system

Abstract

The system according to this embodiment aims to improve the relationship between public officials and citizens. [Solution] The system according to the embodiment comprises a recording unit, an analysis unit, and a warning unit. The recording unit records conversations between public officials and citizens. The analysis unit analyzes the content of the conversations recorded by the recording unit. The warning unit issues warnings based on the results of the analysis performed by the analysis unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, countermeasures against improper claims and remarks against civil servants are lagging, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the relationship between civil servants and citizens.

Means for Solving the Problems

[0006] The system according to the embodiment includes a recording unit, an analysis unit, and a warning unit. The recording unit records conversations between civil servants and citizens. The analysis unit analyzes the conversation content recorded by the recording unit. The warning unit issues a warning based on the result analyzed by the analysis unit.

Effects of the Invention

[0007] The system according to this embodiment can improve relations between public officials and citizens. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An embodiment of the present invention provides a public servant support system in which AI monitors conversations between public servants and citizens in real time, analyzes the conversation content using natural language processing, and performs sentiment analysis. The public servant support system reduces the mental burden on public servants and improves relationships by recording and analyzing conversation content and providing appropriate warnings. For example, the public servant support system monitors conversations between public servants and citizens in real time. At this time, the content of the conversation is recorded so that it can be reviewed later. For example, if a citizen says to a public servant, "Why aren't you wearing a mask?", that statement is recorded by the AI. Next, the public servant support system analyzes the conversation content using natural language processing. The AI ​​analyzes the context of the conversation and the choice of words to determine the fluctuations in emotions. For example, if a citizen's statement is made in a strong tone or is one-sided, the AI ​​analyzes that statement as a negative emotion. If the sentiment analysis detects a statement that constitutes a negative emotion or harassment, the public servant support system provides appropriate warnings. For example, the public servant support system can encourage citizens to reconsider their statements by issuing a warning such as, "Your current statement may constitute harassment." This system can improve relations between civil servants and citizens. Civil servants can appropriately deal with one-sided complaints and remarks through AI intervention, reducing their mental burden. Citizens can also have the opportunity to review their own remarks through AI-based warnings. Furthermore, by using the same system in many areas, it can be deployed as a standard service. This is expected to improve harassment countermeasures against civil servants and enhance the quality of public services throughout the community. In short, this civil servant support system can improve relations between civil servants and citizens and reduce the mental burden on civil servants.

[0029] The civil servant support system according to this embodiment comprises a recording unit, an analysis unit, and a warning unit. The recording unit records conversations between civil servants and citizens. The recording unit can, for example, perform audio recording or text recording. The recording unit can also record conversation content in real time. For example, the recording unit records conversation content in real time so that it can be reviewed later. The recording unit can use, for example, audio files or text files as a format for saving conversation content. The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit analyzes the conversation content using natural language processing and performs sentiment analysis. The analysis unit analyzes the context of the conversation and word choices to determine emotional fluctuations. For example, the analysis unit uses natural language processing technology to perform morphological and grammatical analysis of the conversation content. For sentiment analysis, the analysis unit can use, for example, an emotion classification algorithm. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. The warning unit provides warnings based on the results analyzed by the analysis unit. The alerting unit issues alerts to negative emotions and statements that constitute harassment, based on the results of sentiment analysis. For example, the alerting unit may issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. The alerting unit may provide a message encouraging the user to reconsider their statement. As a result, the civil servant support system according to this embodiment can improve the relationship between civil servants and citizens and reduce the mental burden on civil servants.

[0030] The recording unit records conversations between public officials and citizens. The recording unit can perform, for example, audio recording and text recording. Specifically, the recording unit uses high-performance microphones and speech recognition technology to clearly record the audio of conversations. Speech recognition technology can convert the content of conversations into text in real time and save it as a text file. This makes it possible to record both audio and text data simultaneously. The recording unit can also record conversations in real time. For example, the recording unit can record conversations in real time for later review. Real-time recording is effective in situations requiring quick responses, as it allows for immediate data saving during the conversation and on-the-spot review as needed. The recording unit can use, for example, audio files and text files to save conversation content. Audio files are saved in common formats such as MP3 and WAV, and text files are saved in formats such as TXT and PDF. This allows the recorded data to be easily accessed from a variety of devices and software. Furthermore, the recording unit can utilize cloud storage as a data storage location. Using cloud storage makes data backup and sharing easier and reduces the risk of data loss. This allows the recording unit to efficiently and reliably record conversations between public officials and citizens, which can then be used for later verification and analysis.

[0031] The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit uses natural language processing to analyze the conversation content and perform sentiment analysis. Specifically, the analysis unit performs morphological and grammatical analysis on the conversation content. Morphological analysis breaks down the conversation text data into individual words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the word order and sentence structure to understand the context. For sentiment analysis, the analysis unit can use, for example, a sentiment classification algorithm. The sentiment classification algorithm classifies the conversation text data into sentiment categories such as positive, negative, and neutral. This makes it possible to identify which parts of the conversation express which emotions. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. For example, if certain keywords or phrases are included, it is determined that they may be related to negative emotions or harassment. Furthermore, the analysis unit analyzes the tone and word choice of the conversation to determine the fluctuations in emotion. For example, if a person's tone of voice suddenly becomes higher or aggressive language is used, the system will determine that this is an expression of negative emotion. This allows the analysis unit to analyze the content of the conversation in detail and detect changes in emotion and signs of harassment early. Furthermore, the analysis unit can perform more accurate analysis by utilizing past conversation data and statistical information. As a result, the analysis unit can analyze conversations between public officials and citizens in detail and detect changes in emotion and signs of harassment early.

