For example, the facial expression is analyzed using a camera, the pulse rate is measured using a heart rate sensor, and the sweat amount is measured using an electrodermal activity sensor. The emotional impact evaluation unit evaluates the emotional impact of the story based on the biometric information collected by the biometric information collection unit. For example, a machine learning model is used to estimate the reader's emotions from changes in facial expression, pulse rate, sweat amount, etc., and evaluate the emotional impact of the story. The learning unit trains the generation AI based on the emotional impact evaluation results obtained by the emotional impact evaluation unit. For example, the learning unit extracts characteristics of stories that are highly emotional and trains the generation AI to learn these characteristics. As a result, the story generation evaluation system according to the embodiment can use the generation AI to create interesting stories that move people's hearts. For example, it is possible to generate stories that move readers to tears or stories that are so funny they can't stop laughing.

[0052] The story generation unit can input a prompt to elicit a specific emotion and generate scenes that induce emotional changes. For example, the story generation unit inputs a prompt to the generation AI such as "Please create a story that includes a moving scene," causing it to generate a story that includes a moving scene. For example, it generates a story that includes scenes depicting family reunions and friendship bonds. The story generation unit can also input a prompt to the generation AI such as "Please create a story that includes a tense scene," causing it to generate a story that includes a tense scene. For example, it can generate a story that incorporates elements of suspense or mystery. The story generation unit can also input a prompt to the generation AI such as "Please create a story that includes a humorous scene," causing it to generate a story that includes a humorous scene. For example, it can generate a story that incorporates comedic elements. In this way, by inputting a prompt to elicit a specific emotion and generating scenes that induce emotional changes, it is possible to increase the emotional impact of the story.

[0053] The story generation unit can study scenes from classic literature and movies of the past and generate stories that incorporate those elements. For example, the story generation unit could have the generation AI study classic literature of the past (such as the works of Shakespeare) and generate stories that incorporate those elements. For example, it could generate stories that depict tragic endings or deep human relationships. The story generation unit could also have the generation AI study classic movies of the past (such as "The Godfather") and generate stories that incorporate those elements. For example, it could generate stories with themes of family ties and betrayal. The story generation unit could also have the generation AI study classic anime of the past (such as "My Neighbor Totoro") and generate stories that incorporate those elements. For example, it could generate stories that include fantasy elements and heartwarming scenes. In this way, by learning scenes from classic literature and movies of the past and generating stories that incorporate those elements, the quality of the story can be improved.

[0054] The story generation unit can use the emotion estimation function to generate a prompt based on the user's emotion and generate a story based on the prompt. For example, the story generation unit can use the emotion estimation function to generate a prompt such as "Create an emotional story" when the user is moved, and generate a story based on the prompt. The story generation unit can also use the emotion estimation function to generate a prompt such as "Create an action-packed story" when the user is excited, and generate a story based on the prompt. The story generation unit can also use the emotion estimation function to generate a prompt such as "Create a heartwarming story" when the user is relaxed, and generate a story based on the prompt. In this way, by using the emotion estimation function to generate a prompt based on the user's emotion and generating a story based on the prompt, it is possible to provide a story that corresponds to the user's emotion.

[0055] The biometric information collection unit can additionally measure the dilation and constriction of the reader's pupils, allowing for a more detailed capture of emotional changes. For example, the biometric information collection unit measures the dilation and constriction of the reader's pupils in real time using a camera and analyzes emotional changes based on that data. For example, pupil dilation indicates excitement or surprise. The biometric information collection unit also uses a dedicated pupil measurement device to measure pupil changes and capture emotional changes in detail. For example, pupil constriction indicates a relaxed state. The biometric information collection unit also integrates pupil change data with other biometric information (e.g., pulse rate and sweat volume) to analyze emotional changes from multiple angles. For example, pupil dilation and an increase in pulse rate simultaneously indicate excitement. This allows for the additional measurement of the reader's pupil dilation and constriction to capture emotional changes in more detail, allowing for a more accurate assessment of the impact of a story.

