System

Abstract

An object of the system according to the embodiment is to automatically evaluate a risk for the content of a questionnaire or an interview and to make a specific improvement proposal.SOLUTION: A system includes a text analysis unit, a risk evaluation unit, and an improvement proposal unit. The text analysis unit analyzes the content of a questionnaire or an interview. The risk evaluation unit evaluates a risk on the basis of the content analyzed by the text analysis unit. The improvement proposal unit makes a specific improvement proposal based on the risk evaluated by the risk evaluation 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] With conventional technology, risk assessment of the contents of questionnaires and interviews was left to the discretion of the person in charge, which had the problem of sometimes being insufficiently considerate.

[0005] The system according to the embodiment aims to automatically evaluate the risks associated with the contents of questionnaires and interviews and make specific suggestions for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes a text analysis unit, a risk assessment unit, and an improvement proposal unit. The text analysis unit analyzes the content of questionnaires and interviews. The risk assessment unit assesses risks based on the content analyzed by the text analysis unit. The improvement proposal unit makes specific improvement proposals based on the risks assessed by the risk assessment unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically evaluate the risks associated with the content of questionnaires and interviews and make specific suggestions for improvement. [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 self-check tool according to the embodiment of the present invention is a system that uses AI to self-check for lack of human rights awareness and social considerations at the service planning stage. As a result, the self-check tool can prevent risks at the service planning stage and protect the image of the company.

[0029] A self-check tool according to an embodiment includes a text analysis unit, a risk assessment unit, and an improvement suggestion unit. The text analysis unit analyzes the content of questionnaires and interviews. For example, the generation AI analyzes questionnaire questions and interview scenarios as input and identifies potential risks. The generation AI can also perform risk assessment based on text data. The risk assessment unit evaluates risks based on the content analyzed by the text analysis unit. For example, the generation AI identifies specific risks and proposes improvements based on the analysis results. The generation AI can also create a risk assessment report and provide feedback to relevant parties. The improvement suggestion unit makes specific improvement suggestions based on the risks assessed by the risk assessment unit. For example, the generation AI may generate a suggestion such as "This question may offend certain people" or an improvement suggestion such as "Changing this expression would be more appropriate." The generation AI can also continuously learn based on past risk assessment results and feedback to improve the accuracy of its risk assessment. This allows the self-check tool according to an embodiment to prevent risks from occurring at the service planning stage. For example, we can ensure that the content of questionnaires and interviews is appropriate and that surveys are conducted with due consideration for people outside the company. Furthermore, continuous learning allows us to always conduct risk assessments based on the latest standards.

[0030] The text analysis unit takes into account changes in context and nuances, enabling a detailed evaluation of the potential risks posed by phrases. For example, when generative AI performs text analysis, the text analysis unit takes into account changes in context and evaluates the potential risks posed by specific phrases. For example, if the meaning of the same phrase changes depending on the context before and after, the unit analyzes those changes and identifies the risks. The unit also takes nuances into account to evaluate the potential risks posed by specific phrases. For example, if sarcasm or suggestive expressions are included, the unit analyzes those nuances and identifies the risks. The unit also analyzes changes in context and nuances in detail to evaluate the potential risks posed by specific phrases. For example, if the same words are used in different contexts, the unit analyzes the differences and identifies the risks. This makes it possible to evaluate risks by taking context changes and nuances into account.

[0031] The text analysis unit can evaluate risk by referencing past cases of online outrage or cases that have been considered socially problematic and finding similarities. For example, the text analysis unit can evaluate risk by referencing past cases of online outrage or cases that have been considered socially problematic, finding similarities with the text being analyzed. For example, it can create a database of expressions and content that have been problematic in the past and compare them to identify risks. It can also evaluate risk by referencing cases that have been considered socially problematic and finding similarities with the text being analyzed. For example, it can identify the risk if the text contains discriminatory expressions against a specific social group. It can also create a database of past cases of online outrage or cases that have been considered socially problematic, and refer to that to find similarities with the text being analyzed by the generation AI and evaluate risk. For example, it can identify the risk if the text contains expressions similar to those in past cases. This makes it possible to evaluate risk by referencing past cases.