[0032] The alerting unit issues alerts based on the results of analysis performed by the analysis unit. Based on the sentiment analysis results, the alerting unit issues alerts for negative emotions and statements that constitute harassment. Specifically, the alerting unit may issue an alert such as, "The current statement may constitute harassment." The alerting unit can use various notification methods, such as voice notifications and text notifications. Voice notifications allow for real-time delivery of alert messages, enabling civil servants to respond immediately. Text notifications display the alert message on the screen, allowing civil servants to visually confirm it. The alerting unit provides messages that encourage users to reconsider their statements. Specifically, it may display a message such as, "This statement may cause negative emotions. Please reconsider your statement." Furthermore, the alerting unit can adjust the frequency and timing of alerts. For example, if similar negative statements are repeated, increasing the frequency of alerts can help resolve the problem earlier. The alerting unit also saves a history of past alerts for later review. This allows civil servants to review past warnings and use that information to improve future responses. It also enables the warning department to detect negative emotions and harassing remarks early in conversations between civil servants and citizens, and to issue appropriate warnings, thereby reducing the mental burden on civil servants and improving relationships.

[0033] The recording unit can record conversation content in real time. For example, the recording unit can record conversation content in real time so that it can be reviewed later. The recording unit can use, for example, audio files or text files as a format for saving conversation content. This allows conversation content to be recorded in real time and reviewed later. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can record conversation content in real time and AI can analyze that content.

[0034] The analysis unit can analyze conversation content using natural language processing and perform sentiment analysis. For example, the analysis unit can perform morphological and grammatical analysis of conversation content using natural language processing techniques. For sentiment analysis, the analysis unit can use, for example, sentiment classification algorithms. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. By using natural language processing, the accuracy of conversation content analysis and sentiment analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input conversation content into a generative AI, which can then analyze the content and perform sentiment analysis.

[0035] The alerting unit can issue alerts regarding negative emotions or statements that constitute harassment, based on the results of sentiment analysis. For example, the alerting unit may issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. As content of the alert, the alerting unit may provide a message encouraging the user to reconsider their statement. This can improve relations between public officials and citizens by providing appropriate alerts regarding negative emotions or statements that constitute harassment. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the alerting unit can input the results of sentiment analysis into a generative AI, which can then issue an appropriate alert.

[0036] The analysis unit can analyze the context of a conversation and the choice of words to determine emotional fluctuations. For example, the analysis unit analyzes the context of a conversation and the choice of words to determine emotional fluctuations. The analysis unit understands the context of the conversation and determines emotional fluctuations based on the choice of words. In this way, by analyzing the context of the conversation and the choice of words, emotional fluctuations can be accurately determined. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the conversation content into a generative AI, which can understand the context and determine emotional fluctuations.

[0037] The alerting unit can issue a warning such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. The alerting unit can provide a message that encourages users to reconsider their statements as part of the warning. This allows the alerting unit to encourage citizens to reconsider their statements by providing specific warnings. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the alerting unit can input the results of sentiment analysis into a generative AI, which can then issue an appropriate warning.

[0038] The recording unit can adjust the level of detail in the recording based on the importance of the conversation. For example, the recording unit can record important conversational content in detail, while recording less important conversational content in a simplified manner. The recording unit can use both audio and text recording depending on the importance of the conversation. This allows important information to be recorded in detail by adjusting the level of detail according to the importance of the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the conversational content into a generative AI, which can determine its importance and adjust the level of detail in the recording.

[0039] The recording unit can apply different recording methods depending on the category of the conversation during recording. For example, the recording unit can perform detailed text recording for conversations related to complaints. For conversations related to general inquiries, the recording unit can perform simplified audio recording. For conversations related to emergency responses, the recording unit can use a combination of real-time audio recording and text recording. This allows for efficient recording by changing the recording method according to the category of the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the conversation content into a generative AI, which can determine the category and apply the appropriate recording method.

[0040] The recording unit can adjust the recording priority based on the location where the conversation occurred. For example, the recording unit may prioritize recording conversations in a civil servant's office. It may then prioritize recording conversations in public places. It may record conversations in private places as needed. This allows important conversations to be recorded preferentially by adjusting the recording priority according to the location where the conversation occurred. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit may input the location where the conversation occurred into a generative AI, which can then adjust the recording priority.

[0041] The recording unit can record conversations while considering the attribute information of the participants. For example, the recording unit can adjust the level of detail in the recording by considering the attribute information of citizens (age, gender, etc.). The recording unit can determine the priority of recordings based on the position and duties of public officials. If there are many participants in the conversation, the recording unit can prioritize recording the statements of important speakers. This makes it possible to record more appropriately by considering the attribute information of the participants in the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit can input the attribute information of the participants in the conversation into a generative AI, and the generative AI can adjust the level of detail and priority of the recordings.