[0056] The biometric information collection unit collects changes in the reader's voice tone and speaking style, and is able to evaluate changes in emotions from multiple angles. For example, the biometric information collection unit uses a microphone to collect the voice tone when the reader reads a story aloud, and analyzes changes in emotions based on that data. For example, a higher voice tone indicates excitement. The biometric information collection unit also analyzes changes in the reader's speaking style (for example, speaking speed and rhythm) to evaluate changes in emotions. For example, a faster speaking speed indicates nervousness. The biometric information collection unit also integrates data on voice tone and speaking style with other biometric information (for example, facial expression and pulse rate) to evaluate changes in emotions from multiple angles. For example, emotions can be identified by matching changes in voice tone with changes in facial expression. In this way, by collecting changes in the reader's voice tone and speaking style and evaluating changes in emotions from multiple angles, it is possible to more accurately evaluate the impact of a story.

[0057] The biometric information collection unit can use the emotion estimation function to estimate changes in emotions in real time from the reader's biometric information and collect the data. For example, the biometric information collection unit uses the emotion estimation function to estimate changes in emotions in real time from the reader's facial expressions and pulse rate and collect the data. For example, an increase in smiles indicates joy. The biometric information collection unit also uses the emotion estimation function to estimate changes in emotions in real time from the reader's sweat amount and changes in pupil size and collect the data. For example, an increase in sweat amount indicates tension. The biometric information collection unit also uses the emotion estimation function to comprehensively analyze the reader's biometric information and build a system that estimates changes in emotions in real time. For example, emotions are identified by combining multiple pieces of biometric information. In this way, by using the emotion estimation function to estimate changes in emotions in real time from the reader's biometric information and collecting the data, the impact of a story can be more accurately evaluated.

[0058] The biometric information collection unit can additionally measure changes in the reader's sitting position and posture to capture changes in emotions. For example, the biometric information collection unit measures changes in the reader's sitting position and posture in real time using a camera and analyzes changes in emotions based on that data. For example, leaning forward indicates interest. The biometric information collection unit also uses a dedicated posture sensor to measure changes in sitting position and posture, capturing changes in emotions in detail. For example, a relaxed posture indicates a sense of security. The biometric information collection unit also integrates data on changes in sitting position and posture with other biometric information (e.g., pulse rate and amount of sweat) to analyze changes in emotions from multiple angles. For example, a simultaneous change in posture and an increase in pulse rate indicates excitement. In this way, by additionally measuring changes in the reader's sitting position and posture and capturing changes in emotions, the impact of a story can be more accurately evaluated.

[0059] The biometric information collection unit can collect biometric information from different devices to increase the diversity of data. For example, the biometric information collection unit uses a smartwatch to collect the reader's pulse rate and sweat rate in real time and analyze changes in emotion based on that data. For example, an increase in pulse rate indicates excitement. The biometric information collection unit also uses smartglasses to collect changes in the reader's pupils and eye movements in real time and analyze changes in emotion based on that data. For example, a fixed gaze indicates concentration. The biometric information collection unit also integrates biometric information collected from different devices to build a system that analyzes changes in emotion from multiple angles. For example, emotions can be identified by combining data from a smartwatch and smartglasses. In this way, biometric information can be collected from different devices to increase the diversity of data, making it possible to more accurately evaluate the impact of a story.

[0060] The biometric information collection unit uses the emotion estimation function to estimate changes in emotion from the reader's biometric information and compare the data with other readers, thereby identifying common emotional patterns. The biometric information collection unit, for example, uses the emotion estimation function to estimate changes in emotion from the reader's facial expressions and pulse rate and compares the data with other readers. For example, a common emotional pattern can be identified by many readers smiling in the same scene. The biometric information collection unit also uses the emotion estimation function to estimate changes in emotion from the reader's sweat volume and pupil changes and compares the data with other readers. For example, a common emotional pattern can be identified by many readers sweating in the same scene. The biometric information collection unit also uses the emotion estimation function to comprehensively analyze the reader's biometric information and build a system to identify common emotional patterns. For example, multiple pieces of biometric information can be combined to identify common emotional reactions in a specific scene. As a result, a common emotional pattern can be identified by using the emotion estimation function to estimate changes in emotion from the reader's biometric information and comparing the data with other readers.

