system

Abstract

The system according to the embodiment aims to allow victims to be questioned while reducing their psychological burden. [Solution] A system according to an embodiment includes a reception unit, a question generation unit, a dialogue unit, a recording unit, and an emotion analysis unit. The reception unit receives the victim's story. The question generation unit analyzes the story received by the reception unit and generates appropriate questions. The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. The recording unit records the story obtained by the dialogue unit and saves it as text data. The emotion analysis unit analyzes the story obtained by the dialogue unit and analyzes the victim's emotions.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there is a risk that victims may find it psychologically stressful to speak to the police during questioning about sexual assaults.

[0005] The system according to the embodiment aims to allow victims to be questioned while reducing their psychological burden. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a question generation unit, a dialogue unit, a recording unit, and an emotion analysis unit. The reception unit receives the victim's story. The question generation unit analyzes the story received by the reception unit and generates appropriate questions. The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. The recording unit records the story obtained by the dialogue unit and saves it as text data. The emotion analysis unit analyzes the story obtained by the dialogue unit and analyzes the victim's emotions. [Effects of the Invention]

[0007] The system according to the embodiment allows victims to be questioned while reducing their psychological burden. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) In an embodiment of the present invention, an interrogation support system uses AI to converse with a victim and record the conversation when the victim feels uncomfortable speaking directly to the police. In this interrogation support system, when the victim describes their situation to the AI, the AI ​​understands what the victim is saying and asks appropriate questions. The AI ​​then records the victim's speech and saves it as text data. Furthermore, the AI ​​analyzes the victim's emotions and provides an environment in which the victim feels comfortable speaking. For example, if the victim says, "I was attacked on a dark street," the AI ​​asks, "Please tell me more about the situation." The AI ​​then records the victim's speech and saves it as text data. This recorded data can then be reviewed by the police. For example, the victim's speech can be converted directly into text and provided to the police. Furthermore, the AI ​​analyzes the victim's emotions and provides an environment in which the victim feels comfortable speaking. For example, if the victim is nervous, the AI ​​can respond by playing relaxing music. This system allows victims to feel comfortable speaking without having to speak directly to the police. Furthermore, the recorded data is accurately saved, making it useful for police review later. This allows the interrogation support system to allow victims to speak in peace without having to speak directly to the police. In addition, the recorded data is accurately saved, making it useful for police to review later.

[0029] An interrogation support system according to an embodiment includes a reception unit, a question generation unit, a dialogue unit, a recording unit, and an emotion analysis unit. The reception unit receives a victim's story. The victim's story may include, but is not limited to, oral testimony, written testimony, and audio recordings. The reception unit may, for example, select a quiet location to provide an environment in which the victim feels comfortable speaking. The reception unit may also take measures to ensure privacy when receiving the victim's story. The question generation unit analyzes the victim's story and generates appropriate questions. The question generation unit may, for example, automatically generate the next question to ask based on the victim's story. For example, if the victim says, "I was attacked on a dark street," the question generation unit may generate a question such as, "Please tell me more about the situation at the time." The question generation unit may also adjust the order of questions according to the progress of the victim's story. The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. For example, the dialogue unit may ask questions in a gentle tone to make it easier for the victim to talk. The dialogue unit can also adjust the tempo of the dialogue depending on the progress of the victim's speech. The recording unit records the speech obtained by the dialogue unit and saves it as text data. The recording unit can, for example, record the victim's speech as high-quality audio data and then convert it into text data using voice recognition technology. The recording unit can also take measures to safely save the recorded data. The emotion analysis unit analyzes the speech obtained by the dialogue unit and analyzes the victim's emotions. The emotion analysis unit can, for example, analyze the tone and speed of the victim's voice to infer the victim's emotions. The emotion analysis unit can also analyze the victim's facial expressions to infer the victim's emotions. As a result, the interrogation support system according to the embodiment allows victims to talk about their situation in a safe manner without having to speak directly to the police. Furthermore, because the recorded data is accurately saved, it is useful for the police to review later.

[0030] The question generation unit can generate appropriate questions based on the victim's story. For example, the question generation unit can automatically generate the next question to ask based on what the victim has said. For example, if the victim says, "I was attacked on a dark street," the question generation unit generates a question such as, "Please tell me in detail about what happened at the time." The question generation unit can also adjust the order of questions according to the progress of the victim's story. For example, the question generation unit adjusts the order of questions to make it easier for the victim to talk. Furthermore, the question generation unit can analyze the victim's emotions and generate questions according to those emotions. For example, if the victim is nervous, the question generation unit asks questions in a gentle tone. This improves the accuracy of interrogations by generating appropriate questions based on the victim's story.

[0031] The recording unit can record the victim's speech and save it as text data. For example, the recording unit can record the victim's speech as high-quality audio data and then convert it into text data using speech recognition technology. For example, the recording unit can record the victim's speech and convert the recorded data into text data using speech recognition technology. The recording unit can also take measures to safely store the recorded data. For example, the recording unit can encrypt and store the recorded data. Furthermore, the recording unit can take measures to enable the police to review the recorded data later. For example, the recording unit has an interface for providing the recorded data to the police. In this way, the victim's speech can be accurately recorded and saved as text data, making it easier to review later.

[0032] The dialogue unit can converse with the victim and ask appropriate questions. For example, the dialogue unit can ask questions in a gentle tone so that the victim feels comfortable talking. For example, if the victim is nervous, the dialogue unit will ask questions in a gentle tone. The dialogue unit can also adjust the tempo of the dialogue according to the progress of the victim's story. For example, the dialogue unit will adjust the tempo of the dialogue so that the victim feels comfortable talking. Furthermore, the dialogue unit can analyze the victim's emotions and conduct a dialogue that corresponds to the emotions. For example, if the victim is emotional, the dialogue unit will conduct a dialogue to calm the victim. In this way, by conversing with the victim and asking appropriate questions, the accuracy of the interrogation can be improved.

[0033] The reception unit can analyze the victim's past questioning history and select an appropriate reception method. For example, the reception unit can analyze the time periods when the victim found it easy to speak in the past and conduct the questioning at those times. For example, the reception unit can analyze the time periods when the victim found it easy to speak in the past and conduct the questioning at those times. The reception unit can also analyze the language and tone of voice that the victim used in the past and have the AI ​​respond based on that. For example, the reception unit can analyze the language and tone of voice that the victim used in the past and have the AI ​​respond based on that. Furthermore, the reception unit can analyze the environment in which the victim found it easy to speak in the past (quiet place, specific music, etc.) and recreate that environment. For example, the reception unit can analyze the environment in which the victim found it easy to speak in the past and recreate that environment. In this way, the optimal reception method can be selected by analyzing the victim's past questioning history.

[0034] When receiving information, the reception unit can prioritize receiving highly relevant information by taking into account the geographical location information of the victim. For example, if the victim was victimized in a specific area, the reception unit can prioritize receiving information related to that area. For example, if the victim was victimized in a specific area, the reception unit prioritizes receiving information related to that area. Furthermore, if the victim is on the move, the reception unit can also prioritize receiving related information based on the victim's current location. For example, if the victim is on the move, the reception unit prioritizes receiving related information based on the victim's current location. Furthermore, if the victim is in a specific location, the reception unit can also prioritize receiving information related to that location. For example, if the victim is in a specific location, the reception unit prioritizes receiving information related to that location. In this way, highly relevant information can be prioritized by taking into account the victim's geographical location information.