[0042] The analysis unit can adjust the level of detail of the analysis based on the context of the conversation during analysis. For example, the analysis unit can perform detailed contextual analysis on important conversational content. For general conversational content, the analysis unit can perform simplified contextual analysis. The analysis unit can apply different analysis algorithms depending on the context of the conversation. This allows for efficient analysis by adjusting the level of detail according to the context of the conversation. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input conversational content into a generative AI, which can understand the context and adjust the level of detail of the analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit can apply a detailed sentiment analysis algorithm to conversations about complaints. For conversations about general inquiries, it can apply a simplified analysis algorithm. For conversations about emergency responses, it can apply a rapid analysis algorithm. This allows for efficient analysis by changing the analysis algorithm according to the category of the conversation. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the conversation content into a generative AI, which can determine the category and apply an appropriate analysis algorithm.

[0044] The analysis unit can determine the priority of analysis based on when the conversation occurred. For example, the analysis unit may prioritize analyzing recent conversation content. The analysis unit can analyze past conversation content as needed. The analysis unit can apply different analysis algorithms depending on when the conversation occurred. This allows important conversations to be analyzed preferentially by determining the priority of analysis based on when the conversation occurred. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input conversation content into a generative AI, which can determine the timing of the conversation and determine the priority of analysis.

[0045] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the conversation during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant laws and regulations. The analysis unit can improve the accuracy of its analysis by referring to similar past cases. The analysis unit can improve the accuracy of its analysis by referring to expert opinions. Thus, the accuracy of the analysis is improved by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input relevant literature into a generative AI, which can then improve the accuracy of the analysis.

[0046] The alert unit can adjust the level of detail of its alerts based on the importance of the conversation. For example, the alert unit can provide detailed alerts for important conversation content, and simplified alerts for less important conversation content. The alert unit can apply different alert methods depending on the importance of the conversation. This allows for appropriate alerts for important conversations by adjusting the level of detail according to the importance of the conversation. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alert unit can input conversation content into a generation AI, which can determine the importance and adjust the level of detail of the alert.

[0047] The alerting unit can apply different alerting methods depending on the category of the conversation when issuing an alert. For example, the alerting unit can provide a detailed alert for conversations related to complaints. For conversations related to general inquiries, it can provide a simplified alert. For conversations related to emergency responses, it can provide a rapid alert. This allows for efficient alerting by changing the alerting method according to the category of the conversation. Some or all of the above processing in the alerting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alerting unit can input the conversation content into a generation AI, which can determine the category and apply an appropriate alerting method.

[0048] The alerting unit can adjust its alerting method based on the location where the conversation occurred. For example, the alerting unit may prioritize alerting for conversations in a civil servant's office. It may then prioritize alerting for conversations in public places. It may also alert for conversations in private places as needed. This allows for appropriate alerting by adjusting the alerting method according to the location where the conversation occurred. Some or all of the above processing in the alerting unit may be performed using, for example, a generating AI, or without a generating AI. For example, the alerting unit may input the location where the conversation occurred into the generating AI, which can then adjust the alerting method.

[0049] The alerting unit can issue alerts while considering the attribute information of the conversation participants. For example, the alerting unit can adjust the level of detail of the alert by considering the attribute information of citizens (age, gender, etc.). The alerting unit can determine the priority of alerts based on the position and duties of public officials. If there are many participants in the conversation, the alerting unit can prioritize alerting to the statements of important speakers. This makes it possible to issue more appropriate alerts by considering the attribute information of the conversation participants. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the alerting unit can input the attribute information of the conversation participants into a generative AI, and the generative AI can adjust the level of detail and priority of the alert.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The civil servant support system can also include a feedback section. This section provides a function that allows civil servants to receive feedback on their interactions with citizens after their conversations. For example, the feedback section can play back recordings of conversations, allowing civil servants to review their responses. Furthermore, the feedback section can provide civil servants with the results of an AI-generated sentiment analysis, indicating which parts of the conversation caused negative emotions in citizens. In addition, the feedback section can offer specific advice and improvement measures to help civil servants identify areas for improvement. This enables civil servants to improve their interactions and maintain better relationships with citizens.

[0052] The civil servant support system can also include a training section. This training section provides training to help civil servants improve their skills in interacting with citizens. For example, the training section can use past conversation data to conduct simulations, allowing civil servants to practice handling various scenarios. Furthermore, the training section can enable civil servants to learn appropriate responses in specific situations based on the results of sentiment analysis performed by AI. In addition, the training section can provide feedback to help civil servants evaluate their responses and identify areas for improvement. This allows civil servants to improve their citizen interaction skills and provide better service.

[0053] The civil servant support system can also be equipped with a predictive function. This predictive function provides the ability to predict future conversation trends and potential problems based on past conversation data. For example, it can analyze past data to predict trends in citizen complaints during specific times or situations. It can also predict what problems specific citizens are facing and prepare countermeasures in advance. Furthermore, based on the results of sentiment analysis performed by AI, the predictive function can predict changes in citizens' emotions and provide advice for appropriate responses. This allows civil servants to anticipate problems in advance and respond quickly and appropriately.

[0054] The civil servant support system can also include a reminder function. This function provides civil servants with reminders to take necessary follow-up actions after conversations with citizens. For example, the reminder function can remind civil servants of tasks that need to be completed by a specific deadline, based on the content of the conversation. It can also track the status of responses to citizen requests and complaints and notify civil servants of the progress. Furthermore, the reminder function can remind civil servants of points that are particularly important to them, based on sentiment analysis results analyzed by AI. This allows civil servants to respond to citizen requests quickly and appropriately.