[0032] The text analysis unit can expand the scope of its analysis beyond questionnaires and interviews to also include advertisements, marketing materials, and internal documents, enabling a broader risk assessment. For example, the text analysis unit can expand the scope of its text analysis beyond questionnaires and interviews to also include advertisements and marketing materials, thereby performing a broader risk assessment. For example, if an advertising slogan contains language that is inappropriate for a particular group, the risk can be identified. A broader risk assessment can also be performed by including internal documents in the analysis scope. For example, the unit can evaluate whether internal presentation materials contain language that would be problematic if they were leaked to the public. The scope of text analysis can also be expanded to include advertisements, marketing materials, and internal documents, performing a risk assessment. For example, if marketing materials contain prejudice against a particular social group, the risk can be identified. This allows the analysis scope to be broadened, enabling a comprehensive risk assessment.

[0033] The text analysis unit evaluates risks from the perspectives of different cultures and regions, promoting consideration from a global perspective. For example, the text analysis unit evaluates risks from the perspectives of different cultures for text analyzed by the generative AI. For example, if the text contains expressions that are problematic in a particular culture, it will identify those risks. It also evaluates risks from the perspectives of different regions, promoting consideration from a global perspective. For example, if the text contains expressions that are considered inappropriate in a particular region, it will identify those risks. It also evaluates risks from the perspectives of different cultures and regions for text analyzed by the generative AI. For example, it will identify risks based on social sentiment in a particular culture or region. This makes it possible to evaluate risks from the perspectives of different cultures and regions.

[0034] The risk assessment unit can perform a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking, and identify specific risks. For example, when the generative AI performs an analysis, the risk assessment unit performs a detailed evaluation of any areas where consideration for specific social groups is lacking. For example, if discriminatory language against a specific group is included, the risk is identified. The risk assessment unit can also perform a detailed evaluation of any areas where consideration for minorities is lacking, and identify specific risks. For example, if prejudice against a specific minority group is included, the risk is identified. The risk assessment unit can also perform a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking. For example, if stereotypes against a specific group are included, the risk is identified. This allows for a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking.

[0035] The risk assessment unit can refer to the latest social trends and news and perform risk assessment based on current social sentiment. For example, the risk assessment unit refers to the latest social trends and performs risk assessment based on current social sentiment for the text analyzed by the generation AI. For example, it identifies risks based on recent social trends. It also refers to the latest news and performs risk assessment by finding relevance with the text being analyzed. For example, it identifies the risk if the text contains expressions that have become problematic in recent news. It also refers to the latest social trends and news and performs risk assessment based on current social sentiment for the text analyzed by the generation AI. For example, it identifies risks based on recent social sentiment. This makes it possible to perform risk assessment by referring to the latest social trends and news.

[0036] The risk assessment unit can perform comprehensive risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design and user interface design. For example, the risk assessment unit can perform comprehensive risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design. For example, if a product design contains language that is inappropriate for a specific group, the risk is identified. The risk assessment unit can also perform comprehensive risk assessment by including user interface design in the scope of risk assessment. For example, if a UI design has the potential to cause discomfort to a specific user, the risk is identified. The risk assessment unit can also perform a broader scope of risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design and user interface design. For example, if the way a product is used is inappropriate for a specific group, the risk is identified. This allows the scope of risk assessment to be broadened, enabling comprehensive risk assessment.

[0037] The risk assessment unit can assess risks from the perspectives of different industries and fields, promoting broad consideration. For example, the risk assessment unit assesses risks from the perspectives of different industries for the text analyzed by the generative AI. For example, it identifies risks from the perspectives of the medical industry and the education industry. It also assesses risks from the perspectives of different fields, promoting broad consideration. For example, it identifies risks from the perspectives of the technical field and the cultural field. It also assesses risks from the perspectives of different industries and fields for the text analyzed by the generative AI. For example, it identifies risks from the perspectives of the business field and the social science field. This makes it possible to assess risks from the perspectives of different industries and fields.

[0038] The improvement suggestion unit can make specific improvement suggestions by referring to specific cases and past problem cases. For example, when the generation AI points out a risk, the improvement suggestion unit makes specific improvement suggestions by referring to specific cases. For example, it makes suggestions to avoid similar risks based on past problem cases. It also makes specific improvement suggestions by referring to past problem cases. For example, it makes suggestions to avoid similar expressions based on past cases that caused controversy. It also makes specific improvement suggestions by referring to specific cases and past problem cases when the generation AI points out a risk. For example, it makes suggestions to change specific expressions based on past cases. This makes it possible to make specific improvement suggestions by referring to specific cases and past problem cases.

