system

Abstract

The system of this embodiment aims to detect unconscious biases hidden in statements and convert them appropriately. [Solution] A system according to an embodiment includes a receiving unit, an analysis unit, a detection unit, and a suggestion unit. The receiving unit inputs a utterance. The analysis unit analyzes the utterance input by the receiving unit. The detection unit detects unconscious bias based on the utterance analyzed by the analysis unit. The suggestion unit converts the utterance containing unconscious bias detected by the detection unit into specific technical content.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced the challenge of automatically detecting unconscious bias hidden in statements and appropriately converting them.

[0005] The system of this embodiment aims to detect unconscious biases hidden in statements and convert them appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, an analysis unit, a detection unit, and a proposal unit. The receiving unit inputs a utterance. The analysis unit analyzes the utterance input by the receiving unit. The detection unit detects unconscious bias based on the utterance analyzed by the analysis unit. The proposal unit converts the utterance containing unconscious bias detected by the detection unit into specific technical content. [Effects of the Invention]

[0007] The system according to the embodiment can detect unconscious biases hidden in statements and convert them appropriately. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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) An unconscious bias detection system according to an embodiment of the present invention uses AI to detect "unconscious bias" hidden in speech and propose appropriate conversions. In this unconscious bias detection system, a user inputs a speech, and the AI ​​analyzes the speech to detect whether it contains unconscious bias. If unconscious bias is detected, the AI ​​proposes to convert the speech to an appropriate expression. This allows users to consider whether their speech is offensive to the other person and promote more appropriate communication. For example, if a user inputs a statement such as "Because you are a certain gender, you have certain skills," the statement is input into the AI. The AI ​​then analyzes the input statement, understands its content, and detects whether it contains unconscious bias. For example, it determines that the phrase "Because you are a certain gender" is a gender-based stereotype. If unconscious bias is detected, the AI ​​proposes to convert the statement to an appropriate expression. For example, it proposes to convert the statement to "So you have certain skills." This allows users to consider whether their speech is offensive to the other person. This mechanism allows users to promote more appropriate communication and prevent offense to the other person. For example, in various situations such as at work or school, smooth communication can be achieved by detecting unconscious bias hidden in speech and converting it into appropriate expressions. In this way, the unconscious bias detection system can automatically analyze user speech and convert it into appropriate expressions, thereby achieving more appropriate communication.

[0029] An unconscious bias detection system according to an embodiment includes a reception unit, an analysis unit, a detection unit, and a suggestion unit. The reception unit receives a user's input of a utterance. The method by which the user inputs the utterance includes, but is not limited to, voice input, text input, and gesture input. The reception unit can receive the user's input of a utterance using, for example, voice input. The reception unit can also receive the user's input of a utterance using text input. The reception unit can also receive the user's input of a utterance using gesture input. For example, the reception unit can convert the user's voice into text using speech recognition technology. The analysis unit analyzes the utterance input by the reception unit. The analysis unit can analyze the content of the utterance using, for example, natural language processing technology. The analysis unit can analyze the grammatical structure of the utterance to understand its meaning. The analysis unit can also analyze the context of the utterance to understand its intention. For example, the analysis unit can extract keywords from the utterance and identify the subject of the utterance. The detection unit detects unconscious bias based on the utterance analyzed by the analysis unit. The detection unit detects unconscious biases such as gender bias, racial bias, and age bias. The detection unit can detect, for example, stereotypes contained in utterances. The detection unit can also detect prejudices contained in utterances. For example, the detection unit can detect discriminatory language contained in utterances. The suggestion unit makes a suggestion to convert utterances containing unconscious bias detected by the detection unit into appropriate language. For example, the suggestion unit makes a suggestion to convert utterances containing unconscious biases detected by the detection unit into appropriate language. For example, the suggestion unit can also make a suggestion to convert utterances containing gender stereotypes into neutral language. As a result, the unconscious bias detection system according to the embodiment can automatically analyze user utterances and convert them into appropriate language, thereby enabling more appropriate communication.

[0030] The suggestion unit may include a feedback unit that accepts user feedback. The feedback unit, for example, provides an interface for the user to provide feedback on the suggestion. The feedback unit, for example, can accept text comments. The feedback unit may also accept an evaluation score. For example, the feedback unit may allow the user to input an evaluation score from 1 to 5 for the suggestion. The feedback unit may also accept voice feedback. For example, the feedback unit may allow the user to provide voice feedback on the suggestion. In this way, by accepting user feedback, the accuracy of the suggestion can be improved. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit may input user feedback data to a generation AI and cause the generation AI to analyze the feedback data.

[0031] The analysis unit may include a learning unit that learns past utterance data. The learning unit, for example, collects past utterance data and uses it as learning data for the analysis unit. The learning unit, for example, may collect past conversation logs. The learning unit may also collect past voice recordings. For example, the learning unit may collect past text data and use it as learning data for the analysis unit. This allows the accuracy of analysis to be improved by learning from past utterance data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input past utterance data into a generation AI and cause the generation AI to learn the utterance data.

[0032] The suggestion unit can make a suggestion to convert a statement containing detected unconscious bias into appropriate expression. For example, the suggestion unit can make a suggestion to convert a statement containing detected unconscious bias into expression based on political correctness. The suggestion unit can also make a suggestion to convert into expression based on cultural considerations. For example, the suggestion unit can make a suggestion to convert a statement containing gender stereotypes into neutral expression. This allows for more appropriate communication by converting a statement containing detected unconscious bias into appropriate expression. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input a statement containing detected unconscious bias into a generation AI and have the generation AI convert the statement into appropriate expression.

[0033] The reception unit can analyze the user's past speech history and select the optimal reception method. The reception unit, for example, collects the user's past speech history and selects the optimal reception method. The reception unit, for example, can collect and analyze past conversation logs. The reception unit can also collect and analyze past voice recordings. For example, the reception unit can collect and analyze past text data. In this way, the optimal reception method can be selected by analyzing the user's past speech history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past speech history data to a generation AI and cause the generation AI to analyze the speech history.