[0055] The civil servant support system can also include an escalation function. This escalation function provides the ability to escalate issues to higher-level officials when certain conditions are met during conversations with citizens. For example, the escalation function notifies higher-level officials if a citizen expresses strong dissatisfaction or if specific keywords are included. Furthermore, the escalation function can determine the need for escalation based on the results of sentiment analysis performed by AI. In addition, the escalation function can track the progress of escalations and notify civil servants of the progress. This allows civil servants to respond quickly and appropriately, resolving citizen dissatisfaction.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The recording unit records conversations between public officials and citizens. The recording unit can perform audio and text recordings, recording the conversation content in real time for later review. The recording unit can use audio files or text files as formats for saving the conversation content. Step 2: The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit uses natural language processing to analyze the conversation content and perform sentiment analysis. The analysis unit analyzes the context of the conversation and word choices to determine emotional fluctuations. For example, the analysis unit uses natural language processing techniques to perform morphological and grammatical analysis of the conversation content. The analysis unit can use sentiment classification algorithms for sentiment analysis. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. Step 3: The alerting unit issues an alert based on the results of the analysis performed by the analysis unit. Based on the sentiment analysis results, the alerting unit issues an alert regarding negative emotions or statements that constitute harassment. For example, the alerting unit might issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use voice notifications or text notifications as notification methods. The alerting unit provides a message encouraging the user to reconsider their statement.

[0058] (Example of form 2) An embodiment of the present invention provides a public servant support system in which AI monitors conversations between public servants and citizens in real time, analyzes the conversation content using natural language processing, and performs sentiment analysis. The public servant support system reduces the mental burden on public servants and improves relationships by recording and analyzing conversation content and providing appropriate warnings. For example, the public servant support system monitors conversations between public servants and citizens in real time. At this time, the content of the conversation is recorded so that it can be reviewed later. For example, if a citizen says to a public servant, "Why aren't you wearing a mask?", that statement is recorded by the AI. Next, the public servant support system analyzes the conversation content using natural language processing. The AI ​​analyzes the context of the conversation and the choice of words to determine the fluctuations in emotions. For example, if a citizen's statement is made in a strong tone or is one-sided, the AI ​​analyzes that statement as a negative emotion. If the sentiment analysis detects a statement that constitutes a negative emotion or harassment, the public servant support system provides appropriate warnings. For example, the public servant support system can encourage citizens to reconsider their statements by issuing a warning such as, "Your current statement may constitute harassment." This system can improve relations between civil servants and citizens. Civil servants can appropriately deal with one-sided complaints and remarks through AI intervention, reducing their mental burden. Citizens can also have the opportunity to review their own remarks through AI-based warnings. Furthermore, by using the same system in many areas, it can be deployed as a standard service. This is expected to improve harassment countermeasures against civil servants and enhance the quality of public services throughout the community. In short, this civil servant support system can improve relations between civil servants and citizens and reduce the mental burden on civil servants.

[0059] The civil servant support system according to this embodiment comprises a recording unit, an analysis unit, and a warning unit. The recording unit records conversations between civil servants and citizens. The recording unit can, for example, perform audio recording or text recording. The recording unit can also record conversation content in real time. For example, the recording unit records conversation content in real time so that it can be reviewed later. The recording unit can use, for example, audio files or text files as a format for saving conversation content. The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit analyzes the conversation content using natural language processing and performs sentiment analysis. The analysis unit analyzes the context of the conversation and word choices to determine emotional fluctuations. For example, the analysis unit uses natural language processing technology to perform morphological and grammatical analysis of the conversation content. For sentiment analysis, the analysis unit can use, for example, an emotion classification algorithm. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. The warning unit provides warnings based on the results analyzed by the analysis unit. The alerting unit issues alerts to negative emotions and statements that constitute harassment, based on the results of sentiment analysis. For example, the alerting unit may issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. The alerting unit may provide a message encouraging the user to reconsider their statement. As a result, the civil servant support system according to this embodiment can improve the relationship between civil servants and citizens and reduce the mental burden on civil servants.

[0060] The recording unit records conversations between public officials and citizens. The recording unit can perform, for example, audio recording and text recording. Specifically, the recording unit uses high-performance microphones and speech recognition technology to clearly record the audio of conversations. Speech recognition technology can convert the content of conversations into text in real time and save it as a text file. This makes it possible to record both audio and text data simultaneously. The recording unit can also record conversations in real time. For example, the recording unit can record conversations in real time for later review. Real-time recording is effective in situations requiring quick responses, as it allows for immediate data saving during the conversation and on-the-spot review as needed. The recording unit can use, for example, audio files and text files to save conversation content. Audio files are saved in common formats such as MP3 and WAV, and text files are saved in formats such as TXT and PDF. This allows the recorded data to be easily accessed from a variety of devices and software. Furthermore, the recording unit can utilize cloud storage as a data storage location. Using cloud storage makes data backup and sharing easier and reduces the risk of data loss. This allows the recording unit to efficiently and reliably record conversations between public officials and citizens, which can then be used for later verification and analysis.