[0035] At the time of reception, the reception unit can analyze the victim's social media activity and receive related information. The reception unit can, for example, analyze the content posted by the victim on social media and receive the related information. For example, the reception unit analyzes the content posted by the victim on social media and receives the related information. The reception unit can also analyze information on accounts followed by the victim on social media and receive related information based on the information. For example, the reception unit analyzes information on accounts followed by the victim on social media and receives related information based on the information. The reception unit can also analyze information on groups in which the victim participates on social media and receive related information based on the information. For example, the reception unit analyzes information on groups in which the victim participates on social media and receives related information based on the information. In this way, related information can be received by analyzing the victim's social media activity.

[0036] When generating a question, the question generation unit can adjust the level of detail of the question based on the importance of what the victim says. For example, if the victim is talking about important information, the question generation unit can ask a detailed question. For example, if the victim is talking about important information, the question generation unit asks a detailed question. Furthermore, if the victim is talking about general information, the question generation unit can ask a simple question. For example, if the victim is talking about general information, the question generation unit asks a simple question. Furthermore, if the victim is emotional, the question generation unit can ask a question to calm the victim. For example, if the victim is emotional, the question generation unit asks a question to calm the victim. In this way, by adjusting the level of detail of the question based on the importance of what the victim says, it is possible to ask an appropriate question.

[0037] When generating questions, the question generation unit can apply different question algorithms depending on the category of the victim's story. For example, if the victim is talking about violence, the question generation unit can ask detailed questions about the violence. For example, if the victim is talking about violence, the question generation unit asks detailed questions about the violence. Furthermore, if the victim is talking about harassment, the question generation unit can ask detailed questions about the harassment. For example, if the victim is talking about harassment, the question generation unit can ask detailed questions about the harassment. Furthermore, if the victim is talking about stalking, the question generation unit can ask detailed questions about the stalking. For example, if the victim is talking about stalking, the question generation unit asks detailed questions about the stalking. This makes it possible to ask appropriate questions by applying different question algorithms depending on the category of the victim's story.

[0038] When generating questions, the question generation unit can determine the priority of questions based on when the victim's story was submitted. For example, if the victim is talking about a recent event, the question generation unit can prioritize questions related to that story. For example, if the victim is talking about a recent event, the question generation unit prioritizes questions related to that story. Furthermore, if the victim is talking about a past event, the question generation unit can postpone questions related to that story. For example, if the victim is talking about a past event, the question generation unit postpones questions related to that story. Furthermore, if the victim is emotional, the question generation unit can also prioritize questions to calm the victim. For example, if the victim is emotional, the question generation unit prioritizes questions to calm the victim. In this way, by determining the priority of questions based on when the victim's story was submitted, appropriate questions can be asked.

[0039] When generating questions, the question generation unit can adjust the order of questions based on the relevance of the victim's story. For example, if the victim is talking about important information, the question generation unit can prioritize questions related to that information. For example, if the victim is talking about important information, the question generation unit prioritizes questions related to that information. Furthermore, if the victim is talking about general information, the question generation unit can postpone questions related to that information. For example, if the victim is talking about general information, the question generation unit postpones questions related to that information. Furthermore, if the victim is emotional, the question generation unit can prioritize questions to calm the victim. For example, if the victim is emotional, the question generation unit prioritizes questions to calm the victim. In this way, adjusting the order of questions based on the relevance of the victim's story enables appropriate questions to be asked.

[0040] The dialogue unit can improve the accuracy of the dialogue by taking into account the interrelationships of what the victim has said during the dialogue. For example, the dialogue unit can correlate what the victim has said to each other and conduct a dialogue that is consistent. For example, the dialogue unit correlates what the victim has said to each other and conduct a dialogue that is consistent. The dialogue unit can also appropriately select the next question based on what the victim has said. For example, the dialogue unit can appropriately select the next question based on what the victim has said. The dialogue unit can also analyze what the victim has said and extract important information to proceed with the dialogue. For example, the dialogue unit can analyze what the victim has said and extract important information to proceed with the dialogue. In this way, the accuracy of the dialogue is improved by taking into account the interrelationships of what the victim has said.

[0041] The dialogue unit can conduct the dialogue taking into account the victim's attribute information. The dialogue unit can, for example, conduct the dialogue using appropriate language depending on the victim's age. For example, the dialogue unit conducts the dialogue using appropriate language depending on the victim's age. The dialogue unit can also ask appropriate questions depending on the victim's gender. For example, the dialogue unit can ask appropriate questions depending on the victim's gender. The dialogue unit can also conduct an appropriate dialogue depending on the victim's cultural background. For example, the dialogue unit conducts an appropriate dialogue depending on the victim's cultural background. This makes it possible to conduct an appropriate dialogue by taking into account the victim's attribute information.

[0042] The dialogue unit can conduct a dialogue taking into account the geographical distribution of the victim. For example, if the victim lives in a specific area, the dialogue unit can provide information related to the area. For example, if the victim lives in a specific area, the dialogue unit can provide information related to the area. Furthermore, if the victim is on the move, the dialogue unit can conduct a dialogue based on the victim's current location. For example, if the victim is on the move, the dialogue unit can conduct a dialogue based on the victim's current location. Furthermore, if the victim is in a specific location, the dialogue unit can provide information related to the location. For example, if the victim is in a specific location, the dialogue unit provides information related to the location. This enables an appropriate dialogue by taking into account the geographical distribution of the victim.

[0043] The dialogue unit can improve the accuracy of the dialogue by referring to literature related to the victim during the dialogue. For example, the dialogue unit can improve the accuracy of the dialogue by referring to literature related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to literature related to what the victim is talking about. The dialogue unit can also improve the accuracy of the dialogue by referring to research results related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to research results related to what the victim is talking about. The dialogue unit can also improve the accuracy of the dialogue by referring to statistical data related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to statistical data related to what the victim is talking about. In this way, the accuracy of the dialogue is improved by referring to literature related to the victim.

[0044] When recording, the recording unit can apply different recording algorithms depending on the category of what the victim is saying. For example, if the victim is talking about violence, the recording unit can apply a detailed recording algorithm related to violence. For example, if the victim is talking about violence, the recording unit applies a detailed recording algorithm related to violence. Furthermore, if the victim is talking about harassment, the recording unit can apply a detailed recording algorithm related to harassment. For example, if the victim is talking about harassment, the recording unit applies a detailed recording algorithm related to harassment. Furthermore, if the victim is talking about stalking, the recording unit can apply a detailed recording algorithm related to stalking. For example, if the victim is talking about stalking, the recording unit applies a detailed recording algorithm related to stalking. This makes it possible to perform appropriate recording by applying different recording algorithms depending on the category of what the victim is saying.

