System

Abstract

An object of the system according to the embodiment is to quickly extract a consultation with high urgency in a consultation about bullying damage and to take an appropriate response.SOLUTION: A system according to an embodiment includes a text-data acquiring unit, a generated AI analyzing unit, an urgency determining unit, and a reporting unit. The text data acquisition unit acquires text data sent to the consultation window. The generated AI analyzing unit analyzes the text data acquired by the text data acquiring unit. The urgency determination unit determines urgency of the AI analyzed by the generation data analysis unit. The reporting section reports the consultation determined to be urgent by the urgency determination section to the Board of Education or the third party committee.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] With conventional technology, there was a problem in that it was difficult to quickly identify urgent consultations regarding bullying victimization and to provide appropriate responses.

[0005] The system according to the embodiment aims to quickly extract urgent consultations regarding bullying victims and to respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a text data acquisition unit, a generation AI analysis unit, an urgency determination unit, and a reporting unit. The text data acquisition unit acquires text data submitted to the consultation desk. The generation AI analysis unit analyzes the text data acquired by the text data acquisition unit. The urgency determination unit determines the urgency of the text data analyzed by the generation AI analysis unit. The reporting unit reports consultations that are determined to be highly urgent by the urgency determination unit to the board of education or a third-party committee. [Effects of the Invention]

[0007] The system according to the embodiment can quickly extract urgent consultations regarding bullying victimization and respond appropriately. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The bullying victim consultation system according to an embodiment of the present invention automatically analyzes text data received at the consultation desk, and a generation AI extracts and reports important information and urgent inquiries. This allows bullying victim consultations to be made anonymously, reducing the mental burden on victims and enabling prompt and appropriate responses.

[0029] A bullying victim consultation system according to an embodiment includes a text data acquisition unit, a generation AI analysis unit, an urgency determination unit, and a reporting unit. The text data acquisition unit acquires text data submitted to the consultation service. For example, the text data can be acquired in the form of email, chat message, or social media post. Furthermore, the text data acquisition unit allows bullying victims to anonymously input their consultation details using a dedicated terminal. The generation AI analysis unit analyzes the text data acquired by the text data acquisition unit. For example, the generation AI analyzes the text data using natural language processing technology to extract important information and urgent consultations. The generation AI can also analyze the content of the text data using a text generation AI (e.g., LLM). Furthermore, the generation AI can analyze the content of the text data using a multimodal generation AI. The urgency determination unit determines the urgency of the text data analyzed by the generation AI analysis unit. For example, the urgency determination unit determines whether a situation requires immediate action or whether there is a life-threatening situation based on the content of the text data. The urgency determination unit can also determine the urgency based on important information extracted by the generation AI. The reporting unit reports consultations that are determined by the urgency determination unit to be highly urgent to the board of education or a third-party committee. For example, the reporting unit automatically sends the content of consultations that are highly urgent to the board of education or a third-party committee. The reporting unit can also build a system for quickly reporting consultation content that is highly urgent. As a result, the bullying victim consultation system according to the embodiment allows victims of bullying to consult anonymously and quickly report consultations that are highly urgent. For example, if a victim of bullying consults anonymously, the generation AI analyzes the content and reports it to the board of education or a third-party committee if it is highly urgent, a prompt response is possible. Furthermore, the lack of a response reduces mental stress.

[0030] When analyzing text data, the generative AI analysis unit learns bullying patterns and trends, enabling more accurate urgency judgments. For example, the generative AI may study past bullying consultation data to understand bullying patterns and trends. For example, if a specific word or phrase appears frequently, the urgency is judged based on that pattern. The generative AI analysis unit can also use machine learning models to learn bullying patterns and trends. For example, the generative AI may learn bullying patterns and trends based on past case data to improve the accuracy of urgency judgments. In this way, learning bullying patterns and trends improves the accuracy of urgency judgments.

[0031] When analyzing text data, the generative AI analysis unit can attempt to identify bullies and analyze their behavioral patterns. For example, when the generative AI analyzes text data, it uses an algorithm to identify bullies. For example, if a particular name or nickname appears frequently, that person can be identified as the bully. The generative AI analysis unit can also build a system to analyze the behavioral patterns of bullies. For example, the generative AI can analyze behavioral patterns in text data to identify the behavior of the bully. Furthermore, the generative AI analysis unit can develop an algorithm to analyze the behavioral patterns of bullies. For example, if a particular behavioral pattern is repeated, the perpetrator can be identified based on that behavior. This makes it possible to prevent and take measures against bullying by identifying perpetrators and analyzing their behavioral patterns.