[0061] The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit uses natural language processing to analyze the conversation content and perform sentiment analysis. Specifically, the analysis unit performs morphological and grammatical analysis on the conversation content. Morphological analysis breaks down the conversation text data into individual words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the word order and sentence structure to understand the context. For sentiment analysis, the analysis unit can use, for example, a sentiment classification algorithm. The sentiment classification algorithm classifies the conversation text data into sentiment categories such as positive, negative, and neutral. This makes it possible to identify which parts of the conversation express which emotions. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. For example, if certain keywords or phrases are included, it is determined that they may be related to negative emotions or harassment. Furthermore, the analysis unit analyzes the tone and word choice of the conversation to determine the fluctuations in emotion. For example, if a person's tone of voice suddenly becomes higher or aggressive language is used, the system will determine that this is an expression of negative emotion. This allows the analysis unit to analyze the content of the conversation in detail and detect changes in emotion and signs of harassment early. Furthermore, the analysis unit can perform more accurate analysis by utilizing past conversation data and statistical information. As a result, the analysis unit can analyze conversations between public officials and citizens in detail and detect changes in emotion and signs of harassment early.

[0062] The alerting unit issues alerts based on the results of analysis performed by the analysis unit. Based on the sentiment analysis results, the alerting unit issues alerts for negative emotions and statements that constitute harassment. Specifically, the alerting unit may issue an alert such as, "The current statement may constitute harassment." The alerting unit can use various notification methods, such as voice notifications and text notifications. Voice notifications allow for real-time delivery of alert messages, enabling civil servants to respond immediately. Text notifications display the alert message on the screen, allowing civil servants to visually confirm it. The alerting unit provides messages that encourage users to reconsider their statements. Specifically, it may display a message such as, "This statement may cause negative emotions. Please reconsider your statement." Furthermore, the alerting unit can adjust the frequency and timing of alerts. For example, if similar negative statements are repeated, increasing the frequency of alerts can help resolve the problem earlier. The alerting unit also saves a history of past alerts for later review. This allows civil servants to review past warnings and use that information to improve future responses. It also enables the warning department to detect negative emotions and harassing remarks early in conversations between civil servants and citizens, and to issue appropriate warnings, thereby reducing the mental burden on civil servants and improving relationships.

[0063] The recording unit can record conversation content in real time. For example, the recording unit can record conversation content in real time so that it can be reviewed later. The recording unit can use, for example, audio files or text files as a format for saving conversation content. This allows conversation content to be recorded in real time and reviewed later. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can record conversation content in real time and AI can analyze that content.

[0064] The analysis unit can analyze conversation content using natural language processing and perform sentiment analysis. For example, the analysis unit can perform morphological and grammatical analysis of conversation content using natural language processing techniques. For sentiment analysis, the analysis unit can use, for example, sentiment classification algorithms. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. By using natural language processing, the accuracy of conversation content analysis and sentiment analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input conversation content into a generative AI, which can then analyze the content and perform sentiment analysis.

[0065] The alerting unit can issue alerts regarding negative emotions or statements that constitute harassment, based on the results of sentiment analysis. For example, the alerting unit may issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. As content of the alert, the alerting unit may provide a message encouraging the user to reconsider their statement. This can improve relations between public officials and citizens by providing appropriate alerts regarding negative emotions or statements that constitute harassment. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the alerting unit can input the results of sentiment analysis into a generative AI, which can then issue an appropriate alert.

[0066] The analysis unit can analyze the context of a conversation and the choice of words to determine emotional fluctuations. For example, the analysis unit analyzes the context of a conversation and the choice of words to determine emotional fluctuations. The analysis unit understands the context of the conversation and determines emotional fluctuations based on the choice of words. In this way, by analyzing the context of the conversation and the choice of words, emotional fluctuations can be accurately determined. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the conversation content into a generative AI, which can understand the context and determine emotional fluctuations.

[0067] The alerting unit can issue a warning such as, "Your current statement may constitute harassment." The alerting unit can use methods such as voice notifications or text notifications for notification. The alerting unit can provide a message that encourages users to reconsider their statements as part of the warning. This allows the alerting unit to encourage citizens to reconsider their statements by providing specific warnings. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the alerting unit can input the results of sentiment analysis into a generative AI, which can then issue an appropriate warning.

[0068] The recording unit can estimate the user's emotions and adjust the frequency of conversation recording based on the estimated emotions. For example, if the user is stressed, the recording unit can increase the frequency of conversation recording and record in detail. If the user is relaxed, the recording unit can decrease the frequency of conversation recording and record only the main points. If the user is in a hurry, the recording unit can prioritize recording only important statements. This allows for more appropriate recording by adjusting the recording frequency 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can input user emotion data into the generative AI, which can then adjust the recording frequency.

[0069] The recording unit can adjust the level of detail in the recording based on the importance of the conversation. For example, the recording unit can record important conversational content in detail, while recording less important conversational content in a simplified manner. The recording unit can use both audio and text recording depending on the importance of the conversation. This allows important information to be recorded in detail by adjusting the level of detail according to the importance of the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the conversational content into a generative AI, which can determine its importance and adjust the level of detail in the recording.

[0070] The recording unit can apply different recording methods depending on the category of the conversation during recording. For example, the recording unit can perform detailed text recording for conversations related to complaints. For conversations related to general inquiries, the recording unit can perform simplified audio recording. For conversations related to emergency responses, the recording unit can use a combination of real-time audio recording and text recording. This allows for efficient recording by changing the recording method according to the category of the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the conversation content into a generative AI, which can determine the category and apply the appropriate recording method.

