System

Abstract

An object of the system according to the embodiment is to analyze the contents of bullying and complaints and generate an appropriate handling method.SOLUTION: A system includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives contents of bullying and a claim. The analysis unit analyzes the content of the bullying or the complaint received by the reception unit. The generation unit generates a specific handling method based on the content analyzed by the analysis unit. The output unit outputs the correspondence generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not efficiently analyze the content of bullying and complaints and generate appropriate response methods, so there is room for improvement.

[0005] The system according to the embodiment aims to analyze the content of bullying and complaints and generate appropriate ways of dealing with them. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives the details of the bullying or complaint. The analysis unit analyzes the details of the bullying or complaint received by the reception unit. The generation unit generates a specific response method based on the details analyzed by the analysis unit. The output unit outputs the response generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the content of bullying or complaints and generate appropriate ways of responding. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The punching bag AI system according to an embodiment of the present invention accepts and analyzes bullying and complaints, and generates and outputs appropriate responses. The punching bag AI system accepts and analyzes the content of bullying and complaints, and generates appropriate responses to resolve the bullying and complaints. For example, the punching bag AI system can accept bullying and complaints from various situations, such as workplace bullying and customer complaints. The punching bag AI system records the details of the bullying and complaints and uses them as data for analysis. The punching bag AI system then analyzes the accepted content to understand the causes and background of the bullying and complaints. For example, in the case of workplace bullying, the punching bag AI system analyzes the factors and relationships that led to the bullying and generates an appropriate response. In the case of customer complaints, the punching bag AI system analyzes the content of the complaint and the customer's emotions and generates an appropriate response. The punching bag AI system then outputs the generated response to resolve the bullying and resolve the bullying and complaint. For example, in the case of workplace bullying, the punching bag AI system provides suggestions for resolving the causes of bullying and provides support to the victim. In the case of customer complaints, the punching bag AI system generates suggestions for resolving the customer's dissatisfaction and an apology message. In this way, the punching bag AI system can eliminate productivity stagnation caused by bullying and complaints, and realize a better society.In this way, the punching bag AI system can eliminate productivity stagnation caused by bullying and complaints, and realize a better society.For example, it is expected that bullying in the workplace will decrease and employee productivity will increase.It is also expected that customer complaints will decrease and customer satisfaction will increase.

[0029] The punching bag AI system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives the details of bullying or complaints. Examples of the details of bullying or complaints include, but are not limited to, school bullying, workplace harassment, and customer complaints. The reception unit can receive the details of bullying or complaints using, for example, text input, voice input, or image input. The analysis unit analyzes the details of bullying or complaints received by the reception unit. The analysis can be performed using, for example, text analysis, emotion analysis, or cause analysis, but is not limited to, examples. For example, the analysis unit analyzes the details of bullying or complaints using text analysis technology. The analysis unit can also analyze emotions contained in the details of bullying or complaints using emotion analysis technology. The analysis unit can also identify the cause of the bullying or complaint using cause analysis technology. The generation unit generates a specific response method based on the content analyzed by the analysis unit. The generation can generate, for example, specific response methods such as counseling, problem-solving procedures, and follow-up methods, but is not limited to, examples. For example, the generation unit generates a counseling proposal. The generation unit can also generate a procedure for resolving the problem. The generation unit can also generate a follow-up method. The output unit outputs the response generated by the generation unit. The output can be performed by, for example, email, telephone, face-to-face explanation, or other methods, but is not limited to these examples. For example, the output unit sends the generated response by email. The output unit can also communicate the generated response by telephone. The output unit can also explain the generated response in face-to-face. As a result, the punching bag AI system according to the embodiment can accept and analyze the content of bullying or complaints, generate and output an appropriate response, and thereby resolve bullying or complaints.

[0030] The reception unit includes a recording unit that records specific details of the bullying or complaint. The recording unit records the details of the bullying or complaint in detail. Specific items to be recorded include, but are not limited to, the date and time, location, involved parties, and detailed details. For example, the recording unit records the date and time when the bullying or complaint occurred. The recording unit can also record the location where the bullying or complaint occurred. The recording unit can also record the involved parties involved in the bullying or complaint. The recording unit can also record detailed details of the bullying or complaint. This improves the accuracy of analysis and response by recording the details of the bullying or complaint. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can accept the details of the bullying or complaint as text input and automatically record it using AI.

[0031] The analysis unit includes an identification unit that identifies the specific causes and background of bullying and complaints. The identification unit identifies the causes and background of bullying and complaints. The specific causes and backgrounds to be identified include, but are not limited to, testimony from those involved, past cases, and environmental factors. For example, the identification unit identifies the causes of bullying and complaints based on testimony from those involved. The identification unit can also identify the background of bullying and complaints by referring to past cases. The identification unit can also identify the causes of bullying and complaints by taking environmental factors into consideration. By identifying the causes and background of bullying and complaints, an appropriate response can be generated. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the details of bullying and complaints into AI and use AI to identify the causes and background.

[0032] The generation unit includes a proposal unit that proposes specific methods for resolving bullying or complaints. The proposal unit proposes methods for resolving bullying or complaints. The specific resolution methods proposed include, but are not limited to, promoting dialogue, fundamental solutions to the problem, and measures to prevent recurrence. For example, the proposal unit proposes promoting dialogue. The proposal unit can also propose fundamental solutions to the problem. The proposal unit can also propose measures to prevent recurrence. In this way, by proposing methods for resolving bullying or complaints, bullying or complaints can be effectively resolved. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the proposal unit can input the details of bullying or complaints into the generation AI and use the generation AI to propose a resolution method.

[0033] The output unit provides the generated response to the person or customer who has been bullied or complained about in a specific manner. The output unit provides the generated response to the person or customer who has been bullied or complained about. Specific methods of providing the response include, but are not limited to, email, telephone, and face-to-face explanation, for example. For example, the output unit sends the generated response by email. The output unit can also communicate the generated response by telephone. The output unit can also explain the generated response in face-to-face discussion. In this way, by providing the generated response to the person or customer who has been bullied or complained about, the bullying or complaint can be resolved. Some or all of the above-described processing in the output unit may be performed, for example, using AI, or may be performed without using AI. For example, the output unit can automatically send the generated response by email using AI.

[0034] The reception unit analyzes the user's past complaint history and selects the optimal reception method when receiving bullying or a complaint. The reception unit analyzes the user's past complaint history and selects the optimal reception method when receiving bullying or a complaint. Specific types of optimal reception methods include, but are not limited to, online forms, telephone reception, and in-person reception. For example, the reception unit responds promptly if the user has frequently submitted complaints in the past. The reception unit can also conduct detailed interviews if the user has never submitted a complaint in the past. The reception unit can also assign an appropriate person to handle the complaint based on the content of the user's past complaints. This allows the optimal reception method to be selected by analyzing the user's past complaint history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input the user's past complaint history data into a generation AI and have the generation AI select the optimal reception method.

[0035] The reception unit filters complaints of bullying or complaints based on the user's current situation and areas of interest when receiving the complaints. The reception unit filters complaints of bullying or complaints based on the user's current situation and areas of interest when receiving the complaints. Methods for identifying the current situation and areas of interest include, but are not limited to, survey results and past behavioral history. For example, if the user is currently at work, the reception unit prioritizes receiving workplace-related complaints. Furthermore, if the user submits a complaint related to a specific area of ​​interest, the reception unit can assign a staff member knowledgeable in that area. The reception unit can also select an appropriate response method based on the user's current situation. Thus, filtering based on the user's current situation and areas of interest allows an appropriate response to be selected. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's current situation data into a generation AI and have the generation AI perform filtering.

[0036] The reception unit selects the optimal reception means depending on the user's input method when receiving bullying or a complaint. The reception unit selects the optimal reception means depending on the user's input method when receiving bullying or a complaint. Specific types of input methods include, but are not limited to, voice input, text input, and image input. For example, when a user submits a complaint by voice, the reception unit uses voice recognition technology to receive the complaint. Furthermore, when a user submits a complaint by text, the reception unit can also use text analysis technology to receive the complaint. Furthermore, when a user submits a complaint by image, the reception unit can also use image analysis technology to receive the complaint. This allows bullying or a complaint to be efficiently received by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's input data into a generation AI and have the generation AI select the optimal reception means.

[0037] When receiving bullying or complaints, the reception unit prioritizes the reception of highly relevant bullying or complaints, taking into account the user's geographical location information. When receiving bullying or complaints, the reception unit prioritizes the reception of highly relevant bullying or complaints, taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data, IP address, and user input information. For example, if the user is in a specific area, the reception unit prioritizes the reception of complaints related to that area. Also, if the user is in a specific facility, the reception unit can prioritize the reception of complaints related to that facility. The reception unit can also select an appropriate response method based on the user's geographical location information. This allows the reception of highly relevant bullying or complaints to be prioritized by taking into account the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's geographical location information into a generation AI to determine the priority of highly relevant bullying or complaints.

[0038] The reception unit analyzes the user's social media activity when receiving bullying or a complaint and receives related bullying or a complaint. The reception unit analyzes the user's social media activity when receiving bullying or a complaint and receives related bullying or a complaint. Specific methods for analyzing social media activity include, but are not limited to, the content of posts, the number of likes, and the content of comments. For example, the reception unit analyzes the content posted by the user on social media and receives related complaints. The reception unit can also select an appropriate response method based on the user's social media activity history. The reception unit can also receive related complaints by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, related bullying or a complaint can be efficiently received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media data into a generation AI and have the generation AI receive related bullying or a complaint.

[0039] The reception unit customizes the reception method by reflecting the user's past feedback when receiving bullying or a complaint. The reception unit customizes the reception method by reflecting the user's past feedback when receiving bullying or a complaint. Specific methods for obtaining past feedback include, but are not limited to, survey results and past complaint details. For example, the reception unit customizes the reception method based on feedback from complaints submitted by the user in the past. The reception unit can also select an appropriate response method by referring to the user's past feedback. The reception unit can also optimize the reception procedure by reflecting the user's past feedback. This makes it possible to provide an optimal reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into a generation AI and have the generation AI customize the reception method.