[0032] When analyzing text data, the generative AI analysis unit simultaneously analyzes audio data or image data, allowing for the collection of evidence of bullying from multiple angles. For example, the generative AI analyzes audio data along with text data to collect evidence of bullying. For example, it detects threatening or insulting language in audio data. The generative AI analysis unit can also analyze image data to build a system for collecting evidence of bullying. For example, it can detect evidence of bullying in image data. Furthermore, the generative AI analysis unit can develop algorithms for analyzing audio data and image data. For example, it can use voice recognition technology and image analysis technology to collect evidence of bullying from multiple angles. This allows for the collection of evidence of bullying from multiple angles by analyzing audio data and image data.

[0033] When analyzing text data, the generative AI analysis unit can also analyze text data in different languages ​​to provide a multilingual bullying hotline. The generative AI analysis unit, for example, uses an algorithm that allows the generative AI to analyze text data in different languages. For example, it analyzes text data in English, Spanish, Chinese, etc. to determine the urgency. The generative AI analysis unit can also build a system for providing a multilingual bullying hotline. For example, it can automatically translate and analyze text data in different languages. Furthermore, the generative AI analysis unit can also develop an algorithm for analyzing text data in different languages. For example, it can use machine translation technology to analyze text data in different languages. In this way, a multilingual bullying hotline can be provided by analyzing text data in different languages.

[0034] When extracting highly urgent consultations, the urgency determination unit can refer to past consultation data and compare it with similar cases to determine the urgency. For example, the urgency determination unit uses an algorithm in which the generation AI refers to past consultation data and compares it with similar cases to determine the urgency. For example, it compares the content of past highly urgent consultations with the content of the current consultation. The urgency determination unit can also build a system for referencing past consultation data. For example, it can store past consultation history in a database and reference it as needed. Furthermore, the urgency determination unit can develop an algorithm for determining the urgency by comparing it with similar cases. For example, it can calculate the similarity between the content of past consultations and the content of the current consultation to determine the urgency. In this way, by referring to past consultation data, the urgency determination becomes more accurate.

[0035] When extracting consultations with high urgency, the urgency determination unit can analyze the victim's location information and grasp bullying trends by region. For example, the urgency determination unit uses a generation AI to analyze the victim's location information and build a system to grasp bullying trends by region. For example, if there are many bullying consultations in a particular region, the urgency of that region can be rated high. The urgency determination unit can also develop an algorithm for analyzing location information. For example, it can use GPS data or location information services to obtain and analyze the victim's location information. Furthermore, the urgency determination unit can also build a system to grasp bullying trends by region. For example, it can aggregate bullying consultation data by region and analyze the trends. In this way, by analyzing the victim's location information, it can grasp bullying trends by region.

[0036] When extracting highly urgent consultations, the urgency determination unit can integrate information from other data sources to make a more comprehensive urgency determination. For example, the urgency determination unit builds a system in which the generative AI collects information from social media and message boards and integrates it when extracting highly urgent consultations. For example, it analyzes posts about bullying on social media and determines the urgency. The urgency determination unit can also develop algorithms for integrating information from other data sources. For example, it can analyze social media data and message board data to determine the urgency. Furthermore, the urgency determination unit can build a system for integrating information from other data sources. For example, it can centrally manage information from multiple data sources and determine the urgency. This makes the urgency determination more comprehensive by integrating information from other data sources.

[0037] When extracting consultations with high urgency, the urgency determination unit can compare data from different educational institutions or regions and propose anti-bullying measures for each region. For example, the generation AI of the urgency determination unit compares data from different educational institutions or regions and builds a system that proposes anti-bullying measures for each region. For example, if there are many bullying consultations in a particular region, it will propose measures specific to that region. The urgency determination unit can also develop an algorithm for comparing data from different educational institutions or regions. For example, it can compare data by school or by region and propose anti-bullying measures. Furthermore, the urgency determination unit can build a system for proposing anti-bullying measures for each region. For example, it can aggregate bullying consultation data by region and propose measures. This makes it possible to propose anti-bullying measures for each region by comparing data from different educational institutions and regions.

[0038] When a victim inputs their consultation details at a consultation desk, the generation AI can compare them with past consultation details and provide appropriate advice. For example, the generation AI can build a system that analyzes past consultation details and compares them with the details entered by the victim. For example, it can provide appropriate advice based on similar past cases. The generation AI can also develop algorithms for providing advice by comparing with past consultation details. For example, it can calculate the similarity between past consultation details and the current consultation details and provide appropriate advice. Furthermore, the generation AI can build a system for providing advice by comparing with past consultation details. For example, it can store past consultation history in a database and reference it as needed. This allows it to provide appropriate advice by comparing with past consultation details.