[0045] When recording, the recording unit can determine the priority of the recording based on the time when the victim's story was submitted. For example, if the victim is talking about a recent event, the recording unit can prioritize recording that story. For example, if the victim is talking about a recent event, the recording unit prioritizes recording that story. In addition, if the victim is talking about a past event, the recording unit can postpone recording that story. For example, if the victim is talking about a past event, the recording unit postpones recording that story. Furthermore, if the victim is emotional, the recording unit can prioritize recording stories to calm the victim. For example, if the victim is emotional, the recording unit prioritizes recording stories to calm the victim. In this way, by determining the priority of the recording based on the time when the victim's story was submitted, appropriate recording is possible.

[0046] During recording, the recording unit can adjust the order of recording based on the relevance of the victim's story. For example, if the victim is speaking important information, the recording unit can prioritize recording that information. For example, if the victim is speaking important information, the recording unit records that information first. Furthermore, if the victim is speaking general information, the recording unit can record that information later. For example, if the victim is speaking general information, the recording unit records that information later. Furthermore, if the victim is emotional, the recording unit can prioritize recording stories to calm the victim. For example, if the victim is emotional, the recording unit records stories to calm the victim. In this way, by adjusting the order of recording based on the relevance of the victim's story, appropriate recording is possible.

[0047] During emotion analysis, the emotion analysis unit can optimize the analysis algorithm by referring to the victim's past emotion data. The emotion analysis unit can, for example, analyze the current emotion based on the victim's past emotion data. For example, the emotion analysis unit analyzes the current emotion based on the victim's past emotion data. The emotion analysis unit can also analyze changes in emotion by referring to the victim's past emotion data. For example, the emotion analysis unit analyzes changes in emotion by referring to the victim's past emotion data. Furthermore, the emotion analysis unit can also select an optimal analysis algorithm based on the victim's past emotion data. For example, the emotion analysis unit selects an optimal analysis algorithm based on the victim's past emotion data. In this way, the analysis algorithm can be optimized by referring to the victim's past emotion data.

[0048] During emotion analysis, the emotion analysis unit can apply different analysis methods depending on the category of the victim's story. For example, if the victim is talking about violence, the emotion analysis unit can apply an emotion analysis method related to violence. For example, if the victim is talking about violence, the emotion analysis unit applies an emotion analysis method related to violence. Furthermore, if the victim is talking about harassment, the emotion analysis unit can also apply an emotion analysis method related to harassment. For example, if the victim is talking about harassment, the emotion analysis unit applies an emotion analysis method related to harassment. Furthermore, if the victim is talking about stalking, the emotion analysis unit can also apply an emotion analysis method related to stalking. For example, if the victim is talking about stalking, the emotion analysis unit applies an emotion analysis method related to stalking. This enables appropriate analysis by applying different analysis methods depending on the category of the victim's story.

[0049] During emotion analysis, the emotion analysis unit can weight the analysis based on when the victim's story was submitted. For example, if the victim is talking about a recent event, the emotion analysis unit can prioritize emotion analysis related to that story. For example, if the victim is talking about a recent event, the emotion analysis unit prioritizes emotion analysis related to that story. Furthermore, if the victim is talking about a past event, the emotion analysis unit can postpone emotion analysis related to that story. For example, if the victim is talking about a past event, the emotion analysis unit postpones emotion analysis related to that story. Furthermore, if the victim is emotional, the emotion analysis unit can also prioritize analysis to calm the victim. For example, if the victim is emotional, the emotion analysis unit prioritizes analysis to calm the victim. In this way, weighting the analysis based on when the victim's story was submitted enables appropriate analysis.

[0050] When analyzing emotions, the emotion analysis unit can perform the analysis by referring to market data related to the victim. For example, the emotion analysis unit can perform emotion analysis by referring to market data related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to market data related to what the victim is talking about. The emotion analysis unit can also perform emotion analysis by referring to statistical data related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to statistical data related to what the victim is talking about. The emotion analysis unit can also perform emotion analysis by referring to research results related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to research results related to what the victim is talking about. This makes it possible to perform an appropriate analysis by referring to market data related to the victim.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] When accepting a victim's story, the reception unit can analyze the victim's past questioning history and select the appropriate reception method. For example, it can analyze the time of day when the victim found it easiest to speak in the past and conduct the questioning at that time. It can also analyze the language and tone that the victim used in the past that made them feel comfortable speaking, and have the AI ​​respond based on that. It can also analyze the environment in which the victim found it easiest to speak in the past (quiet places, specific music, etc.) and recreate that environment. This makes it possible to select the optimal reception method by analyzing the victim's past questioning history.

[0053] The question generation unit can apply different question algorithms depending on the category of the victim's story. For example, if the victim talks about violence, detailed questions about violence can be asked. If the victim talks about harassment, detailed questions about harassment can be asked. Furthermore, if the victim talks about stalking, detailed questions about stalking can be asked. This makes it possible to ask appropriate questions by applying different question algorithms depending on the category of the victim's story.

[0054] The dialogue unit can take into account the victim's attribute information when conducting a dialogue. For example, it can use appropriate language depending on the victim's age. It can also ask appropriate questions depending on the victim's gender. It can also conduct an appropriate dialogue depending on the victim's cultural background. This makes it possible to have an appropriate dialogue by taking into account the victim's attribute information.

[0055] During emotion analysis, the emotion analysis unit can optimize the analysis algorithm by referring to the victim's past emotion data. For example, it can analyze the victim's current emotion based on the victim's past emotion data. It can also analyze changes in emotion by referring to the victim's past emotion data. It can also select the optimal analysis algorithm based on the victim's past emotion data. In this way, the analysis algorithm can be optimized by referring to the victim's past emotion data.

[0056] When generating questions, the question generation unit can determine the priority of questions based on when the victim's story was submitted. For example, if the victim is talking about recent events, questions related to that story can be prioritized. Also, if the victim is talking about past events, questions related to that story can be postponed. Furthermore, if the victim is emotional, questions to calm the victim can be prioritized. In this way, by determining the priority of questions based on when the victim's story was submitted, appropriate questions can be asked.

[0057] The recording unit can apply different recording algorithms depending on the category of what the victim is saying during recording. For example, if the victim is talking about violence, a detailed recording algorithm related to violence can be applied. Also, if the victim is talking about harassment, a detailed recording algorithm related to harassment can be applied. Furthermore, if the victim is talking about stalking, a detailed recording algorithm related to stalking can be applied. This allows for appropriate recording by applying different recording algorithms depending on the category of what the victim is saying.

[0058] During emotion analysis, the emotion analysis unit can weight the analysis based on when the victim's story was submitted. For example, if the victim is talking about a recent event, it can prioritize emotion analysis related to that story. Also, if the victim is talking about a past event, it can postpone emotion analysis related to that story. Furthermore, if the victim is emotional, it can prioritize analysis aimed at calming the victim. This allows for appropriate analysis by weighting the analysis based on when the victim's story was submitted.