[0040] When analyzing bullying or complaints, the analysis unit optimizes the analysis algorithm by referring to past bullying or complaint data. When analyzing bullying or complaints, the analysis unit optimizes the analysis algorithm by referring to past bullying or complaint data. Methods for optimizing the analysis algorithm include, but are not limited to, training a machine learning model using past data. For example, the analysis unit selects an optimal analysis algorithm based on past bullying or complaint data. The analysis unit can also identify the cause of bullying or complaints by referring to past data. The analysis unit can also generate optimal countermeasures based on past data. In this way, by referring to past data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past bullying or complaint data into a generation AI and have the generation AI optimize the analysis algorithm.

[0041] When analyzing bullying or complaints, the analysis unit applies different analysis methods depending on the category of the bullying or complaint. When analyzing bullying or complaints, the analysis unit applies different analysis methods depending on the category of the bullying or complaint. Specific types of different analysis methods include, but are not limited to, text analysis, image analysis, and audio analysis. For example, in the case of bullying in the workplace, the analysis unit applies an analysis method specialized for the workplace environment. In addition, in the case of complaints from customers, the analysis unit can also apply an analysis method specialized for customer service. In addition, in the case of bullying at school, the analysis unit can apply an analysis method specialized for the educational environment. In this way, appropriate analysis can be performed by applying an analysis method depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input category data of bullying or complaints into the generation AI and cause the generation AI to apply the analysis method.

[0042] The analysis unit improves the accuracy of the analysis by referring to the user's past analysis results when analyzing bullying or complaints. The analysis unit improves the accuracy of the analysis by referring to the user's past analysis results when analyzing bullying or complaints. Specific methods for acquiring past analysis results include, but are not limited to, past complaint data and analysis reports. For example, the analysis unit optimizes the analysis algorithm based on the user's past analysis results. The analysis unit can also identify the cause of bullying or complaints by referring to the user's past analysis results. The analysis unit can also generate optimal countermeasures based on the user's past analysis results. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the user's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0043] When analyzing bullying or complaints, the analysis unit determines the analysis priority based on the time of submission of the bullying or complaint. When analyzing bullying or complaints, the analysis unit determines the analysis priority based on the time of submission of the bullying or complaint. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the analysis unit prioritizes analysis of recently submitted complaints. The analysis unit can also prioritize analysis of complaints that have been left unattended for a long time. The analysis unit can also determine an appropriate analysis order based on the submission time. Thus, by determining the analysis priority based on the submission time, analysis can be performed in an appropriate order. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the submission time of bullying or complaints into the generation AI and have the generation AI determine the analysis priority.

[0044] When analyzing bullying or complaints, the analysis unit adjusts the order of analysis based on the relevance of the bullying or complaints. When analyzing bullying or complaints, the analysis unit adjusts the order of analysis based on the relevance of the bullying or complaints. Specific evaluation criteria for relevance include, but are not limited to, content similarity and common keywords. For example, the analysis unit prioritizes analysis of highly relevant bullying or complaints. The analysis unit can also postpone analysis of less relevant bullying or complaints. The analysis unit can also determine an appropriate analysis order based on relevance. This allows for efficient analysis by adjusting the analysis order based on relevance. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input relevance data of bullying or complaints into a generation AI and have the generation AI adjust the analysis order.

[0045] When analyzing bullying or complaints, the analysis unit adjusts the level of detail of the analysis according to the user's level of expertise. When analyzing bullying or complaints, the analysis unit adjusts the level of detail of the analysis according to the user's level of expertise. Specific evaluation criteria for the level of expertise include, but are not limited to, qualifications and past statements. For example, the analysis unit performs a detailed analysis if the user has expertise. The analysis unit can also perform a concise analysis if the user does not have expertise. The analysis unit can also adjust the level of detail of the analysis according to the user's level of expertise. This allows for appropriate analysis by adjusting the level of detail of the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0046] When generating a response, the generation unit adjusts the level of detail of the response based on the importance of the bullying or complaint. When generating a response, the generation unit adjusts the level of detail of the response based on the importance of the bullying or complaint. Specific criteria for adjusting the level of detail include, but are not limited to, adding or omitting information based on the importance. For example, the generation unit generates a detailed response for bullying or complaints with a high level of importance. The generation unit can also generate a concise response for bullying or complaints with a low level of importance. The generation unit can also adjust the level of detail of the response based on the importance. In this way, an appropriate response can be generated by adjusting the level of detail of the response based on the importance of the bullying or complaint. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input importance data of bullying or complaints into the generation AI and have the generation AI adjust the level of detail of the response.

[0047] When generating a response, the generation unit applies different generation algorithms depending on the category of bullying or complaint. When generating a response, the generation unit applies different generation algorithms depending on the category of bullying or complaint. Specific types of different generation algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, in the case of workplace bullying, the generation unit applies a generation algorithm specialized for the workplace environment. In addition, in the case of a complaint from a customer, the generation unit can apply a generation algorithm specialized for customer service. In addition, in the case of bullying at school, the generation unit can apply a generation algorithm specialized for the educational environment. In this way, by applying a generation algorithm depending on the category of bullying or complaint, an appropriate response can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the generation algorithm.

[0048] When generating a response, the generation unit refers to the user's past response results to improve the accuracy of the generation. When generating a response, the generation unit refers to the user's past response results to improve the accuracy of the generation. Specific methods for acquiring past response results include, but are not limited to, past complaint response history and feedback results. For example, the generation unit optimizes the generation algorithm based on the user's past response results. The generation unit can also generate an optimal response by referring to the user's past response results. The generation unit can also improve the accuracy of the generation based on the user's past response results. In this way, the accuracy of the generation can be improved by referring to the user's past response results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past response result data into the generation AI and cause the generation AI to improve the accuracy of the generation.

[0049] When generating responses, the generation unit determines the priority of the responses based on the timing of the bullying or complaints. When generating responses, the generation unit determines the priority of the responses based on the timing of the bullying or complaints. Criteria for determining the priority of responses include, but are not limited to, the timing of submission, urgency, and impact. For example, the generation unit may prioritize generating responses for recently submitted complaints. The generation unit may also prioritize generating responses for complaints that have been left unattended for a long time. The generation unit may also determine an appropriate order of responses based on the timing of submission. Thus, by prioritizing responses based on the timing of submission, responses can be generated in an appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input data on the timing of submission of bullying or complaints into the generation AI and have the generation AI determine the priority of the responses.

[0050] When generating responses, the generation unit adjusts the order of responses based on the relevance of bullying or complaints. When generating responses, the generation unit adjusts the order of responses based on the relevance of bullying or complaints. Specific criteria for adjusting the order of responses include, but are not limited to, changing the order based on relevance. For example, the generation unit may prioritize generating responses for bullying or complaints that are highly relevant. The generation unit may also postpone generating responses for bullying or complaints that are less relevant. The generation unit may also determine an appropriate order of responses based on relevance. This allows responses to be generated efficiently by adjusting the order of responses based on relevance. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input relevance data for bullying or complaints into the generation AI and have the generation AI adjust the order of responses.

[0051] The generation unit adjusts the use of technical terms in the corresponding response according to the user's level of expertise when generating the response. The generation unit adjusts the use of technical terms in the corresponding response according to the user's level of expertise when generating the response. Specific criteria for adjusting the use of technical terms include, but are not limited to, selecting terms according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a response that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the generation unit can also generate a concise and easy-to-understand response. Furthermore, the generation unit can adjust the use of technical terms in the corresponding response according to the user's level of expertise. This allows for the generation of an appropriate response by adjusting the use of technical terms in the corresponding response according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the user's level of expertise data into the generation AI and cause the generation AI to execute the use of technical terms.

[0052] The output unit, when outputting the corresponding data, selects the optimal display method by referring to the user's past operation history. The output unit, when outputting the corresponding data, selects the optimal display method by referring to the user's past operation history. Specific types of the optimal display method include, but are not limited to, selecting a display format based on the past operation history. For example, the output unit selects the optimal display method based on a display method previously used by the user. The output unit can also provide a display method with high visibility by referring to the user's past operation history. The output unit can also customize the display method based on the user's past operation history. In this way, the optimal display method can be provided by referring to the user's past operation history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past operation history data to a generation AI and cause the generation AI to select the optimal display method.

[0053] The output unit customizes the display content according to the user's current task when outputting the corresponding information. The output unit customizes the display content according to the user's current task when outputting the corresponding information. Specific methods for identifying the current task include, but are not limited to, current work content, ongoing projects, etc. For example, the output unit may prioritize displaying information related to the user's current task. The output unit may also simplify the display content according to the user's current task. The output unit may also select an optimal display method based on the user's current task. This allows for customizing the display content according to the user's current task, thereby providing an appropriate display. Some or all of the above-described processing in the output unit may be performed using, or without, AI. For example, the output unit may input the user's current task data to a generation AI and have the generation AI customize the display content.

[0054] The output unit improves the display method by reflecting user feedback when outputting a response. The output unit improves the display method by reflecting user feedback when outputting a response. Specific methods for obtaining feedback include, but are not limited to, survey results, past complaints, etc. For example, the output unit improves the display method based on user feedback. The output unit can also provide an optimal display method by referring to past user feedback. The output unit can also customize the display content by reflecting user feedback. In this way, the display method can be improved and an appropriate display can be provided by reflecting user feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user feedback data to a generation AI and cause the generation AI to improve the display method.