[0039] The improvement suggestion unit can explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, the generation AI can explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, if a specific question may pose a risk, it can explain the reason in detail and propose an alternative. It can also explain high-risk parts in detail and propose specific improvement measures. For example, it can explain why a specific expression is problematic and propose changing it to an appropriate expression. It can also explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, it can explain why a specific wording poses a risk and propose a more appropriate wording. In this way, it can explain high-risk parts in detail and propose specific improvement measures.

[0040] The improvement proposal department can make comprehensive improvement proposals by expanding the scope of its improvement proposals beyond the content of questionnaires and interviews to also include the overall service design and marketing strategy. For example, the improvement proposal department can make comprehensive improvement proposals by expanding the scope of its improvement proposals beyond the content of questionnaires and interviews to also include the overall service design. For example, if the service design includes language that is inappropriate for a specific group, the department can identify that risk and make improvement proposals. The improvement proposal department can also make comprehensive improvement proposals by including the marketing strategy in its improvement proposals. For example, if marketing materials may offend specific users, the department can identify that risk and make improvement proposals. The department can also broaden the scope of its improvement proposals to include not only the content of questionnaires and interviews but also the overall service design and marketing strategy. For example, if the way the service is used is inappropriate for a specific group, the department can identify that risk and make improvement proposals. This makes it possible to broaden the scope of its improvement proposals and make comprehensive improvement proposals.

[0041] The improvement proposal unit can assess risks from the perspectives of different cultures and regions and make improvement proposals from a global perspective. For example, the generation AI evaluates risks from the perspective of different cultures based on the analysis results and makes improvement proposals from a global perspective. For example, if the content contains expressions that are problematic in a specific culture, the improvement proposal unit identifies the risk and makes improvement proposals. The generation AI also evaluates risks from the perspective of different regions and makes improvement proposals from a global perspective. For example, if the content contains expressions that are considered inappropriate in a specific region, the improvement proposal unit identifies the risk and makes improvement proposals. The generation AI also evaluates risks from the perspective of different cultures and regions based on the analysis results and makes improvement proposals from a global perspective. For example, the generation AI identifies risks based on social sentiment in a specific culture or region and makes improvement proposals. This makes it possible to assess risks from the perspective of different cultures and regions and make improvement proposals from a global perspective.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The self-check tool may further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit may analyze, for example, what services the user has used in the past and what kind of feedback the user has provided, and use this information to help with risk assessment. For example, if there is a lot of negative feedback about a particular service, it may be determined that a new project related to that service poses a similar risk. Furthermore, based on the user's behavioral history, it may be possible to evaluate the impact that a particular service has on a particular social group. This makes it possible to perform risk assessment that takes the user's behavioral history into account.

[0044] The self-check tool may further include an image analysis unit. The image analysis unit may analyze images contained in, for example, advertisements or marketing materials and perform risk assessment. For example, it may evaluate whether a particular image is inappropriate for a particular social group. The image analysis unit may also analyze text or symbols contained in an image and assess whether they pose a risk. For example, if a particular symbol has a discriminatory meaning, it may identify that risk. This enables risk assessment that takes image data into consideration.

[0045] The self-check tool can further include a database reference unit. The database reference unit can, for example, create a database of past risk assessment results and feedback and perform risk assessment by referring to it. For example, it can search the database for expressions or content that have been problematic in the past and identify risks by comparing them. The database reference unit can also refer to risk assessment results from other companies or industries and perform risk assessment based on those results. This makes it possible to perform risk assessment by utilizing past data.

[0046] The self-check tool may further include a profile analysis unit that analyzes the user's profile. The profile analysis unit may analyze profile information such as the user's age, gender, and occupation, and perform risk assessment based on the information. For example, if a content contains language that is inappropriate for a particular age group or gender, the risk may be identified. The profile analysis unit may also evaluate areas where consideration for specific social groups is lacking, based on the user's profile information. This enables risk assessment that takes the user's profile information into account.

[0047] The self-check tool can further include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit can analyze, for example, what products the user has purchased in the past and what services the user has used, and perform risk assessment based on that analysis. For example, if a particular product has received a lot of negative feedback, it can be determined that a new project related to that product also poses a similar risk. The purchase history analysis unit can also evaluate areas where consideration for specific social groups is lacking, based on the user's purchase history. This makes it possible to perform risk assessment that takes the user's purchase history into account.