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

[0060] Step 1: The reception desk accepts victims' stories. Victim stories can include oral statements, written statements, and audio recordings. The reception desk can select a quiet location and take measures to ensure privacy to provide an environment where victims can talk comfortably. Step 2: The question generator analyzes the story received by the reception unit and generates appropriate questions. For example, it can automatically generate the next question to ask based on what the victim has said and adjust the order of the questions. Step 3: The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. The dialogue unit asks questions in a gentle tone to make it easier for the victim to talk, and can adjust the tempo of the dialogue. Step 4: The recording unit records the story obtained by the dialogue unit and saves it as text data. The recording unit can record the victim's story as high-quality audio data and then convert it into text data using voice recognition technology. It can also take measures to safely store the recorded data. Step 5: The emotion analysis unit analyzes the story obtained by the dialogue unit and analyzes the victim's emotions. The emotion analysis unit can estimate the victim's emotions by analyzing the tone, speed, and facial expressions of the victim's voice.

[0061] (Example 2) In an embodiment of the present invention, an interrogation support system uses AI to converse with a victim and record the conversation when the victim feels uncomfortable speaking directly to the police. In this interrogation support system, when the victim describes their situation to the AI, the AI ​​understands what the victim is saying and asks appropriate questions. The AI ​​then records the victim's speech and saves it as text data. Furthermore, the AI ​​analyzes the victim's emotions and provides an environment in which the victim feels comfortable speaking. For example, if the victim says, "I was attacked on a dark street," the AI ​​asks, "Please tell me more about the situation." The AI ​​then records the victim's speech and saves it as text data. This recorded data can then be reviewed by the police. For example, the victim's speech can be converted directly into text and provided to the police. Furthermore, the AI ​​analyzes the victim's emotions and provides an environment in which the victim feels comfortable speaking. For example, if the victim is nervous, the AI ​​can respond by playing relaxing music. This system allows victims to feel comfortable speaking without having to speak directly to the police. Furthermore, the recorded data is accurately saved, making it useful for police review later. This allows the interrogation support system to allow victims to speak in peace without having to speak directly to the police. In addition, the recorded data is accurately saved, making it useful for police to review later.

[0062] An interrogation support system according to an embodiment includes a reception unit, a question generation unit, a dialogue unit, a recording unit, and an emotion analysis unit. The reception unit receives a victim's story. The victim's story may include, but is not limited to, oral testimony, written testimony, and audio recordings. The reception unit may, for example, select a quiet location to provide an environment in which the victim feels comfortable speaking. The reception unit may also take measures to ensure privacy when receiving the victim's story. The question generation unit analyzes the victim's story and generates appropriate questions. The question generation unit may, for example, automatically generate the next question to ask based on the victim's story. For example, if the victim says, "I was attacked on a dark street," the question generation unit may generate a question such as, "Please tell me more about the situation at the time." The question generation unit may also adjust the order of questions according to the progress of the victim's story. The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. For example, the dialogue unit may ask questions in a gentle tone to make it easier for the victim to talk. The dialogue unit can also adjust the tempo of the dialogue depending on the progress of the victim's speech. The recording unit records the speech obtained by the dialogue unit and saves it as text data. The recording unit can, for example, record the victim's speech as high-quality audio data and then convert it into text data using voice recognition technology. The recording unit can also take measures to safely save the recorded data. The emotion analysis unit analyzes the speech obtained by the dialogue unit and analyzes the victim's emotions. The emotion analysis unit can, for example, analyze the tone and speed of the victim's voice to infer the victim's emotions. The emotion analysis unit can also analyze the victim's facial expressions to infer the victim's emotions. As a result, the interrogation support system according to the embodiment allows victims to talk about their situation in a safe manner without having to speak directly to the police. Furthermore, because the recorded data is accurately saved, it is useful for the police to review later.

[0063] The emotion analysis unit can provide an environment where the victim can feel at ease. For example, the emotion analysis unit can play music that helps the victim relax. For example, the emotion analysis unit analyzes the victim's emotions and selects and plays relaxing music. The emotion analysis unit can also select a quiet place to make it easier for the victim to talk. For example, the emotion analysis unit analyzes the victim's emotions and selects and guides the victim to a quiet place. Furthermore, the emotion analysis unit can also take measures to ensure the victim's privacy. For example, the emotion analysis unit analyzes the victim's emotions and takes measures to ensure privacy. This provides an environment where the victim can relax, making it easier for the victim to talk.

[0064] The question generation unit can generate appropriate questions based on the victim's story. For example, the question generation unit can automatically generate the next question to ask based on what the victim has said. For example, if the victim says, "I was attacked on a dark street," the question generation unit generates a question such as, "Please tell me in detail about what happened at the time." The question generation unit can also adjust the order of questions according to the progress of the victim's story. For example, the question generation unit adjusts the order of questions to make it easier for the victim to talk. Furthermore, the question generation unit can analyze the victim's emotions and generate questions according to those emotions. For example, if the victim is nervous, the question generation unit asks questions in a gentle tone. This improves the accuracy of interrogations by generating appropriate questions based on the victim's story.

[0065] The recording unit can record the victim's speech and save it as text data. For example, the recording unit can record the victim's speech as high-quality audio data and then convert it into text data using speech recognition technology. For example, the recording unit can record the victim's speech and convert the recorded data into text data using speech recognition technology. The recording unit can also take measures to safely store the recorded data. For example, the recording unit can encrypt and store the recorded data. Furthermore, the recording unit can take measures to enable the police to review the recorded data later. For example, the recording unit has an interface for providing the recorded data to the police. In this way, the victim's speech can be accurately recorded and saved as text data, making it easier to review later.

[0066] The dialogue unit can converse with the victim and ask appropriate questions. For example, the dialogue unit can ask questions in a gentle tone so that the victim feels comfortable talking. For example, if the victim is nervous, the dialogue unit will ask questions in a gentle tone. The dialogue unit can also adjust the tempo of the dialogue according to the progress of the victim's story. For example, the dialogue unit will adjust the tempo of the dialogue so that the victim feels comfortable talking. Furthermore, the dialogue unit can analyze the victim's emotions and conduct a dialogue that corresponds to the emotions. For example, if the victim is emotional, the dialogue unit will conduct a dialogue to calm the victim. In this way, by conversing with the victim and asking appropriate questions, the accuracy of the interrogation can be improved.

[0067] The emotion analysis unit can analyze the victim's emotions and play relaxing music. The emotion analysis unit can, for example, analyze the victim's emotions and select and play relaxing music. For example, the emotion analysis unit analyzes the victim's emotions and selects and plays relaxing music. The emotion analysis unit can also select a quiet place to make it easier for the victim to talk. For example, the emotion analysis unit analyzes the victim's emotions and selects and guides the victim to a quiet place. Furthermore, the emotion analysis unit can take measures to ensure the victim's privacy. For example, the emotion analysis unit analyzes the victim's emotions and takes measures to ensure privacy. In this way, by analyzing the victim's emotions and playing relaxing music, the victim can be more likely to talk.