[0039] Generative AI allows victims to input voice and image data when entering their consultation details at consultation centers, making it possible to collect evidence of bullying from multiple angles. For example, generative AI can analyze voice and image inputs to build systems that collect evidence of bullying from multiple angles. For example, it can detect threatening or insulting words in voice data. Generative AI can also develop algorithms for analyzing voice and image inputs. For example, it can use voice recognition technology and image analysis technology to collect evidence of bullying from multiple angles. Furthermore, generative AI can build systems that analyze voice and image inputs. For example, it can analyze voice and image data to collect evidence of bullying. This allows for voice and image input, making it possible to collect evidence of bullying from multiple angles.

[0040] Generative AI can enable victims to input their consultation details in different languages ​​at the consultation desk, thereby providing a multilingual bullying consultation desk. Generative AI, for example, uses algorithms to analyze text data in different languages. For example, it can analyze text data in English, Spanish, Chinese, etc. and determine the urgency of the case. Generative AI can also build a system to provide a multilingual bullying consultation desk. For example, it can automatically translate and analyze text data in different languages. Furthermore, generative AI can develop algorithms to analyze text data in different languages. For example, it can use machine translation technology to analyze text data in different languages. This allows input in different languages, thereby providing a multilingual bullying consultation desk.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The bullying victim consultation system can further include an audio data acquisition unit. The audio data acquisition unit allows victims to input their consultation details by voice, and the generation AI analysis unit can analyze the audio data and extract important information and urgent consultation details in the same way as text data. For example, when a victim speaks about their consultation over the phone, the audio data is acquired, and the generation AI uses voice recognition technology to convert it into text data and analyze it. The audio data acquisition unit also allows victims to upload audio files they have recorded. Furthermore, the audio data acquisition unit can acquire audio data in real time, allowing the generation AI to analyze it immediately. This allows victims to seek consultation in a variety of ways, enabling faster and more appropriate responses by utilizing audio data.

[0043] The generating AI analysis unit can further include an image data acquisition unit. The image data acquisition unit allows victims to upload images that serve as evidence of bullying, and the generating AI analysis unit can analyze the image data to extract evidence of bullying. For example, if a victim uploads a photo taken at the scene of bullying, the image data is acquired, and the generating AI uses image analysis technology to detect evidence of bullying. The image data acquisition unit also allows victims to upload screenshots. Furthermore, the image data acquisition unit can acquire image data in real time, allowing the generating AI to analyze it immediately. This makes it possible to use image data to collect evidence of bullying from multiple angles, enabling rapid and appropriate responses.

[0044] The generation AI analysis unit can also be equipped with a multilingual support function. The multilingual support function can analyze text data in different languages ​​and determine the urgency of the call. For example, text data in English, Spanish, Chinese, etc. can be analyzed, and the generation AI can automatically translate and determine the urgency. The multilingual support function also allows victims to input their consultation content in different languages. For example, the victim can input their consultation content in their native language, and the generation AI can translate and analyze it. Furthermore, the multilingual support function can translate and analyze text data in different languages ​​in real time. This allows victims who speak different languages ​​to consult with confidence, enabling quick and appropriate responses.

[0045] The generation AI analysis unit can also be equipped with a function to acquire the victim's location information. The location information acquisition function allows victims to provide location information when entering their consultation details, and the generation AI analysis unit can analyze the location information to understand bullying trends by region. For example, if a victim provides GPS data, the location information can be acquired and the generation AI can analyze bullying trends by region. The location information acquisition function also allows victims to manually enter location information. Furthermore, the location information acquisition function can acquire location information in real time, allowing the generation AI to perform instant analysis. This makes it possible to utilize location information to understand bullying trends by region and respond quickly and appropriately.