[0034] The reception unit can filter utterances based on the user's current situation and areas of interest when receiving the utterances. The reception unit, for example, grasps the user's current situation and adjusts the method for receiving utterances. The reception unit can, for example, acquire the user's location information and grasp the current situation. The reception unit can also grasp the user's activity status and adjust the method for receiving utterances. For example, the reception unit adjusts the method for receiving utterances when the user is in a meeting. The reception unit can also adjust the method for receiving utterances when the user is on a break. Furthermore, the reception unit can grasp the user's areas of interest and filter the utterances. For example, the reception unit preferentially accepts utterances related to topics in which the user is currently interested. The reception unit can also filter and accept highly relevant utterances based on the user's areas of interest. In this way, by filtering based on the user's current situation and areas of interest, highly relevant utterances can be preferentially accepted. Some or all of the above-described processing in the reception unit may be performed, for example, using AI or without AI. For example, the reception unit can input the user's location information and activity status data into the generation AI and have the generation AI perform filtering.

[0035] When receiving a utterance, the reception unit can prioritize receiving highly relevant utterances based on the user's geographical location information. The reception unit, for example, acquires the user's geographical location information and adjusts the method for receiving the utterances. The reception unit can acquire the user's location information using GPS data, for example. The reception unit can also acquire the user's address information and adjust the method for receiving the utterances. For example, when the user is in a specific area, the reception unit can prioritize receiving utterances related to that area. When the user is traveling, the reception unit can prioritize receiving utterances related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving utterances related to the home. In this way, by taking the user's geographical location information into consideration, highly relevant utterances can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input GPS data and address information to the generation AI and cause the generation AI to filter highly relevant utterances.

[0036] The reception unit can analyze the user's online activity when receiving a comment and receive relevant comments. The reception unit can, for example, analyze the user's social media activity and adjust the method for receiving comments. The reception unit can, for example, analyze the user's social media posts. The reception unit can also analyze the user's browsing history and adjust the method for receiving comments. For example, the reception unit can prioritize receiving comments related to topics in which the user has recently shown interest on social media. The reception unit can also analyze the user's social media activity history and receive highly relevant comments. Furthermore, the reception unit can prioritize receiving comments related to accounts the user follows on social media. In this way, by analyzing the user's social media activity, highly relevant comments can be preferentially received. Some or all of the above-described processing by the reception unit can be performed, for example, using AI or without AI. For example, the reception unit can input social media post data and browsing history data into the generation AI and cause the generation AI to filter highly relevant comments.

[0037] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the statement. For example, the analysis unit analyzes the content of the statement and evaluates the importance of the statement. For example, the analysis unit can evaluate the impact of the statement and determine the importance. The analysis unit can also evaluate the importance based on the content of the statement. For example, the analysis unit performs a detailed analysis if the content of the statement contains important information. For example, the analysis unit can perform a concise analysis if the content of the statement contains general information. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the statement. For example, the analysis unit prioritizes analysis of statements with high importance. This allows for adjusting the level of detail of the analysis based on the importance of the statement, thereby providing more appropriate analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input content data of the statement to a generation AI and have the generation AI evaluate the importance.

[0038] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the statement. For example, the analysis unit classifies the category of the statement and selects an appropriate analysis algorithm. For example, the analysis unit can apply a gender bias detection algorithm to statements related to gender. The analysis unit can also apply a racial bias detection algorithm to statements related to race. For example, the analysis unit can apply an age bias detection algorithm to statements related to age. In this way, by applying different analysis algorithms depending on the category of the statement, more accurate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input statement category data into the generation AI and cause the generation AI to select an appropriate analysis algorithm.

[0039] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the comments. The analysis unit, for example, evaluates the time of submission of the comments and determines the priority of analysis. The analysis unit can determine the priority of comments based on the submission date and time, for example. The analysis unit can also determine the priority of comments based on the order of submission. For example, the analysis unit prioritizes analysis of recently submitted comments. The analysis unit can also prioritize analysis of comments submitted within a specific time period. In this way, by determining the priority of analysis based on the time of submission of the comments, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time of submission of comments to the generation AI and have the generation AI determine the priority.

[0040] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the statements. The analysis unit, for example, analyzes the content of the statements and evaluates the relevance. The analysis unit can, for example, evaluate the similarity of the content of the statements and determine the relevance. The analysis unit can also evaluate the consistency of the topics of the statements and determine the relevance. For example, the analysis unit prioritizes analysis of highly relevant statements. The analysis unit can also postpone analysis of less relevant statements. In this way, by adjusting the order of analysis based on the relevance of the statements, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input content data of the statements to a generation AI and have the generation AI perform a relevance evaluation.

[0041] The detection unit can improve the accuracy of detection by taking into account the interrelationships between statements during detection. The detection unit can, for example, analyze the interrelationships between multiple statements to improve the accuracy of bias detection. The detection unit can, for example, consider the context of statements to improve the accuracy of bias detection. The detection unit can also improve the accuracy of bias detection by taking into account the context of statements. For example, the detection unit analyzes the context before and after statements to improve the accuracy of bias detection. In this way, by taking into account the interrelationships between statements, the accuracy of detection can be improved. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input interrelationship data between statements to a generation AI and cause the generation AI to perform an analysis of the interrelationships.

[0042] The detection unit can perform detection by taking into account attribute information of the person who submitted the comment. The detection unit can detect bias, for example, by taking into account gender information of the person who submitted the comment. The detection unit can detect bias, for example, by taking into account age information of the person who submitted the comment. The detection unit can also detect bias by taking into account occupation information of the person who submitted the comment. For example, the detection unit detects bias based on attribute information of the person who submitted the comment. In this way, by taking into account the attribute information of the person who submitted the comment, more accurate detection results can be provided. Some or all of the above-mentioned processing in the detection unit can be performed using AI, for example, or can be performed without using AI. For example, the detection unit can input attribute information data of the person who submitted the comment into the generation AI and cause the generation AI to analyze the attribute information.

[0043] The detection unit can perform detection by taking into account the geographical distribution of statements. For example, the detection unit can analyze the geographical distribution of statements to detect bias. For example, the detection unit can analyze the distribution of statements by region to detect bias. The detection unit can also analyze the distribution of statements by country to detect bias. For example, the detection unit preferentially detects statements related to a specific region. The detection unit can also detect statements that cover a wide geographical area. In this way, by taking the geographical distribution of statements into consideration, more accurate detection results can be provided. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input geographical distribution data of statements to a generation AI and cause the generation AI to analyze the geographical distribution.