[0068] The reception unit can estimate the victim's emotions and adjust the timing to make it easier for the victim to talk based on the estimated victim's emotions. For example, if the victim seems nervous, the AI ​​can temporarily pause the conversation and suggest a short break to relax. For example, if the victim seems nervous, the AI ​​can temporarily pause the conversation and suggest a short break to relax. Furthermore, if the victim appears calm, the AI ​​can encourage the victim to continue talking, smoothly progressing the questioning. For example, if the victim seems calm, the AI ​​can encourage the victim to continue talking, smoothly progressing the questioning. Furthermore, if the victim seems emotional, the AI ​​can temporarily pause the conversation and suggest relaxation techniques such as encouraging the victim to take a deep breath. For example, if the victim seems emotional, the AI ​​can temporarily pause the conversation and suggest relaxation techniques such as encouraging the victim to take a deep breath. This makes it easier for the victim to talk by adjusting the timing to make it easier for the victim to talk based on the victim's emotions.

[0069] The reception unit can analyze the victim's past questioning history and select an appropriate reception method. For example, the reception unit can analyze the time periods when the victim found it easy to speak in the past and conduct the questioning at those times. For example, the reception unit can analyze the time periods when the victim found it easy to speak in the past and conduct the questioning at those times. The reception unit can also analyze the language and tone of voice that the victim used in the past and have the AI ​​respond based on that. For example, the reception unit can analyze the language and tone of voice that the victim used in the past and have the AI ​​respond based on that. Furthermore, the reception unit can analyze the environment in which the victim found it easy to speak in the past (quiet place, specific music, etc.) and recreate that environment. For example, the reception unit can analyze the environment in which the victim found it easy to speak in the past and recreate that environment. In this way, the optimal reception method can be selected by analyzing the victim's past questioning history.

[0070] The reception department can filter based on the victim's current psychological state when receiving the call. For example, if the victim is very nervous, the reception department can have the AI ​​start with simple questions and gradually move on to more detailed questions. For example, if the victim is very nervous, the reception department can have the AI ​​start with simple questions and gradually move on to more detailed questions. Furthermore, if the victim is relaxed, the reception department can have the AI ​​ask detailed questions early on to efficiently proceed with the interrogation. For example, if the victim is relaxed, the reception department can have the AI ​​ask detailed questions early on to efficiently proceed with the interrogation. Furthermore, if the victim is emotional, the reception department can have the AI ​​ask questions to calm the victim down before getting to the main topic. For example, if the victim is emotional, the reception department can have the AI ​​ask questions to calm the victim down before getting to the main topic. This makes it possible to filter based on the victim's current psychological state and respond appropriately.

[0071] The reception unit can estimate the victim's emotions and determine the priority of the content to be received based on the estimated victim's emotions. For example, if the victim is very nervous, the AI ​​can first prioritize questions to help them relax. For example, if the victim is very nervous, the AI ​​can first prioritize questions to help them relax. Furthermore, if the victim is calm, the AI ​​can prioritize important questions. For example, if the victim is calm, the AI ​​can prioritize important questions. Furthermore, if the victim is emotional, the AI ​​can prioritize questions to help them calm down. For example, if the victim is emotional, the AI ​​can prioritize questions to help them calm down. This makes it possible to prioritize the content to be received based on the victim's emotions, enabling appropriate responses.

[0072] When receiving information, the reception unit can prioritize receiving highly relevant information by taking into account the geographical location information of the victim. For example, if the victim was victimized in a specific area, the reception unit can prioritize receiving information related to that area. For example, if the victim was victimized in a specific area, the reception unit prioritizes receiving information related to that area. Furthermore, if the victim is on the move, the reception unit can also prioritize receiving related information based on the victim's current location. For example, if the victim is on the move, the reception unit prioritizes receiving related information based on the victim's current location. Furthermore, if the victim is in a specific location, the reception unit can also prioritize receiving information related to that location. For example, if the victim is in a specific location, the reception unit prioritizes receiving information related to that location. In this way, highly relevant information can be prioritized by taking into account the victim's geographical location information.

[0073] At the time of reception, the reception unit can analyze the victim's social media activity and receive related information. The reception unit can, for example, analyze the content posted by the victim on social media and receive the related information. For example, the reception unit analyzes the content posted by the victim on social media and receives the related information. The reception unit can also analyze information on accounts followed by the victim on social media and receive related information based on the information. For example, the reception unit analyzes information on accounts followed by the victim on social media and receives related information based on the information. The reception unit can also analyze information on groups in which the victim participates on social media and receive related information based on the information. For example, the reception unit analyzes information on groups in which the victim participates on social media and receives related information based on the information. In this way, related information can be received by analyzing the victim's social media activity.

[0074] The question generation unit can estimate the victim's emotions and adjust the way the questions are phrased based on the estimated victim's emotions. For example, if the victim is nervous, the question generation unit can ask questions in a gentle tone. For example, if the victim is nervous, the question generation unit asks questions in a gentle tone. Furthermore, if the victim is relaxed, the question generation unit can ask detailed questions. For example, if the victim is relaxed, the question generation unit asks detailed questions. Furthermore, if the victim is emotional, the question generation unit can ask questions to calm the victim. For example, if the victim is emotional, the question generation unit asks questions to calm the victim. In this way, adjusting the way the questions are phrased based on the victim's emotions makes it easier for the victim to talk.

[0075] When generating a question, the question generation unit can adjust the level of detail of the question based on the importance of what the victim says. For example, if the victim is talking about important information, the question generation unit can ask a detailed question. For example, if the victim is talking about important information, the question generation unit asks a detailed question. Furthermore, if the victim is talking about general information, the question generation unit can ask a simple question. For example, if the victim is talking about general information, the question generation unit asks a simple question. Furthermore, if the victim is emotional, the question generation unit can ask a question to calm the victim. For example, if the victim is emotional, the question generation unit asks a question to calm the victim. In this way, by adjusting the level of detail of the question based on the importance of what the victim says, it is possible to ask an appropriate question.

[0076] When generating questions, the question generation unit can apply different question algorithms depending on the category of the victim's story. For example, if the victim is talking about violence, the question generation unit can ask detailed questions about the violence. For example, if the victim is talking about violence, the question generation unit asks detailed questions about the violence. Furthermore, if the victim is talking about harassment, the question generation unit can ask detailed questions about the harassment. For example, if the victim is talking about harassment, the question generation unit can ask detailed questions about the harassment. Furthermore, if the victim is talking about stalking, the question generation unit can ask detailed questions about the stalking. For example, if the victim is talking about stalking, the question generation unit asks detailed questions about the stalking. This makes it possible to ask appropriate questions by applying different question algorithms depending on the category of the victim's story.

[0077] The question generation unit can estimate the emotion of the victim and adjust the length of the question based on the estimated emotion of the victim. For example, the question generation unit can ask a short question when the victim is nervous. For example, the question generation unit asks a short question when the victim is nervous. The question generation unit can also ask a long question when the victim is relaxed. For example, the question generation unit asks a long question when the victim is relaxed. Furthermore, the question generation unit can also ask a short question to calm the victim when the victim is emotional. For example, the question generation unit asks a short question to calm the victim when the victim is emotional. In this way, adjusting the length of the question based on the emotion of the victim makes it easier for the victim to talk.