[0061] The emotional impact evaluation unit can feed back changes in the reader's emotions to the machine learning model in real time, thereby continuously improving the accuracy of the model. For example, the emotional impact evaluation unit feeds back data on changes in the reader's emotions to the machine learning model in real time, thereby improving the accuracy of the model. For example, the model is trained based on data on the reader's smiles and tears. The emotional impact evaluation unit also uses the emotional data collected in real time to dynamically adjust the parameters of the machine learning model, thereby improving the accuracy of the emotional impact evaluation. For example, the model is optimized based on data on changes in pulse rate. The emotional impact evaluation unit also builds a system that analyzes data on changes in the reader's emotions in real time and feeds the results back to the machine learning model. For example, it focuses on learning data from emotional peaks. In this way, changes in the reader's emotions are fed back to the machine learning model in real time, thereby continuously improving the accuracy of the model, making it possible to more accurately evaluate the emotional impact of a story.

[0062] The emotional impact evaluation unit can refer to the reader's past emotional data and take into account individual emotional tendencies when evaluating the emotional impact. The emotional impact evaluation unit, for example, refers to the reader's past emotional data and evaluates the emotional impact by taking into account individual emotional tendencies. For example, the evaluation is made based on data on scenes that moved the reader in the past. The emotional impact evaluation unit also analyzes the reader's emotional history and builds a machine learning model that reflects individual emotional tendencies. For example, if a particular reader shows strong emotions toward a particular genre, this tendency is incorporated into the model. The emotional impact evaluation unit also uses the past emotional data to profile the emotional tendencies of each reader and builds a system that evaluates the emotional impact based on this profile. For example, the evaluation is made by taking into account the intensity and frequency of emotions. In this way, by referring to the reader's past emotional data and taking into account individual emotional tendencies when evaluating the emotional impact, the emotional impact of a story can be more accurately evaluated.

[0063] The emotional impact evaluation unit can use the emotion estimation function to evaluate changes in the reader's emotions in real time and train a machine learning model based on that data. The emotional impact evaluation unit, for example, uses the emotion estimation function to evaluate changes in emotions in real time from the reader's facial expressions and pulse rate, and trains the machine learning model based on that data. For example, the model is optimized using data on smiles and tears. The emotional impact evaluation unit also uses the emotion data collected in real time to dynamically adjust the parameters of the machine learning model and improve the accuracy of the emotional impact evaluation. For example, the model is optimized based on pulse rate change data. The emotional impact evaluation unit also builds a system that analyzes data on changes in the reader's emotions in real time and feeds the results back to the machine learning model. For example, data at the peak of emotions is focused on learning. In this way, by using the emotion estimation function to evaluate changes in the reader's emotions in real time and training the machine learning model based on that data, it is possible to more accurately evaluate the emotional impact of a story.

[0064] The impact assessment unit can assess emotional changes from multiple angles using reader data from different age groups and genders when assessing the impact. The impact assessment unit, for example, uses reader data from different age groups to assess the impact. For example, it analyzes differences in emotional responses between children and adults and reflects this in the assessment. The impact assessment unit also takes gender differences into account when assessing the impact. For example, it analyzes differences in emotional responses between men and women and reflects this in the assessment. The impact assessment unit also comprehensively analyzes data from age groups and genders to build a system that assesses emotional changes from multiple angles. For example, it incorporates emotional responses specific to specific age groups and genders into a model. This allows for a more accurate assessment of the impact of a story by assessing emotional changes from multiple angles using reader data from different age groups and genders.