[0071] The recording unit can estimate the user's emotions and determine the priority of conversations to record based on the estimated emotions. For example, if the user is angry, the recording unit may prioritize recording that conversation. If the user is sad, the recording unit may prioritize recording that conversation next. If the user has neutral emotions, the recording unit may record that conversation with normal priority. This allows important conversations to be prioritized by determining the recording priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI, or not using AI. For example, the recording unit can input user emotion data into a generative AI, which can then determine the recording priority.

[0072] The recording unit can adjust the recording priority based on the location where the conversation occurred. For example, the recording unit may prioritize recording conversations in a civil servant's office. It may then prioritize recording conversations in public places. It may record conversations in private places as needed. This allows important conversations to be recorded preferentially by adjusting the recording priority according to the location where the conversation occurred. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit may input the location where the conversation occurred into a generative AI, which can then adjust the recording priority.

[0073] The recording unit can record conversations while considering the attribute information of the participants. For example, the recording unit can adjust the level of detail in the recording by considering the attribute information of citizens (age, gender, etc.). The recording unit can determine the priority of recordings based on the position and duties of public officials. If there are many participants in the conversation, the recording unit can prioritize recording the statements of important speakers. This makes it possible to record more appropriately by considering the attribute information of the participants in the conversation. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit can input the attribute information of the participants in the conversation into a generative AI, and the generative AI can adjust the level of detail and priority of the recordings.

[0074] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is angry, the analysis unit can perform a detailed emotion analysis. If the user is relaxed, the analysis unit can perform a simplified emotion analysis. If the user is in a hurry, the analysis unit can perform a rapid emotion analysis. By adjusting the accuracy of the analysis according to the user's emotions, more accurate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the user's emotion data into the generative AI, and the generative AI can adjust the accuracy of the analysis.

[0075] The analysis unit can adjust the level of detail of the analysis based on the context of the conversation during analysis. For example, the analysis unit can perform detailed contextual analysis on important conversational content. For general conversational content, the analysis unit can perform simplified contextual analysis. The analysis unit can apply different analysis algorithms depending on the context of the conversation. This allows for efficient analysis by adjusting the level of detail according to the context of the conversation. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input conversational content into a generative AI, which can understand the context and adjust the level of detail of the analysis.

[0076] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit can apply a detailed sentiment analysis algorithm to conversations about complaints. For conversations about general inquiries, it can apply a simplified analysis algorithm. For conversations about emergency responses, it can apply a rapid analysis algorithm. This allows for efficient analysis by changing the analysis algorithm according to the category of the conversation. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the conversation content into a generative AI, which can determine the category and apply an appropriate analysis algorithm.

[0077] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. By adjusting the display method according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI, and the generative AI can adjust the display method.

[0078] The analysis unit can determine the priority of analysis based on when the conversation occurred. For example, the analysis unit may prioritize analyzing recent conversation content. The analysis unit can analyze past conversation content as needed. The analysis unit can apply different analysis algorithms depending on when the conversation occurred. This allows important conversations to be analyzed preferentially by determining the priority of analysis based on when the conversation occurred. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input conversation content into a generative AI, which can determine the timing of the conversation and determine the priority of analysis.

[0079] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the conversation during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant laws and regulations. The analysis unit can improve the accuracy of its analysis by referring to similar past cases. The analysis unit can improve the accuracy of its analysis by referring to expert opinions. Thus, the accuracy of the analysis is improved by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input relevant literature into a generative AI, which can then improve the accuracy of the analysis.

[0080] The alert unit can estimate the user's emotions and adjust the alerting method based on the estimated emotions. For example, if the user is tense, the alert unit can issue an alert in a calm voice. If the user is relaxed, the alert unit can issue an alert in a cheerful voice. If the user is in a hurry, the alert unit can issue a quick and concise alert. By adjusting the alerting method according to the user's emotions, more appropriate alerts can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the alert unit may be performed using AI, or not using AI. For example, the alert unit can input user emotion data into the generative AI, which can then adjust the alerting method.

[0081] The alert unit can adjust the level of detail of its alerts based on the importance of the conversation. For example, the alert unit can provide detailed alerts for important conversation content, and simplified alerts for less important conversation content. The alert unit can apply different alert methods depending on the importance of the conversation. This allows for appropriate alerts for important conversations by adjusting the level of detail according to the importance of the conversation. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alert unit can input conversation content into a generation AI, which can determine the importance and adjust the level of detail of the alert.

[0082] The alerting unit can apply different alerting methods depending on the category of the conversation when issuing an alert. For example, the alerting unit can provide a detailed alert for conversations related to complaints. For conversations related to general inquiries, it can provide a simplified alert. For conversations related to emergency responses, it can provide a rapid alert. This allows for efficient alerting by changing the alerting method according to the category of the conversation. Some or all of the above processing in the alerting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alerting unit can input the conversation content into a generation AI, which can determine the category and apply an appropriate alerting method.

[0083] The alert unit can estimate the user's emotions and determine the priority of alerts based on the estimated emotions. For example, if the user is angry, the alert unit will prioritize alerting to that conversation. If the user is sad, the alert unit can then prioritize alerting to that conversation. If the user has neutral emotions, the alert unit can alert to that conversation with normal priority. In this way, important conversations can be prioritized by determining the priority of alerts 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the alert unit may be performed using AI, or not using AI. For example, the alert unit can input user emotion data into the generative AI, which can then determine the priority of alerts.

