System

Abstract

To provide a system which detects a crime word input in a prompt and prevent a dangerous action.SOLUTION: A system includes a prompt acquisition section, a detection section, a specification section, a retrieval history acquisition section, a determination section, and an information providing section. The prompt acquisition section acquires a prompt. The detection section detects a crime word from the prompt acquired by the prompt acquisition section. The specification section specifies information on a user who inputs the prompt including the crime word detected by the detection section. The retrieval history acquisition section acquires a retrieval history of the user specified by the specification section. The determination section determines whether the user has a possibility of performing a dangerous action on the basis of the retrieval history acquired by the retrieval history acquisition section. The information providing section provides information on the user to the police office when the determination section determines that the user has the possibility of performing the dangerous action.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately develop a system for detecting crime words entered into a prompt and preventing risky behavior, and there is room for improvement.

[0005] The system according to the embodiment aims to detect crime words entered in a prompt and prevent risky behavior before it occurs. [Means for solving the problem]

[0006] The system according to the embodiment includes a prompt acquisition unit, a detection unit, an identification unit, a search history acquisition unit, a determination unit, and an information provision unit. The prompt acquisition unit acquires a prompt. The detection unit detects crime words from the prompt acquired by the prompt acquisition unit. The identification unit identifies information of a user who inputs a prompt including a crime word detected by the detection unit. The search history acquisition unit acquires a search history of the user identified by the identification unit. The determination unit determines whether or not the user is likely to engage in risky behavior based on the search history acquired by the search history acquisition unit. The information provision unit provides information of the user to the police when the determination unit determines that the user is likely to engage in risky behavior. Effect of the Invention

[0007] The system according to the embodiment can detect crime words entered in a prompt and prevent risky behavior before it occurs. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The dangerous person identification system according to the embodiment of the present invention is a system that, when a word entered in a prompt contains a crime word, identifies the account and the PC used, and further identifies a dangerous person hiding in society by linking it with the search history from the PC, and prevents crimes in advance in cooperation with the police. This system can detect crime words entered in a prompt, identify user information, and identify a dangerous person by linking it with the search history. Furthermore, it becomes possible to prevent crimes in advance in cooperation with the police. For example, a prompt acquisition unit acquires a prompt entered by a user. Next, a detection unit detects crime words from the acquired prompt. For example, it detects whether or not words related to crimes such as "bomb" and "terrorism" are included. Next, an identification unit identifies information of a user who entered a prompt containing the detected crime word. The user information includes account information, network address, device information, and the like. For example, the identification unit identifies the user's IP address and device ID. Then, a search history acquisition unit acquires the search history of the identified user. For example, it acquires information such as what kind of searches the user has performed in the past and which websites the user has visited. Next, a determination unit determines whether or not the user is a dangerous person based on the acquired search history. For example, if a user has frequently performed searches related to crimes in the past, the user may be determined to be a dangerous person. Finally, when the determination unit determines that the user is a dangerous person, the providing unit provides the user's information to the police. This allows the police to identify dangerous people and prevent crimes from occurring. This allows the dangerous person identification system to detect crime words entered in the prompt, identify the user's information, and identify dangerous people by combining it with the search history. Furthermore, it becomes possible to cooperate with the police to prevent crimes from occurring.

[0029] The dangerous person identification system according to the embodiment includes a prompt acquisition unit, a detection unit, an identification unit, a search history acquisition unit, a determination unit, and a provision unit. The prompt acquisition unit acquires a prompt input by a user. The prompt includes, for example, a text input and a voice input, but is not limited to such examples. The prompt acquisition unit acquires, for example, a text input by a user in real time. The prompt acquisition unit can also convert a voice input into text and acquire it. For example, the voice is converted into text using a voice recognition technology. The detection unit detects a crime word from the prompt acquired by the prompt acquisition unit. The crime word includes, for example, "bomb" and "terrorism", but is not limited to such examples. The detection unit detects a crime word in the prompt using, for example, a natural language processing technology. The detection unit can also detect a crime word using a machine learning model. For example, the prompt is analyzed based on a list of crime words to detect the corresponding word. The identification unit identifies information of a user who inputs a prompt including a crime word detected by the detection unit. The user information includes, for example, account information, network address, device information, etc., but is not limited to such examples. The identification unit, for example, identifies the IP address of the user. The identification unit can also identify the device ID. For example, the identification unit analyzes network traffic to acquire device information of the user. The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit acquires, for example, the browser history of the user. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. For example, it collects information on keywords searched by the user in the past and websites visited. The determination unit determines whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, a combination of a specific behavior pattern and a search history is used as a criterion for the determination, but is not limited to such examples. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person.The determination unit can also determine whether the user is a dangerous person using a machine learning model. For example, the determination unit uses a model learned based on past data to analyze the user's behavioral pattern and determine whether the user is a dangerous person. The provision unit provides the user's information to the police when the determination unit determines that the user is a dangerous person. The information provided includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The provision unit, for example, electronically transmits the user's information to the police. The provision unit can also create a report for the police and mail it. As a result, the dangerous person identification system according to the embodiment can detect crime words entered in the prompt, identify the user's information, and identify the dangerous person in conjunction with the search history. Furthermore, it becomes possible to prevent crimes in advance in cooperation with the police.

[0030] The prompt acquisition unit acquires a prompt input by a user. Prompts include, for example, text input and voice input, but are not limited to such examples. For example, the prompt acquisition unit acquires text input by a user in real time. The prompt acquisition unit can also convert voice input into text and acquire it. For example, voice is converted into text using voice recognition technology. Specifically, the prompt acquisition unit instantly captures text data input by a user using a keyboard or touch screen and transmits it to the system. In the case of voice input, voice data collected through a microphone is passed to a voice recognition engine, which analyzes the voice data and converts it into text data. This voice recognition engine realizes highly accurate voice recognition using deep learning technology and can also handle noise and dialects. In addition, the prompt acquisition unit can automatically switch the input method depending on the user's input device and environment. For example, when a user performs voice input in a car, the voice is acquired using an in-car microphone, and background sound is removed using noise canceling technology. This allows the prompt acquisition unit to accurately and quickly acquire the user's input, thereby improving the accuracy and responsiveness of the entire system.

[0031] The detection unit detects crime words from the prompt acquired by the prompt acquisition unit. Examples of crime words include, but are not limited to, "bomb" and "terrorism". The detection unit detects crime words in the prompt using, for example, natural language processing technology. The detection unit can also detect crime words using a machine learning model. Specifically, the detection unit scans the prompt using a predefined crime word list and highlights the corresponding words. Furthermore, the detection unit uses natural language processing technology to analyze the context and determine the meaning of the crime word used. For example, context analysis is performed to distinguish between cases where the word "bomb" is used as a joke and cases where it is used as an actual threat. The machine learning model is designed to learn based on a large amount of text data and to be able to handle unknown crime words and new ways of expression. For example, slang and abbreviations used in SNS and chat apps can also be detected. As a result, the detection unit can detect crime words in the prompt with high accuracy and improve the reliability of the entire system.

[0032] The identification unit identifies information of a user who inputs a prompt including a crime word detected by the detection unit. The user information includes, but is not limited to, account information, network address, and device information. For example, the identification unit identifies the user's IP address. The identification unit can also identify a device ID. Specifically, the identification unit analyzes network traffic to obtain the user's IP address and MAC address. Furthermore, it is also possible to identify a unique identifier such as a serial number or IMEI number of a device used by the user. This allows the identification unit to accurately grasp the user's physical location and the device used. In addition, the identification unit can refer to the user's account information and check the user's registration information and past activity history. For example, it can track what prompts the user has input in the past and what devices the user has used. This allows the identification unit to grasp the user's behavioral patterns and devices used in detail, which can be useful in identifying dangerous people.