[0044] The detection unit can improve the accuracy of detection by referring to literature related to the statement during detection. The detection unit can, for example, improve the accuracy of bias detection by referring to related literature. The detection unit can, for example, improve the accuracy of bias detection by referring to academic papers. The detection unit can also improve the accuracy of bias detection by referring to specialized books. For example, the detection unit detects bias based on related literature. In this way, by referring to literature related to the statement, the accuracy of detection can be improved. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input related literature data into the generation AI and cause the generation AI to refer to the literature.

[0045] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the statement. For example, the suggestion unit analyzes the content of the statement and evaluates the importance of the statement. For example, the suggestion unit can evaluate the influence of the statement and determine the importance. The suggestion unit can also evaluate the importance based on the content of the statement. For example, the suggestion unit makes a detailed proposal if the content of the statement contains important information. The suggestion unit can also make a concise proposal if the content of the statement contains general information. Furthermore, the suggestion unit can determine the priority of the proposal based on the importance of the statement. For example, the suggestion unit prioritizes suggestions with high importance. In this way, by adjusting the level of detail of the proposal based on the importance of the statement, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input content data of the statement to a generation AI and cause the generation AI to evaluate the importance.

[0046] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the utterance. For example, the suggestion unit classifies the category of the utterance and selects an appropriate suggestion algorithm. For example, the suggestion unit can apply a gender bias correction algorithm to utterances related to gender. The suggestion unit can also apply a race bias correction algorithm to utterances related to race. For example, the suggestion unit can apply an age bias correction algorithm to utterances related to age. In this way, by applying different suggestion algorithms depending on the category of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI, for example. For example, the suggestion unit can input utterance category data into a generation AI and cause the generation AI to select an appropriate suggestion algorithm.

[0047] When making a proposal, the suggestion unit can determine the priority of the proposal based on the time of submission of the comment. The suggestion unit, for example, evaluates the time of submission of the comment and determines the priority of the proposal. The suggestion unit can determine the priority of the comment based on the submission date and time, for example. The suggestion unit can also determine the priority of the comment based on the order of submission. For example, the suggestion unit can prioritize proposals for recently submitted comments. The suggestion unit can also prioritize proposals for comments submitted within a specific time period. In this way, by determining the priority of the proposal based on the time of submission of the comment, more appropriate proposals can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input comment submission time data into a generation AI and have the generation AI determine the priority.

[0048] When making a suggestion, the suggestion unit can adjust the order of suggestions based on the relevance of the utterances. The suggestion unit, for example, analyzes the content of the utterances and evaluates the relevance. The suggestion unit, for example, can evaluate the similarity of the content of the utterances and determine the relevance. The suggestion unit can also evaluate the matching of the topics of the utterances and determine the relevance. For example, the suggestion unit prioritizes suggestions for highly relevant utterances. The suggestion unit can also postpone suggestions for less relevant utterances. In this way, by adjusting the order of suggestions based on the relevance of the utterances, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input content data of the utterances to a generation AI and cause the generation AI to evaluate the relevance.

[0049] When receiving feedback, the feedback unit can select the optimal reception method by referring to the user's past feedback history. The feedback unit, for example, collects the user's past feedback history and selects the optimal reception method. The feedback unit, for example, can collect and analyze past comments. The feedback unit can also collect and analyze past evaluation scores. For example, the feedback unit can collect and analyze past survey results. In this way, the optimal reception method can be selected by referring to the user's past feedback history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, AI, for example. For example, the feedback unit can input past feedback history data into a generation AI and cause the generation AI to analyze the feedback history.

[0050] When receiving feedback, the feedback unit can select the optimal feedback reception method by taking into account the user's device information. The feedback unit, for example, acquires the user's device information and selects the optimal feedback reception method. The feedback unit can, for example, acquire the type of device being used. The feedback unit can also acquire the device's OS and browser information and adjust the feedback reception method. For example, if the user is using a smartphone, the feedback unit can provide a feedback reception method tailored to the screen size. If the user is using a tablet, the feedback unit can provide a feedback reception method optimized for a large screen. Furthermore, if the user is using a smartwatch, the feedback unit can provide a simple and highly visible feedback reception method. In this way, the optimal feedback reception method can be provided by taking into account the user's device information. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input device information data to a generation AI and cause the generation AI to select the optimal reception method.

[0051] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, collects past learning data and optimizes the learning algorithm. The learning unit, for example, can collect and analyze past training data. The learning unit can also collect and analyze past verification data. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. Furthermore, the learning unit can adjust parameters of the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or without AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the algorithm.

[0052] During learning, the learning unit can weight the learning data based on the time of submission of the utterances. The learning unit, for example, evaluates the time of submission of the utterances and weights the learning data. The learning unit can weight the learning data based on the submission date and time, for example. The learning unit can also weight the learning data based on the order of submission. For example, the learning unit weights recently submitted utterances. The learning unit can also weight utterances submitted within a specific time period. In this way, more appropriate learning can be performed by weighting the learning data based on the time of submission of the utterances. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the time of submission of the utterances to a generation AI and have the generation AI evaluate the weighting.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] When inputting a user's comment, the reception unit can monitor the user's current health condition and accept the comment at an appropriate timing. For example, the reception unit can measure the user's heart rate and blood pressure with a sensor and temporarily delay accepting the comment if the user's stress level is high. The reception unit can also monitor the user's sleep state and refrain from accepting comments if the user is sleep-deprived. Furthermore, the reception unit can grasp the user's eating habits and refrain from accepting comments immediately after a meal. This allows for more appropriate communication by adjusting the timing of accepting comments according to the user's health condition.

[0055] When analyzing a user's utterances, the analysis unit learns the user's past utterance patterns and can more accurately understand the intention of the utterance. For example, the analysis unit can memorize specific phrases and expressions used by the user in the past and infer the intention when a similar phrase is used again. The analysis unit can also refer to the context of the user's past utterances to more deeply understand the meaning of the current utterance. Furthermore, the analysis unit can analyze the emotional tone of the user's past utterances and estimate the emotional tone of the current utterance. In this way, by learning the user's past utterance patterns, the intention of the utterance can be more accurately understood and appropriate analysis results can be provided.