[0055] The output unit selects the optimal display method by taking into account the user's device information when outputting the corresponding information. The output unit selects the optimal display method by taking into account the user's device information when outputting the corresponding information. Specific methods for acquiring device information include, but are not limited to, the device type and OS version. For example, if the user is using a smartphone, the output unit provides a display method tailored to the screen size. Furthermore, if the user is using a tablet, the output unit can provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the output unit can provide a display method that is simple and highly visible. This makes it possible to provide the optimal display method by taking into account the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit may input the user's device information to a generation AI and cause the generation AI to select the optimal display method.

[0056] The output unit, when outputting the corresponding content, makes the display content multilingual according to the user's language setting. The output unit, when outputting the corresponding content, makes the display content multilingual according to the user's language setting. Specific methods for multilingual support include, but are not limited to, the types of supported languages ​​and the accuracy of translation. For example, the output unit automatically sets the display content based on the language setting of the user's device. The output unit can also provide a language switching function when the user uses multiple languages. The output unit can also provide the display content in a specific language when the user selects that language. This makes it possible to provide an appropriate display by making the display content multilingual according to the user's language setting. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's language setting data to a generation AI and cause the generation AI to execute multilingual display content.

[0057] The output unit customizes the output method by reflecting the user's past feedback when providing corresponding output. The output unit customizes the output method by reflecting the user's past feedback when providing corresponding output. Specific customization criteria for the output method include, but are not limited to, changing the display format based on the past feedback. For example, the output unit customizes the output method based on the user's past feedback. The output unit can also provide an optimal output method by referring to the user's past feedback. The output unit can also improve the output content by reflecting the user's past feedback. In this way, the output method can be customized and an appropriate display can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI or without AI. For example, the output unit can input the user's past feedback data into a generation AI and cause the generation AI to customize the output method.

[0058] The recording unit determines the priority of recording based on the importance of bullying or complaints when recording. The recording unit determines the priority of recording based on the importance of bullying or complaints when recording. Criteria for determining the priority of recording include, but are not limited to, importance, urgency, and impact. For example, the recording unit prioritizes recording of bullying or complaints with high importance. The recording unit can also record bullying or complaints with low importance later. The recording unit can also determine the priority of recording based on importance. In this way, by determining the priority of recording based on the importance of bullying or complaints, important information can be recorded preferentially. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input importance data of bullying or complaints into a generation AI and have the generation AI determine the priority of recording.

[0059] The recording unit applies different recording methods depending on the category of bullying or complaint when recording. The recording unit applies different recording methods depending on the category of bullying or complaint when recording. Specific types of different recording methods include, but are not limited to, text recording, audio recording, and image recording. For example, in the case of bullying in the workplace, the recording unit applies a recording method specialized for the workplace environment. In addition, in the case of a complaint from a customer, the recording unit can also apply a recording method specialized for customer service. In addition, in the case of bullying at school, the recording unit can apply a recording method specialized for the educational environment. In this way, appropriate recording can be performed by applying a recording method depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input category data of bullying or complaint into a generation AI and cause the generation AI to apply the recording method.

[0060] The recording unit determines the priority of recording based on the time when bullying or complaints were submitted during recording. The recording unit determines the priority of recording based on the time when bullying or complaints were submitted during recording. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the recording unit prioritizes recording of recently submitted complaints. The recording unit can also prioritize recording of complaints that have been left unattended for a long time. The recording unit can also determine an appropriate recording order based on the time of submission. This allows recording to be performed in an appropriate order by determining the priority of recording based on the time of submission. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input data on the time when bullying or complaints were submitted into a generation AI and have the generation AI determine the priority of recording.

[0061] The recording unit adjusts the order of recording based on the relevance of bullying and complaints when recording. The recording unit adjusts the order of recording based on the relevance of bullying and complaints when recording. Specific criteria for adjusting the order of recording include, but are not limited to, changing the order based on relevance. For example, the recording unit prioritizes recording of highly relevant bullying and complaints. The recording unit can also record less relevant bullying and complaints later. The recording unit can also determine an appropriate recording order based on relevance. This allows for efficient recording by adjusting the order of recording based on relevance. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input relevance data of bullying and complaints into a generation AI and have the generation AI adjust the order of recording.

[0062] The identification unit optimizes the identification algorithm by referring to past bullying and complaint data when identifying the cause. The identification unit optimizes the identification algorithm by referring to past bullying and complaint data when identifying the cause. Methods for optimizing the identification algorithm include, but are not limited to, training a machine learning model using past data. For example, the identification unit selects an optimal identification algorithm based on past bullying and complaint data. The identification unit can also identify the cause of bullying and complaints by referring to past data. The identification unit can also select an optimal cause identification method based on past data. In this way, by referring to past data, the identification algorithm can be optimized and the accuracy of cause identification can be improved. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past bullying and complaint data into a generation AI and cause the generation AI to optimize the identification algorithm.

[0063] When identifying the cause, the identification unit applies different identification methods depending on the category of bullying or complaint. When identifying the cause, the identification unit applies different identification methods depending on the category of bullying or complaint. Specific types of different identification methods include, but are not limited to, text analysis, image analysis, and audio analysis. For example, in the case of workplace bullying, the identification unit applies an identification method specialized for the workplace environment. In addition, in the case of customer complaints, the identification unit can also apply an identification method specialized for customer service. In addition, in the case of bullying at school, the identification unit can apply an identification method specialized for the educational environment. In this way, by applying an identification method depending on the category of bullying or complaint, appropriate cause identification can be performed. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the identification method.

[0064] When identifying causes, the identification unit determines a specific priority based on the time when the bullying or complaint was submitted. When identifying causes, the identification unit determines a specific priority based on the time when the bullying or complaint was submitted. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the identification unit prioritizes identifying the cause of a complaint that was submitted recently. The identification unit can also prioritize identifying the cause of a complaint that has been left unattended for a long time. The identification unit can also determine an appropriate identification order based on the time of submission. As a result, by determining a specific priority based on the time of submission, causes can be identified in an appropriate order. Some or all of the above-described processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit may input data on the time when the bullying or complaint was submitted into a generation AI and have the generation AI determine the specific priority.

[0065] The identification unit adjusts the specific order based on the relevance of bullying and complaints when identifying causes. The identification unit adjusts the specific order based on the relevance of bullying and complaints when identifying causes. Specific criteria for adjusting the specific order include, but are not limited to, changing the order based on relevance. For example, the identification unit prioritizes identifying causes of bullying and complaints that are highly relevant. The identification unit can also identify causes of bullying and complaints that are less relevant later. The identification unit can also determine an appropriate identification order based on relevance. This allows for efficient cause identification by adjusting the specific order based on relevance. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit may input relevance data of bullying and complaints into a generation AI and have the generation AI adjust the specific order.

[0066] The suggestion unit adjusts the level of detail of the proposal based on the importance of the bullying or complaint when making the proposal. The suggestion unit adjusts the level of detail of the proposal based on the importance of the bullying or complaint when making the proposal. Specific criteria for adjusting the level of detail of the proposal include, but are not limited to, adding or omitting information based on the importance. For example, the suggestion unit makes a detailed proposal for bullying or complaints with a high level of importance. The suggestion unit can also make a concise proposal for bullying or complaints with a low level of importance. The suggestion unit can also adjust the level of detail of the proposal based on the importance. As a result, an appropriate proposal can be made by adjusting the level of detail of the proposal based on the importance of the bullying or complaint. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input importance data of bullying or complaints into the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0067] When making a proposal, the suggestion unit applies different proposal algorithms depending on the category of bullying or complaint. When making a proposal, the suggestion unit applies different proposal algorithms depending on the category of bullying or complaint. Specific types of different proposal algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, in the case of workplace bullying, the suggestion unit applies a proposal algorithm specialized for the workplace environment. In addition, in the case of customer complaints, the suggestion unit can also apply a proposal algorithm specialized for customer service. In addition, in the case of bullying at school, the suggestion unit can also apply a proposal algorithm specialized for the educational environment. In this way, appropriate suggestions can be made by applying a proposal algorithm depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the proposal algorithm.

[0068] The suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results when making a suggestion. The suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results when making a suggestion. Specific methods for acquiring past suggestion results include, but are not limited to, past complaint response history and feedback results. For example, the suggestion unit optimizes the suggestion algorithm based on the user's past suggestion results. The suggestion unit can also make optimal suggestions by referring to the user's past suggestion results. The suggestion unit can also improve the accuracy of the suggestion based on the user's past suggestion results. In this way, the accuracy of the suggestion can be improved by referring to the user's past suggestion results. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit may input the user's past suggestion result data into the generation AI and cause the generation AI to improve the accuracy of the suggestion.

[0069] The suggestion unit, when making a proposal, determines the priority of the proposal based on the time when the bullying or complaint was submitted. The suggestion unit, when making a proposal, determines the priority of the proposal based on the time when the bullying or complaint was submitted. Criteria for determining the priority of the proposal include, but are not limited to, the time of submission, urgency, and impact. For example, the suggestion unit may prioritize proposals for recently submitted complaints. The suggestion unit may also prioritize proposals for complaints that have been left unattended for a long time. The suggestion unit may also determine an appropriate proposal order based on the time of submission. Thus, by prioritizing the proposals based on the time of submission, the proposals can be submitted in an appropriate order. Some or all of the above-described processing in the suggestion unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input data on the time when the bullying or complaint was submitted into the generation AI and have the generation AI determine the priority of the proposals.

[0070] The suggestion unit adjusts the order of the suggestions based on the relevance of the bullying and complaints when making a suggestion. The suggestion unit adjusts the order of the suggestions based on the relevance of the bullying and complaints when making a suggestion. Specific criteria for adjusting the order of the suggestions include, but are not limited to, changing the order based on relevance. For example, the suggestion unit prioritizes suggestions for bullying and complaints that are highly relevant. The suggestion unit can also postpone suggestions for bullying and complaints that are less relevant. The suggestion unit can also determine an appropriate order of suggestions based on relevance. This allows suggestions to be made efficiently by adjusting the order of suggestions based on relevance. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit may input relevance data for bullying and complaints into the generation AI and cause the generation AI to adjust the order of the suggestions.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The reception unit can also analyze the user's past complaint history and select the optimal reception method. For example, if the user has frequently submitted complaints in the past, a prompt response can be made. Also, if the user has never submitted a complaint in the past, a detailed interview can be conducted. Furthermore, an appropriate person can be assigned based on the content of the user's past complaints. In this way, the optimal reception method can be selected by analyzing the user's past complaint history.