[0033] The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit acquires, for example, the browser history of the user. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. Specifically, the search history acquisition unit analyzes the browser cache and cookies of the user to extract websites and search queries visited in the past. It is also possible to acquire the search queries and search result click history performed by the user using the API of the search engine. Furthermore, the search history acquisition unit can integrate the search histories between multiple devices used by the user to generate consistent history data. This allows the search history acquisition unit to grasp the user's past behavior in detail and provide information necessary for identifying a dangerous person.

[0034] The determination unit determines whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, a combination of a specific behavior pattern and a search history is used as a criterion for the determination, but is not limited to such an example. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person. The determination unit can also determine whether the user is a dangerous person using a machine learning model. Specifically, the determination unit analyzes the user's search history and behavior patterns using a model that has learned past crime data and behavior patterns of dangerous people. For example, if the frequent appearance of a specific keyword or frequent access to a specific website is recognized as a characteristic of a dangerous person, the determination unit determines that the user is a dangerous person based on these patterns. The determination unit can also detect behavior patterns that are different from normal using an anomaly detection algorithm and issue an early warning. This allows the determination unit to analyze the user's behavior in detail and use it to identify dangerous people.

[0035] The providing unit provides the police with information on the user when the determining unit determines that the user is a dangerous person. The information provided includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The providing unit, for example, electronically transmits the user's information to the police. The providing unit can also create a report for the police and mail it. Specifically, the providing unit encrypts the user's information received from the determining unit and transmits it to the police's system using a secure communication protocol. Furthermore, the providing unit can automatically generate a detailed report including the user's information and mail it on paper as necessary. The providing unit can also set a protocol for regular information sharing and rapid response in emergencies in order to strengthen cooperation with the police. As a result, the providing unit can quickly and reliably provide information on dangerous people to the police, contributing to crime prevention.

[0036] The identification unit can identify at least one of the user's account and network address as the user's information. The identification unit, for example, identifies the user's account information. The account information includes, for example, an email address and a user name, but is not limited to such examples. The identification unit can also identify the user's network address. The network address includes, for example, an IP address and a MAC address, but is not limited to such examples. For example, the identification unit can analyze network traffic to identify the user's IP address. The identification unit can also identify device information. The device information includes, for example, a device ID and a device type, but is not limited to such examples. For example, the identification unit identifies the user's device ID and determines the type of device. As a result, the identification unit can acquire more accurate user information by identifying the user's account, network address, or device. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input network traffic to AI and cause the AI ​​to execute a process of identifying the user's network address.

[0037] The search history acquisition unit can acquire the search history of the user identified by the identification unit. The search history acquisition unit acquires, for example, the browser history of the user. The browser history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. For example, the search history acquisition unit collects information on keywords searched by the user in the past and websites visited. As a result, the search history acquisition unit can grasp the behavior history of the user by acquiring the search history of the identified user. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the browser history to AI and cause the AI ​​to acquire the search history.

[0038] The determination unit can determine whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person. The determination unit can also determine whether the user is a dangerous person using a machine learning model. For example, the determination unit analyzes the user's behavioral patterns using a model learned based on past data to determine whether the user is a dangerous person. As a result, the determination unit determines whether the user is a dangerous person based on the search history, thereby improving the accuracy of identifying the dangerous person. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the search history to an AI and cause the AI ​​to perform a determination of the dangerous person.

[0039] The providing unit can provide the user's information to the police when the determining unit determines that the user may perform risky behavior. The providing unit, for example, electronically transmits the user's information to the police. The provided information includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The providing unit can also create a report for the police and mail it. In this way, the providing unit can prevent crimes by providing the police with information on the user who has been determined to be a dangerous person. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's information into AI and cause the AI ​​to provide the information to the police.

[0040] The prompt acquisition unit can analyze the user's past prompt input history and select the optimal acquisition method. For example, the prompt acquisition unit preferentially acquires a prompt format that the user has frequently used in the past. The prompt acquisition unit can also select a prompt acquisition method suitable for a specific time period from the user's past input history. Furthermore, the prompt acquisition unit can analyze the user's past input patterns and propose the most efficient prompt acquisition method. In this way, the prompt acquisition unit can provide the user with the optimal prompt acquisition method by analyzing the past prompt input history. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the past prompt input history to AI and cause the AI ​​to execute a process of selecting the optimal acquisition method.

[0041] The prompt acquisition unit can perform filtering based on the user's current activity status and field of interest when acquiring a prompt. For example, when the user is at work, the prompt acquisition unit preferentially acquires a prompt related to work. In addition, when the user is engaged in a hobby-related activity, the prompt acquisition unit can also acquire a prompt related to the hobby. Furthermore, when the user is traveling, the prompt acquisition unit can also acquire a prompt related to the travel. In this way, the prompt acquisition unit can provide a highly relevant prompt by filtering the prompt based on the user's current activity status and field of interest. Part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the user's current activity status and field of interest to AI and cause the AI ​​to perform filtering of the prompt.

[0042] When acquiring a prompt, the prompt acquisition unit can preferentially acquire a highly relevant prompt in consideration of the geographical location information of the user. For example, when the user is in a specific area, the prompt acquisition unit preferentially acquires a prompt related to the area. In addition, when the user is traveling, the prompt acquisition unit can also preferentially acquire a prompt related to the travel destination. Furthermore, when the user is at home, the prompt acquisition unit can also preferentially acquire a prompt related to the vicinity of the home. In this way, the prompt acquisition unit can provide a highly relevant prompt by considering the geographical location information of the user. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the geographical location information of the user to the AI ​​and cause the AI ​​to execute a process of preferentially acquiring a highly relevant prompt.

[0043] The prompt acquisition unit can analyze the user's social media activity and acquire a related prompt when acquiring a prompt. For example, when the user posts about a specific topic on social media, the prompt acquisition unit acquires a prompt related to the topic. The prompt acquisition unit can also acquire a prompt based on the activity of an account that the user follows on social media. Furthermore, the prompt acquisition unit can also acquire a prompt based on the activity of a group that the user participates in on social media. In this way, the prompt acquisition unit can provide a highly relevant prompt by analyzing the user's social media activity. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the user's social media activity into AI and cause the AI ​​to execute a process of acquiring a related prompt.

[0044] The detection unit can improve the detection accuracy of the crime word by taking into account the context of the prompt at the time of detection. The detection unit, for example, analyzes the context before and after the prompt to accurately understand the meaning of the crime word. The detection unit can also improve the detection accuracy of the crime word by taking into account the association with other words in the prompt. Furthermore, the detection unit can prevent erroneous detection of the crime word based on the context of the prompt. As a result, the detection unit improves the detection accuracy of the crime word by taking into account the context of the prompt. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input context data of the prompt to AI and cause the AI ​​to execute processing to improve the detection accuracy of the crime word.

[0045] The detection unit can apply different detection algorithms depending on the category of the prompt at the time of detection. For example, the detection unit applies a detection algorithm specialized for terrorism to a terrorism-related prompt. The detection unit can also apply a detection algorithm specialized for cybercrime to a cybercrime-related prompt. The detection unit can also apply a detection algorithm specialized for violence to a violence-related prompt. In this way, the detection unit applies different detection algorithms depending on the category of the prompt, thereby improving the detection accuracy. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input category data of the prompt to AI and cause the AI ​​to execute a process of applying different detection algorithms.

[0046] The detection unit can determine the detection priority based on the submission time of the prompt at the time of detection. For example, the detection unit preferentially detects a prompt that was submitted recently. The detection unit can also preferentially detect a prompt that was submitted in a specific time period. Furthermore, the detection unit can adjust the detection priority based on the past submission time. This allows the detection unit to determine the detection priority based on the submission time of the prompt, thereby enabling efficient detection. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input prompt submission time data to an AI and cause the AI ​​to execute a process of determining the detection priority.