[0056] When making a suggestion in response to a user's utterance, the suggestion unit can adjust the content of the suggestion taking into account the user's current activity status. For example, when the user is in a meeting, the suggestion unit can make a concise and to-the-point suggestion. When the user is in a relaxed state, the suggestion unit can also make a detailed and polite suggestion. Furthermore, when the user is on the move, the suggestion unit can make a suggestion that can be understood in a short time. In this way, by adjusting the content of the suggestion according to the user's current activity status, more appropriate suggestions can be provided.

[0057] When accepting feedback from a user, the feedback unit can select the optimal feedback acceptance method by referring to the user's past feedback history. For example, the feedback unit can record the content and format of feedback given by the user in the past and accept feedback in a similar format. The feedback unit can also make a similar suggestion to a suggestion that the user previously gave a high rating to. Furthermore, the feedback unit can analyze the frequency and timing of feedback given by the user in the past and accept feedback at the optimal timing. In this way, by referring to the user's past feedback history, the optimal feedback acceptance method can be selected and more appropriate feedback can be accepted.

[0058] When analyzing a user's comments, the analysis unit analyzes the frequency and patterns of the user's comments, allowing for a more accurate understanding of the intention of the comments. For example, the analysis unit can detect a pattern in which a user frequently makes comments during a specific time period and infer the intention of the comments during that time period. The analysis unit can also analyze the pattern in which a user repeatedly makes comments about a specific topic and evaluate the user's level of interest in that topic. Furthermore, the analysis unit can analyze the length and complexity of the user's comments to gain a deeper understanding of the intention of the comments. In this way, by analyzing the frequency and patterns of a user's comments, the intention of the comments can be more accurately understood and appropriate analysis results can be provided.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The reception unit receives a user's input of a speech. Methods for the user to input a speech include voice input, text input, gesture input, etc. For example, the reception unit can convert the user's speech into text using speech recognition technology. Step 2: The analysis unit analyzes the utterances input by the reception unit. The analysis unit uses natural language processing technology to analyze the content of the utterances and understand their grammatical structure and context. For example, it can extract keywords from the utterances and identify the topic of the utterances. Step 3: The detection unit detects unconscious bias based on the utterances analyzed by the analysis unit. For example, it can detect unconscious biases such as gender bias, racial bias, and age bias, and can detect stereotypes, prejudices, and discriminatory language contained in the utterances. Step 4: The suggestion unit makes suggestions to convert statements containing unconscious bias detected by the detection unit into appropriate expressions. For example, it makes suggestions to convert statements into expressions based on political correctness or cultural considerations. This allows the user's statements to be converted into more appropriate expressions, enabling appropriate communication.

[0061] (Example 2) An unconscious bias detection system according to an embodiment of the present invention uses AI to detect "unconscious bias" hidden in speech and propose appropriate conversions. In this unconscious bias detection system, a user inputs a speech, and the AI ​​analyzes the speech to detect whether it contains unconscious bias. If unconscious bias is detected, the AI ​​proposes to convert the speech to an appropriate expression. This allows users to consider whether their speech is offensive to the other person and promote more appropriate communication. For example, if a user inputs a statement such as "Because you are a certain gender, you have certain skills," the statement is input into the AI. The AI ​​then analyzes the input statement, understands its content, and detects whether it contains unconscious bias. For example, it determines that the phrase "Because you are a certain gender" is a gender-based stereotype. If unconscious bias is detected, the AI ​​proposes to convert the statement to an appropriate expression. For example, it proposes to convert the statement to "So you have certain skills." This allows users to consider whether their speech is offensive to the other person. This mechanism allows users to promote more appropriate communication and prevent offense to the other person. For example, in various situations such as at work or school, smooth communication can be achieved by detecting unconscious bias hidden in speech and converting it into appropriate expressions. In this way, the unconscious bias detection system can automatically analyze user speech and convert it into appropriate expressions, thereby achieving more appropriate communication.

[0062] An unconscious bias detection system according to an embodiment includes a reception unit, an analysis unit, a detection unit, and a suggestion unit. The reception unit receives a user's input of a utterance. The method by which the user inputs the utterance includes, but is not limited to, voice input, text input, and gesture input. The reception unit can receive the user's input of a utterance using, for example, voice input. The reception unit can also receive the user's input of a utterance using text input. The reception unit can also receive the user's input of a utterance using gesture input. For example, the reception unit can convert the user's voice into text using speech recognition technology. The analysis unit analyzes the utterance input by the reception unit. The analysis unit can analyze the content of the utterance using, for example, natural language processing technology. The analysis unit can analyze the grammatical structure of the utterance to understand its meaning. The analysis unit can also analyze the context of the utterance to understand its intention. For example, the analysis unit can extract keywords from the utterance and identify the subject of the utterance. The detection unit detects unconscious bias based on the utterance analyzed by the analysis unit. The detection unit detects unconscious biases such as gender bias, racial bias, and age bias. The detection unit can detect, for example, stereotypes contained in utterances. The detection unit can also detect prejudices contained in utterances. For example, the detection unit can detect discriminatory language contained in utterances. The suggestion unit makes a suggestion to convert utterances containing unconscious bias detected by the detection unit into appropriate language. For example, the suggestion unit makes a suggestion to convert utterances containing unconscious biases detected by the detection unit into appropriate language. For example, the suggestion unit can also make a suggestion to convert utterances containing gender stereotypes into neutral language. As a result, the unconscious bias detection system according to the embodiment can automatically analyze user utterances and convert them into appropriate language, thereby enabling more appropriate communication.

[0063] The suggestion unit may include a feedback unit that accepts user feedback. The feedback unit, for example, provides an interface for the user to provide feedback on the suggestion. The feedback unit, for example, can accept text comments. The feedback unit may also accept an evaluation score. For example, the feedback unit may allow the user to input an evaluation score from 1 to 5 for the suggestion. The feedback unit may also accept voice feedback. For example, the feedback unit may allow the user to provide voice feedback on the suggestion. In this way, by accepting user feedback, the accuracy of the suggestion can be improved. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit may input user feedback data to a generation AI and cause the generation AI to analyze the feedback data.