[0073] When analyzing bullying or complaints, the analysis unit can also optimize the analysis algorithm by referencing past bullying or complaint data. For example, it can train a machine learning model using past data. It can also identify the causes of bullying or complaints based on past data. It can also generate optimal countermeasures based on past data. In this way, by referencing past data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved.

[0074] When receiving bullying or complaints, the reception unit can also filter based on the user's current situation and areas of interest. For example, if the user is currently at work, workplace-related complaints can be received first. Also, if the user submits a complaint about a specific area of ​​interest, a person knowledgeable in that area can be assigned. Furthermore, an appropriate response method can be selected depending on the user's current situation. In this way, by filtering based on the user's current situation and areas of interest, an appropriate response can be selected.

[0075] When analyzing bullying or complaints, the analysis unit can also apply different analysis methods depending on the category of bullying or complaint. For example, in the case of bullying in the workplace, an analysis method specialized for the workplace environment can be applied. In the case of complaints from customers, an analysis method specialized for customer service can be applied. Furthermore, in the case of bullying in schools, an analysis method specialized for the educational environment can be applied. In this way, appropriate analysis can be performed by applying an analysis method according to the category of bullying or complaint.

[0076] When generating a response, the generation unit can also adjust the level of detail of the response based on the importance of the bullying or complaint. For example, a detailed response can be generated for bullying or complaints with high importance. A concise response can also be generated for bullying or complaints with low importance. Furthermore, the level of detail of the response can be adjusted based on the importance. In this way, an appropriate response can be generated by adjusting the level of detail of the response based on the importance of the bullying or complaint.

[0077] The output unit can also select the optimal display method by referring to the user's past operation history when outputting the corresponding information. For example, the output unit selects the optimal display method based on the display methods used by the user in the past. Also, the output unit can provide a display method with high visibility by referring to the user's past operation history. Furthermore, the output unit can customize the display method based on the user's past operation history. In this way, the output unit can provide the optimal display method by referring to the user's past operation history.

[0078] When recording, the recording department can also determine the priority of recording based on the time of submission of bullying or complaints. For example, it can give priority to recording complaints that have been submitted recently. It can also give priority to recording complaints that have been left unattended for a long time. Furthermore, it can also determine the appropriate recording order based on the time of submission. This allows recording to be done in the appropriate order by determining the priority of recording based on the time of submission.

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

[0080] Step 1: The reception department accepts reports of bullying or complaints. Bullying and complaints include bullying at school, harassment in the workplace, and complaints from customers. The reception department can accept reports of bullying or complaints using methods such as text input, voice input, and image input. Step 2: The analysis unit analyzes the content of the bullying or complaint received by the reception unit. The analysis is performed using methods such as text analysis, sentiment analysis, and cause analysis. For example, text analysis technology is used to analyze the content of the bullying or complaint, sentiment analysis technology is used to analyze the emotions contained in the content, and cause analysis technology is used to identify the cause. Step 3: The generation unit generates specific response methods based on the content analyzed by the analysis unit. The generation unit generates specific response methods such as counseling, procedures for problem solving, and follow-up methods. For example, counseling suggestions, procedures for problem solving, and follow-up methods are generated. Step 4: The output unit outputs the response generated by the generation unit. The output is performed by email, telephone, face-to-face explanation, etc. For example, the generated response is sent by email, communicated by telephone, or explained face-to-face.

[0081] (Example 2) The punching bag AI system according to an embodiment of the present invention accepts and analyzes bullying and complaints, and generates and outputs appropriate responses. The punching bag AI system accepts and analyzes the content of bullying and complaints, and generates appropriate responses to resolve the bullying and complaints. For example, the punching bag AI system can accept bullying and complaints from various situations, such as workplace bullying and customer complaints. The punching bag AI system records the details of the bullying and complaints and uses them as data for analysis. The punching bag AI system then analyzes the accepted content to understand the causes and background of the bullying and complaints. For example, in the case of workplace bullying, the punching bag AI system analyzes the factors and relationships that led to the bullying and generates an appropriate response. In the case of customer complaints, the punching bag AI system analyzes the content of the complaint and the customer's emotions and generates an appropriate response. The punching bag AI system then outputs the generated response to resolve the bullying and resolve the bullying and complaint. For example, in the case of workplace bullying, the punching bag AI system provides suggestions for resolving the causes of bullying and provides support to the victim. In the case of customer complaints, the punching bag AI system generates suggestions for resolving the customer's dissatisfaction and an apology message. In this way, the punching bag AI system can eliminate productivity stagnation caused by bullying and complaints, and realize a better society.In this way, the punching bag AI system can eliminate productivity stagnation caused by bullying and complaints, and realize a better society.For example, it is expected that bullying in the workplace will decrease and employee productivity will increase.It is also expected that customer complaints will decrease and customer satisfaction will increase.

[0082] The punching bag AI system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives the details of bullying or complaints. Examples of the details of bullying or complaints include, but are not limited to, school bullying, workplace harassment, and customer complaints. The reception unit can receive the details of bullying or complaints using, for example, text input, voice input, or image input. The analysis unit analyzes the details of bullying or complaints received by the reception unit. The analysis can be performed using, for example, text analysis, emotion analysis, or cause analysis, but is not limited to, examples. For example, the analysis unit analyzes the details of bullying or complaints using text analysis technology. The analysis unit can also analyze emotions contained in the details of bullying or complaints using emotion analysis technology. The analysis unit can also identify the cause of the bullying or complaint using cause analysis technology. The generation unit generates a specific response method based on the content analyzed by the analysis unit. The generation can generate, for example, specific response methods such as counseling, problem-solving procedures, and follow-up methods, but is not limited to, examples. For example, the generation unit generates a counseling proposal. The generation unit can also generate a procedure for resolving the problem. The generation unit can also generate a follow-up method. The output unit outputs the response generated by the generation unit. The output can be performed by, for example, email, telephone, face-to-face explanation, or other methods, but is not limited to these examples. For example, the output unit sends the generated response by email. The output unit can also communicate the generated response by telephone. The output unit can also explain the generated response in face-to-face. As a result, the punching bag AI system according to the embodiment can accept and analyze the content of bullying or complaints, generate and output an appropriate response, and thereby resolve bullying or complaints.

[0083] The reception unit includes a recording unit that records specific details of the bullying or complaint. The recording unit records the details of the bullying or complaint in detail. Specific items to be recorded include, but are not limited to, the date and time, location, involved parties, and detailed details. For example, the recording unit records the date and time when the bullying or complaint occurred. The recording unit can also record the location where the bullying or complaint occurred. The recording unit can also record the involved parties involved in the bullying or complaint. The recording unit can also record detailed details of the bullying or complaint. This improves the accuracy of analysis and response by recording the details of the bullying or complaint. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can accept the details of the bullying or complaint as text input and automatically record it using AI.

[0084] The analysis unit includes an identification unit that identifies the specific causes and background of bullying and complaints. The identification unit identifies the causes and background of bullying and complaints. The specific causes and backgrounds to be identified include, but are not limited to, testimony from those involved, past cases, and environmental factors. For example, the identification unit identifies the causes of bullying and complaints based on testimony from those involved. The identification unit can also identify the background of bullying and complaints by referring to past cases. The identification unit can also identify the causes of bullying and complaints by taking environmental factors into consideration. By identifying the causes and background of bullying and complaints, an appropriate response can be generated. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the details of bullying and complaints into AI and use AI to identify the causes and background.

[0085] The generation unit includes a proposal unit that proposes specific methods for resolving bullying or complaints. The proposal unit proposes methods for resolving bullying or complaints. The specific resolution methods proposed include, but are not limited to, promoting dialogue, fundamental solutions to the problem, and measures to prevent recurrence. For example, the proposal unit proposes promoting dialogue. The proposal unit can also propose fundamental solutions to the problem. The proposal unit can also propose measures to prevent recurrence. In this way, by proposing methods for resolving bullying or complaints, bullying or complaints can be effectively resolved. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the proposal unit can input the details of bullying or complaints into the generation AI and use the generation AI to propose a resolution method.

[0086] The output unit provides the generated response to the person or customer who has been bullied or complained about in a specific manner. The output unit provides the generated response to the person or customer who has been bullied or complained about. Specific methods of providing the response include, but are not limited to, email, telephone, and face-to-face explanation, for example. For example, the output unit sends the generated response by email. The output unit can also communicate the generated response by telephone. The output unit can also explain the generated response in face-to-face discussion. In this way, by providing the generated response to the person or customer who has been bullied or complained about, the bullying or complaint can be resolved. Some or all of the above-described processing in the output unit may be performed, for example, using AI, or may be performed without using AI. For example, the output unit can automatically send the generated response by email using AI.

[0087] The reception unit estimates the user's emotions and adjusts the timing of accepting bullying and complaints based on the estimated user emotions. The reception unit estimates the user's emotions and adjusts the timing of accepting bullying and complaints based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, facial expression analysis, voice analysis, and text analysis. For example, if the user is very angry, the reception unit immediately starts accepting calls and responds quickly. Furthermore, if the user is calm, the reception unit can slightly delay accepting calls and prioritize other urgent matters. Furthermore, if the user is feeling anxious, the reception unit can accept calls earlier to provide a sense of security. This allows bullying and complaints to be accepted at an appropriate time by adjusting the timing of acceptance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input the user's facial expression data into the generation AI and have the generation AI estimate the emotion.