[0047] The detection unit can adjust the detection order based on the relevance of the prompts at the time of detection. For example, the detection unit preferentially detects prompts with high relevance. The detection unit can also postpone prompts with low relevance. Furthermore, the detection unit can dynamically adjust the detection order based on the relevance of the prompts. In this way, the detection unit can preferentially detect important prompts by adjusting the detection order based on the relevance of the prompts. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input relevance data of the prompts to the AI ​​and cause the AI ​​to execute a process of adjusting the detection order.

[0048] The identification unit can select the optimal identification method by analyzing the user's past behavior history at the time of identification. The identification unit, for example, extracts a specific pattern from the user's past behavior history and selects the optimal identification method. The identification unit can also improve the accuracy of identification based on the user's past behavior history. Furthermore, the identification unit can analyze the user's past behavior history and optimize the identification speed. As a result, the identification unit improves the accuracy of identification by analyzing the user's past behavior history. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's past behavior history data to AI and cause AI to execute a process of selecting the optimal identification method.

[0049] The identification unit can customize the specific means based on the user's current activity status at the time of identification. For example, when the user is at work, the identification unit uses a work-related identification means. In addition, when the user is engaged in a hobby-related activity, the identification unit can also use a hobby-related identification means. Furthermore, when the user is traveling, the identification unit can also use a travel-related identification means. As a result, the identification unit customizes the specific means based on the user's current activity status, thereby improving the accuracy of identification. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the user's current activity status data into AI and cause AI to execute processing to customize the specific means.

[0050] The identification unit can select the optimal identification method in consideration of the geographical location information of the user at the time of identification. For example, when the user is in a specific area, the identification unit selects a identification method related to the area. In addition, when the user is traveling, the identification unit can also select a identification method related to the travel destination. Furthermore, when the user is at home, the identification unit can also select a identification method related to the vicinity of the home. In this way, the identification unit improves the accuracy of identification by considering the geographical location information of the user. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of selecting the optimal identification method.

[0051] The identification unit can analyze the user's social media activity at the time of identification and suggest a specific means. For example, when the user posts about a specific topic on social media, the identification unit suggests a specific means related to the topic. The identification unit can also suggest a specific means based on the activity of an account the user follows on social media. Furthermore, the identification unit can also suggest a specific means based on the activity of a group the user participates in on social media. In this way, the identification unit analyzes the user's social media activity, thereby improving the accuracy of identification. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the user's social media activity data into AI and cause AI to execute a process of suggesting a specific means.

[0052] The search history acquisition unit can analyze the user's past search history and select the optimal acquisition method. The search history acquisition unit, for example, preferentially acquires keywords that the user has frequently searched in the past. The search history acquisition unit can also select a search history acquisition method suitable for a specific time period from the user's past search history. Furthermore, the search history acquisition unit can analyze the user's past search patterns and propose the most efficient search history acquisition method. In this way, the search history acquisition unit can provide the user with the optimal search history acquisition method by analyzing the past search history. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input past search history data to AI and cause AI to execute a process of selecting the optimal acquisition method.

[0053] The search history acquisition unit can perform filtering based on the user's current activity status and field of interest when acquiring the search history. For example, when the user is at work, the search history acquisition unit preferentially acquires a search history related to work. In addition, when the user is engaged in a hobby-related activity, the search history acquisition unit can also acquire a search history related to the hobby. Furthermore, when the user is traveling, the search history acquisition unit can also acquire a search history related to the travel. In this way, the search history acquisition unit can provide a highly relevant search history by filtering the search history based on the user's current activity status and field of interest. Part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the user's current activity status and field of interest data to AI and cause AI to filter the search history.

[0054] When acquiring a search history, the search history acquisition unit can preferentially acquire a history with high relevance in consideration of the geographical location information of the user. For example, when the user is in a specific area, the search history acquisition unit preferentially acquires a search history related to the area. In addition, when the user is traveling, the search history acquisition unit can also preferentially acquire a search history related to the travel destination. Furthermore, when the user is at home, the search history acquisition unit can also preferentially acquire a search history related to the vicinity of the home. In this way, the search history acquisition unit can provide a search history with high relevance by considering the geographical location information of the user. Part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the geographical location information data of the user to the AI ​​and cause the AI ​​to execute a process of preferentially acquiring a search history with high relevance.

[0055] The search history acquisition unit can analyze the user's social media activities and acquire related histories when acquiring the search history. For example, when the user posts about a specific topic on social media, the search history acquisition unit acquires search histories related to the topic. The search history acquisition unit can also acquire the search history based on the activities of accounts the user follows on social media. Furthermore, the search history acquisition unit can also acquire the search history based on the activities of groups the user participates in on social media. In this way, the search history acquisition unit can provide a highly relevant search history by analyzing the user's social media activities. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the user's social media activity data into AI and cause AI to execute a process of acquiring related search histories.

[0056] The judgment unit can optimize the judgment algorithm by referring to past judgment data at the time of judgment. The judgment unit improves the accuracy of the judgment algorithm based on, for example, past judgment data. The judgment unit can also analyze past judgment data and adjust parameters of the judgment algorithm. Furthermore, the judgment unit can also learn the judgment algorithm by referring to past judgment data. As a result, the judgment unit improves the accuracy of the judgment algorithm by referring to the past judgment data. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input past judgment data to AI and cause AI to execute optimization of the judgment algorithm.

[0057] The determination unit can make a determination by taking into consideration the attribute information of the user at the time of the determination. The determination unit makes a determination by taking into consideration attribute information such as the user's age and gender, for example. The determination unit can also make a determination by taking into consideration attribute information such as the user's occupation and hobbies. Furthermore, the determination unit can also make a determination by taking into consideration attribute information such as the user's place of residence and educational background. As a result, the determination unit improves the determination accuracy by taking into consideration the attribute information of the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit can input the user's attribute information data into the AI ​​and cause the AI ​​to execute a process of making a determination.

[0058] The determination unit can make a determination taking into consideration the geographical location information of the user at the time of the determination. For example, when the user is in a specific area, the determination unit makes a determination based on information related to the area. In addition, when the user is traveling, the determination unit can also make a determination based on information related to the travel destination. Furthermore, when the user is at home, the determination unit can also make a determination based on information related to the surroundings of the home. As a result, the determination unit improves the accuracy of the determination by taking into consideration the geographical location information of the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of making a determination.

[0059] The judgment unit can improve the accuracy of the judgment by referring to the user's related literature at the time of judgment. The judgment unit, for example, makes a judgment based on literature that the user has previously referred to. In addition, when the user refers to literature on a specific topic, the judgment unit can also make a judgment based on the literature. Furthermore, when the user refers to academic literature, the judgment unit can also make a judgment based on the literature. As a result, the judgment unit improves the judgment accuracy by referring to the user's related literature. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input the user's related literature data into AI and cause AI to execute processing to improve the accuracy of the judgment.

[0060] The providing unit can select the optimal providing method by referring to the user's past providing history at the time of providing. For example, the providing unit preferentially selects a providing method that the user has preferred in the past. The providing unit can also select a providing method suitable for a specific time period from the user's past providing history. Furthermore, the providing unit can analyze the user's past providing history and propose the most efficient providing method. As a result, the providing unit can provide the optimal providing method to the user by referring to the past providing history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input past providing history data to AI and cause AI to execute a process of selecting the optimal providing method.

[0061] The providing unit can customize the means of providing based on the user's current activity status at the time of providing. For example, when the user is at work, the providing unit uses a providing means related to work. In addition, when the user is engaged in a hobby-related activity, the providing unit can also use a providing means related to the hobby. Furthermore, when the user is traveling, the providing unit can also use a providing means related to travel. As a result, the providing unit can provide optimal information to the user by customizing the means of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's current activity status data into AI and cause AI to execute a process of customizing the means of providing.