[0078] When generating questions, the question generation unit can determine the priority of questions based on when the victim's story was submitted. For example, if the victim is talking about a recent event, the question generation unit can prioritize questions related to that story. For example, if the victim is talking about a recent event, the question generation unit prioritizes questions related to that story. Furthermore, if the victim is talking about a past event, the question generation unit can postpone questions related to that story. For example, if the victim is talking about a past event, the question generation unit postpones questions related to that story. Furthermore, if the victim is emotional, the question generation unit can also prioritize questions to calm the victim. For example, if the victim is emotional, the question generation unit prioritizes questions to calm the victim. In this way, by determining the priority of questions based on when the victim's story was submitted, appropriate questions can be asked.

[0079] When generating questions, the question generation unit can adjust the order of questions based on the relevance of the victim's story. For example, if the victim is talking about important information, the question generation unit can prioritize questions related to that information. For example, if the victim is talking about important information, the question generation unit prioritizes questions related to that information. Furthermore, if the victim is talking about general information, the question generation unit can postpone questions related to that information. For example, if the victim is talking about general information, the question generation unit postpones questions related to that information. Furthermore, if the victim is emotional, the question generation unit can prioritize questions to calm the victim. For example, if the victim is emotional, the question generation unit prioritizes questions to calm the victim. In this way, adjusting the order of questions based on the relevance of the victim's story enables appropriate questions to be asked.

[0080] The dialogue unit can estimate the victim's emotions and adjust the way the dialogue proceeds based on the estimated victim's emotions. For example, if the victim is nervous, the dialogue unit can proceed slowly. For example, if the victim is nervous, the dialogue unit proceeds slowly. Furthermore, if the victim is relaxed, the dialogue unit can proceed smoothly. For example, if the victim is relaxed, the dialogue unit can proceed smoothly. Furthermore, if the victim is emotional, the dialogue unit can temporarily halt the dialogue and engage in dialogue to calm the victim. For example, if the victim is emotional, the dialogue unit can temporarily halt the dialogue and engage in dialogue to calm the victim. In this way, adjusting the way the dialogue proceeds based on the victim's emotions makes it easier for the victim to talk.

[0081] The dialogue unit can improve the accuracy of the dialogue by taking into account the interrelationships of what the victim has said during the dialogue. For example, the dialogue unit can correlate what the victim has said to each other and conduct a dialogue that is consistent. For example, the dialogue unit correlates what the victim has said to each other and conduct a dialogue that is consistent. The dialogue unit can also appropriately select the next question based on what the victim has said. For example, the dialogue unit can appropriately select the next question based on what the victim has said. The dialogue unit can also analyze what the victim has said and extract important information to proceed with the dialogue. For example, the dialogue unit can analyze what the victim has said and extract important information to proceed with the dialogue. In this way, the accuracy of the dialogue is improved by taking into account the interrelationships of what the victim has said.

[0082] The dialogue unit can conduct the dialogue taking into account the victim's attribute information. The dialogue unit can, for example, conduct the dialogue using appropriate language depending on the victim's age. For example, the dialogue unit conducts the dialogue using appropriate language depending on the victim's age. The dialogue unit can also ask appropriate questions depending on the victim's gender. For example, the dialogue unit can ask appropriate questions depending on the victim's gender. The dialogue unit can also conduct an appropriate dialogue depending on the victim's cultural background. For example, the dialogue unit conducts an appropriate dialogue depending on the victim's cultural background. This makes it possible to conduct an appropriate dialogue by taking into account the victim's attribute information.

[0083] The dialogue unit can estimate the victim's emotions and adjust the order in which dialogue results are displayed based on the estimated victim's emotions. For example, if the victim is nervous, the dialogue unit can display important information first. For example, if the victim is nervous, the dialogue unit displays important information first. The dialogue unit can also display detailed information first if the victim is relaxed. For example, if the victim is relaxed, the dialogue unit displays detailed information first. Furthermore, if the victim is emotional, the dialogue unit can also display information to calm the victim first. For example, if the victim is emotional, the dialogue unit displays information to calm the victim first. In this way, adjusting the order in which dialogue results are displayed based on the victim's emotions makes it easier for the victim to talk.

[0084] The dialogue unit can conduct a dialogue taking into account the geographical distribution of the victim. For example, if the victim lives in a specific area, the dialogue unit can provide information related to the area. For example, if the victim lives in a specific area, the dialogue unit can provide information related to the area. Furthermore, if the victim is on the move, the dialogue unit can conduct a dialogue based on the victim's current location. For example, if the victim is on the move, the dialogue unit can conduct a dialogue based on the victim's current location. Furthermore, if the victim is in a specific location, the dialogue unit can provide information related to the location. For example, if the victim is in a specific location, the dialogue unit provides information related to the location. This enables an appropriate dialogue by taking into account the geographical distribution of the victim.

[0085] The dialogue unit can improve the accuracy of the dialogue by referring to literature related to the victim during the dialogue. For example, the dialogue unit can improve the accuracy of the dialogue by referring to literature related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to literature related to what the victim is talking about. The dialogue unit can also improve the accuracy of the dialogue by referring to research results related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to research results related to what the victim is talking about. The dialogue unit can also improve the accuracy of the dialogue by referring to statistical data related to what the victim is talking about. For example, the dialogue unit can improve the accuracy of the dialogue by referring to statistical data related to what the victim is talking about. In this way, the accuracy of the dialogue is improved by referring to literature related to the victim.

[0086] The recording unit can estimate the victim's emotions and adjust the recording method based on the estimated victim's emotions. For example, if the victim is nervous, the recording unit can pause the recording and provide time for the victim to relax. For example, if the victim is nervous, the recording unit can pause the recording and provide time for the victim to relax. The recording unit can also proceed smoothly if the victim is relaxed. For example, if the victim is relaxed, the recording unit can pause the recording and provide time for the victim to calm down. Furthermore, if the victim is emotional, the recording unit can pause the recording and provide time for the victim to calm down. For example, if the victim is emotional, the recording unit can pause the recording and provide time for the victim to calm down. In this way, adjusting the recording method based on the victim's emotions makes it easier for the victim to talk.

[0087] When recording, the recording unit can apply different recording algorithms depending on the category of what the victim is saying. For example, if the victim is talking about violence, the recording unit can apply a detailed recording algorithm related to violence. For example, if the victim is talking about violence, the recording unit applies a detailed recording algorithm related to violence. Furthermore, if the victim is talking about harassment, the recording unit can apply a detailed recording algorithm related to harassment. For example, if the victim is talking about harassment, the recording unit applies a detailed recording algorithm related to harassment. Furthermore, if the victim is talking about stalking, the recording unit can apply a detailed recording algorithm related to stalking. For example, if the victim is talking about stalking, the recording unit applies a detailed recording algorithm related to stalking. This makes it possible to perform appropriate recording by applying different recording algorithms depending on the category of what the victim is saying.

[0088] The recording unit can estimate the emotion of the victim and adjust the length of the recording based on the estimated emotion of the victim. For example, the recording unit can perform a short recording session when the victim is tense. For example, the recording unit can perform a short recording session when the victim is tense. The recording unit can also perform a long recording session when the victim is relaxed. For example, the recording unit can perform a long recording session when the victim is relaxed. Furthermore, the recording unit can also perform a short recording session to calm the victim when the victim is emotional. For example, the recording unit can perform a short recording session to calm the victim when the victim is emotional. In this way, adjusting the length of the recording based on the emotion of the victim makes it easier for the victim to talk.