[0046] The generation AI analysis unit can also be equipped with a function to reference the victim's past consultation history. The past consultation history reference function stores the details of the victim's past consultations in a database, and the generation AI analysis unit can reference that data to determine the urgency. For example, it can compare the details of the victim's past consultations with the current consultation content and determine the urgency based on similar cases. The past consultation history reference function also allows the victim to check the details of past consultations. Furthermore, the past consultation history reference function can reference past consultation history in real time, allowing the generation AI to perform instant analysis. This makes it possible to more accurately determine the urgency by utilizing past consultation history.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The text data acquisition unit acquires text data submitted to the consultation service. For example, text data can be acquired in the form of emails, chat messages, or social media posts. The text data acquisition unit also allows bullying victims to anonymously input their consultation details using a dedicated terminal. Step 2: The generation AI analysis unit analyzes the text data acquired by the text data acquisition unit. For example, the generation AI analyzes the text data using natural language processing technology to extract important information and urgent consultations. The generation AI can also analyze the content of the text data using a text generation AI (e.g., LLM). Furthermore, the generation AI can also analyze the content of the text data using a multimodal generation AI. Step 3: The urgency determination unit determines the urgency of the text data analyzed by the generation AI analysis unit. For example, the urgency determination unit determines whether a situation requires immediate action or whether there is a risk of death based on the content of the text data. The urgency determination unit can also determine the urgency based on important information extracted by the generation AI. Step 4: The Reporting Department reports consultations that are deemed to be highly urgent by the Urgency Assessment Department to the Board of Education or a third-party committee. For example, the Reporting Department can automatically send the content of consultations that are highly urgent to the Board of Education or a third-party committee. The Reporting Department can also build a system for quickly reporting consultations that are highly urgent.

[0049] (Example 2) The bullying victim consultation system according to an embodiment of the present invention automatically analyzes text data received at the consultation desk, and a generation AI extracts and reports important information and urgent inquiries. This allows bullying victim consultations to be made anonymously, reducing the mental burden on victims and enabling prompt and appropriate responses.

[0050] A bullying victim consultation system according to an embodiment includes a text data acquisition unit, a generation AI analysis unit, an urgency determination unit, and a reporting unit. The text data acquisition unit acquires text data submitted to the consultation service. For example, the text data can be acquired in the form of email, chat message, or social media post. Furthermore, the text data acquisition unit allows bullying victims to anonymously input their consultation details using a dedicated terminal. The generation AI analysis unit analyzes the text data acquired by the text data acquisition unit. For example, the generation AI analyzes the text data using natural language processing technology to extract important information and urgent consultations. The generation AI can also analyze the content of the text data using a text generation AI (e.g., LLM). Furthermore, the generation AI can analyze the content of the text data using a multimodal generation AI. The urgency determination unit determines the urgency of the text data analyzed by the generation AI analysis unit. For example, the urgency determination unit determines whether a situation requires immediate action or whether there is a life-threatening situation based on the content of the text data. The urgency determination unit can also determine the urgency based on important information extracted by the generation AI. The reporting unit reports consultations that are determined by the urgency determination unit to be highly urgent to the board of education or a third-party committee. For example, the reporting unit automatically sends the content of consultations that are highly urgent to the board of education or a third-party committee. The reporting unit can also build a system for quickly reporting consultation content that is highly urgent. As a result, the bullying victim consultation system according to the embodiment allows victims of bullying to consult anonymously and quickly report consultations that are highly urgent. For example, if a victim of bullying consults anonymously, the generation AI analyzes the content and reports it to the board of education or a third-party committee if it is highly urgent, a prompt response is possible. Furthermore, the lack of a response reduces mental stress.

[0051] When analyzing text data, the generative AI analysis unit learns bullying patterns and trends, enabling more accurate urgency judgments. For example, the generative AI may study past bullying consultation data to understand bullying patterns and trends. For example, if a specific word or phrase appears frequently, the urgency is judged based on that pattern. The generative AI analysis unit can also use machine learning models to learn bullying patterns and trends. For example, the generative AI may learn bullying patterns and trends based on past case data to improve the accuracy of urgency judgments. In this way, learning bullying patterns and trends improves the accuracy of urgency judgments.

[0052] When analyzing text data, the generative AI analysis unit can estimate the victim's emotional state and determine the urgency based on changes in emotion. For example, when the generative AI analyzes text data, the generative AI analysis unit uses an algorithm to estimate the victim's emotional state. For example, it analyzes emotional expressions in the text and calculates an emotion score. The generative AI analysis unit can also build a system for determining the urgency based on changes in emotion. For example, the generative AI analyzes changes in the emotion score of the text data and determines the urgency. Furthermore, the generative AI analysis unit can develop an algorithm for determining the urgency based on changes in emotion. For example, if the emotion score changes suddenly, it determines the consultation content to be urgent. This makes the urgency determination more accurate by taking the victim's emotional state into account.

[0053] When analyzing text data, the generative AI analysis unit can attempt to identify bullies and analyze their behavioral patterns. For example, when the generative AI analyzes text data, it uses an algorithm to identify bullies. For example, if a particular name or nickname appears frequently, that person can be identified as the bully. The generative AI analysis unit can also build a system to analyze the behavioral patterns of bullies. For example, the generative AI can analyze behavioral patterns in text data to identify the behavior of the bully. Furthermore, the generative AI analysis unit can develop an algorithm to analyze the behavioral patterns of bullies. For example, if a particular behavioral pattern is repeated, the perpetrator can be identified based on that behavior. This makes it possible to prevent and take measures against bullying by identifying perpetrators and analyzing their behavioral patterns.