[0062] The providing unit can select the optimal providing method in consideration of the geographical location information of the user at the time of providing. For example, when the user is in a specific area, the providing unit selects a providing method related to the area. In addition, when the user is traveling, the providing unit can also select a providing method related to the travel destination. Furthermore, when the user is at home, the providing unit can also select a providing method related to the vicinity of the home. In this way, the providing unit can provide optimal information to the user by considering the geographical location information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of selecting the optimal providing method.

[0063] The providing unit can analyze the user's social media activity at the time of providing and suggest a means of providing. For example, when the user posts about a specific topic on social media, the providing unit suggests a means of providing related to the topic. The providing unit can also suggest a means of providing based on the activity of an account the user follows on social media. Furthermore, the providing unit can also suggest a means of providing based on the activity of a group the user participates in on social media. In this way, the providing unit can provide optimal information to the user by analyzing the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into AI and cause AI to execute a process of suggesting a means of providing.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The dangerous person identification system may further include a behavior analysis unit that analyzes the behavioral patterns of the user. The behavior analysis unit may, for example, analyze the user's movement history and detect a pattern of frequent visits to specific locations. The behavior analysis unit may also monitor the user's online activities and detect a pattern of visiting specific websites at specific times of the day. Furthermore, the behavior analysis unit may analyze the user's purchasing history and detect a pattern of frequent purchases of specific products. This allows the dangerous person identification system to identify dangerous people based on the user's behavioral patterns and prevent crimes from occurring.

[0066] The dangerous person identification system may further include a social network analysis unit that analyzes the user's social network. The social network analysis unit may, for example, analyze the user's friendships and detect the possibility of contact with a dangerous person. The social network analysis unit may also analyze the content posted by the user and detect content related to crime. Furthermore, the social network analysis unit may analyze the accounts followed by the user and detect associations with accounts with dangerous ideas. In this way, the dangerous person identification system may identify dangerous people based on the user's social network and prevent crimes from occurring.

[0067] The dangerous person identification system may further include a real-time monitoring unit that monitors the user's search history in real time. For example, the real-time monitoring unit issues an alert the moment the user searches for a specific crime word. The real-time monitoring unit may also issue an alert when the user visits a specific website. Furthermore, the real-time monitoring unit may also issue an alert when the user performs a specific action during a specific time period. This allows the dangerous person identification system to monitor the user's actions in real time and respond immediately.

[0068] The dangerous person identification system may further include a device monitoring unit that monitors the device usage of the user. For example, if a user frequently uses a particular device, the device monitoring unit monitors the usage history of the device in detail. In addition, if a user starts using a new device, the device monitoring unit can also obtain initial setting information for the device. Furthermore, if a user uses a particular device during a particular time period, the device monitoring unit can also monitor the usage history during that time period. This allows the dangerous person identification system to identify dangerous people based on the user's device usage and prevent crimes from occurring.

[0069] The dangerous person identification system may further include a data encryption unit that encrypts user data. The data encryption unit, for example, encrypts the user's search history and account information to protect them from unauthorized access. The data encryption unit may also encrypt the user's device information to protect privacy. Furthermore, the data encryption unit may also encrypt the user's communication data to ensure safe communication. In this way, the dangerous person identification system can strengthen security and protect the user's privacy by encrypting the user's data.

[0070] The process flow of the first embodiment will be briefly described below.

[0071] Step 1: The prompt acquisition unit acquires a prompt input from the user. The prompt includes text input and voice input. The prompt acquisition unit acquires text input by the user in real time, and can also convert voice input into text and acquire it. Step 2: The detection unit detects crime words from the prompt acquired by the prompt acquisition unit. Crime words include words such as "bomb" and "terrorism" and are detected using natural language processing technology and machine learning models. Step 3: The identification unit identifies information of a user who inputs a prompt containing the crime word detected by the detection unit, including account information, network address, device information, etc. Step 4: The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes past search queries, search dates and times, visited websites, and the like. Step 5: The determination unit determines whether or not the user is likely to perform risky behavior based on the search history acquired by the search history acquisition unit. A combination of a specific behavior pattern and search history is used as a criterion. Step 6: If the judgment unit judges that the user is likely to engage in risky behavior, the information provision unit provides the user's information to the police. The information provided includes the user ID, IP address, search history, etc.

[0072] (Example 2) The dangerous person identification system according to the embodiment of the present invention is a system that, when a word entered in a prompt contains a crime word, identifies the account and the PC used, and further identifies a dangerous person hiding in society by linking it with the search history from the PC, and prevents crimes in advance in cooperation with the police. This system can detect crime words entered in a prompt, identify user information, and identify a dangerous person by linking it with the search history. Furthermore, it becomes possible to prevent crimes in advance in cooperation with the police. For example, a prompt acquisition unit acquires a prompt entered by a user. Next, a detection unit detects crime words from the acquired prompt. For example, it detects whether or not words related to crimes such as "bomb" and "terrorism" are included. Next, an identification unit identifies information of a user who entered a prompt containing the detected crime word. The user information includes account information, network address, device information, and the like. For example, the identification unit identifies the user's IP address and device ID. Then, a search history acquisition unit acquires the search history of the identified user. For example, it acquires information such as what kind of searches the user has performed in the past and which websites the user has visited. Next, a determination unit determines whether or not the user is a dangerous person based on the acquired search history. For example, if a user has frequently performed searches related to crimes in the past, the user may be determined to be a dangerous person. Finally, when the determination unit determines that the user is a dangerous person, the providing unit provides the user's information to the police. This allows the police to identify dangerous people and prevent crimes from occurring. This allows the dangerous person identification system to detect crime words entered in the prompt, identify the user's information, and identify dangerous people by combining it with the search history. Furthermore, it becomes possible to cooperate with the police to prevent crimes from occurring.

[0073] The dangerous person identification system according to the embodiment includes a prompt acquisition unit, a detection unit, an identification unit, a search history acquisition unit, a determination unit, and a provision unit. The prompt acquisition unit acquires a prompt input by a user. The prompt includes, for example, a text input and a voice input, but is not limited to such examples. The prompt acquisition unit acquires, for example, a text input by a user in real time. The prompt acquisition unit can also convert a voice input into text and acquire it. For example, the voice is converted into text using a voice recognition technology. The detection unit detects a crime word from the prompt acquired by the prompt acquisition unit. The crime word includes, for example, "bomb" and "terrorism", but is not limited to such examples. The detection unit detects a crime word in the prompt using, for example, a natural language processing technology. The detection unit can also detect a crime word using a machine learning model. For example, the prompt is analyzed based on a list of crime words to detect the corresponding word. The identification unit identifies information of a user who inputs a prompt including a crime word detected by the detection unit. The user information includes, for example, account information, network address, device information, etc., but is not limited to such examples. The identification unit, for example, identifies the IP address of the user. The identification unit can also identify the device ID. For example, the identification unit analyzes network traffic to acquire device information of the user. The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit acquires, for example, the browser history of the user. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. For example, it collects information on keywords searched by the user in the past and websites visited. The determination unit determines whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, a combination of a specific behavior pattern and a search history is used as a criterion for the determination, but is not limited to such examples. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person.The determination unit can also determine whether the user is a dangerous person using a machine learning model. For example, the determination unit uses a model learned based on past data to analyze the user's behavioral pattern and determine whether the user is a dangerous person. The provision unit provides the user's information to the police when the determination unit determines that the user is a dangerous person. The information provided includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The provision unit, for example, electronically transmits the user's information to the police. The provision unit can also create a report for the police and mail it. As a result, the dangerous person identification system according to the embodiment can detect crime words entered in the prompt, identify the user's information, and identify the dangerous person in conjunction with the search history. Furthermore, it becomes possible to prevent crimes in advance in cooperation with the police.