[0064] The analysis unit may include a learning unit that learns past utterance data. The learning unit, for example, collects past utterance data and uses it as learning data for the analysis unit. The learning unit, for example, may collect past conversation logs. The learning unit may also collect past voice recordings. For example, the learning unit may collect past text data and use it as learning data for the analysis unit. This allows the accuracy of analysis to be improved by learning from past utterance data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input past utterance data into a generation AI and cause the generation AI to learn the utterance data.

[0065] The suggestion unit can make a suggestion to convert a statement containing detected unconscious bias into appropriate expression. For example, the suggestion unit can make a suggestion to convert a statement containing detected unconscious bias into expression based on political correctness. The suggestion unit can also make a suggestion to convert into expression based on cultural considerations. For example, the suggestion unit can make a suggestion to convert a statement containing gender stereotypes into neutral expression. This allows for more appropriate communication by converting a statement containing detected unconscious bias into appropriate expression. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input a statement containing detected unconscious bias into a generation AI and have the generation AI convert the statement into appropriate expression.

[0066] The reception unit can estimate the user's emotion and adjust the timing of utterance acceptance based on the estimated user emotion. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression and adjusts the timing of utterance acceptance. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the timing of utterance acceptance. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on fluctuations in heart rate and adjusts the timing of utterance acceptance. This allows the timing of utterance acceptance to be adjusted according to the user's emotion, thereby allowing utterances to be accepted at more appropriate times. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0067] The reception unit can analyze the user's past speech history and select the optimal reception method. The reception unit, for example, collects the user's past speech history and selects the optimal reception method. The reception unit, for example, can collect and analyze past conversation logs. The reception unit can also collect and analyze past voice recordings. For example, the reception unit can collect and analyze past text data. In this way, the optimal reception method can be selected by analyzing the user's past speech history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past speech history data to a generation AI and cause the generation AI to analyze the speech history.

[0068] The reception unit can filter utterances based on the user's current situation and areas of interest when receiving the utterances. The reception unit, for example, grasps the user's current situation and adjusts the method for receiving utterances. The reception unit can, for example, acquire the user's location information and grasp the current situation. The reception unit can also grasp the user's activity status and adjust the method for receiving utterances. For example, the reception unit adjusts the method for receiving utterances when the user is in a meeting. The reception unit can also adjust the method for receiving utterances when the user is on a break. Furthermore, the reception unit can grasp the user's areas of interest and filter the utterances. For example, the reception unit preferentially accepts utterances related to topics in which the user is currently interested. The reception unit can also filter and accept highly relevant utterances based on the user's areas of interest. In this way, by filtering based on the user's current situation and areas of interest, highly relevant utterances can be preferentially accepted. Some or all of the above-described processing in the reception unit may be performed, for example, using AI or without AI. For example, the reception unit can input the user's location information and activity status data into the generation AI and have the generation AI perform filtering.

[0069] The reception unit can estimate the user's emotions and determine the priority of utterances to be received based on the estimated user emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expressions and determines the priority of utterances. The reception unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of utterances. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations and determines the priority of utterances. By determining the priority of utterances according to the user's emotions, more appropriate utterances can be preferentially received. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0070] When receiving a utterance, the reception unit can prioritize receiving highly relevant utterances based on the user's geographical location information. The reception unit, for example, acquires the user's geographical location information and adjusts the method for receiving the utterances. The reception unit can acquire the user's location information using GPS data, for example. The reception unit can also acquire the user's address information and adjust the method for receiving the utterances. For example, when the user is in a specific area, the reception unit can prioritize receiving utterances related to that area. When the user is traveling, the reception unit can prioritize receiving utterances related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving utterances related to the home. In this way, by taking the user's geographical location information into consideration, highly relevant utterances can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input GPS data and address information to the generation AI and cause the generation AI to filter highly relevant utterances.

[0071] The reception unit can analyze the user's online activity when receiving a comment and receive relevant comments. The reception unit can, for example, analyze the user's social media activity and adjust the method for receiving comments. The reception unit can, for example, analyze the user's social media posts. The reception unit can also analyze the user's browsing history and adjust the method for receiving comments. For example, the reception unit can prioritize receiving comments related to topics in which the user has recently shown interest on social media. The reception unit can also analyze the user's social media activity history and receive highly relevant comments. Furthermore, the reception unit can prioritize receiving comments related to accounts the user follows on social media. In this way, by analyzing the user's social media activity, highly relevant comments can be preferentially received. Some or all of the above-described processing by the reception unit can be performed, for example, using AI or without AI. For example, the reception unit can input social media post data and browsing history data into the generation AI and cause the generation AI to filter highly relevant comments.

[0072] The analysis unit can estimate the user's emotions and adjust the analysis presentation method based on the estimated user emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions and adjusts the analysis presentation method. The analysis unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the analysis presentation method. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations and adjusts the analysis presentation method. This allows the analysis presentation method to be adjusted according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0073] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the statement. For example, the analysis unit analyzes the content of the statement and evaluates the importance of the statement. For example, the analysis unit can evaluate the impact of the statement and determine the importance. The analysis unit can also evaluate the importance based on the content of the statement. For example, the analysis unit performs a detailed analysis if the content of the statement contains important information. For example, the analysis unit can perform a concise analysis if the content of the statement contains general information. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the statement. For example, the analysis unit prioritizes analysis of statements with high importance. This allows for adjusting the level of detail of the analysis based on the importance of the statement, thereby providing more appropriate analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input content data of the statement to a generation AI and have the generation AI evaluate the importance.

[0074] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the statement. For example, the analysis unit classifies the category of the statement and selects an appropriate analysis algorithm. For example, the analysis unit can apply a gender bias detection algorithm to statements related to gender. The analysis unit can also apply a racial bias detection algorithm to statements related to race. For example, the analysis unit can apply an age bias detection algorithm to statements related to age. In this way, by applying different analysis algorithms depending on the category of the statement, more accurate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input statement category data into the generation AI and cause the generation AI to select an appropriate analysis algorithm.