[0054] When analyzing text data, the generative AI analysis unit simultaneously analyzes audio data or image data, allowing for the collection of evidence of bullying from multiple angles. For example, the generative AI analyzes audio data along with text data to collect evidence of bullying. For example, it detects threatening or insulting language in audio data. The generative AI analysis unit can also analyze image data to build a system for collecting evidence of bullying. For example, it can detect evidence of bullying in image data. Furthermore, the generative AI analysis unit can develop algorithms for analyzing audio data and image data. For example, it can use voice recognition technology and image analysis technology to collect evidence of bullying from multiple angles. This allows for the collection of evidence of bullying from multiple angles by analyzing audio data and image data.

[0055] When analyzing text data, the generative AI analysis unit can also analyze text data in different languages ​​to provide a multilingual bullying hotline. The generative AI analysis unit, for example, uses an algorithm that allows the generative AI to analyze text data in different languages. For example, it analyzes text data in English, Spanish, Chinese, etc. to determine the urgency. The generative AI analysis unit can also build a system for providing a multilingual bullying hotline. For example, it can automatically translate and analyze text data in different languages. Furthermore, the generative AI analysis unit can also develop an algorithm for analyzing text data in different languages. For example, it can use machine translation technology to analyze text data in different languages. In this way, a multilingual bullying hotline can be provided by analyzing text data in different languages.

[0056] When analyzing text data, the generative AI analysis unit uses the emotion estimation function to monitor the victim's emotions in real time and respond according to changes in emotions. For example, when the generative AI analyzes text data, the generative AI analysis unit uses the emotion estimation function to monitor the victim's emotions in real time. For example, it analyzes emotional expressions in the text and calculates an emotion score. The generative AI analysis unit can also build a system to respond according to changes in emotions. For example, if the emotion score changes suddenly, it can prioritize the handling of that consultation content. Furthermore, the generative AI analysis unit can develop algorithms to respond according to changes in emotions. For example, it can suggest appropriate countermeasures based on changes in the emotion score. This makes it possible to monitor the victim's emotions in real time and respond appropriately.

[0057] When extracting highly urgent consultations, the urgency determination unit can refer to past consultation data and compare it with similar cases to determine the urgency. For example, the urgency determination unit uses an algorithm in which the generation AI refers to past consultation data and compares it with similar cases to determine the urgency. For example, it compares the content of past highly urgent consultations with the content of the current consultation. The urgency determination unit can also build a system for referencing past consultation data. For example, it can store past consultation history in a database and reference it as needed. Furthermore, the urgency determination unit can develop an algorithm for determining the urgency by comparing it with similar cases. For example, it can calculate the similarity between the content of past consultations and the content of the current consultation to determine the urgency. In this way, by referring to past consultation data, the urgency determination becomes more accurate.

[0058] When extracting consultations with high urgency, the urgency determination unit can analyze the victim's location information and grasp bullying trends by region. For example, the urgency determination unit uses a generation AI to analyze the victim's location information and build a system to grasp bullying trends by region. For example, if there are many bullying consultations in a particular region, the urgency of that region can be rated high. The urgency determination unit can also develop an algorithm for analyzing location information. For example, it can use GPS data or location information services to obtain and analyze the victim's location information. Furthermore, the urgency determination unit can also build a system to grasp bullying trends by region. For example, it can aggregate bullying consultation data by region and analyze the trends. In this way, by analyzing the victim's location information, it can grasp bullying trends by region.

[0059] When extracting highly urgent consultations, the urgency determination unit can integrate information from other data sources to make a more comprehensive urgency determination. For example, the urgency determination unit builds a system in which the generative AI collects information from social media and message boards and integrates it when extracting highly urgent consultations. For example, it analyzes posts about bullying on social media and determines the urgency. The urgency determination unit can also develop algorithms for integrating information from other data sources. For example, it can analyze social media data and message board data to determine the urgency. Furthermore, the urgency determination unit can build a system for integrating information from other data sources. For example, it can centrally manage information from multiple data sources and determine the urgency. This makes the urgency determination more comprehensive by integrating information from other data sources.