[0074] The prompt acquisition unit acquires a prompt input by a user. Prompts include, for example, text input and voice input, but are not limited to such examples. For example, the prompt acquisition unit acquires text input by a user in real time. The prompt acquisition unit can also convert voice input into text and acquire it. For example, voice is converted into text using voice recognition technology. Specifically, the prompt acquisition unit instantly captures text data input by a user using a keyboard or touch screen and transmits it to the system. In the case of voice input, voice data collected through a microphone is passed to a voice recognition engine, which analyzes the voice data and converts it into text data. This voice recognition engine realizes highly accurate voice recognition using deep learning technology and can also handle noise and dialects. In addition, the prompt acquisition unit can automatically switch the input method depending on the user's input device and environment. For example, when a user performs voice input in a car, the voice is acquired using an in-car microphone, and background sound is removed using noise canceling technology. This allows the prompt acquisition unit to accurately and quickly acquire the user's input, thereby improving the accuracy and responsiveness of the entire system.

[0075] The detection unit detects crime words from the prompt acquired by the prompt acquisition unit. Examples of crime words include, but are not limited to, "bomb" and "terrorism". The detection unit detects crime words in the prompt using, for example, natural language processing technology. The detection unit can also detect crime words using a machine learning model. Specifically, the detection unit scans the prompt using a predefined crime word list and highlights the corresponding words. Furthermore, the detection unit uses natural language processing technology to analyze the context and determine the meaning of the crime word used. For example, context analysis is performed to distinguish between cases where the word "bomb" is used as a joke and cases where it is used as an actual threat. The machine learning model is designed to learn based on a large amount of text data and to be able to handle unknown crime words and new ways of expression. For example, slang and abbreviations used in SNS and chat apps can also be detected. As a result, the detection unit can detect crime words in the prompt with high accuracy and improve the reliability of the entire system.

[0076] The identification unit identifies information of a user who inputs a prompt including a crime word detected by the detection unit. The user information includes, but is not limited to, account information, network address, and device information. For example, the identification unit identifies the user's IP address. The identification unit can also identify a device ID. Specifically, the identification unit analyzes network traffic to obtain the user's IP address and MAC address. Furthermore, it is also possible to identify a unique identifier such as a serial number or IMEI number of a device used by the user. This allows the identification unit to accurately grasp the user's physical location and the device used. In addition, the identification unit can refer to the user's account information and check the user's registration information and past activity history. For example, it can track what prompts the user has input in the past and what devices the user has used. This allows the identification unit to grasp the user's behavioral patterns and devices used in detail, which can be useful in identifying dangerous people.

[0077] The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit acquires, for example, the browser history of the user. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. Specifically, the search history acquisition unit analyzes the browser cache and cookies of the user to extract websites and search queries visited in the past. It is also possible to acquire the search queries and search result click history performed by the user using the API of the search engine. Furthermore, the search history acquisition unit can integrate the search histories between multiple devices used by the user to generate consistent history data. This allows the search history acquisition unit to grasp the user's past behavior in detail and provide information necessary for identifying a dangerous person.

[0078] The determination unit determines whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, a combination of a specific behavior pattern and a search history is used as a criterion for the determination, but is not limited to such an example. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person. The determination unit can also determine whether the user is a dangerous person using a machine learning model. Specifically, the determination unit analyzes the user's search history and behavior patterns using a model that has learned past crime data and behavior patterns of dangerous people. For example, if the frequent appearance of a specific keyword or frequent access to a specific website is recognized as a characteristic of a dangerous person, the determination unit determines that the user is a dangerous person based on these patterns. The determination unit can also detect behavior patterns that are different from normal using an anomaly detection algorithm and issue an early warning. This allows the determination unit to analyze the user's behavior in detail and use it to identify dangerous people.

[0079] The providing unit provides the police with information on the user when the determining unit determines that the user is a dangerous person. The information provided includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The providing unit, for example, electronically transmits the user's information to the police. The providing unit can also create a report for the police and mail it. Specifically, the providing unit encrypts the user's information received from the determining unit and transmits it to the police's system using a secure communication protocol. Furthermore, the providing unit can automatically generate a detailed report including the user's information and mail it on paper as necessary. The providing unit can also set a protocol for regular information sharing and rapid response in emergencies in order to strengthen cooperation with the police. As a result, the providing unit can quickly and reliably provide information on dangerous people to the police, contributing to crime prevention.

[0080] The identification unit can identify at least one of the user's account and network address as the user's information. The identification unit, for example, identifies the user's account information. The account information includes, for example, an email address and a user name, but is not limited to such examples. The identification unit can also identify the user's network address. The network address includes, for example, an IP address and a MAC address, but is not limited to such examples. For example, the identification unit can analyze network traffic to identify the user's IP address. The identification unit can also identify device information. The device information includes, for example, a device ID and a device type, but is not limited to such examples. For example, the identification unit identifies the user's device ID and determines the type of device. As a result, the identification unit can acquire more accurate user information by identifying the user's account, network address, or device. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input network traffic to AI and cause the AI ​​to execute a process of identifying the user's network address.

[0081] The search history acquisition unit can acquire the search history of the user identified by the identification unit. The search history acquisition unit acquires, for example, the browser history of the user. The browser history includes, for example, past search queries, search dates and times, and visited websites, but is not limited to such examples. The search history acquisition unit can also analyze the log of a search engine to acquire the search history. For example, the search history acquisition unit collects information on keywords searched by the user in the past and websites visited. As a result, the search history acquisition unit can grasp the behavior history of the user by acquiring the search history of the identified user. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the browser history to AI and cause the AI ​​to acquire the search history.

[0082] The determination unit can determine whether the user is a dangerous person based on the search history acquired by the search history acquisition unit. For example, if the user has frequently performed searches related to crimes in the past, the determination unit determines that the user is a dangerous person. The determination unit can also determine whether the user is a dangerous person using a machine learning model. For example, the determination unit analyzes the user's behavioral patterns using a model learned based on past data to determine whether the user is a dangerous person. As a result, the determination unit determines whether the user is a dangerous person based on the search history, thereby improving the accuracy of identifying the dangerous person. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the search history to an AI and cause the AI ​​to perform a determination of the dangerous person.

[0083] The providing unit can provide the user's information to the police when the determining unit determines that the user may perform risky behavior. The providing unit, for example, electronically transmits the user's information to the police. The provided information includes, for example, a user ID, an IP address, a search history, and the like, but is not limited to such examples. The providing unit can also create a report for the police and mail it. In this way, the providing unit can prevent crimes by providing the police with information on the user who has been determined to be a dangerous person. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's information into AI and cause the AI ​​to provide the information to the police.

[0084] The prompt acquisition unit can estimate the user's emotion and adjust the timing of acquiring the prompt based on the estimated user's emotion. For example, when the user is feeling stressed, the prompt acquisition unit delays the acquisition of the prompt and waits until the user is relaxed. Also, when the user is relaxed, the prompt acquisition unit can immediately acquire the prompt and provide a smooth operation. Furthermore, when the user is in a hurry, the prompt acquisition unit can quickly acquire the prompt and respond to the user's request immediately. In this way, the prompt acquisition unit can reduce the user's stress and provide a smooth operation by adjusting the timing of acquiring the prompt according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prompt acquisition unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the timing of acquiring the prompt.

[0085] The prompt acquisition unit can analyze the user's past prompt input history and select the optimal acquisition method. For example, the prompt acquisition unit preferentially acquires a prompt format that the user has frequently used in the past. The prompt acquisition unit can also select a prompt acquisition method suitable for a specific time period from the user's past input history. Furthermore, the prompt acquisition unit can analyze the user's past input patterns and propose the most efficient prompt acquisition method. In this way, the prompt acquisition unit can provide the user with the optimal prompt acquisition method by analyzing the past prompt input history. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the past prompt input history to AI and cause the AI ​​to execute a process of selecting the optimal acquisition method.