[0075] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user emotion. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression and adjusts the length of the analysis. The analysis unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the analysis. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the analysis. This allows the length of the analysis to be adjusted according to the user's emotion, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0076] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the comments. The analysis unit, for example, evaluates the time of submission of the comments and determines the priority of analysis. The analysis unit can determine the priority of comments based on the submission date and time, for example. The analysis unit can also determine the priority of comments based on the order of submission. For example, the analysis unit prioritizes analysis of recently submitted comments. The analysis unit can also prioritize analysis of comments submitted within a specific time period. In this way, by determining the priority of analysis based on the time of submission of the comments, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time of submission of comments to the generation AI and have the generation AI determine the priority.

[0077] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the statements. The analysis unit, for example, analyzes the content of the statements and evaluates the relevance. The analysis unit can, for example, evaluate the similarity of the content of the statements and determine the relevance. The analysis unit can also evaluate the consistency of the topics of the statements and determine the relevance. For example, the analysis unit prioritizes analysis of highly relevant statements. The analysis unit can also postpone analysis of less relevant statements. In this way, by adjusting the order of analysis based on the relevance of the statements, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input content data of the statements to a generation AI and have the generation AI perform a relevance evaluation.

[0078] The detection unit can estimate the user's emotion and adjust the detection criteria based on the estimated user's emotion. For example, the detection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on changes in facial expression and adjusts the detection criteria. The detection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the detection unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the detection criteria. The detection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on heart rate fluctuations and adjusts the detection criteria. This allows the detection criteria to be adjusted according to the user's emotion, thereby providing more appropriate detection results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0079] The detection unit can improve the accuracy of detection by taking into account the interrelationships between statements during detection. The detection unit can, for example, analyze the interrelationships between multiple statements to improve the accuracy of bias detection. The detection unit can, for example, consider the context of statements to improve the accuracy of bias detection. The detection unit can also improve the accuracy of bias detection by taking into account the context of statements. For example, the detection unit analyzes the context before and after statements to improve the accuracy of bias detection. In this way, by taking into account the interrelationships between statements, the accuracy of detection can be improved. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input interrelationship data between statements to a generation AI and cause the generation AI to perform an analysis of the interrelationships.

[0080] The detection unit can perform detection by taking into account attribute information of the person who submitted the comment. The detection unit can detect bias, for example, by taking into account gender information of the person who submitted the comment. The detection unit can detect bias, for example, by taking into account age information of the person who submitted the comment. The detection unit can also detect bias by taking into account occupation information of the person who submitted the comment. For example, the detection unit detects bias based on attribute information of the person who submitted the comment. In this way, by taking into account the attribute information of the person who submitted the comment, more accurate detection results can be provided. Some or all of the above-mentioned processing in the detection unit can be performed using AI, for example, or can be performed without using AI. For example, the detection unit can input attribute information data of the person who submitted the comment into the generation AI and cause the generation AI to analyze the attribute information.

[0081] The detection unit can estimate the user's emotion and adjust the display order of the detection results based on the estimated user emotion. For example, the detection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on changes in facial expression and adjusts the display order of the detection results. The detection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the detection unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the display order of the detection results. The detection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on fluctuations in heart rate and adjusts the display order of the detection results. This allows for more appropriate detection results to be provided by adjusting the display order of the detection results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit may input image data of a user captured by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0082] The detection unit can perform detection by taking into account the geographical distribution of statements. For example, the detection unit can analyze the geographical distribution of statements to detect bias. For example, the detection unit can analyze the distribution of statements by region to detect bias. The detection unit can also analyze the distribution of statements by country to detect bias. For example, the detection unit preferentially detects statements related to a specific region. The detection unit can also detect statements that cover a wide geographical area. In this way, by taking the geographical distribution of statements into consideration, more accurate detection results can be provided. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input geographical distribution data of statements to a generation AI and cause the generation AI to analyze the geographical distribution.

[0083] The detection unit can improve the accuracy of detection by referring to literature related to the statement during detection. The detection unit can, for example, improve the accuracy of bias detection by referring to related literature. The detection unit can, for example, improve the accuracy of bias detection by referring to academic papers. The detection unit can also improve the accuracy of bias detection by referring to specialized books. For example, the detection unit detects bias based on related literature. In this way, by referring to literature related to the statement, the accuracy of detection can be improved. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input related literature data into the generation AI and cause the generation AI to refer to the literature.

[0084] The suggestion unit can estimate the user's emotion and adjust the way the suggestions are presented based on the estimated emotion. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expression and adjusts the way the suggestions are presented. The suggestion unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the way the suggestions are presented. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on heart rate fluctuations and adjusts the way the suggestions are presented. This allows the user to provide more appropriate suggestions by adjusting the way the suggestions are presented based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0085] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the statement. For example, the suggestion unit analyzes the content of the statement and evaluates the importance of the statement. For example, the suggestion unit can evaluate the influence of the statement and determine the importance. The suggestion unit can also evaluate the importance based on the content of the statement. For example, the suggestion unit makes a detailed proposal if the content of the statement contains important information. The suggestion unit can also make a concise proposal if the content of the statement contains general information. Furthermore, the suggestion unit can determine the priority of the proposal based on the importance of the statement. For example, the suggestion unit prioritizes suggestions with high importance. In this way, by adjusting the level of detail of the proposal based on the importance of the statement, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input content data of the statement to a generation AI and cause the generation AI to evaluate the importance.

[0086] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the utterance. For example, the suggestion unit classifies the category of the utterance and selects an appropriate suggestion algorithm. For example, the suggestion unit can apply a gender bias correction algorithm to utterances related to gender. The suggestion unit can also apply a race bias correction algorithm to utterances related to race. For example, the suggestion unit can apply an age bias correction algorithm to utterances related to age. In this way, by applying different suggestion algorithms depending on the category of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI, for example. For example, the suggestion unit can input utterance category data into a generation AI and cause the generation AI to select an appropriate suggestion algorithm.

[0087] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expression and adjusts the length of the suggestion. The suggestion unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the suggestion. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the suggestion. This allows the length of the suggestion to be adjusted according to the user's emotion, thereby providing more appropriate suggestions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0088] When making a proposal, the suggestion unit can determine the priority of the proposal based on the time of submission of the comment. The suggestion unit, for example, evaluates the time of submission of the comment and determines the priority of the proposal. The suggestion unit can determine the priority of the comment based on the submission date and time, for example. The suggestion unit can also determine the priority of the comment based on the order of submission. For example, the suggestion unit can prioritize proposals for recently submitted comments. The suggestion unit can also prioritize proposals for comments submitted within a specific time period. In this way, by determining the priority of the proposal based on the time of submission of the comment, more appropriate proposals can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input comment submission time data into a generation AI and have the generation AI determine the priority.