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

[0049] Step 1: The text analysis unit analyzes the content of the survey or interview. For example, the generative AI analyzes the survey questions or interview scenario as input and identifies potential risks. Step 2: The risk assessment unit assesses risks based on the content analyzed by the text analysis unit. For example, the generation AI may identify specific risks based on the analysis results, create a risk assessment report, and provide feedback to relevant parties. Step 3: The Improvement Suggestion Department makes specific improvement suggestions based on the risks assessed by the Risk Assessment Department. For example, the Generation AI may generate suggestions such as, "This question may offend certain people," or "Changing this wording would be more appropriate." The Generation AI also continuously learns based on past risk assessment results and feedback, improving the accuracy of its risk assessments.

[0050] (Example 2) The self-check tool according to the embodiment of the present invention is a system that uses AI to self-check for lack of human rights awareness and social considerations at the service planning stage. As a result, the self-check tool can prevent risks at the service planning stage and protect the image of the company.

[0051] A self-check tool according to an embodiment includes a text analysis unit, a risk assessment unit, and an improvement suggestion unit. The text analysis unit analyzes the content of questionnaires and interviews. For example, the generation AI analyzes questionnaire questions and interview scenarios as input and identifies potential risks. The generation AI can also perform risk assessment based on text data. The risk assessment unit evaluates risks based on the content analyzed by the text analysis unit. For example, the generation AI identifies specific risks and proposes improvements based on the analysis results. The generation AI can also create a risk assessment report and provide feedback to relevant parties. The improvement suggestion unit makes specific improvement suggestions based on the risks assessed by the risk assessment unit. For example, the generation AI may generate a suggestion such as "This question may offend certain people" or an improvement suggestion such as "Changing this expression would be more appropriate." The generation AI can also continuously learn based on past risk assessment results and feedback to improve the accuracy of its risk assessment. This allows the self-check tool according to an embodiment to prevent risks from occurring at the service planning stage. For example, we can ensure that the content of questionnaires and interviews is appropriate and that surveys are conducted with due consideration for people outside the company. Furthermore, continuous learning allows us to always conduct risk assessments based on the latest standards.

[0052] The text analysis unit takes into account changes in context and nuances, enabling a detailed evaluation of the potential risks posed by phrases. For example, when generative AI performs text analysis, the text analysis unit takes into account changes in context and evaluates the potential risks posed by specific phrases. For example, if the meaning of the same phrase changes depending on the context before and after, the unit analyzes those changes and identifies the risks. The unit also takes nuances into account to evaluate the potential risks posed by specific phrases. For example, if sarcasm or suggestive expressions are included, the unit analyzes those nuances and identifies the risks. The unit also analyzes changes in context and nuances in detail to evaluate the potential risks posed by specific phrases. For example, if the same words are used in different contexts, the unit analyzes the differences and identifies the risks. This makes it possible to evaluate risks by taking context changes and nuances into account.

[0053] The text analysis unit can evaluate risk by referencing past cases of online outrage or cases that have been considered socially problematic and finding similarities. For example, the text analysis unit can evaluate risk by referencing past cases of online outrage or cases that have been considered socially problematic, finding similarities with the text being analyzed. For example, it can create a database of expressions and content that have been problematic in the past and compare them to identify risks. It can also evaluate risk by referencing cases that have been considered socially problematic and finding similarities with the text being analyzed. For example, it can identify the risk if the text contains discriminatory expressions against a specific social group. It can also create a database of past cases of online outrage or cases that have been considered socially problematic, and refer to that to find similarities with the text being analyzed by the generation AI and evaluate risk. For example, it can identify the risk if the text contains expressions similar to those in past cases. This makes it possible to evaluate risk by referencing past cases.

[0054] The text analysis unit can use the emotion estimation function to evaluate the emotional impact of the content of a questionnaire or interview on a user and identify parts that may cause negative emotions. The text analysis unit, for example, uses the emotion estimation function to evaluate the emotional impact of the content of a questionnaire or interview on a user. For example, if a particular question is likely to cause discomfort to the user, the risk is identified. The emotion estimation function also identifies parts that may cause negative emotions. For example, if a particular expression is likely to cause anger or sadness to the user, the risk is identified. The text analysis unit also evaluates the emotional impact of the content of a questionnaire or interview on a user and identifies parts that may cause negative emotions. For example, if a particular question is likely to cause stress to the user, the risk is identified. This makes it possible to evaluate the emotional impact on the user and identify the risk of causing negative emotions.