[0088] The reception unit analyzes the user's past complaint history and selects the optimal reception method when receiving bullying or a complaint. The reception unit analyzes the user's past complaint history and selects the optimal reception method when receiving bullying or a complaint. Specific types of optimal reception methods include, but are not limited to, online forms, telephone reception, and in-person reception. For example, the reception unit responds promptly if the user has frequently submitted complaints in the past. The reception unit can also conduct detailed interviews if the user has never submitted a complaint in the past. The reception unit can also assign an appropriate person to handle the complaint based on the content of the user's past complaints. This allows the optimal reception method to be selected by analyzing the user's past complaint history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input the user's past complaint history data into a generation AI and have the generation AI select the optimal reception method.

[0089] The reception unit filters complaints of bullying or complaints based on the user's current situation and areas of interest when receiving the complaints. The reception unit filters complaints of bullying or complaints based on the user's current situation and areas of interest when receiving the complaints. Methods for identifying the current situation and areas of interest include, but are not limited to, survey results and past behavioral history. For example, if the user is currently at work, the reception unit prioritizes receiving workplace-related complaints. Furthermore, if the user submits a complaint related to a specific area of ​​interest, the reception unit can assign a staff member knowledgeable in that area. The reception unit can also select an appropriate response method based on the user's current situation. Thus, filtering based on the user's current situation and areas of interest allows an appropriate response to be selected. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's current situation data into a generation AI and have the generation AI perform filtering.

[0090] The reception unit selects the optimal reception means depending on the user's input method when receiving bullying or a complaint. The reception unit selects the optimal reception means depending on the user's input method when receiving bullying or a complaint. Specific types of input methods include, but are not limited to, voice input, text input, and image input. For example, when a user submits a complaint by voice, the reception unit uses voice recognition technology to receive the complaint. Furthermore, when a user submits a complaint by text, the reception unit can also use text analysis technology to receive the complaint. Furthermore, when a user submits a complaint by image, the reception unit can also use image analysis technology to receive the complaint. This allows bullying or a complaint to be efficiently received by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's input data into a generation AI and have the generation AI select the optimal reception means.

[0091] The reception unit estimates the user's emotions and determines the priority of bullying and complaints to be received based on the estimated user emotions. The reception unit estimates the user's emotions and determines the priority of bullying and complaints to be received based on the estimated user emotions. Priority determination criteria include, but are not limited to, urgency, impact, and emotional strength. For example, if the user is very angry, the reception unit may receive the complaint as a top priority. Alternatively, if the user is calm, the reception unit may prioritize other urgent matters. Alternatively, if the user is feeling anxious, the reception unit may receive the complaint early. This allows important complaints to be handled promptly by determining the priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into the generation AI and have the generation AI determine the priority.

[0092] When receiving bullying or complaints, the reception unit prioritizes the reception of highly relevant bullying or complaints, taking into account the user's geographical location information. When receiving bullying or complaints, the reception unit prioritizes the reception of highly relevant bullying or complaints, taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data, IP address, and user input information. For example, if the user is in a specific area, the reception unit prioritizes the reception of complaints related to that area. Also, if the user is in a specific facility, the reception unit can prioritize the reception of complaints related to that facility. The reception unit can also select an appropriate response method based on the user's geographical location information. This allows the reception of highly relevant bullying or complaints to be prioritized by taking into account the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's geographical location information into a generation AI to determine the priority of highly relevant bullying or complaints.

[0093] The reception unit analyzes the user's social media activity when receiving bullying or a complaint and receives related bullying or a complaint. The reception unit analyzes the user's social media activity when receiving bullying or a complaint and receives related bullying or a complaint. Specific methods for analyzing social media activity include, but are not limited to, the content of posts, the number of likes, and the content of comments. For example, the reception unit analyzes the content posted by the user on social media and receives related complaints. The reception unit can also select an appropriate response method based on the user's social media activity history. The reception unit can also receive related complaints by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, related bullying or a complaint can be efficiently received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media data into a generation AI and have the generation AI receive related bullying or a complaint.

[0094] The reception unit customizes the reception method by reflecting the user's past feedback when receiving bullying or a complaint. The reception unit customizes the reception method by reflecting the user's past feedback when receiving bullying or a complaint. Specific methods for obtaining past feedback include, but are not limited to, survey results and past complaint details. For example, the reception unit customizes the reception method based on feedback from complaints submitted by the user in the past. The reception unit can also select an appropriate response method by referring to the user's past feedback. The reception unit can also optimize the reception procedure by reflecting the user's past feedback. This makes it possible to provide an optimal reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into a generation AI and have the generation AI customize the reception method.

[0095] The analysis unit estimates the user's emotions and adjusts the analysis method for bullying and complaints based on the estimated user emotions. The analysis unit estimates the user's emotions and adjusts the analysis method for bullying and complaints based on the estimated user emotions. Specific criteria for adjusting the analysis method include, but are not limited to, changing the analysis method depending on the strength of the emotion. For example, if the user is very angry, the analysis unit performs a quick analysis and immediately generates a countermeasure. Furthermore, if the user is calm, the analysis unit can also perform a detailed analysis and generate an optimal countermeasure. Furthermore, if the user is feeling anxious, the analysis unit can perform an analysis to provide a sense of security. Thus, by adjusting the analysis method based on the user's emotions, appropriate analysis can be performed. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI adjust the analysis method.

[0096] When analyzing bullying or complaints, the analysis unit optimizes the analysis algorithm by referring to past bullying or complaint data. When analyzing bullying or complaints, the analysis unit optimizes the analysis algorithm by referring to past bullying or complaint data. Methods for optimizing the analysis algorithm include, but are not limited to, training a machine learning model using past data. For example, the analysis unit selects an optimal analysis algorithm based on past bullying or complaint data. The analysis unit can also identify the cause of bullying or complaints by referring to past data. The analysis unit can also generate optimal countermeasures based on past data. In this way, by referring to past data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past bullying or complaint data into a generation AI and have the generation AI optimize the analysis algorithm.

[0097] When analyzing bullying or complaints, the analysis unit applies different analysis methods depending on the category of the bullying or complaint. When analyzing bullying or complaints, the analysis unit applies different analysis methods depending on the category of the bullying or complaint. Specific types of different analysis methods include, but are not limited to, text analysis, image analysis, and audio analysis. For example, in the case of bullying in the workplace, the analysis unit applies an analysis method specialized for the workplace environment. In addition, in the case of complaints from customers, the analysis unit can also apply an analysis method specialized for customer service. In addition, in the case of bullying at school, the analysis unit can apply an analysis method specialized for the educational environment. In this way, appropriate analysis can be performed by applying an analysis method depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input category data of bullying or complaints into the generation AI and cause the generation AI to apply the analysis method.

[0098] The analysis unit improves the accuracy of the analysis by referring to the user's past analysis results when analyzing bullying or complaints. The analysis unit improves the accuracy of the analysis by referring to the user's past analysis results when analyzing bullying or complaints. Specific methods for acquiring past analysis results include, but are not limited to, past complaint data and analysis reports. For example, the analysis unit optimizes the analysis algorithm based on the user's past analysis results. The analysis unit can also identify the cause of bullying or complaints by referring to the user's past analysis results. The analysis unit can also generate optimal countermeasures based on the user's past analysis results. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the user's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0099] The analysis unit estimates the user's emotions and determines the analysis priority based on the estimated user emotions. The analysis unit estimates the user's emotions and determines the analysis priority based on the estimated user emotions. Criteria for determining the analysis priority include, but are not limited to, the intensity of the emotion, the urgency, and the impact. For example, if the user is very angry, the analysis unit may analyze the complaint as a top priority. Alternatively, if the user is calm, the analysis unit may prioritize other urgent cases. Alternatively, if the user is feeling anxious, the analysis unit may analyze the complaint early. This allows important complaints to be analyzed quickly by determining the analysis priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI determine the analysis priorities.

[0100] When analyzing bullying or complaints, the analysis unit determines the analysis priority based on the time of submission of the bullying or complaint. When analyzing bullying or complaints, the analysis unit determines the analysis priority based on the time of submission of the bullying or complaint. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the analysis unit prioritizes analysis of recently submitted complaints. The analysis unit can also prioritize analysis of complaints that have been left unattended for a long time. The analysis unit can also determine an appropriate analysis order based on the submission time. Thus, by determining the analysis priority based on the submission time, analysis can be performed in an appropriate order. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the submission time of bullying or complaints into the generation AI and have the generation AI determine the analysis priority.

[0101] When analyzing bullying or complaints, the analysis unit adjusts the order of analysis based on the relevance of the bullying or complaints. When analyzing bullying or complaints, the analysis unit adjusts the order of analysis based on the relevance of the bullying or complaints. Specific evaluation criteria for relevance include, but are not limited to, content similarity and common keywords. For example, the analysis unit prioritizes analysis of highly relevant bullying or complaints. The analysis unit can also postpone analysis of less relevant bullying or complaints. The analysis unit can also determine an appropriate analysis order based on relevance. This allows for efficient analysis by adjusting the analysis order based on relevance. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input relevance data of bullying or complaints into a generation AI and have the generation AI adjust the analysis order.

[0102] When analyzing bullying or complaints, the analysis unit adjusts the level of detail of the analysis according to the user's level of expertise. When analyzing bullying or complaints, the analysis unit adjusts the level of detail of the analysis according to the user's level of expertise. Specific evaluation criteria for the level of expertise include, but are not limited to, qualifications and past statements. For example, the analysis unit performs a detailed analysis if the user has expertise. The analysis unit can also perform a concise analysis if the user does not have expertise. The analysis unit can also adjust the level of detail of the analysis according to the user's level of expertise. This allows for appropriate analysis by adjusting the level of detail of the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0103] The generation unit estimates the user's emotion and adjusts the expression of the response to be generated based on the estimated user emotion. The generation unit estimates the user's emotion and adjusts the expression of the response to be generated based on the estimated user emotion. Specific criteria for adjusting the expression include, but are not limited to, changing the wording depending on the intensity of the emotion. For example, if the user is very angry, the generation unit uses calm and polite expression. If the user is calm, the generation unit can also use expression including detailed explanation. If the user is anxious, the generation unit can also use expression that gives a sense of security. In this way, an appropriate response can be generated by adjusting the expression of the response based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI or without AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the corresponding expression method.