[0089] When making a suggestion, the suggestion unit can adjust the order of suggestions based on the relevance of the utterances. The suggestion unit, for example, analyzes the content of the utterances and evaluates the relevance. The suggestion unit, for example, can evaluate the similarity of the content of the utterances and determine the relevance. The suggestion unit can also evaluate the matching of the topics of the utterances and determine the relevance. For example, the suggestion unit prioritizes suggestions for highly relevant utterances. The suggestion unit can also postpone suggestions for less relevant utterances. In this way, by adjusting the order of suggestions based on the relevance of the utterances, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input content data of the utterances to a generation AI and cause the generation AI to evaluate the relevance.

[0090] The feedback unit can estimate the user's emotions and adjust the feedback acceptance method based on the estimated user's emotions. For example, the feedback unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expressions and adjusts the feedback acceptance method. The feedback unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the feedback unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the feedback acceptance method. The feedback unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on fluctuations in heart rate and adjusts the feedback acceptance method. This allows the user to receive more appropriate feedback by adjusting the feedback acceptance method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using AI, or may be performed without using AI. For example, the feedback unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0091] When receiving feedback, the feedback unit can select the optimal reception method by referring to the user's past feedback history. The feedback unit, for example, collects the user's past feedback history and selects the optimal reception method. The feedback unit, for example, can collect and analyze past comments. The feedback unit can also collect and analyze past evaluation scores. For example, the feedback unit can collect and analyze past survey results. In this way, the optimal reception method can be selected by referring to the user's past feedback history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, AI, for example. For example, the feedback unit can input past feedback history data into a generation AI and cause the generation AI to analyze the feedback history.

[0092] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated user emotions. For example, the feedback unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expression and determines the priority of feedback. The feedback unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the feedback unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of feedback. The feedback unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on heart rate fluctuations and determines the priority of feedback. This allows the user to receive more appropriate feedback by determining the priority of feedback according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input image data of the user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0093] When receiving feedback, the feedback unit can select the optimal feedback reception method by taking into account the user's device information. The feedback unit, for example, acquires the user's device information and selects the optimal feedback reception method. The feedback unit can, for example, acquire the type of device being used. The feedback unit can also acquire the device's OS and browser information and adjust the feedback reception method. For example, if the user is using a smartphone, the feedback unit can provide a feedback reception method tailored to the screen size. If the user is using a tablet, the feedback unit can provide a feedback reception method optimized for a large screen. Furthermore, if the user is using a smartwatch, the feedback unit can provide a simple and highly visible feedback reception method. In this way, the optimal feedback reception method can be provided by taking into account the user's device information. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input device information data to a generation AI and cause the generation AI to select the optimal reception method.

[0094] The learning unit can estimate a user's emotions and select training data based on the estimated user emotions. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on changes in facial expressions and selects training data. The learning unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice, calculates an emotion score, and selects training data. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on heart rate fluctuations and selects training data. This allows for the selection of training data based on the user's emotions, thereby providing more appropriate training data. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0095] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, collects past learning data and optimizes the learning algorithm. The learning unit, for example, can collect and analyze past training data. The learning unit can also collect and analyze past verification data. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. Furthermore, the learning unit can adjust parameters of the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or without AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the algorithm.

[0096] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on changes in facial expressions and adjusts the frequency of learning. The learning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the frequency of learning. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on heart rate fluctuations and adjusts the frequency of learning. This allows for more appropriate learning by adjusting the frequency of learning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0097] During learning, the learning unit can weight the learning data based on the time of submission of the utterances. The learning unit, for example, evaluates the time of submission of the utterances and weights the learning data. The learning unit can weight the learning data based on the submission date and time, for example. The learning unit can also weight the learning data based on the order of submission. For example, the learning unit weights recently submitted utterances. The learning unit can also weight utterances submitted within a specific time period. In this way, more appropriate learning can be performed by weighting the learning data based on the time of submission of the utterances. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the time of submission of the utterances to a generation AI and have the generation AI evaluate the weighting. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and suggestion unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and accepts a user's voice or text input. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes utterances using natural language processing technology. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects unconscious bias contained in utterances. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and makes suggestions to convert utterances into appropriate expressions. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or text input function of the smart glasses 214 and accepts a user's voice or text input. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes utterances using natural language processing technology. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects unconscious bias contained in utterances. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and makes suggestions to convert utterances into appropriate expressions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and suggestion unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or text input function of the headset-type terminal 314 and accepts a user's voice or text input. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes utterances using natural language processing technology. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects unconscious bias contained in utterances. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and makes suggestions to convert utterances into appropriate expressions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and suggestion unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or text input function of the robot 414 and accepts a user's voice or text input. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes utterances using natural language processing technology. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects unconscious bias contained in utterances. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and makes suggestions to convert utterances into appropriate expressions.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] When inputting a user's comment, the reception unit can monitor the user's current health condition and accept the comment at an appropriate timing. For example, the reception unit can measure the user's heart rate and blood pressure with a sensor and temporarily delay accepting the comment if the user's stress level is high. The reception unit can also monitor the user's sleep state and refrain from accepting comments if the user is sleep-deprived. Furthermore, the reception unit can grasp the user's eating habits and refrain from accepting comments immediately after a meal. This allows for more appropriate communication by adjusting the timing of accepting comments according to the user's health condition.

[0100] When analyzing a user's utterances, the analysis unit learns the user's past utterance patterns and can more accurately understand the intention of the utterance. For example, the analysis unit can memorize specific phrases and expressions used by the user in the past and infer the intention when a similar phrase is used again. The analysis unit can also refer to the context of the user's past utterances to more deeply understand the meaning of the current utterance. Furthermore, the analysis unit can analyze the emotional tone of the user's past utterances and estimate the emotional tone of the current utterance. In this way, by learning the user's past utterance patterns, the intention of the utterance can be more accurately understood and appropriate analysis results can be provided.