[0055] The text analysis unit can expand the scope of its analysis beyond questionnaires and interviews to also include advertisements, marketing materials, and internal documents, enabling a broader risk assessment. For example, the text analysis unit can expand the scope of its text analysis beyond questionnaires and interviews to also include advertisements and marketing materials, thereby performing a broader risk assessment. For example, if an advertising slogan contains language that is inappropriate for a particular group, the risk can be identified. A broader risk assessment can also be performed by including internal documents in the analysis scope. For example, the unit can evaluate whether internal presentation materials contain language that would be problematic if they were leaked to the public. The scope of text analysis can also be expanded to include advertisements, marketing materials, and internal documents, performing a risk assessment. For example, if marketing materials contain prejudice against a particular social group, the risk can be identified. This allows the analysis scope to be broadened, enabling a comprehensive risk assessment.

[0056] The text analysis unit evaluates risks from the perspectives of different cultures and regions, promoting consideration from a global perspective. For example, the text analysis unit evaluates risks from the perspectives of different cultures for text analyzed by the generative AI. For example, if the text contains expressions that are problematic in a particular culture, it will identify those risks. It also evaluates risks from the perspectives of different regions, promoting consideration from a global perspective. For example, if the text contains expressions that are considered inappropriate in a particular region, it will identify those risks. It also evaluates risks from the perspectives of different cultures and regions for text analyzed by the generative AI. For example, it will identify risks based on social sentiment in a particular culture or region. This makes it possible to evaluate risks from the perspectives of different cultures and regions.

[0057] The text analysis unit can use the emotion estimation function to predict the user's emotional response based on the results of text analysis and suggest expressions that will elicit positive emotions. The text analysis unit, for example, uses the emotion estimation function to predict the user's emotional response based on the results of text analysis. For example, if a particular expression is likely to give the user a sense of joy or relief, the text analysis unit suggests that expression. The text analysis unit also predicts the user's emotional response and suggests expressions that will elicit positive emotions. For example, if a particular question evokes positive emotions in the user, the text analysis unit suggests that question. The text analysis unit also uses the emotion estimation function to predict the user's emotional response based on the results of text analysis and suggests expressions that will elicit positive emotions. For example, if a particular phrase evokes positive emotions in the user, the text analysis unit suggests that phrase. This makes it possible to predict the user's emotional response and suggest expressions that will elicit positive emotions.

[0058] The risk assessment unit can perform a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking, and identify specific risks. For example, when the generative AI performs an analysis, the risk assessment unit performs a detailed evaluation of any areas where consideration for specific social groups is lacking. For example, if discriminatory language against a specific group is included, the risk is identified. The risk assessment unit can also perform a detailed evaluation of any areas where consideration for minorities is lacking, and identify specific risks. For example, if prejudice against a specific minority group is included, the risk is identified. The risk assessment unit can also perform a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking. For example, if stereotypes against a specific group are included, the risk is identified. This allows for a detailed evaluation of any areas where consideration for specific social groups or minorities is lacking.

[0059] The risk assessment unit can refer to the latest social trends and news and perform risk assessment based on current social sentiment. For example, the risk assessment unit refers to the latest social trends and performs risk assessment based on current social sentiment for the text analyzed by the generation AI. For example, it identifies risks based on recent social trends. It also refers to the latest news and performs risk assessment by finding relevance with the text being analyzed. For example, it identifies the risk if the text contains expressions that have become problematic in recent news. It also refers to the latest social trends and news and performs risk assessment based on current social sentiment for the text analyzed by the generation AI. For example, it identifies risks based on recent social sentiment. This makes it possible to perform risk assessment by referring to the latest social trends and news.

[0060] The risk assessment unit can use the emotion estimation function to evaluate the likelihood that the content of a questionnaire or interview will cause a specific emotion and identify high-risk parts. The risk assessment unit, for example, uses the emotion estimation function to evaluate the likelihood that the content of a questionnaire or interview will cause a specific emotion. For example, if a specific question is likely to cause anger or sadness in the user, the risk is identified. The risk assessment unit also evaluates the likelihood that the content of a questionnaire or interview will cause a specific emotion and identifies high-risk parts. For example, if a specific expression is likely to cause discomfort to the user, the risk is identified. The emotion estimation function also evaluates the likelihood that the content of a questionnaire or interview will cause a specific emotion and identifies high-risk parts. For example, if a specific phrase is likely to cause stress to the user, the risk is identified. In this way, the likelihood of causing a specific emotion can be evaluated and high-risk parts can be identified.