[0060] When extracting consultations with high urgency, the urgency determination unit can compare data from different educational institutions or regions and propose anti-bullying measures for each region. For example, the generation AI of the urgency determination unit compares data from different educational institutions or regions and builds a system that proposes anti-bullying measures for each region. For example, if there are many bullying consultations in a particular region, it will propose measures specific to that region. The urgency determination unit can also develop an algorithm for comparing data from different educational institutions or regions. For example, it can compare data by school or by region and propose anti-bullying measures. Furthermore, the urgency determination unit can build a system for proposing anti-bullying measures for each region. For example, it can aggregate bullying consultation data by region and propose measures. This makes it possible to propose anti-bullying measures for each region by comparing data from different educational institutions and regions.

[0061] When extracting consultations with high urgency, the urgency determination unit can use the emotion estimation function to monitor the victim's emotions in real time and respond according to changes in emotions. For example, the urgency determination unit can build a system in which a generation AI uses the emotion estimation function to monitor the victim's emotions in real time and extract consultations with high urgency. For example, if the emotion score changes suddenly, the consultation content will be handled as a priority. The urgency determination unit can also develop an algorithm for responding according to changes in emotions. For example, it can propose appropriate countermeasures based on changes in the emotion score. Furthermore, the urgency determination unit can build a system for responding according to changes in emotions. For example, if the emotion score changes suddenly, the consultation content will be handled as a priority. This makes it possible to monitor the victim's emotions in real time and respond appropriately.

[0062] When a victim enters their consultation details at a consultation desk, the generative AI can estimate their emotions in real time and complement the input content. For example, the generative AI can analyze the victim's input content and build a system that estimates their emotions in real time. For example, it can calculate an emotion score based on the input content and make appropriate completions. The generative AI can also develop an algorithm to complete the input content based on emotion estimation. For example, it can complete the victim's input content based on the emotion score. Furthermore, the generative AI can build a system to complete the input content based on emotion estimation. For example, if the emotion score is high, it will complete the content. This makes it possible to estimate the victim's emotions in real time and complete the input content, thereby providing more accurate consultation content.

[0063] When a victim inputs their consultation details at a consultation desk, the generation AI can compare them with past consultation details and provide appropriate advice. For example, the generation AI can build a system that analyzes past consultation details and compares them with the details entered by the victim. For example, it can provide appropriate advice based on similar past cases. The generation AI can also develop algorithms for providing advice by comparing with past consultation details. For example, it can calculate the similarity between past consultation details and the current consultation details and provide appropriate advice. Furthermore, the generation AI can build a system for providing advice by comparing with past consultation details. For example, it can store past consultation history in a database and reference it as needed. This allows it to provide appropriate advice by comparing with past consultation details.

[0064] When a victim inputs their consultation details at a consultation desk, the generative AI can estimate the victim's emotional state and respond according to changes in their emotions. For example, the generative AI can build a system that monitors the victim's emotional state in real time and responds according to changes in their emotions. For example, if the emotional score changes suddenly, it can propose appropriate countermeasures. The generative AI can also develop algorithms for responding according to changes in emotions. For example, it can propose appropriate countermeasures based on changes in the emotional score. The generative AI can also build a system for responding according to changes in emotions. For example, if the emotional score changes suddenly, it can prioritize the consultation details. This makes it possible to provide appropriate support by estimating the victim's emotional state and responding according to changes in their emotions.

[0065] Generative AI allows victims to input voice and image data when entering their consultation details at consultation centers, making it possible to collect evidence of bullying from multiple angles. For example, generative AI can analyze voice and image inputs to build systems that collect evidence of bullying from multiple angles. For example, it can detect threatening or insulting words in voice data. Generative AI can also develop algorithms for analyzing voice and image inputs. For example, it can use voice recognition technology and image analysis technology to collect evidence of bullying from multiple angles. Furthermore, generative AI can build systems that analyze voice and image inputs. For example, it can analyze voice and image data to collect evidence of bullying. This allows for voice and image input, making it possible to collect evidence of bullying from multiple angles.

[0066] Generative AI can enable victims to input their consultation details in different languages ​​at the consultation desk, thereby providing a multilingual bullying consultation desk. Generative AI, for example, uses algorithms to analyze text data in different languages. For example, it can analyze text data in English, Spanish, Chinese, etc. and determine the urgency of the case. Generative AI can also build a system to provide a multilingual bullying consultation desk. For example, it can automatically translate and analyze text data in different languages. Furthermore, generative AI can develop algorithms to analyze text data in different languages. For example, it can use machine translation technology to analyze text data in different languages. This allows input in different languages, thereby providing a multilingual bullying consultation desk.