[0084] The alerting unit can adjust its alerting method based on the location where the conversation occurred. For example, the alerting unit may prioritize alerting for conversations in a civil servant's office. It may then prioritize alerting for conversations in public places. It may also alert for conversations in private places as needed. This allows for appropriate alerting by adjusting the alerting method according to the location where the conversation occurred. Some or all of the above processing in the alerting unit may be performed using, for example, a generating AI, or without a generating AI. For example, the alerting unit may input the location where the conversation occurred into the generating AI, which can then adjust the alerting method.

[0085] The alerting unit can issue alerts while considering the attribute information of the conversation participants. For example, the alerting unit can adjust the level of detail of the alert by considering the attribute information of citizens (age, gender, etc.). The alerting unit can determine the priority of alerts based on the position and duties of public officials. If there are many participants in the conversation, the alerting unit can prioritize alerting to the statements of important speakers. This makes it possible to issue more appropriate alerts by considering the attribute information of the conversation participants. Some or all of the above processing in the alerting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the alerting unit can input the attribute information of the conversation participants into a generative AI, and the generative AI can adjust the level of detail and priority of the alert.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The civil servant support system can also include a feedback section. This section provides a function that allows civil servants to receive feedback on their interactions with citizens after their conversations. For example, the feedback section can play back recordings of conversations, allowing civil servants to review their responses. Furthermore, the feedback section can provide civil servants with the results of an AI-generated sentiment analysis, indicating which parts of the conversation caused negative emotions in citizens. In addition, the feedback section can offer specific advice and improvement measures to help civil servants identify areas for improvement. This enables civil servants to improve their interactions and maintain better relationships with citizens.

[0088] The civil servant support system can also include a training section. This training section provides training to help civil servants improve their skills in interacting with citizens. For example, the training section can use past conversation data to conduct simulations, allowing civil servants to practice handling various scenarios. Furthermore, the training section can enable civil servants to learn appropriate responses in specific situations based on the results of sentiment analysis performed by AI. In addition, the training section can provide feedback to help civil servants evaluate their responses and identify areas for improvement. This allows civil servants to improve their citizen interaction skills and provide better service.

[0089] The civil servant support system can also be equipped with a predictive function. This predictive function provides the ability to predict future conversation trends and potential problems based on past conversation data. For example, it can analyze past data to predict trends in citizen complaints during specific times or situations. It can also predict what problems specific citizens are facing and prepare countermeasures in advance. Furthermore, based on the results of sentiment analysis performed by AI, the predictive function can predict changes in citizens' emotions and provide advice for appropriate responses. This allows civil servants to anticipate problems in advance and respond quickly and appropriately.

[0090] The civil servant support system can also include a reminder function. This function provides civil servants with reminders to take necessary follow-up actions after conversations with citizens. For example, the reminder function can remind civil servants of tasks that need to be completed by a specific deadline, based on the content of the conversation. It can also track the status of responses to citizen requests and complaints and notify civil servants of the progress. Furthermore, the reminder function can remind civil servants of points that are particularly important to them, based on sentiment analysis results analyzed by AI. This allows civil servants to respond to citizen requests quickly and appropriately.

[0091] The civil servant support system can also include an escalation function. This escalation function provides the ability to escalate issues to higher-level officials when certain conditions are met during conversations with citizens. For example, the escalation function notifies higher-level officials if a citizen expresses strong dissatisfaction or if specific keywords are included. Furthermore, the escalation function can determine the need for escalation based on the results of sentiment analysis performed by AI. In addition, the escalation function can track the progress of escalations and notify civil servants of the progress. This allows civil servants to respond quickly and appropriately, resolving citizen dissatisfaction.

[0092] The civil servant support system can further use emotion estimation to adjust the tone of conversation based on the user's emotions. For example, the analysis unit can instruct the system to respond in a calm and composed tone if the user is angry. It can also instruct the system to respond in a gentle tone if the user is sad. Furthermore, it can instruct the system to respond in a friendly tone if the user is relaxed. This enables better communication by responding in an appropriate tone according to the user's emotions.

[0093] The civil servant support system can further utilize sentiment estimation capabilities to prioritize responses based on the user's emotions. For example, the analysis unit can prioritize responses to users who express strong dissatisfaction. It can then prioritize responses to urgent issues. Furthermore, if a user is making a general inquiry, it can handle that inquiry with the usual priority. This allows for prompt and appropriate service delivery by responding with appropriate priorities based on the user's emotions.

[0094] The civil servant support system can further utilize emotion estimation capabilities to adjust its response based on the user's emotions. For example, the analysis unit can instruct the system to provide a concise and clear explanation if the user is stressed, or a detailed explanation if the user is relaxed. Furthermore, if the user is in a hurry, it can instruct the system to provide a concise and rapid response. This allows the system to provide services using appropriate responses tailored to the user's emotions.

[0095] The civil servant support system can further utilize emotion estimation capabilities to adjust feedback based on the user's emotions. For example, if the user expresses dissatisfaction, the feedback system can suggest specific solutions. If the user is satisfied, it can provide feedback expressing gratitude. Furthermore, if the user has neutral emotions, it can provide general feedback. This allows for better relationships to be built by providing appropriate feedback tailored to the user's emotions.