[0104] When generating a response, the generation unit adjusts the level of detail of the response based on the importance of the bullying or complaint. When generating a response, the generation unit adjusts the level of detail of the response based on the importance of the bullying or complaint. Specific criteria for adjusting the level of detail include, but are not limited to, adding or omitting information based on the importance. For example, the generation unit generates a detailed response for bullying or complaints with a high level of importance. The generation unit can also generate a concise response for bullying or complaints with a low level of importance. The generation unit can also adjust the level of detail of the response based on the importance. In this way, an appropriate response can be generated by adjusting the level of detail of the response based on the importance of the bullying or complaint. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input importance data of bullying or complaints into the generation AI and have the generation AI adjust the level of detail of the response.

[0105] When generating a response, the generation unit applies different generation algorithms depending on the category of bullying or complaint. When generating a response, the generation unit applies different generation algorithms depending on the category of bullying or complaint. Specific types of different generation algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, in the case of workplace bullying, the generation unit applies a generation algorithm specialized for the workplace environment. In addition, in the case of a complaint from a customer, the generation unit can apply a generation algorithm specialized for customer service. In addition, in the case of bullying at school, the generation unit can apply a generation algorithm specialized for the educational environment. In this way, by applying a generation algorithm depending on the category of bullying or complaint, an appropriate response can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the generation algorithm.

[0106] When generating a response, the generation unit refers to the user's past response results to improve the accuracy of the generation. When generating a response, the generation unit refers to the user's past response results to improve the accuracy of the generation. Specific methods for acquiring past response results include, but are not limited to, past complaint response history and feedback results. For example, the generation unit optimizes the generation algorithm based on the user's past response results. The generation unit can also generate an optimal response by referring to the user's past response results. The generation unit can also improve the accuracy of the generation based on the user's past response results. In this way, the accuracy of the generation can be improved by referring to the user's past response results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past response result data into the generation AI and cause the generation AI to improve the accuracy of the generation.

[0107] The generation unit estimates the user's emotion and adjusts the length of the response to be generated based on the estimated user emotion. The generation unit estimates the user's emotion and adjusts the length of the response to be generated based on the estimated user emotion. Specific criteria for adjusting the length of the response include, but are not limited to, changing the length of the sentence depending on the strength of the emotion. For example, if the user is very angry, the generation unit generates a short and to-the-point response. Furthermore, if the user is calm, the generation unit can generate a longer response including detailed explanations. Furthermore, if the user is anxious, the generation unit can generate a response of appropriate length to provide a sense of security. Thus, by adjusting the length of the response based on the user's emotion, an appropriate response can be generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input user emotion data to the generation AI and cause the generation AI to adjust the length of the correspondence.

[0108] When generating responses, the generation unit determines the priority of the responses based on the timing of the bullying or complaints. When generating responses, the generation unit determines the priority of the responses based on the timing of the bullying or complaints. Criteria for determining the priority of responses include, but are not limited to, the timing of submission, urgency, and impact. For example, the generation unit may prioritize generating responses for recently submitted complaints. The generation unit may also prioritize generating responses for complaints that have been left unattended for a long time. The generation unit may also determine an appropriate order of responses based on the timing of submission. Thus, by prioritizing responses based on the timing of submission, responses can be generated in an appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input data on the timing of submission of bullying or complaints into the generation AI and have the generation AI determine the priority of the responses.

[0109] When generating responses, the generation unit adjusts the order of responses based on the relevance of bullying or complaints. When generating responses, the generation unit adjusts the order of responses based on the relevance of bullying or complaints. Specific criteria for adjusting the order of responses include, but are not limited to, changing the order based on relevance. For example, the generation unit may prioritize generating responses for bullying or complaints that are highly relevant. The generation unit may also postpone generating responses for bullying or complaints that are less relevant. The generation unit may also determine an appropriate order of responses based on relevance. This allows responses to be generated efficiently by adjusting the order of responses based on relevance. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input relevance data for bullying or complaints into the generation AI and have the generation AI adjust the order of responses.

[0110] The generation unit adjusts the use of technical terms in the corresponding response according to the user's level of expertise when generating the response. The generation unit adjusts the use of technical terms in the corresponding response according to the user's level of expertise when generating the response. Specific criteria for adjusting the use of technical terms include, but are not limited to, selecting terms according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a response that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the generation unit can also generate a concise and easy-to-understand response. Furthermore, the generation unit can adjust the use of technical terms in the corresponding response according to the user's level of expertise. This allows for the generation of an appropriate response by adjusting the use of technical terms in the corresponding response according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the user's level of expertise data into the generation AI and cause the generation AI to execute the use of technical terms.

[0111] The output unit estimates the user's emotion and adjusts the display method of the response to be output based on the estimated user emotion. The output unit estimates the user's emotion and adjusts the display method of the response to be output based on the estimated user emotion. Specific criteria for adjusting the display method include, but are not limited to, changing the display format according to the intensity of the emotion. For example, if the user is very angry, the output unit provides a calm and highly visible display method. If the user is calm, the output unit can also provide a display method including detailed information. If the user is anxious, the output unit can also provide a display method that gives a sense of security. This makes it possible to provide an appropriate display by adjusting the display method based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the output unit can input the user's emotional data into the generation AI and have the generation AI adjust the display method.

[0112] The output unit, when outputting the corresponding data, selects the optimal display method by referring to the user's past operation history. The output unit, when outputting the corresponding data, selects the optimal display method by referring to the user's past operation history. Specific types of the optimal display method include, but are not limited to, selecting a display format based on the past operation history. For example, the output unit selects the optimal display method based on a display method previously used by the user. The output unit can also provide a display method with high visibility by referring to the user's past operation history. The output unit can also customize the display method based on the user's past operation history. In this way, the optimal display method can be provided by referring to the user's past operation history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past operation history data to a generation AI and cause the generation AI to select the optimal display method.

[0113] The output unit customizes the display content according to the user's current task when outputting the corresponding information. The output unit customizes the display content according to the user's current task when outputting the corresponding information. Specific methods for identifying the current task include, but are not limited to, current work content, ongoing projects, etc. For example, the output unit may prioritize displaying information related to the user's current task. The output unit may also simplify the display content according to the user's current task. The output unit may also select an optimal display method based on the user's current task. This allows for customizing the display content according to the user's current task, thereby providing an appropriate display. Some or all of the above-described processing in the output unit may be performed using, or without, AI. For example, the output unit may input the user's current task data to a generation AI and have the generation AI customize the display content.

[0114] The output unit improves the display method by reflecting user feedback when outputting a response. The output unit improves the display method by reflecting user feedback when outputting a response. Specific methods for obtaining feedback include, but are not limited to, survey results, past complaints, etc. For example, the output unit improves the display method based on user feedback. The output unit can also provide an optimal display method by referring to past user feedback. The output unit can also customize the display content by reflecting user feedback. In this way, the display method can be improved and an appropriate display can be provided by reflecting user feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user feedback data to a generation AI and cause the generation AI to improve the display method.

[0115] The output unit estimates the user's emotion and adjusts the corresponding operation procedure to be output based on the estimated user emotion. The output unit estimates the user's emotion and adjusts the corresponding operation procedure to be output based on the estimated user emotion. Specific criteria for adjusting the operation procedure include, but are not limited to, changing the operation procedure depending on the intensity of the emotion. For example, the output unit may provide concise and quick operation procedures when the user is very angry. The output unit may also provide detailed operation procedures when the user is calm. The output unit may also provide operation procedures that give the user a sense of security when the user is anxious. This allows appropriate operation procedures to be provided by adjusting the operation procedures based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the output unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the operating procedure.

[0116] The output unit selects the optimal display method by taking into account the user's device information when outputting the corresponding information. The output unit selects the optimal display method by taking into account the user's device information when outputting the corresponding information. Specific methods for acquiring device information include, but are not limited to, the device type and OS version. For example, if the user is using a smartphone, the output unit provides a display method tailored to the screen size. Furthermore, if the user is using a tablet, the output unit can provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the output unit can provide a display method that is simple and highly visible. This makes it possible to provide the optimal display method by taking into account the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit may input the user's device information to a generation AI and cause the generation AI to select the optimal display method.

[0117] The output unit, when outputting the corresponding content, makes the display content multilingual according to the user's language setting. The output unit, when outputting the corresponding content, makes the display content multilingual according to the user's language setting. Specific methods for multilingual support include, but are not limited to, the types of supported languages ​​and the accuracy of translation. For example, the output unit automatically sets the display content based on the language setting of the user's device. The output unit can also provide a language switching function when the user uses multiple languages. The output unit can also provide the display content in a specific language when the user selects that language. This makes it possible to provide an appropriate display by making the display content multilingual according to the user's language setting. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's language setting data to a generation AI and cause the generation AI to execute multilingual display content.

[0118] The output unit customizes the output method by reflecting the user's past feedback when providing corresponding output. The output unit customizes the output method by reflecting the user's past feedback when providing corresponding output. Specific customization criteria for the output method include, but are not limited to, changing the display format based on the past feedback. For example, the output unit customizes the output method based on the user's past feedback. The output unit can also provide an optimal output method by referring to the user's past feedback. The output unit can also improve the output content by reflecting the user's past feedback. In this way, the output method can be customized and an appropriate display can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI or without AI. For example, the output unit can input the user's past feedback data into a generation AI and cause the generation AI to customize the output method.