[0065] The emotional impact evaluation unit can compare the evaluation result of the emotional impact with other entertainment content and relatively evaluate the emotional impact of the story. For example, the emotional impact evaluation unit compares the evaluation result of the emotional impact of the story with the evaluation result of the emotional impact of a movie to perform a relative evaluation. For example, it compares a movie and a story with the same emotional impact score. The emotional impact evaluation unit also compares the evaluation result of the emotional impact of music with the evaluation result of the emotional impact of a story to perform a relative evaluation. For example, it compares the emotional responses of emotional music with those of a story. The emotional impact evaluation unit also constructs a system that comprehensively analyzes the evaluation results of the emotional impact of other entertainment content (e.g., a play or a game) and the evaluation result of the emotional impact of a story to perform a relative evaluation. For example, it analyzes the differences in emotional responses between different content. In this way, the quality of the story can be improved by comparing the evaluation result of the emotional impact with other entertainment content and relatively evaluating the emotional impact of the story.

[0066] The emotional impact evaluation unit can use the emotion estimation function to evaluate changes in the reader's emotions and provide feedback to the generation of a new story based on that data. For example, the emotional impact evaluation unit uses the emotion estimation function to evaluate changes in emotions from the reader's facial expressions and pulse rate and provides feedback to the generation of a new story based on that data. For example, the next story is generated based on data from moving scenes. The emotional impact evaluation unit also builds a system that collects data on changes in the reader's emotions in real time and feeds the results back to the generation AI. For example, it improves a story based on data at the peak of emotions. The emotional impact evaluation unit also identifies the elements that most move the reader based on the emotion estimation data and generates a new story that incorporates those elements. For example, it incorporates a moving ending or humorous characters. In this way, the quality of a story can be improved by using the emotion estimation function to evaluate changes in the reader's emotions and providing feedback to the generation of a new story based on that data.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The story generation unit can generate individually customized stories based on the user's past reading history. For example, it can analyze the genres and themes of stories the user has read in the past and generate new stories based on those tendencies. Also, if the user has a preference for a particular author or style, it can generate a story that incorporates those elements. It can also extract moving scenes and character characteristics from the user's reading history and generate a story that reflects them. This can increase reader satisfaction by providing stories that match the user's preferences.

[0069] The story generation unit can generate stories that incorporate elements of different cultures and languages. For example, it can study folk tales and legends from different countries and generate stories based on them. It can also generate stories that incorporate expressions and phrases from different languages. It can also generate stories that include scenes that reflect the customs and habits of different cultures. This allows the system to provide readers with new perspectives and knowledge by providing stories that incorporate elements of different cultures and languages.

[0070] The story generation unit can generate a story based on information about the user's current environment. For example, it can acquire the user's current location and weather information and generate a story that includes scenes based on that information. It can also generate a story that incorporates information about the sound and light around the user. It can also generate a story that takes into account the user's device usage status and the time of day. This allows for a more immersive reading experience by providing a story that is tailored to the user's current environment.

[0071] The story generation unit can use the emotion estimation function to generate character dialogue based on the user's emotions. For example, if the user is sad, the story generation unit can generate dialogue in which the character comforts the user. Also, if the user is excited, the story generation unit can generate dialogue in which the character empathizes with the user. Furthermore, if the user is relaxed, the story generation unit can generate dialogue in which the character is calm. This can increase the sense of immersion in the story by providing character dialogue that corresponds to the user's emotions.

[0072] The story generation unit can predict emotional changes based on the user's past emotional data and generate a story accordingly. For example, based on data of scenes that moved the user in the past, a story including scenes that evoke similar emotions can be generated. Also, based on data of scenes that excited the user in the past, a story including scenes that evoke similar excitement can be generated. Furthermore, based on data of scenes that relaxed the user in the past, a story including scenes that evoke similar relaxation can be generated. In this way, by predicting emotional changes based on the user's past emotional data and providing a story that evokes the changes, it is possible to provide a story that is in tune with the reader's emotions.

[0073] The story generation unit can adjust the progress of the story according to the user's reading speed. For example, if the user reads quickly, the story can be accelerated. On the other hand, if the user reads slowly, the story can be slowed down. Furthermore, it is possible to add or omit detailed descriptions and explanations of the story according to the user's reading speed. This reduces the burden on the reader by providing a story that matches the user's reading speed, making it possible to provide a more comfortable reading experience.