[0089] When recording, the recording unit can determine the priority of the recording based on the time when the victim's story was submitted. For example, if the victim is talking about a recent event, the recording unit can prioritize recording that story. For example, if the victim is talking about a recent event, the recording unit prioritizes recording that story. In addition, if the victim is talking about a past event, the recording unit can postpone recording that story. For example, if the victim is talking about a past event, the recording unit postpones recording that story. Furthermore, if the victim is emotional, the recording unit can prioritize recording stories to calm the victim. For example, if the victim is emotional, the recording unit prioritizes recording stories to calm the victim. In this way, by determining the priority of the recording based on the time when the victim's story was submitted, appropriate recording is possible.

[0090] During recording, the recording unit can adjust the order of recording based on the relevance of the victim's story. For example, if the victim is speaking important information, the recording unit can prioritize recording that information. For example, if the victim is speaking important information, the recording unit records that information first. Furthermore, if the victim is speaking general information, the recording unit can record that information later. For example, if the victim is speaking general information, the recording unit records that information later. Furthermore, if the victim is emotional, the recording unit can prioritize recording stories to calm the victim. For example, if the victim is emotional, the recording unit records stories to calm the victim. In this way, by adjusting the order of recording based on the relevance of the victim's story, appropriate recording is possible.

[0091] The emotion analysis unit can estimate the emotion of the victim and adjust the analysis method based on the estimated emotion of the victim. For example, if the victim is nervous, the emotion analysis unit can apply an analysis method to calm the emotion. For example, if the victim is nervous, the emotion analysis unit applies an analysis method to calm the emotion. Furthermore, if the victim is relaxed, the emotion analysis unit can also perform a detailed emotion analysis. For example, if the victim is relaxed, the emotion analysis unit performs a detailed emotion analysis. Furthermore, if the victim is emotional, the emotion analysis unit can also apply an analysis method to calm the emotion. For example, if the victim is emotional, the emotion analysis unit applies an analysis method to calm the emotion. In this way, by adjusting the analysis method based on the emotion of the victim, appropriate analysis is possible.

[0092] During emotion analysis, the emotion analysis unit can optimize the analysis algorithm by referring to the victim's past emotion data. The emotion analysis unit can, for example, analyze the current emotion based on the victim's past emotion data. For example, the emotion analysis unit analyzes the current emotion based on the victim's past emotion data. The emotion analysis unit can also analyze changes in emotion by referring to the victim's past emotion data. For example, the emotion analysis unit analyzes changes in emotion by referring to the victim's past emotion data. Furthermore, the emotion analysis unit can also select an optimal analysis algorithm based on the victim's past emotion data. For example, the emotion analysis unit selects an optimal analysis algorithm based on the victim's past emotion data. In this way, the analysis algorithm can be optimized by referring to the victim's past emotion data.

[0093] During emotion analysis, the emotion analysis unit can apply different analysis methods depending on the category of the victim's story. For example, if the victim is talking about violence, the emotion analysis unit can apply an emotion analysis method related to violence. For example, if the victim is talking about violence, the emotion analysis unit applies an emotion analysis method related to violence. Furthermore, if the victim is talking about harassment, the emotion analysis unit can also apply an emotion analysis method related to harassment. For example, if the victim is talking about harassment, the emotion analysis unit applies an emotion analysis method related to harassment. Furthermore, if the victim is talking about stalking, the emotion analysis unit can also apply an emotion analysis method related to stalking. For example, if the victim is talking about stalking, the emotion analysis unit applies an emotion analysis method related to stalking. This enables appropriate analysis by applying different analysis methods depending on the category of the victim's story.

[0094] The emotion analysis unit can estimate the emotion of the victim and determine the priority of the analysis based on the estimated emotion of the victim. For example, if the victim is nervous, the emotion analysis unit can prioritize analysis to calm the victim. For example, if the victim is nervous, the emotion analysis unit prioritizes analysis to calm the victim. Furthermore, if the victim is relaxed, the emotion analysis unit can prioritize detailed emotion analysis. For example, if the victim is relaxed, the emotion analysis unit prioritizes detailed emotion analysis. Furthermore, if the victim is emotional, the emotion analysis unit can prioritize analysis to calm the victim. For example, if the victim is emotional, the emotion analysis unit prioritizes analysis to calm the victim. In this way, by determining the priority of the analysis based on the emotion of the victim, appropriate analysis is possible.

[0095] During emotion analysis, the emotion analysis unit can weight the analysis based on when the victim's story was submitted. For example, if the victim is talking about a recent event, the emotion analysis unit can prioritize emotion analysis related to that story. For example, if the victim is talking about a recent event, the emotion analysis unit prioritizes emotion analysis related to that story. Furthermore, if the victim is talking about a past event, the emotion analysis unit can postpone emotion analysis related to that story. For example, if the victim is talking about a past event, the emotion analysis unit postpones emotion analysis related to that story. Furthermore, if the victim is emotional, the emotion analysis unit can also prioritize analysis to calm the victim. For example, if the victim is emotional, the emotion analysis unit prioritizes analysis to calm the victim. In this way, weighting the analysis based on when the victim's story was submitted enables appropriate analysis.

[0096] When analyzing emotions, the emotion analysis unit can perform the analysis by referring to market data related to the victim. For example, the emotion analysis unit can perform emotion analysis by referring to market data related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to market data related to what the victim is talking about. The emotion analysis unit can also perform emotion analysis by referring to statistical data related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to statistical data related to what the victim is talking about. The emotion analysis unit can also perform emotion analysis by referring to research results related to what the victim is talking about. For example, the emotion analysis unit can perform emotion analysis by referring to research results related to what the victim is talking about. This makes it possible to perform an appropriate analysis by referring to market data related to the victim. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, question generation unit, dialogue unit, recording unit, and emotion analysis unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives the victim's speech. The question generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the victim's speech and generates appropriate questions. The dialogue unit is realized by the control unit 46A of the smart device 14 and interacts with the victim based on the generated questions. The recording unit uses the camera 42 and microphone 38B of the smart device 14 to record the victim's speech and saves it as text data by the specific processing unit 290 of the data processing device 12. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the victim's tone of voice, speed, and facial expression to estimate the victim's emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, question generation unit, dialogue unit, recording unit, and emotion analysis unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives the victim's speech. The question generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the victim's speech and generates appropriate questions. The dialogue unit is realized by the control unit 46A of the smart glasses 214 and interacts with the victim based on the generated questions. The recording unit uses the camera 42 and microphone 238 of the smart glasses 214 to record the victim's speech and saves it as text data by the specific processing unit 290 of the data processing device 12. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the tone, speed, and facial expression of the victim's voice to estimate the victim's emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the reception unit, question generation unit, dialogue unit, recording unit, and emotion analysis unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives the victim's speech. The question generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the victim's speech and generates appropriate questions. The dialogue unit is realized by the control unit 46A of the headset-type terminal 314 and interacts with the victim based on the generated questions. The recording unit uses the camera 42 and microphone 238 of the headset-type terminal 314 to record the victim's speech and saves it as text data by the specific processing unit 290 of the data processing device 12. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the tone, speed, and facial expression of the victim's voice to estimate the victim's emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, question generation unit, dialogue unit, recording unit, and emotion analysis unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives the victim's speech. The question generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the victim's speech and generates appropriate questions. The dialogue unit is realized by the control unit 46A of the robot 414 and converses with the victim based on the generated questions. The recording unit uses the camera 42 and microphone 238 of the robot 414 to record the victim's speech and saves it as text data by the specific processing unit 290 of the data processing device 12. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the tone, speed, and facial expression of the victim's voice to estimate the victim's emotions.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] When accepting a victim's story, the reception unit can analyze the victim's past questioning history and select the appropriate reception method. For example, it can analyze the time of day when the victim found it easiest to speak in the past and conduct the questioning at that time. It can also analyze the language and tone that the victim used in the past that made them feel comfortable speaking, and have the AI ​​respond based on that. It can also analyze the environment in which the victim found it easiest to speak in the past (quiet places, specific music, etc.) and recreate that environment. This makes it possible to select the optimal reception method by analyzing the victim's past questioning history.