[0119] The recording unit estimates the user's emotion and adjusts the level of detail of the recorded content based on the estimated user's emotion. The recording unit estimates the user's emotion and adjusts the level of detail of the recorded content based on the estimated user's emotion. Specific criteria for adjusting the level of detail of the recorded content include, but are not limited to, adding or omitting information depending on the intensity of the emotion. For example, the recording unit may record in detail when the user is very angry. The recording unit may also record in brief when the user is calm. The recording unit may also record in detail to provide a sense of security when the user is anxious. This allows appropriate recording by adjusting the level of detail of the recorded content based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input the user's emotional data into the generation AI and have the generation AI adjust the level of detail of the recording.

[0120] The recording unit determines the priority of recording based on the importance of bullying or complaints when recording. The recording unit determines the priority of recording based on the importance of bullying or complaints when recording. Criteria for determining the priority of recording include, but are not limited to, importance, urgency, and impact. For example, the recording unit prioritizes recording of bullying or complaints with high importance. The recording unit can also record bullying or complaints with low importance later. The recording unit can also determine the priority of recording based on importance. In this way, by determining the priority of recording based on the importance of bullying or complaints, important information can be recorded preferentially. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input importance data of bullying or complaints into a generation AI and have the generation AI determine the priority of recording.

[0121] The recording unit applies different recording methods depending on the category of bullying or complaint when recording. The recording unit applies different recording methods depending on the category of bullying or complaint when recording. Specific types of different recording methods include, but are not limited to, text recording, audio recording, and image recording. For example, in the case of bullying in the workplace, the recording unit applies a recording method specialized for the workplace environment. In addition, in the case of a complaint from a customer, the recording unit can also apply a recording method specialized for customer service. In addition, in the case of bullying at school, the recording unit can apply a recording method specialized for the educational environment. In this way, appropriate recording can be performed by applying a recording method depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input category data of bullying or complaint into a generation AI and cause the generation AI to apply the recording method.

[0122] The recording unit estimates the user's emotion and adjusts the display method of the record based on the estimated user emotion. The recording unit estimates the user's emotion and adjusts the display method of the record based on the estimated user emotion. Specific criteria for adjusting the display method of the record include, but are not limited to, changing the display format according to the intensity of the emotion. For example, if the user is very angry, the recording unit provides a calm and highly visible display method. If the user is calm, the recording unit can also provide a display method including detailed information. If the user is anxious, the recording unit can also provide a display method that gives a sense of security. This makes it possible to provide an appropriate display by adjusting the display method based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input the user's emotional data into the generation AI and have the generation AI adjust the display method.

[0123] The recording unit determines the priority of recording based on the time when bullying or complaints were submitted during recording. The recording unit determines the priority of recording based on the time when bullying or complaints were submitted during recording. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the recording unit prioritizes recording of recently submitted complaints. The recording unit can also prioritize recording of complaints that have been left unattended for a long time. The recording unit can also determine an appropriate recording order based on the time of submission. This allows recording to be performed in an appropriate order by determining the priority of recording based on the time of submission. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input data on the time when bullying or complaints were submitted into a generation AI and have the generation AI determine the priority of recording.

[0124] The recording unit adjusts the order of recording based on the relevance of bullying and complaints when recording. The recording unit adjusts the order of recording based on the relevance of bullying and complaints when recording. Specific criteria for adjusting the order of recording include, but are not limited to, changing the order based on relevance. For example, the recording unit prioritizes recording of highly relevant bullying and complaints. The recording unit can also record less relevant bullying and complaints later. The recording unit can also determine an appropriate recording order based on relevance. This allows for efficient recording by adjusting the order of recording based on relevance. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input relevance data of bullying and complaints into a generation AI and have the generation AI adjust the order of recording.

[0125] The identification unit estimates the user's emotions and adjusts the method for identifying the cause of the bullying or complaint based on the estimated user emotions. The identification unit estimates the user's emotions and adjusts the method for identifying the cause of the bullying or complaint based on the estimated user emotions. Specific criteria for adjusting the cause identification method include, but are not limited to, changing the identification method depending on the strength of the emotion. For example, the identification unit may quickly identify the cause if the user is very angry. The identification unit may also perform detailed cause identification if the user is calm. The identification unit may also perform cause identification to provide a sense of security if the user is feeling anxious. This allows appropriate cause identification by adjusting the cause identification method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input user emotion data into the generation AI and cause the generation AI to adjust the cause identification method.

[0126] The identification unit optimizes the identification algorithm by referring to past bullying and complaint data when identifying the cause. The identification unit optimizes the identification algorithm by referring to past bullying and complaint data when identifying the cause. Methods for optimizing the identification algorithm include, but are not limited to, training a machine learning model using past data. For example, the identification unit selects an optimal identification algorithm based on past bullying and complaint data. The identification unit can also identify the cause of bullying and complaints by referring to past data. The identification unit can also select an optimal cause identification method based on past data. In this way, by referring to past data, the identification algorithm can be optimized and the accuracy of cause identification can be improved. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past bullying and complaint data into a generation AI and cause the generation AI to optimize the identification algorithm.

[0127] When identifying the cause, the identification unit applies different identification methods depending on the category of bullying or complaint. When identifying the cause, the identification unit applies different identification methods depending on the category of bullying or complaint. Specific types of different identification methods include, but are not limited to, text analysis, image analysis, and audio analysis. For example, in the case of workplace bullying, the identification unit applies an identification method specialized for the workplace environment. In addition, in the case of customer complaints, the identification unit can also apply an identification method specialized for customer service. In addition, in the case of bullying at school, the identification unit can apply an identification method specialized for the educational environment. In this way, by applying an identification method depending on the category of bullying or complaint, appropriate cause identification can be performed. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the identification method.

[0128] The identification unit estimates the user's emotions and determines the priority of cause identification based on the estimated user emotions. The identification unit estimates the user's emotions and determines the priority of cause identification based on the estimated user emotions. Criteria for determining the priority of cause identification include, but are not limited to, the intensity of the emotion, the urgency, and the impact. For example, if the user is very angry, the identification unit may identify the cause of the anger as the highest priority. Alternatively, if the user is calm, the identification unit may prioritize other urgent matters. Alternatively, if the user is feeling anxious, the identification unit may quickly identify the cause of the anxiety. Thus, by determining the priority of cause identification based on the user's emotions, important causes can be quickly identified. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input user emotion data to the generation AI and have the generation AI determine the priority of cause identification.

[0129] When identifying causes, the identification unit determines a specific priority based on the time when the bullying or complaint was submitted. When identifying causes, the identification unit determines a specific priority based on the time when the bullying or complaint was submitted. Specific methods for obtaining the submission time include, but are not limited to, the submission date and time, the elapsed time since submission, etc. For example, the identification unit prioritizes identifying the cause of a complaint that was submitted recently. The identification unit can also prioritize identifying the cause of a complaint that has been left unattended for a long time. The identification unit can also determine an appropriate identification order based on the time of submission. As a result, by determining a specific priority based on the time of submission, causes can be identified in an appropriate order. Some or all of the above-described processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit may input data on the time when the bullying or complaint was submitted into a generation AI and have the generation AI determine the specific priority.

[0130] The identification unit adjusts the specific order based on the relevance of bullying and complaints when identifying causes. The identification unit adjusts the specific order based on the relevance of bullying and complaints when identifying causes. Specific criteria for adjusting the specific order include, but are not limited to, changing the order based on relevance. For example, the identification unit prioritizes identifying causes of bullying and complaints that are highly relevant. The identification unit can also identify causes of bullying and complaints that are less relevant later. The identification unit can also determine an appropriate identification order based on relevance. This allows for efficient cause identification by adjusting the specific order based on relevance. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit may input relevance data of bullying and complaints into a generation AI and have the generation AI adjust the specific order.

[0131] The suggestion unit estimates the user's emotion and adjusts the way the suggestion is expressed based on the estimated user's emotion. The suggestion unit estimates the user's emotion and adjusts the way the suggestion is expressed based on the estimated user's emotion. Specific criteria for adjusting the way the suggestion is expressed include, but are not limited to, changing the wording depending on the strength of the emotion. For example, if the user is very angry, the suggestion unit uses calm and polite language. If the user is calm, the suggestion unit can also use language that includes detailed explanations. If the user is anxious, the suggestion unit can also use language that gives a sense of security. This allows appropriate suggestions to be made by adjusting the way the suggestion is expressed based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotional data into the generation AI and have the generation AI adjust the way the suggestion is expressed.

[0132] The suggestion unit adjusts the level of detail of the proposal based on the importance of the bullying or complaint when making the proposal. The suggestion unit adjusts the level of detail of the proposal based on the importance of the bullying or complaint when making the proposal. Specific criteria for adjusting the level of detail of the proposal include, but are not limited to, adding or omitting information based on the importance. For example, the suggestion unit makes a detailed proposal for bullying or complaints with a high level of importance. The suggestion unit can also make a concise proposal for bullying or complaints with a low level of importance. The suggestion unit can also adjust the level of detail of the proposal based on the importance. As a result, an appropriate proposal can be made by adjusting the level of detail of the proposal based on the importance of the bullying or complaint. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input importance data of bullying or complaints into the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0133] When making a proposal, the suggestion unit applies different proposal algorithms depending on the category of bullying or complaint. When making a proposal, the suggestion unit applies different proposal algorithms depending on the category of bullying or complaint. Specific types of different proposal algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, in the case of workplace bullying, the suggestion unit applies a proposal algorithm specialized for the workplace environment. In addition, in the case of customer complaints, the suggestion unit can also apply a proposal algorithm specialized for customer service. In addition, in the case of bullying at school, the suggestion unit can also apply a proposal algorithm specialized for the educational environment. In this way, appropriate suggestions can be made by applying a proposal algorithm depending on the category of bullying or complaint. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input category data of bullying or complaint into the generation AI and cause the generation AI to apply the proposal algorithm.