[0086] The prompt acquisition unit can perform filtering based on the user's current activity status and field of interest when acquiring a prompt. For example, when the user is at work, the prompt acquisition unit preferentially acquires a prompt related to work. In addition, when the user is engaged in a hobby-related activity, the prompt acquisition unit can also acquire a prompt related to the hobby. Furthermore, when the user is traveling, the prompt acquisition unit can also acquire a prompt related to the travel. In this way, the prompt acquisition unit can provide a highly relevant prompt by filtering the prompt based on the user's current activity status and field of interest. Part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the user's current activity status and field of interest to AI and cause the AI ​​to perform filtering of the prompt.

[0087] The prompt acquisition unit can estimate the user's emotion and determine the priority of the prompts to be acquired based on the estimated user's emotion. For example, when the user is nervous, the prompt acquisition unit preferentially acquires a prompt for relaxing the user. Furthermore, when the user is relaxed, the prompt acquisition unit can also preferentially acquire an interesting prompt. Furthermore, when the user is in a hurry, the prompt acquisition unit can also preferentially acquire a prompt that allows a quick response. In this way, the prompt acquisition unit can provide the optimal prompt for the user by determining the priority of the prompts according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prompt acquisition unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of determining the priority of the prompts.

[0088] When acquiring a prompt, the prompt acquisition unit can preferentially acquire a highly relevant prompt in consideration of the geographical location information of the user. For example, when the user is in a specific area, the prompt acquisition unit preferentially acquires a prompt related to the area. In addition, when the user is traveling, the prompt acquisition unit can also preferentially acquire a prompt related to the travel destination. Furthermore, when the user is at home, the prompt acquisition unit can also preferentially acquire a prompt related to the vicinity of the home. In this way, the prompt acquisition unit can provide a highly relevant prompt by considering the geographical location information of the user. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the geographical location information of the user to the AI ​​and cause the AI ​​to execute a process of preferentially acquiring a highly relevant prompt.

[0089] The prompt acquisition unit can analyze the user's social media activity and acquire a related prompt when acquiring a prompt. For example, when the user posts about a specific topic on social media, the prompt acquisition unit acquires a prompt related to the topic. The prompt acquisition unit can also acquire a prompt based on the activity of an account that the user follows on social media. Furthermore, the prompt acquisition unit can also acquire a prompt based on the activity of a group that the user participates in on social media. In this way, the prompt acquisition unit can provide a highly relevant prompt by analyzing the user's social media activity. A part or all of the above-mentioned processing in the prompt acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the prompt acquisition unit can input the user's social media activity into AI and cause the AI ​​to execute a process of acquiring a related prompt.

[0090] The detection unit can estimate the user's emotion and adjust the detection criteria for crime words based on the estimated emotion of the user. For example, when the user is excited, the detection unit detects crime words by applying strict detection criteria. In addition, when the user is relaxed, the detection unit can also detect crime words by applying normal detection criteria. Furthermore, when the user is stressed, the detection unit can detect crime words by applying loose detection criteria. Thereby, the detection unit adjusts the detection criteria for crime words according to the emotion of the user, thereby improving the detection accuracy. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the detection unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the detection criteria for crime words.

[0091] The detection unit can improve the detection accuracy of the crime word by taking into account the context of the prompt at the time of detection. The detection unit, for example, analyzes the context before and after the prompt to accurately understand the meaning of the crime word. The detection unit can also improve the detection accuracy of the crime word by taking into account the association with other words in the prompt. Furthermore, the detection unit can prevent erroneous detection of the crime word based on the context of the prompt. As a result, the detection unit improves the detection accuracy of the crime word by taking into account the context of the prompt. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input context data of the prompt to AI and cause the AI ​​to execute processing to improve the detection accuracy of the crime word.

[0092] The detection unit can apply different detection algorithms depending on the category of the prompt at the time of detection. For example, the detection unit applies a detection algorithm specialized for terrorism to a terrorism-related prompt. The detection unit can also apply a detection algorithm specialized for cybercrime to a cybercrime-related prompt. The detection unit can also apply a detection algorithm specialized for violence to a violence-related prompt. In this way, the detection unit applies different detection algorithms depending on the category of the prompt, thereby improving the detection accuracy. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input category data of the prompt to AI and cause the AI ​​to execute a process of applying different detection algorithms.

[0093] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, when the user is nervous, the detection unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the detection unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the detection unit can also provide a display method that focuses on the main points. As a result, the detection unit can adjust the display method of the detection result according to the user's emotion, thereby enabling a display that is easy for the user to see. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the display method of the detection result.

[0094] The detection unit can determine the detection priority based on the submission time of the prompt at the time of detection. For example, the detection unit preferentially detects a prompt that was submitted recently. The detection unit can also preferentially detect a prompt that was submitted in a specific time period. Furthermore, the detection unit can adjust the detection priority based on the past submission time. This allows the detection unit to determine the detection priority based on the submission time of the prompt, thereby enabling efficient detection. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input prompt submission time data to an AI and cause the AI ​​to execute a process of determining the detection priority.

[0095] The detection unit can adjust the detection order based on the relevance of the prompts at the time of detection. For example, the detection unit preferentially detects prompts with high relevance. The detection unit can also postpone prompts with low relevance. Furthermore, the detection unit can dynamically adjust the detection order based on the relevance of the prompts. In this way, the detection unit can preferentially detect important prompts by adjusting the detection order based on the relevance of the prompts. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input relevance data of the prompts to the AI ​​and cause the AI ​​to execute a process of adjusting the detection order.

[0096] The identification unit can estimate the user's emotion and adjust the identification method based on the estimated user's emotion. For example, when the user is excited, the identification unit performs identification quickly. Also, when the user is relaxed, the identification unit can perform identification at a normal speed. Furthermore, when the user is stressed, the identification unit can perform identification carefully. As a result, the identification unit adjusts the identification method according to the user's emotion, thereby improving the accuracy of identification. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the identification method.

[0097] The identification unit can select the optimal identification method by analyzing the user's past behavior history at the time of identification. The identification unit, for example, extracts a specific pattern from the user's past behavior history and selects the optimal identification method. The identification unit can also improve the accuracy of identification based on the user's past behavior history. Furthermore, the identification unit can analyze the user's past behavior history and optimize the identification speed. As a result, the identification unit improves the accuracy of identification by analyzing the user's past behavior history. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's past behavior history data to AI and cause AI to execute a process of selecting the optimal identification method.

[0098] The identification unit can customize the specific means based on the user's current activity status at the time of identification. For example, when the user is at work, the identification unit uses a work-related identification means. In addition, when the user is engaged in a hobby-related activity, the identification unit can also use a hobby-related identification means. Furthermore, when the user is traveling, the identification unit can also use a travel-related identification means. As a result, the identification unit customizes the specific means based on the user's current activity status, thereby improving the accuracy of identification. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the user's current activity status data into AI and cause AI to execute processing to customize the specific means.

[0099] The identification unit can estimate the user's emotion and determine a specific priority based on the estimated user's emotion. For example, when the user is nervous, the identification unit performs the identification quickly. Also, when the user is relaxed, the identification unit can perform the identification at a normal speed. Furthermore, when the user is in a hurry, the identification unit can set the specific priority high. As a result, the identification unit determines the specific priority according to the user's emotion, thereby improving the accuracy of the identification. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of determining the specific priority.

[0100] The identification unit can select the optimal identification method in consideration of the geographical location information of the user at the time of identification. For example, when the user is in a specific area, the identification unit selects a identification method related to the area. In addition, when the user is traveling, the identification unit can also select a identification method related to the travel destination. Furthermore, when the user is at home, the identification unit can also select a identification method related to the vicinity of the home. In this way, the identification unit improves the accuracy of identification by considering the geographical location information of the user. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of selecting the optimal identification method.