[0067] At the consultation desk, the generative AI can use its emotion estimation function to monitor the victim's emotions in real time and respond according to changes in emotion. For example, the generative AI can use its emotion estimation function to monitor the victim's emotions in real time and build a system to extract consultations with high urgency. For example, if the emotion score changes suddenly, the consultation will be given priority. The generative AI can also develop algorithms to respond according to changes in emotion. For example, it can propose appropriate countermeasures based on changes in the emotion score. The generative AI can also build a system to respond according to changes in emotion. For example, if the emotion score changes suddenly, the consultation will be given priority. This makes it possible to monitor the victim's emotions in real time and respond appropriately.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The bullying victim consultation system can further include an audio data acquisition unit. The audio data acquisition unit allows victims to input their consultation details by voice, and the generation AI analysis unit can analyze the audio data and extract important information and urgent consultation details in the same way as text data. For example, when a victim speaks about their consultation over the phone, the audio data is acquired, and the generation AI uses voice recognition technology to convert it into text data and analyze it. The audio data acquisition unit also allows victims to upload audio files they have recorded. Furthermore, the audio data acquisition unit can acquire audio data in real time, allowing the generation AI to analyze it immediately. This allows victims to seek consultation in a variety of ways, enabling faster and more appropriate responses by utilizing audio data.

[0070] The generating AI analysis unit can further include an image data acquisition unit. The image data acquisition unit allows victims to upload images that serve as evidence of bullying, and the generating AI analysis unit can analyze the image data to extract evidence of bullying. For example, if a victim uploads a photo taken at the scene of bullying, the image data is acquired, and the generating AI uses image analysis technology to detect evidence of bullying. The image data acquisition unit also allows victims to upload screenshots. Furthermore, the image data acquisition unit can acquire image data in real time, allowing the generating AI to analyze it immediately. This makes it possible to use image data to collect evidence of bullying from multiple angles, enabling rapid and appropriate responses.

[0071] The generation AI analysis unit can also be equipped with a multilingual support function. The multilingual support function can analyze text data in different languages ​​and determine the urgency of the call. For example, text data in English, Spanish, Chinese, etc. can be analyzed, and the generation AI can automatically translate and determine the urgency. The multilingual support function also allows victims to input their consultation content in different languages. For example, the victim can input their consultation content in their native language, and the generation AI can translate and analyze it. Furthermore, the multilingual support function can translate and analyze text data in different languages ​​in real time. This allows victims who speak different languages ​​to consult with confidence, enabling quick and appropriate responses.

[0072] The generative AI analysis unit can further be equipped with an emotion estimation function. When analyzing text data, the emotion estimation function can estimate the victim's emotional state and determine the urgency based on changes in emotion. For example, the generative AI analyzes emotional expressions in the text data and calculates an emotion score. The emotion estimation function can also build a system to determine the urgency based on changes in emotion. For example, if the emotion score changes suddenly, the consultation content is determined to be urgent. Furthermore, the emotion estimation function can develop an algorithm to determine the urgency based on changes in emotion. This allows for more accurate urgency determination by taking the victim's emotional state into account.

[0073] The generation AI analysis unit can also be equipped with a function to acquire the victim's location information. The location information acquisition function allows victims to provide location information when entering their consultation details, and the generation AI analysis unit can analyze the location information to understand bullying trends by region. For example, if a victim provides GPS data, the location information can be acquired and the generation AI can analyze bullying trends by region. The location information acquisition function also allows victims to manually enter location information. Furthermore, the location information acquisition function can acquire location information in real time, allowing the generation AI to perform instant analysis. This makes it possible to utilize location information to understand bullying trends by region and respond quickly and appropriately.

[0074] The generative AI analysis unit can also be equipped with a function to monitor the victim's emotional state in real time. The emotion monitoring function can monitor the victim's emotional state in real time when analyzing text data and respond according to changes in emotion. For example, the generative AI analyzes emotional expressions in the text data and calculates an emotion score. The emotion monitoring function can also build a system to respond according to changes in emotion. For example, if the emotion score changes suddenly, the consultation content can be handled as a priority. Furthermore, the emotion monitoring function can develop an algorithm to respond according to changes in emotion. This makes it possible to monitor the victim's emotions in real time and respond appropriately.

[0075] The generation AI analysis unit can also be equipped with a function to reference the victim's past consultation history. The past consultation history reference function stores the details of the victim's past consultations in a database, and the generation AI analysis unit can reference that data to determine the urgency. For example, it can compare the details of the victim's past consultations with the current consultation content and determine the urgency based on similar cases. The past consultation history reference function also allows the victim to check the details of past consultations. Furthermore, the past consultation history reference function can reference past consultation history in real time, allowing the generation AI to perform instant analysis. This makes it possible to more accurately determine the urgency by utilizing past consultation history.