[0061] The risk assessment unit can perform comprehensive risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design and user interface design. For example, the risk assessment unit can perform comprehensive risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design. For example, if a product design contains language that is inappropriate for a specific group, the risk is identified. The risk assessment unit can also perform comprehensive risk assessment by including user interface design in the scope of risk assessment. For example, if a UI design has the potential to cause discomfort to a specific user, the risk is identified. The risk assessment unit can also perform a broader scope of risk assessment by expanding the scope of risk assessment beyond the service planning stage to include product design and user interface design. For example, if the way a product is used is inappropriate for a specific group, the risk is identified. This allows the scope of risk assessment to be broadened, enabling comprehensive risk assessment.

[0062] The risk assessment unit can assess risks from the perspectives of different industries and fields, promoting broad consideration. For example, the risk assessment unit assesses risks from the perspectives of different industries for the text analyzed by the generative AI. For example, it identifies risks from the perspectives of the medical industry and the education industry. It also assesses risks from the perspectives of different fields, promoting broad consideration. For example, it identifies risks from the perspectives of the technical field and the cultural field. It also assesses risks from the perspectives of different industries and fields for the text analyzed by the generative AI. For example, it identifies risks from the perspectives of the business field and the social science field. This makes it possible to assess risks from the perspectives of different industries and fields.

[0063] The risk assessment unit can use the emotion estimation function to predict the user's emotional reaction based on the results of the risk assessment and make improvement suggestions to avoid causing negative emotions. The risk assessment unit, for example, uses the emotion estimation function to predict the user's emotional reaction based on the results of the risk assessment. For example, if a specific expression is likely to cause discomfort to the user, a suggestion to change the expression is made. The risk assessment unit also predicts the user's emotional reaction and makes improvement suggestions to avoid causing negative emotions. For example, if a specific question is likely to cause stress to the user, a suggestion to change the question is made. The emotion estimation function also predicts the user's emotional reaction based on the results of the risk assessment and makes improvement suggestions to avoid causing negative emotions. For example, if a specific phrase is likely to cause anger or sadness to the user, a suggestion to change the phrase is made. This makes it possible to predict the user's emotional reaction and make improvement suggestions to avoid causing negative emotions.

[0064] The improvement suggestion unit can make specific improvement suggestions by referring to specific cases and past problem cases. For example, when the generation AI points out a risk, the improvement suggestion unit makes specific improvement suggestions by referring to specific cases. For example, it makes suggestions to avoid similar risks based on past problem cases. It also makes specific improvement suggestions by referring to past problem cases. For example, it makes suggestions to avoid similar expressions based on past cases that caused controversy. It also makes specific improvement suggestions by referring to specific cases and past problem cases when the generation AI points out a risk. For example, it makes suggestions to change specific expressions based on past cases. This makes it possible to make specific improvement suggestions by referring to specific cases and past problem cases.

[0065] The improvement suggestion unit can explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, the generation AI can explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, if a specific question may pose a risk, it can explain the reason in detail and propose an alternative. It can also explain high-risk parts in detail and propose specific improvement measures. For example, it can explain why a specific expression is problematic and propose changing it to an appropriate expression. It can also explain high-risk parts in detail based on the analysis results and propose specific improvement measures. For example, it can explain why a specific wording poses a risk and propose a more appropriate wording. In this way, it can explain high-risk parts in detail and propose specific improvement measures.

[0066] The improvement suggestion unit can use the emotion estimation function to make specific suggestions that take the user's emotions into consideration when pointing out risks and making improvement suggestions. The improvement suggestion unit, for example, uses the emotion estimation function to make specific suggestions that take the user's emotions into consideration when pointing out risks and making improvement suggestions. For example, if a specific expression is likely to cause discomfort to the user, a suggestion to change the expression is made. The improvement suggestion unit also makes risk suggestion and improvement suggestions taking the user's emotions into consideration. For example, if a specific question is likely to cause stress to the user, a suggestion to change the question is made. The emotion estimation function also makes specific suggestions that take the user's emotions into consideration when pointing out risks and making improvement suggestions. For example, if a specific phrase is likely to cause anger or sadness to the user, a suggestion to change the phrase is made. This makes it possible to make specific suggestions that take the user's emotions into consideration.