[0134] The suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results when making a suggestion. The suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results when making a suggestion. Specific methods for acquiring past suggestion results include, but are not limited to, past complaint response history and feedback results. For example, the suggestion unit optimizes the suggestion algorithm based on the user's past suggestion results. The suggestion unit can also make optimal suggestions by referring to the user's past suggestion results. The suggestion unit can also improve the accuracy of the suggestion based on the user's past suggestion results. In this way, the accuracy of the suggestion can be improved by referring to the user's past suggestion results. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit may input the user's past suggestion result data into the generation AI and cause the generation AI to improve the accuracy of the suggestion.

[0135] The suggestion unit estimates the user's emotion and adjusts the length of the suggestion based on the estimated user emotion. The suggestion unit estimates the user's emotion and adjusts the length of the suggestion based on the estimated user emotion. Specific criteria for adjusting the length of the suggestion include, but are not limited to, changing the length of the sentence depending on the strength of the emotion. For example, if the user is very angry, the suggestion unit may make a short, to-the-point suggestion. Furthermore, if the user is calm, the suggestion unit may make a longer suggestion with detailed explanations. Furthermore, if the user is anxious, the suggestion unit may make a suggestion of an appropriate length to provide a sense of security. Thus, by adjusting the length of the suggestion based on the user's emotion, an appropriate suggestion can be made. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the suggestion unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the suggestion unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the length of the suggestion.

[0136] The suggestion unit, when making a proposal, determines the priority of the proposal based on the time when the bullying or complaint was submitted. The suggestion unit, when making a proposal, determines the priority of the proposal based on the time when the bullying or complaint was submitted. Criteria for determining the priority of the proposal include, but are not limited to, the time of submission, urgency, and impact. For example, the suggestion unit may prioritize proposals for recently submitted complaints. The suggestion unit may also prioritize proposals for complaints that have been left unattended for a long time. The suggestion unit may also determine an appropriate proposal order based on the time of submission. Thus, by prioritizing the proposals based on the time of submission, the proposals can be submitted in an appropriate order. Some or all of the above-described processing in the suggestion unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the suggestion unit may input data on the time when the bullying or complaint was submitted into the generation AI and have the generation AI determine the priority of the proposals.

[0137] The suggestion unit adjusts the order of the suggestions based on the relevance of the bullying and complaints when making a suggestion. The suggestion unit adjusts the order of the suggestions based on the relevance of the bullying and complaints when making a suggestion. Specific criteria for adjusting the order of the suggestions include, but are not limited to, changing the order based on relevance. For example, the suggestion unit prioritizes suggestions for bullying and complaints that are highly relevant. The suggestion unit can also postpone suggestions for bullying and complaints that are less relevant. The suggestion unit can also determine an appropriate order of suggestions based on relevance. This allows suggestions to be made efficiently by adjusting the order of suggestions based on relevance. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit may input relevance data for bullying and complaints into the generation AI and cause the generation AI to adjust the order of the suggestions. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit can receive the details of bullying or complaints using the reception device 38 of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the details of bullying or complaints. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific response method based on the analysis results. The output unit can output the generated response using the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive the details of the bullying or complaint using the microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the details of the bullying or complaint. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific response method based on the analysis results. The output unit can output the generated response using the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit can receive the details of the bullying or complaint using the microphone 238 of the headset-type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the details of the bullying or complaint. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific response method based on the analysis results. The output unit can output the generated response using the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive the details of the bullying or complaint using the microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the details of the bullying or complaint. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific response method based on the analysis results. The output unit can output the generated response using the speaker 240 of the robot 414.

[0138] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0139] The reception unit can also analyze the user's past complaint history and select the optimal reception method. For example, if the user has frequently submitted complaints in the past, a prompt response can be made. Also, if the user has never submitted a complaint in the past, a detailed interview can be conducted. Furthermore, an appropriate person can be assigned based on the content of the user's past complaints. In this way, the optimal reception method can be selected by analyzing the user's past complaint history.

[0140] The recording unit can also estimate the user's emotions and adjust the level of detail to be recorded based on the estimated user emotions. For example, if the user is very angry, detailed recording can be performed. If the user is calm, concise recording can be performed. Furthermore, if the user is feeling anxious, detailed recording can be performed to provide a sense of security. In this way, by adjusting the level of detail to be recorded based on the user's emotions, appropriate recording can be performed.

[0141] When analyzing bullying or complaints, the analysis unit can also optimize the analysis algorithm by referencing past bullying or complaint data. For example, it can train a machine learning model using past data. It can also identify the causes of bullying or complaints based on past data. It can also generate optimal countermeasures based on past data. In this way, by referencing past data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved.

[0142] The generation unit can also estimate the user's emotions and adjust the way in which the response is expressed based on the estimated user's emotions. For example, if the user is very angry, a calm and polite expression can be used. If the user is calm, an expression including a detailed explanation can be used. Furthermore, if the user is feeling anxious, an expression that gives a sense of security can be used. In this way, an appropriate response can be generated by adjusting the way in which the response is expressed based on the user's emotions.

[0143] The output unit can also estimate the user's emotions and adjust the display method of the response to be output based on the estimated user emotions. For example, if the user is very angry, a calm and highly visible display method can be provided. If the user is calm, a display method including detailed information can be provided. Furthermore, if the user is feeling anxious, a display method that gives a sense of security can be provided. In this way, by adjusting the display method based on the user's emotions, an appropriate display can be provided.

[0144] When receiving bullying or complaints, the reception unit can also filter based on the user's current situation and areas of interest. For example, if the user is currently at work, workplace-related complaints can be received first. Also, if the user submits a complaint about a specific area of ​​interest, a person knowledgeable in that area can be assigned. Furthermore, an appropriate response method can be selected depending on the user's current situation. In this way, by filtering based on the user's current situation and areas of interest, an appropriate response can be selected.

[0145] When analyzing bullying or complaints, the analysis unit can also apply different analysis methods depending on the category of bullying or complaint. For example, in the case of bullying in the workplace, an analysis method specialized for the workplace environment can be applied. In the case of complaints from customers, an analysis method specialized for customer service can be applied. Furthermore, in the case of bullying in schools, an analysis method specialized for the educational environment can be applied. In this way, appropriate analysis can be performed by applying an analysis method according to the category of bullying or complaint.

[0146] When generating a response, the generation unit can also adjust the level of detail of the response based on the importance of the bullying or complaint. For example, a detailed response can be generated for bullying or complaints with high importance. A concise response can also be generated for bullying or complaints with low importance. Furthermore, the level of detail of the response can be adjusted based on the importance. In this way, an appropriate response can be generated by adjusting the level of detail of the response based on the importance of the bullying or complaint.

[0147] The output unit can also select the optimal display method by referring to the user's past operation history when outputting the corresponding information. For example, the output unit selects the optimal display method based on the display methods used by the user in the past. Also, the output unit can provide a display method with high visibility by referring to the user's past operation history. Furthermore, the output unit can customize the display method based on the user's past operation history. In this way, the output unit can provide the optimal display method by referring to the user's past operation history.

[0148] When recording, the recording department can also determine the priority of recording based on the time of submission of bullying or complaints. For example, it can give priority to recording complaints that have been submitted recently. It can also give priority to recording complaints that have been left unattended for a long time. Furthermore, it can also determine the appropriate recording order based on the time of submission. This allows recording to be done in the appropriate order by determining the priority of recording based on the time of submission.

[0149] The processing flow of the second embodiment will be briefly explained below.

[0150] Step 1: The reception department accepts reports of bullying or complaints. Bullying and complaints include bullying at school, harassment in the workplace, and complaints from customers. The reception department can accept reports of bullying or complaints using methods such as text input, voice input, and image input. Step 2: The analysis unit analyzes the content of the bullying or complaint received by the reception unit. The analysis is performed using methods such as text analysis, sentiment analysis, and cause analysis. For example, text analysis technology is used to analyze the content of the bullying or complaint, sentiment analysis technology is used to analyze the emotions contained in the content, and cause analysis technology is used to identify the cause. Step 3: The generation unit generates specific response methods based on the content analyzed by the analysis unit. The generation unit generates specific response methods such as counseling, procedures for problem solving, and follow-up methods. For example, counseling suggestions, procedures for problem solving, and follow-up methods are generated. Step 4: The output unit outputs the response generated by the generation unit. The output is performed by email, telephone, face-to-face explanation, etc. For example, the generated response is sent by email, communicated by telephone, or explained face-to-face.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] 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.

[0167] 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.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] 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.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0172] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0182] 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.

[0183] 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.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0188] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0198] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0199] 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.

[0200] 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.

[0201] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0202] 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.

[0203] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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).

[0208] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0209] 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."

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Explanation of symbols]

[0223] 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 system comprising: a reception unit that receives details of bullying or complaints; an analysis unit that analyzes the details of the bullying or complaints received by the reception unit; a generation unit that generates specific response methods based on the details analyzed by the analysis unit; and an output unit that outputs the response generated by the generation unit.

2. The system according to claim 1, wherein the reception unit includes a recording unit that records specific items of the bullying or complaint.

3. The system according to claim 1 , wherein the analysis unit includes an identification unit that identifies specific causes and backgrounds of bullying and complaints.

4. The system according to claim 1 , wherein the generation unit includes a suggestion unit that proposes specific methods for resolving bullying or complaints.

5. The system according to claim 1 , wherein the output unit provides the generated response in a specific manner to the person or customer who has been bullied or complained about.

6. The reception unit Estimate user emotions and adjust the timing of bullying and complaint acceptance based on the estimated user emotions The system of claim 1 .

7. The reception unit When receiving a complaint about bullying or a complaint, analyze the user's past complaint history and select the most appropriate method of receipt. The system of claim 1 .

8. The reception unit Filtering bullying and complaints based on the user's current situation and areas of interest The system of claim 1 .

9. The reception unit When receiving reports of bullying or complaints, select the most appropriate method of reception depending on the user's input method. The system of claim 1 .

Images