[0096] The civil servant support system can further adjust the content of warnings based on the user's emotions using an emotion estimation function. For example, if the user is angry, the warning unit can issue a warning in a calm and composed tone. If the user is sad, it can issue a warning in a gentle tone. Furthermore, if the user is relaxed, it can issue a warning in a friendly tone. This enables better communication by providing warnings in an appropriate tone according to the user's emotions.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The recording unit records conversations between public officials and citizens. The recording unit can perform audio and text recordings, recording the conversation content in real time for later review. The recording unit can use audio files or text files as formats for saving the conversation content. Step 2: The analysis unit analyzes the conversation content recorded by the recording unit. The analysis unit uses natural language processing to analyze the conversation content and perform sentiment analysis. The analysis unit analyzes the context of the conversation and word choices to determine emotional fluctuations. For example, the analysis unit uses natural language processing techniques to perform morphological and grammatical analysis of the conversation content. The analysis unit can use sentiment classification algorithms for sentiment analysis. The analysis unit detects negative emotions and statements that constitute harassment in the conversation content. Step 3: The alerting unit issues an alert based on the results of the analysis performed by the analysis unit. Based on the sentiment analysis results, the alerting unit issues an alert regarding negative emotions or statements that constitute harassment. For example, the alerting unit might issue an alert such as, "Your current statement may constitute harassment." The alerting unit can use voice notifications or text notifications as notification methods. The alerting unit provides a message encouraging the user to reconsider their statement.

[0099] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0100] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0101] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0102] Each of the multiple elements described above, including the recording unit, analysis unit, and warning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit is implemented by the computer 36 of the smart device 14 and records the conversation content in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the conversation content using natural language processing and performs sentiment analysis. The warning unit is implemented by the control unit 46A of the smart device 14 and provides appropriate warnings based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] As shown in Figure 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.

[0105] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0109] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0110] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0111] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0112] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0113] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0115] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0117] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the recording unit, analysis unit, and alerting unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit is implemented by the computer 36 of the smart glasses 214 and records the conversation content in real time. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the conversation content using natural language processing and performs sentiment analysis. The alerting unit is implemented by the control unit 46A of the smart glasses 214 and provides appropriate alerts based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the recording unit, analysis unit, and alerting unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit is implemented by the computer 36 of the headset terminal 314 and records the conversation content in real time. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the conversation content using natural language processing and performs sentiment analysis. The alerting unit is implemented by the control unit 46A of the headset terminal 314 and provides appropriate alerts based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0143] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the recording unit, analysis unit, and warning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit is implemented by the computer 36 of the robot 414 and records the conversation content in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the conversation content using natural language processing and performs sentiment analysis. The warning unit is implemented by the control unit 46A of the robot 414 and provides appropriate warnings based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0152] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0154] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0155] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0156] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0160] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0161] 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.

[0162] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0163] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0164] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0165] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0167] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0168] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0169] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0170] (Note 1) A recording department that records conversations between civil servants and citizens, An analysis unit analyzes the content of the conversation recorded by the recording unit, The system includes a warning unit that issues a warning based on the results of the analysis performed by the aforementioned analysis unit. A system characterized by the following features. (Note 2) The aforementioned recording unit is Record conversations in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, We analyze conversation content using natural language processing and perform sentiment analysis. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned warning unit is, Based on the results of the sentiment analysis, we will issue warnings regarding negative emotions and remarks that constitute harassment. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, It analyzes the context of the conversation and the choice of words to determine emotional fluctuations. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned warning unit is, They issue a warning such as, "Your current statement may constitute harassment." The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recording unit is It estimates the user's emotions and adjusts the frequency of conversation recording based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is During recording, adjust the level of detail based on the importance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is When recording, apply different recording methods depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is It estimates the user's emotions and determines the priority of conversations to record based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is When recording, prioritize recordings based on where the conversation occurred. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is When recording, the recorder takes into account the attribute information of the conversation participants. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the context of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of analysis is determined based on when the conversation occurred. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, we refer to relevant literature related to the conversation to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned warning unit is, The system estimates the user's emotions and adjusts the method of alerting users based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned warning unit is, When issuing a warning, adjust the level of detail in the warning based on the importance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned warning unit is, When issuing a warning, apply different warning methods depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned warning unit is, The system estimates the user's emotions and prioritizes alerts based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned warning unit is, When issuing a warning, adjust the method of warning based on the location where the conversation occurred. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned warning unit is, When issuing a warning, the warning should be given while taking into account the attribute information of the participants in the conversation. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording department that records conversations between civil servants and citizens, An analysis unit analyzes the content of the conversation recorded by the recording unit, The system includes a warning unit that issues a warning based on the results of the analysis performed by the aforementioned analysis unit. A system characterized by the following features.

2. The aforementioned recording unit is Record conversations in real time. The system according to feature 1.

3. The aforementioned analysis unit, We analyze conversation content using natural language processing and perform sentiment analysis. The system according to feature 1.

4. The aforementioned warning unit is, Based on the results of the sentiment analysis, we will issue warnings regarding negative emotions and remarks that constitute harassment. The system according to feature 1.

5. The aforementioned analysis unit, It analyzes the context of the conversation and the choice of words to determine emotional fluctuations. The system according to feature 1.

6. The aforementioned recording unit is It estimates the user's emotions and adjusts the frequency of conversation recording based on the estimated user emotions. The system according to feature 1.

7. The aforementioned recording unit is During recording, adjust the level of detail based on the importance of the conversation. The system according to feature 1.

Images