[0067] The improvement proposal department can make comprehensive improvement proposals by expanding the scope of its improvement proposals beyond the content of questionnaires and interviews to also include the overall service design and marketing strategy. For example, the improvement proposal department can make comprehensive improvement proposals by expanding the scope of its improvement proposals beyond the content of questionnaires and interviews to also include the overall service design. For example, if the service design includes language that is inappropriate for a specific group, the department can identify that risk and make improvement proposals. The improvement proposal department can also make comprehensive improvement proposals by including the marketing strategy in its improvement proposals. For example, if marketing materials may offend specific users, the department can identify that risk and make improvement proposals. The department can also broaden the scope of its improvement proposals to include not only the content of questionnaires and interviews but also the overall service design and marketing strategy. For example, if the way the service is used is inappropriate for a specific group, the department can identify that risk and make improvement proposals. This makes it possible to broaden the scope of its improvement proposals and make comprehensive improvement proposals.

[0068] The improvement proposal unit can assess risks from the perspectives of different cultures and regions and make improvement proposals from a global perspective. For example, the generation AI evaluates risks from the perspective of different cultures based on the analysis results and makes improvement proposals from a global perspective. For example, if the content contains expressions that are problematic in a specific culture, the improvement proposal unit identifies the risk and makes improvement proposals. The generation AI also evaluates risks from the perspective of different regions and makes improvement proposals from a global perspective. For example, if the content contains expressions that are considered inappropriate in a specific region, the improvement proposal unit identifies the risk and makes improvement proposals. The generation AI also evaluates risks from the perspective of different cultures and regions based on the analysis results and makes improvement proposals from a global perspective. For example, the generation AI identifies risks based on social sentiment in a specific culture or region and makes improvement proposals. This makes it possible to assess risks from the perspective of different cultures and regions and make improvement proposals from a global perspective.

[0069] The improvement suggestion unit can use the emotion estimation function to predict the user's emotional response when making an improvement suggestion and make specific suggestions to elicit positive emotions. The improvement suggestion unit, for example, uses the emotion estimation function to predict the user's emotional response when making an improvement suggestion. For example, if a specific expression is likely to give the user a sense of joy or relief, the improvement suggestion unit suggests the expression. The improvement suggestion unit also predicts the user's emotional response and makes specific suggestions to elicit positive emotions. For example, if a specific question evokes positive emotions in the user, the improvement suggestion unit suggests the question. The improvement suggestion unit also uses the emotion estimation function to predict the user's emotional response when making an improvement suggestion and make specific suggestions to elicit positive emotions. For example, if a specific phrase evokes positive emotions in the user, the improvement suggestion unit suggests the phrase. This makes it possible to predict the user's emotional response and make specific suggestions to elicit positive emotions.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The self-check tool may further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit may analyze, for example, what services the user has used in the past and what kind of feedback the user has provided, and use this information to help with risk assessment. For example, if there is a lot of negative feedback about a particular service, it may be determined that a new project related to that service poses a similar risk. Furthermore, based on the user's behavioral history, it may be possible to evaluate the impact that a particular service has on a particular social group. This makes it possible to perform risk assessment that takes the user's behavioral history into account.

[0072] The self-check tool can further include a voice analysis unit. The voice analysis unit can analyze, for example, voice data from interviews or meetings and perform risk assessment in the same way as with text data. For example, it can evaluate whether specific phrases or expressions are inappropriate from the voice data. It can also estimate the speaker's emotions from the voice data and assess risk based on those emotions. For example, if the speaker expresses anger or annoyance, it can determine that those parts may pose a risk. This makes it possible to perform risk assessment that takes voice data into consideration.

[0073] The self-check tool may further include an image analysis unit. The image analysis unit may analyze images contained in, for example, advertisements or marketing materials and perform risk assessment. For example, it may evaluate whether a particular image is inappropriate for a particular social group. The image analysis unit may also analyze text or symbols contained in an image and assess whether they pose a risk. For example, if a particular symbol has a discriminatory meaning, it may identify that risk. This enables risk assessment that takes image data into consideration.

[0074] The self-check tool may further include a real-time feedback unit. The real-time feedback unit may assess risks in real time and provide immediate feedback during the conduct of, for example, a questionnaire or interview. For example, if a particular question is determined to be inappropriate, the real-time feedback unit may suggest changing the question on the spot. The real-time feedback unit may also monitor the user's emotional reactions in real time and issue a warning if a question is likely to cause negative emotions. This enables real-time risk assessment and feedback.