[0101] When detecting a user's utterances, the detection unit can improve the detection accuracy by taking into account the user's current emotional state. For example, the detection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on changes in facial expression, thereby improving the utterance detection accuracy. The detection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the detection unit analyzes the tone and speed of the voice, calculates an emotion score, and improves the utterance detection accuracy. The detection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the detection unit calculates an emotion score based on fluctuations in heart rate, thereby improving the utterance detection accuracy. This improves the utterance detection accuracy according to the user's emotional state, thereby providing more appropriate detection results.

[0102] When making a suggestion in response to a user's utterance, the suggestion unit can adjust the content of the suggestion taking into account the user's current activity status. For example, when the user is in a meeting, the suggestion unit can make a concise and to-the-point suggestion. When the user is in a relaxed state, the suggestion unit can also make a detailed and polite suggestion. Furthermore, when the user is on the move, the suggestion unit can make a suggestion that can be understood in a short time. In this way, by adjusting the content of the suggestion according to the user's current activity status, more appropriate suggestions can be provided.

[0103] When accepting feedback from a user, the feedback unit can select the optimal feedback acceptance method by referring to the user's past feedback history. For example, the feedback unit can record the content and format of feedback given by the user in the past and accept feedback in a similar format. The feedback unit can also make a similar suggestion to a suggestion that the user previously gave a high rating to. Furthermore, the feedback unit can analyze the frequency and timing of feedback given by the user in the past and accept feedback at the optimal timing. In this way, by referring to the user's past feedback history, the optimal feedback acceptance method can be selected and more appropriate feedback can be accepted.

[0104] When analyzing a user's speech, the analysis unit can adjust the method of expression of the analysis taking into account the user's current emotional state. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression and adjusts the method of expression of the analysis. The analysis unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the method of expression of the analysis. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on fluctuations in heart rate and adjusts the method of expression of the analysis. In this way, by adjusting the method of expression of the analysis according to the user's emotional state, more appropriate analysis results can be provided.

[0105] When making a suggestion in response to a user's utterance, the suggestion unit can adjust the way the suggestion is expressed by taking into account the user's current emotional state. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expression and adjusts the way the suggestion is expressed. The suggestion unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the way the suggestion is expressed. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on fluctuations in heart rate and adjusts the way the suggestion is expressed. In this way, the way the suggestion is expressed can be adjusted according to the user's emotional state, thereby providing more appropriate suggestions.

[0106] When receiving feedback from a user, the feedback unit can adjust the feedback acceptance method taking into account the user's current emotional state. For example, the feedback unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expression and adjusts the feedback acceptance method. The feedback unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the feedback unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the feedback acceptance method. The feedback unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on fluctuations in heart rate and adjusts the feedback acceptance method. In this way, by adjusting the feedback acceptance method according to the user's emotional state, more appropriate feedback can be received.

[0107] When learning a user's utterances, the learning unit can select learning data taking into account the user's current emotional state. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on changes in facial expression and selects learning data. The learning unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice, calculates an emotion score, and selects learning data. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on fluctuations in heart rate and selects learning data. This makes it possible to provide more appropriate learning data by selecting learning data according to the user's emotional state.

[0108] When analyzing a user's comments, the analysis unit analyzes the frequency and patterns of the user's comments, allowing for a more accurate understanding of the intention of the comments. For example, the analysis unit can detect a pattern in which a user frequently makes comments during a specific time period and infer the intention of the comments during that time period. The analysis unit can also analyze the pattern in which a user repeatedly makes comments about a specific topic and evaluate the user's level of interest in that topic. Furthermore, the analysis unit can analyze the length and complexity of the user's comments to gain a deeper understanding of the intention of the comments. In this way, by analyzing the frequency and patterns of a user's comments, the intention of the comments can be more accurately understood and appropriate analysis results can be provided.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The reception unit receives a user's input of a speech. Methods for the user to input a speech include voice input, text input, gesture input, etc. For example, the reception unit can convert the user's speech into text using speech recognition technology. Step 2: The analysis unit analyzes the utterances input by the reception unit. The analysis unit uses natural language processing technology to analyze the content of the utterances and understand their grammatical structure and context. For example, it can extract keywords from the utterances and identify the topic of the utterances. Step 3: The detection unit detects unconscious bias based on the utterances analyzed by the analysis unit. For example, it can detect unconscious biases such as gender bias, racial bias, and age bias, and can detect stereotypes, prejudices, and discriminatory language contained in the utterances. Step 4: The suggestion unit makes suggestions to convert statements containing unconscious bias detected by the detection unit into appropriate expressions. For example, it makes suggestions to convert statements into expressions based on political correctness or cultural considerations. This allows the user's statements to be converted into more appropriate expressions, enabling appropriate communication.

[0111] 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.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0113] 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.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0125] 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.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0129] 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.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] 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.

[0143] 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.

[0144] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0159] 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.

[0160] 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.

[0161] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] The hardware resource that executes the specific processing 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 processing may be a single processor.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] [Explanation of symbols]

[0183] 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 reception unit for inputting comments; an analysis unit that analyzes the comments input by the reception unit; a detection unit that detects unconscious bias based on the utterances analyzed by the analysis unit; a suggestion unit that converts statements containing unconscious bias detected by the detection unit into specific technical content. A system characterized by:

2. The proposal unit A feedback unit is provided to receive user feedback.

2. The system of claim 1.

3. The analysis unit Equipped with a learning unit that learns from past utterance data 2. The system of claim 1.

4. The proposal unit Makes suggestions to convert detected statements containing unconscious bias into appropriate expressions 2. The system of claim 1.

5. The reception unit Estimates the user's emotions and adjusts the timing of speech acceptance based on the estimated user emotions.

2. The system of claim 1.

6. The reception unit Analyze the user's past comment history and select a specific reception method 2. The system of claim 1.

7. The reception unit Filtering incoming comments based on the user's current situation or interests 2. The system of claim 1.

8. The reception unit Estimate the user's emotions and prioritize the comments to be accepted based on the estimated user emotions.

2. The system of claim 1.

9. The reception unit When accepting comments, prioritize relevant comments based on the user's geographic location information.

2. The system of claim 1.

10. The reception unit When receiving a comment, analyze the user's online activity and receive related comments.

2. The system of claim 1.

Images