[0076] The generative AI analysis unit can further include a function to estimate the victim's emotional state and provide appropriate advice based on changes in emotion. The emotion estimation function can estimate the victim's emotional state when analyzing text data and provide appropriate advice based on changes in emotion. For example, the generative AI analyzes emotional expressions in text data and calculates an emotion score. The emotion estimation function can also build a system to provide appropriate advice based on changes in emotion. For example, if the emotion score changes suddenly, appropriate advice can be provided for the consultation content. Furthermore, the emotion estimation function can develop an algorithm to provide appropriate advice based on changes in emotion. This allows for more appropriate advice to be provided by taking the victim's emotional state into consideration.

[0077] The generative AI analysis unit can further include a function to estimate the victim's emotional state and determine the urgency based on changes in emotion. The emotion estimation function can estimate the victim's emotional state when analyzing text data and determine the urgency based on changes in emotion. For example, the generative AI analyzes emotional expressions in the text data and calculates an emotion score. The emotion estimation function can also build a system to determine the urgency based on changes in emotion. For example, if the emotion score changes suddenly, the consultation content is determined to be urgent. Furthermore, the emotion estimation function can develop an algorithm to determine the urgency based on changes in emotion. This makes it possible to more accurately determine the urgency by taking the victim's emotional state into account.

[0078] The generative AI analysis unit can further be equipped with a function to estimate the victim's emotional state and respond appropriately based on changes in emotion. The emotion estimation function can estimate the victim's emotional state when analyzing text data and respond appropriately based on changes in emotion. For example, the generative AI analyzes emotional expressions in the text data and calculates an emotion score. The emotion estimation function can also build a system to respond appropriately based on changes in emotion. For example, if the emotion score changes suddenly, the consultation content can be given priority. Furthermore, the emotion estimation function can develop an algorithm to respond appropriately based on changes in emotion. This makes it possible to monitor the victim's emotions in real time and respond appropriately.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: The text data acquisition unit acquires text data submitted to the consultation service. For example, text data can be acquired in the form of emails, chat messages, or social media posts. The text data acquisition unit also allows bullying victims to anonymously input their consultation details using a dedicated terminal. Step 2: The generation AI analysis unit analyzes the text data acquired by the text data acquisition unit. For example, the generation AI analyzes the text data using natural language processing technology to extract important information and urgent consultations. The generation AI can also analyze the content of the text data using a text generation AI (e.g., LLM). Furthermore, the generation AI can also analyze the content of the text data using a multimodal generation AI. Step 3: The urgency determination unit determines the urgency of the text data analyzed by the generation AI analysis unit. For example, the urgency determination unit determines whether a situation requires immediate action or whether there is a risk of death based on the content of the text data. The urgency determination unit can also determine the urgency based on important information extracted by the generation AI. Step 4: The Reporting Department reports consultations that are deemed to be highly urgent by the Urgency Assessment Department to the Board of Education or a third-party committee. For example, the Reporting Department can automatically send the content of consultations that are highly urgent to the Board of Education or a third-party committee. The Reporting Department can also build a system for quickly reporting consultations that are highly urgent.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0094] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0109] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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."

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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]

[0148] 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 text data acquisition unit that acquires text data submitted to the consultation desk; a generation AI analysis unit that analyzes the text data acquired by the text data acquisition unit; an urgency determination unit that determines the urgency of the text data analyzed by the generation AI analysis unit; a reporting unit that reports the consultation that is determined to be highly urgent by the urgency determination unit to the board of education or a third-party committee. A system characterized by:

2. The generation AI analysis unit When analyzing the text data, audio data or image data is also analyzed at the same time to collect evidence of bullying from multiple angles.

2. The system of claim 1.

3. The urgency determination unit When extracting urgent inquiries, past consultation data is referenced and compared with similar cases to determine the urgency.

2. The system of claim 1.

4. The generated AI is When the victim inputs the details of their consultation at the consultation desk, the system estimates their emotions in real time and completes the input.

2. The system of claim 1.

5. The generation AI analysis unit When analyzing the text data, the victim's emotional state is estimated and the urgency is determined based on the change in emotion.

2. The system of claim 1.

6. The urgency determination unit When extracting urgent consultations, estimate the victim's emotional state and determine the urgency based on the intensity of the emotion.

2. The system of claim 1.

7. The generated AI is When the victim inputs the details of their consultation at the consultation desk, the emotional state of the victim is estimated and a response is made according to the change in their emotions.

2. The system of claim 1.

8. The generation AI analysis unit When analyzing the text data, monitor the victim's emotions in real time and respond accordingly.

2. The system of claim 1.

Images