[0101] The identification unit can analyze the user's social media activity at the time of identification and suggest a specific means. For example, when the user posts about a specific topic on social media, the identification unit suggests a specific means related to the topic. The identification unit can also suggest a specific means based on the activity of an account the user follows on social media. Furthermore, the identification unit can also suggest a specific means based on the activity of a group the user participates in on social media. In this way, the identification unit analyzes the user's social media activity, thereby improving the accuracy of identification. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the user's social media activity data into AI and cause AI to execute a process of suggesting a specific means.

[0102] The search history acquisition unit can estimate the user's emotion and adjust the timing of acquiring the search history based on the estimated user's emotion. For example, when the user is stressed, the search history acquisition unit delays the acquisition of the search history and waits until the user is relaxed. In addition, when the user is relaxed, the search history acquisition unit can immediately acquire the search history and provide a smooth operation. Furthermore, when the user is in a hurry, the search history acquisition unit can quickly acquire the search history and respond to the user's request. In this way, the search history acquisition unit can reduce the user's stress and provide a smooth operation by adjusting the timing of acquiring the search history according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the search history acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the search history acquisition unit can input a user's emotional data into an AI and have the AI ​​execute a process to adjust the timing of search history acquisition.

[0103] The search history acquisition unit can analyze the user's past search history and select the optimal acquisition method. The search history acquisition unit, for example, preferentially acquires keywords that the user has frequently searched in the past. The search history acquisition unit can also select a search history acquisition method suitable for a specific time period from the user's past search history. Furthermore, the search history acquisition unit can analyze the user's past search patterns and propose the most efficient search history acquisition method. In this way, the search history acquisition unit can provide the user with the optimal search history acquisition method by analyzing the past search history. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input past search history data to AI and cause AI to execute a process of selecting the optimal acquisition method.

[0104] The search history acquisition unit can perform filtering based on the user's current activity status and field of interest when acquiring the search history. For example, when the user is at work, the search history acquisition unit preferentially acquires a search history related to work. In addition, when the user is engaged in a hobby-related activity, the search history acquisition unit can also acquire a search history related to the hobby. Furthermore, when the user is traveling, the search history acquisition unit can also acquire a search history related to the travel. In this way, the search history acquisition unit can provide a highly relevant search history by filtering the search history based on the user's current activity status and field of interest. Part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the user's current activity status and field of interest data to AI and cause AI to filter the search history.

[0105] The search history acquisition unit can estimate the user's emotion and determine the priority of the search history to be acquired based on the estimated user's emotion. For example, when the user is nervous, the search history acquisition unit preferentially acquires a search history for relaxing the user. In addition, when the user is relaxed, the search history acquisition unit can also preferentially acquire an interesting search history. Furthermore, when the user is in a hurry, the search history acquisition unit can also preferentially acquire a search history that allows a quick response. In this way, the search history acquisition unit can provide an optimal search history for the user by determining the priority of the search history according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the search history acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the search history acquisition unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of determining the priority of the search history.

[0106] When acquiring a search history, the search history acquisition unit can preferentially acquire a history with high relevance in consideration of the geographical location information of the user. For example, when the user is in a specific area, the search history acquisition unit preferentially acquires a search history related to the area. In addition, when the user is traveling, the search history acquisition unit can also preferentially acquire a search history related to the travel destination. Furthermore, when the user is at home, the search history acquisition unit can also preferentially acquire a search history related to the vicinity of the home. In this way, the search history acquisition unit can provide a search history with high relevance by considering the geographical location information of the user. Part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the geographical location information data of the user to the AI ​​and cause the AI ​​to execute a process of preferentially acquiring a search history with high relevance.

[0107] The search history acquisition unit can analyze the user's social media activities and acquire related histories when acquiring the search history. For example, when the user posts about a specific topic on social media, the search history acquisition unit acquires search histories related to the topic. The search history acquisition unit can also acquire the search history based on the activities of accounts the user follows on social media. Furthermore, the search history acquisition unit can also acquire the search history based on the activities of groups the user participates in on social media. In this way, the search history acquisition unit can provide a highly relevant search history by analyzing the user's social media activities. A part or all of the above-mentioned processing in the search history acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the search history acquisition unit can input the user's social media activity data into AI and cause AI to execute a process of acquiring related search histories.

[0108] The determination unit can estimate the user's emotion and adjust the judgment criteria based on the estimated user's emotion. For example, when the user is excited, the determination unit applies strict judgment criteria to determine whether the user is a dangerous person. In addition, when the user is relaxed, the determination unit can also apply normal judgment criteria to determine whether the user is a dangerous person. Furthermore, when the user is stressed, the determination unit can also apply loose judgment criteria to determine whether the user is a dangerous person. Thereby, the determination unit adjusts the judgment criteria according to the user's emotion, thereby improving the judgment accuracy. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the judgment criteria.

[0109] The judgment unit can optimize the judgment algorithm by referring to past judgment data at the time of judgment. The judgment unit improves the accuracy of the judgment algorithm based on, for example, past judgment data. The judgment unit can also analyze past judgment data and adjust parameters of the judgment algorithm. Furthermore, the judgment unit can also learn the judgment algorithm by referring to past judgment data. As a result, the judgment unit improves the accuracy of the judgment algorithm by referring to the past judgment data. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input past judgment data to AI and cause AI to execute optimization of the judgment algorithm.

[0110] The determination unit can make a determination by taking into consideration the attribute information of the user at the time of the determination. The determination unit makes a determination by taking into consideration attribute information such as the user's age and gender, for example. The determination unit can also make a determination by taking into consideration attribute information such as the user's occupation and hobbies. Furthermore, the determination unit can also make a determination by taking into consideration attribute information such as the user's place of residence and educational background. As a result, the determination unit improves the determination accuracy by taking into consideration the attribute information of the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit can input the user's attribute information data into the AI ​​and cause the AI ​​to execute a process of making a determination.

[0111] The determination unit can estimate the user's emotion and adjust the display method of the determination result based on the estimated user's emotion. For example, when the user is nervous, the determination unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the determination unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the determination unit can also provide a display method that focuses on the main points. As a result, the determination unit can adjust the display method of the determination result according to the user's emotion, thereby enabling a display that is easy for the user to see. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the display method of the determination result.

[0112] The determination unit can make a determination taking into consideration the geographical location information of the user at the time of the determination. For example, when the user is in a specific area, the determination unit makes a determination based on information related to the area. In addition, when the user is traveling, the determination unit can also make a determination based on information related to the travel destination. Furthermore, when the user is at home, the determination unit can also make a determination based on information related to the surroundings of the home. As a result, the determination unit improves the accuracy of the determination by taking into consideration the geographical location information of the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of making a determination.

[0113] The judgment unit can improve the accuracy of the judgment by referring to the user's related literature at the time of judgment. The judgment unit, for example, makes a judgment based on literature that the user has previously referred to. In addition, when the user refers to literature on a specific topic, the judgment unit can also make a judgment based on the literature. Furthermore, when the user refers to academic literature, the judgment unit can also make a judgment based on the literature. As a result, the judgment unit improves the judgment accuracy by referring to the user's related literature. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input the user's related literature data into AI and cause AI to execute processing to improve the accuracy of the judgment.

[0114] The providing unit can estimate the user's emotion and adjust the providing method based on the estimated user's emotion. For example, when the user is nervous, the providing unit provides information in a calm manner. Furthermore, when the user is relaxed, the providing unit can also provide detailed information. Furthermore, when the user is in a hurry, the providing unit can quickly provide information. As a result, the providing unit can provide optimal information to the user by adjusting the providing method according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of adjusting the providing method.