[0074] The story generation unit can generate a story while playing music that the user likes in the background. For example, if the user wants to relax, the story can be generated while playing calm music in the background. If the user wants to get excited, the story can be generated while playing up-tempo music in the background. Furthermore, if the user wants to be moved, the story can be generated while playing moving music in the background. This makes it possible to provide a story while playing music that the user likes in the background, thereby enriching the reading experience.

[0075] The story generation unit can customize the visual elements of a story according to the user's visual preferences. For example, if a user has a preference for a particular color or style, the unit can generate visuals that incorporate those elements. Also, if a user has a preference for a particular art style or the work of an illustrator, the unit can generate visuals that reflect that style. Furthermore, the unit can customize the design of story scenes and characters according to the user's visual preferences. This can increase reader satisfaction by providing a story that matches the user's visual preferences.

[0076] The story generation unit can modify the story in real time based on user feedback. For example, if a user provides feedback on a specific scene or character, the story is modified based on that feedback. Also, if a user gives an opinion on the progression of the story, the story can be adjusted to reflect that opinion. Furthermore, it is also possible to change the ending of the story based on user feedback. In this way, by modifying the story in real time based on user feedback, it is possible to provide a story that reflects the reader's opinions.

[0077] The story generation unit can use the emotion estimation function to generate a story ending based on the user's emotions. For example, if the user is moved, an emotional ending can be generated. If the user is excited, an action-packed ending can be generated. Furthermore, if the user is relaxed, a calm ending can be generated. In this way, by using the emotion estimation function to provide a story ending based on the user's emotions, a story that is in tune with the reader's emotions can be provided.

[0078] The processing flow of the second embodiment will be briefly explained below.

[0079] Step 1: The story generation unit generates a story using a generation AI. For example, the generation AI receives a prompt containing instructions from a user as input and generates a story based on the prompt. The generation AI can use a text generation AI such as GPT-3 or BERT. Step 2: The biometric information collection unit collects biometric information such as the reader's facial expression, pulse rate, and sweat rate. For example, facial expression is analyzed using a camera, pulse rate is measured using a heart rate sensor, and sweat rate is measured using an electrodermal activity sensor. Step 3: The emotional impact assessment unit assesses the emotional impact of the story based on the biometric information collected by the biometric information collection unit. For example, a machine learning model can be used to estimate the reader's emotions from changes in facial expressions, pulse rate, sweat volume, etc., and assess the emotional impact of the story. Step 4: The learning unit trains the generation AI based on the emotional impact assessment results from the emotional impact assessment unit. For example, it extracts the characteristics of stories that are highly emotional and trains the generation AI to learn those characteristics.

[0080] 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.

[0081] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0082] 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.

[0083] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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).

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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 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.

[0097] 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.

[0098] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0099] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0109] 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.

[0110] 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.

[0111] 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 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.

[0112] 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.

[0113] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0114] 7, the 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] In the robot 414, 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 robot 414 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.

[0125] 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.

[0126] 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.

[0127] 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 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0134] 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."

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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. [Explanation of symbols]

[0147] 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. a story generation unit that generates a story using a generation AI; A biometric information collection unit that collects biometric information such as the reader's facial expression, pulse rate, and amount of sweat. an emotional impact evaluation unit that evaluates the emotional impact of a story based on the biometric information collected by the biometric information collection unit; a learning unit that trains a generation AI based on the emotional impact result evaluated by the emotional impact evaluation unit. A system characterized by:

2. The story generation unit Enter a prompt to elicit a specific emotion and generate a scene that induces a change in that emotion.

2. The system of claim 1.

3. The story generation unit Learn scenes from classic literature and movies and generate stories incorporating those elements 2. The system of claim 1.

4. The story generation unit Generate prompts based on the user's emotions and generate a story based on those prompts 2. The system of claim 1.

5. The biological information collection unit The reader's pupil dilation and contraction are additionally measured to capture more detailed changes in emotion.

2. The system of claim 1.

6. The biological information collection unit Collect changes in the reader's tone of voice and speaking style to evaluate changes in emotions from multiple angles 2. The system of claim 1.

Images