[0099] The emotion analysis unit can estimate the emotion of the victim and adjust the analysis method based on the estimated emotion of the victim. For example, if the victim is tense, an analysis method to calm the emotion can be applied. Also, if the victim is relaxed, detailed emotion analysis can be performed. Furthermore, if the victim is emotional, an analysis method to calm the emotion can be applied. In this way, by adjusting the analysis method based on the emotion of the victim, appropriate analysis is possible.

[0100] The question generation unit can apply different question algorithms depending on the category of the victim's story. For example, if the victim talks about violence, detailed questions about violence can be asked. If the victim talks about harassment, detailed questions about harassment can be asked. Furthermore, if the victim talks about stalking, detailed questions about stalking can be asked. This makes it possible to ask appropriate questions by applying different question algorithms depending on the category of the victim's story.

[0101] The recording unit can estimate the victim's emotions and adjust the recording method based on the estimated victim's emotions. For example, if the victim is nervous, the recording can be paused to provide time for the victim to relax. Also, if the victim is relaxed, the recording can proceed smoothly. Furthermore, if the victim is emotional, the recording can be paused to provide time for the victim to calm down. In this way, adjusting the recording method based on the victim's emotions makes it easier for the victim to talk.

[0102] The dialogue unit can take into account the victim's attribute information when conducting a dialogue. For example, it can use appropriate language depending on the victim's age. It can also ask appropriate questions depending on the victim's gender. It can also conduct an appropriate dialogue depending on the victim's cultural background. This makes it possible to have an appropriate dialogue by taking into account the victim's attribute information.

[0103] During emotion analysis, the emotion analysis unit can optimize the analysis algorithm by referring to the victim's past emotion data. For example, it can analyze the victim's current emotion based on the victim's past emotion data. It can also analyze changes in emotion by referring to the victim's past emotion data. It can also select the optimal analysis algorithm based on the victim's past emotion data. In this way, the analysis algorithm can be optimized by referring to the victim's past emotion data.

[0104] When generating questions, the question generation unit can determine the priority of questions based on when the victim's story was submitted. For example, if the victim is talking about recent events, questions related to that story can be prioritized. Also, if the victim is talking about past events, questions related to that story can be postponed. Furthermore, if the victim is emotional, questions to calm the victim can be prioritized. In this way, by determining the priority of questions based on when the victim's story was submitted, appropriate questions can be asked.

[0105] The dialogue unit can estimate the victim's emotions and adjust the way the dialogue proceeds based on the estimated victim's emotions. For example, if the victim is nervous, the dialogue can proceed slowly. Alternatively, if the victim is relaxed, the dialogue can proceed smoothly. Furthermore, if the victim is emotional, the dialogue can be temporarily paused and a dialogue can be held to calm the victim. In this way, adjusting the way the dialogue proceeds based on the victim's emotions makes it easier for the victim to talk.

[0106] The recording unit can apply different recording algorithms depending on the category of what the victim is saying during recording. For example, if the victim is talking about violence, a detailed recording algorithm related to violence can be applied. Also, if the victim is talking about harassment, a detailed recording algorithm related to harassment can be applied. Furthermore, if the victim is talking about stalking, a detailed recording algorithm related to stalking can be applied. This allows for appropriate recording by applying different recording algorithms depending on the category of what the victim is saying.

[0107] During emotion analysis, the emotion analysis unit can weight the analysis based on when the victim's story was submitted. For example, if the victim is talking about a recent event, it can prioritize emotion analysis related to that story. Also, if the victim is talking about a past event, it can postpone emotion analysis related to that story. Furthermore, if the victim is emotional, it can prioritize analysis aimed at calming the victim. This allows for appropriate analysis by weighting the analysis based on when the victim's story was submitted.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The reception desk accepts victims' stories. Victim stories can include oral statements, written statements, and audio recordings. The reception desk can select a quiet location and take measures to ensure privacy to provide an environment where victims can talk comfortably. Step 2: The question generator analyzes the story received by the reception unit and generates appropriate questions. For example, it can automatically generate the next question to ask based on what the victim has said and adjust the order of the questions. Step 3: The dialogue unit dialogues with the victim based on the questions generated by the question generation unit. The dialogue unit asks questions in a gentle tone to make it easier for the victim to talk, and can adjust the tempo of the dialogue. Step 4: The recording unit records the story obtained by the dialogue unit and saves it as text data. The recording unit can record the victim's story as high-quality audio data and then convert it into text data using voice recognition technology. It can also take measures to safely store the recorded data. Step 5: The emotion analysis unit analyzes the story obtained by the dialogue unit and analyzes the victim's emotions. The emotion analysis unit can estimate the victim's emotions by analyzing the tone, speed, and facial expressions of the victim's voice.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0112] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] 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.

[0173] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0175] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0179] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0181] [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk that accepts victims' stories, a question generation unit that analyzes the story received by the reception unit and generates an appropriate question; a dialogue unit that dialogues with the victim based on the question generated by the question generation unit; a recording unit that records the speech obtained by the dialogue unit and stores it as text data; an emotion analysis unit that analyzes the story obtained by the dialogue unit and analyzes the emotions of the victim; Equipped with A system characterized by:

2. The emotion analysis unit Providing a safe environment for victims 2. The system of claim 1.

3. The question generation unit Generate appropriate questions based on the victim's story 2. The system of claim 1.

4. The recording unit Record the victim's story and save it as text data 2. The system of claim 1.

5. The dialogue unit Talk to the victim and ask the right questions 2. The system of claim 1.

6. The emotion analysis unit Analyze the victim's emotions and play comforting music 2. The system of claim 1.

7. The reception unit Estimate the victim's emotions and adjust the timing to speak based on the victim's estimated emotions.

2. The system of claim 1.

8. The reception unit Analyze the victim's past interview history and select the appropriate reception method.

2. The system of claim 1.

9. The reception unit At the time of reception, filtering is performed based on the victim's current psychological state.

2. The system of claim 1.

Images