[0075] The self-check tool may further include a feedback collection unit that collects user feedback. The feedback collection unit may collect user feedback after, for example, a questionnaire or interview, and use the collected feedback for risk assessment. For example, if a user expresses discomfort with a particular question, the risk may be reassessed based on the feedback. The feedback collection unit may also collect the user's emotional reactions and use the emotional reactions to improve the accuracy of the risk assessment. This allows for risk assessment that takes user feedback into consideration.

[0076] The self-check tool can further include a database reference unit. The database reference unit can, for example, create a database of past risk assessment results and feedback and perform risk assessment by referring to it. For example, it can search the database for expressions or content that have been problematic in the past and identify risks by comparing them. The database reference unit can also refer to risk assessment results from other companies or industries and perform risk assessment based on those results. This makes it possible to perform risk assessment by utilizing past data.

[0077] The self-check tool may further include a profile analysis unit that analyzes the user's profile. The profile analysis unit may analyze profile information such as the user's age, gender, and occupation, and perform risk assessment based on the information. For example, if a content contains language that is inappropriate for a particular age group or gender, the risk may be identified. The profile analysis unit may also evaluate areas where consideration for specific social groups is lacking, based on the user's profile information. This enables risk assessment that takes the user's profile information into account.

[0078] The self-check tool may further include a biometric information analysis unit that analyzes the user's biometric information. The biometric information analysis unit may analyze, for example, the user's heart rate, electrodermal activity, and other biometric information, and perform risk assessment based on the analysis. For example, if a particular question causes stress to the user, the biometric information change can be detected and the risk identified. The biometric information analysis unit may also estimate the user's emotional response from the biometric information and perform risk assessment based on the estimation. This enables risk assessment that takes biometric information into account.

[0079] The self-check tool can further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit can, for example, analyze what comments the user makes on social media and what reactions they receive, and perform risk assessment based on the results. For example, if a particular comment causes controversy, the risk can be identified. The social media analysis unit can also estimate the user's emotional reaction from their social media activity and perform risk assessment based on that. This enables risk assessment that takes social media activity into account.

[0080] The self-check tool can further include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit can analyze, for example, what products the user has purchased in the past and what services the user has used, and perform risk assessment based on that analysis. For example, if a particular product has received a lot of negative feedback, it can be determined that a new project related to that product also poses a similar risk. The purchase history analysis unit can also evaluate areas where consideration for specific social groups is lacking, based on the user's purchase history. This makes it possible to perform risk assessment that takes the user's purchase history into account.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The text analysis unit analyzes the content of the survey or interview. For example, the generative AI analyzes the survey questions or interview scenario as input and identifies potential risks. Step 2: The risk assessment unit assesses risks based on the content analyzed by the text analysis unit. For example, the generation AI may identify specific risks based on the analysis results, create a risk assessment report, and provide feedback to relevant parties. Step 3: The Improvement Suggestion Department makes specific improvement suggestions based on the risks assessed by the Risk Assessment Department. For example, the Generation AI may generate suggestions such as, "This question may offend certain people," or "Changing this wording would be more appropriate." The Generation AI also continuously learns based on past risk assessment results and feedback, improving the accuracy of its risk assessments.

[0083] 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.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 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 processing similar to that of the specific processing unit 290 using these models.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 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 equipped with a generative AI, A text analysis section that analyzes the contents of questionnaires and interviews, a risk assessment unit that assesses risk based on the content analyzed by the text analysis unit; an improvement suggestion unit that makes specific improvement suggestions based on the risks assessed by the risk assessment unit; A system characterized by:

2. The text analysis unit Considering contextual variations and nuances, we thoroughly evaluate the potential risks of phrases.

2. The system of claim 1.

3. The text analysis unit We look at past cases of online outrage and socially problematic cases, find similarities, and assess risks.

2. The system of claim 1.

4. The text analysis unit Evaluate the emotional impact of the survey or interview on users and identify areas that may trigger negative emotions 2. The system of claim 1.

5. The text analysis unit Expand the scope of analysis beyond the surveys and interviews to include advertising, marketing materials, internal company documents, etc., to conduct a broad risk assessment.

2. The system of claim 1.

6. The text analysis unit Conduct risk assessments from different cultural and regional perspectives to promote global consideration 2. The system of claim 1.

7. The text analysis unit Predicts the user's emotional response based on the results of text analysis and suggests expressions that will elicit positive emotions.

2. The system of claim 1.

8. The risk assessment unit Conduct a detailed assessment of areas where consideration for specific social groups and minorities is lacking and identify specific risks.

2. The system of claim 1.

Images