[0115] The providing unit can select the optimal providing method by referring to the user's past providing history at the time of providing. For example, the providing unit preferentially selects a providing method that the user has preferred in the past. The providing unit can also select a providing method suitable for a specific time period from the user's past providing history. Furthermore, the providing unit can analyze the user's past providing history and propose the most efficient providing method. As a result, the providing unit can provide the optimal providing method to the user by referring to the past providing history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input past providing history data to AI and cause AI to execute a process of selecting the optimal providing method.

[0116] The providing unit can customize the means of providing based on the user's current activity status at the time of providing. For example, when the user is at work, the providing unit uses a providing means related to work. In addition, when the user is engaged in a hobby-related activity, the providing unit can also use a providing means related to the hobby. Furthermore, when the user is traveling, the providing unit can also use a providing means related to travel. As a result, the providing unit can provide optimal information to the user by customizing the means of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's current activity status data into AI and cause AI to execute a process of customizing the means of providing.

[0117] The providing unit can estimate the user's emotion and determine the priority of provision based on the estimated user's emotion. For example, when the user is nervous, the providing unit provides information quickly. Also, when the user is relaxed, the providing unit can provide information at a normal speed. Furthermore, when the user is in a hurry, the providing unit can set the priority of provision high. As a result, the providing unit can provide optimal information to the user by determining the priority of provision according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the AI ​​and cause the AI ​​to execute a process of determining the priority of provision.

[0118] The providing unit can select the optimal providing method in consideration of the geographical location information of the user at the time of providing. For example, when the user is in a specific area, the providing unit selects a providing method related to the area. In addition, when the user is traveling, the providing unit can also select a providing method related to the travel destination. Furthermore, when the user is at home, the providing unit can also select a providing method related to the vicinity of the home. In this way, the providing unit can provide optimal information to the user by considering the geographical location information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information data of the user to AI and cause the AI ​​to execute a process of selecting the optimal providing method.

[0119] The providing unit can analyze the user's social media activity at the time of providing and suggest a means of providing. For example, when the user posts about a specific topic on social media, the providing unit suggests a means of providing related to the topic. The providing unit can also suggest a means of providing based on the activity of an account the user follows on social media. Furthermore, the providing unit can also suggest a means of providing based on the activity of a group the user participates in on social media. In this way, the providing unit can provide optimal information to the user by analyzing the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into AI and cause AI to execute a process of suggesting a means of providing.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The dangerous person identification system may further include a biometric information acquisition unit that acquires biometric information of the user. The biometric information acquisition unit, for example, acquires the user's heart rate and electrodermal activity, and estimates the user's tension and stress level. The biometric information acquisition unit may also analyze the user's facial expression using face recognition technology to estimate emotions. Furthermore, the biometric information acquisition unit may perform voice analysis of the user and estimate emotions from the tone and pitch of the voice. This allows the dangerous person identification system to estimate emotions based on the user's biometric information, enabling more accurate identification of dangerous people.

[0122] The dangerous person identification system may further include a behavior analysis unit that analyzes the behavioral patterns of the user. The behavior analysis unit may, for example, analyze the user's movement history and detect a pattern of frequent visits to specific locations. The behavior analysis unit may also monitor the user's online activities and detect a pattern of visiting specific websites at specific times of the day. Furthermore, the behavior analysis unit may analyze the user's purchasing history and detect a pattern of frequent purchases of specific products. This allows the dangerous person identification system to identify dangerous people based on the user's behavioral patterns and prevent crimes from occurring.

[0123] The dangerous person identification system may further include a social network analysis unit that analyzes the user's social network. The social network analysis unit may, for example, analyze the user's friendships and detect the possibility of contact with a dangerous person. The social network analysis unit may also analyze the content posted by the user and detect content related to crime. Furthermore, the social network analysis unit may analyze the accounts followed by the user and detect associations with accounts with dangerous ideas. In this way, the dangerous person identification system may identify dangerous people based on the user's social network and prevent crimes from occurring.

[0124] The dangerous person identification system may further include a warning adjustment unit that estimates the user's emotions and adjusts the warning level based on the estimated emotions. For example, when the user is excited, the warning adjustment unit sets the warning level high and immediately notifies the police. When the user is relaxed, the warning adjustment unit may also set the warning level to normal and monitor the situation. Furthermore, when the user is feeling stressed, the warning adjustment unit may set the warning level to a medium level and call for caution. This allows the dangerous person identification system to adjust the warning level according to the user's emotions and take appropriate action.

[0125] The dangerous person identification system may further include a real-time monitoring unit that monitors the user's search history in real time. For example, the real-time monitoring unit issues an alert the moment the user searches for a specific crime word. The real-time monitoring unit may also issue an alert when the user visits a specific website. Furthermore, the real-time monitoring unit may also issue an alert when the user performs a specific action during a specific time period. This allows the dangerous person identification system to monitor the user's actions in real time and respond immediately.

[0126] The dangerous person identification system may further include a search history adjustment unit that estimates the user's emotions and adjusts the method of acquiring the search history based on the estimated emotions. For example, the search history adjustment unit quickly acquires the search history when the user is nervous. Furthermore, the search history adjustment unit may also acquire the search history at a normal speed when the user is relaxed. Furthermore, the search history adjustment unit may also carefully acquire the search history when the user is feeling stressed. This allows the dangerous person identification system to adjust the method of acquiring the search history according to the user's emotions and collect appropriate information.

[0127] The dangerous person identification system may further include a device monitoring unit that monitors the device usage of the user. For example, if a user frequently uses a particular device, the device monitoring unit monitors the usage history of the device in detail. In addition, if a user starts using a new device, the device monitoring unit can also obtain initial setting information for the device. Furthermore, if a user uses a particular device during a particular time period, the device monitoring unit can also monitor the usage history during that time period. This allows the dangerous person identification system to identify dangerous people based on the user's device usage and prevent crimes from occurring.

[0128] The dangerous person identification system can further include an information adjustment unit that estimates the user's emotions and adjusts the content of the information to be provided based on the estimated emotions. For example, the information adjustment unit provides concise and important information when the user is nervous. The information adjustment unit can also provide detailed information when the user is relaxed. Furthermore, the information adjustment unit can provide information to relax the user when the user is feeling stressed. In this way, the dangerous person identification system can adjust the content of the information to be provided according to the user's emotions and provide the most suitable information for the user.

[0129] The dangerous person identification system can further include a behavior prediction unit that predicts the user's behavior. The behavior prediction unit predicts the user's most likely next behavior based on, for example, the user's past behavior history. The behavior prediction unit can also predict the user's future behavior based on the user's current situation. Furthermore, the behavior prediction unit can estimate the user's emotions and predict the user's behavior based on the emotions. This allows the dangerous person identification system to predict the user's behavior and prevent dangerous behavior before it occurs.

[0130] The dangerous person identification system may further include a data encryption unit that encrypts user data. The data encryption unit, for example, encrypts the user's search history and account information to protect them from unauthorized access. The data encryption unit may also encrypt the user's device information to protect privacy. Furthermore, the data encryption unit may also encrypt the user's communication data to ensure safe communication. In this way, the dangerous person identification system can strengthen security and protect the user's privacy by encrypting the user's data.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The prompt acquisition unit acquires a prompt input from the user. The prompt includes text input and voice input. The prompt acquisition unit acquires text input by the user in real time, and can also convert voice input into text and acquire it. Step 2: The detection unit detects crime words from the prompt acquired by the prompt acquisition unit. Crime words include words such as "bomb" and "terrorism" and are detected using natural language processing technology and machine learning models. Step 3: The identification unit identifies information of a user who inputs a prompt containing the crime word detected by the detection unit, including account information, network address, device information, etc. Step 4: The search history acquisition unit acquires the search history of the user identified by the identification unit. The search history includes past search queries, search dates and times, visited websites, and the like. Step 5: The determination unit determines whether or not the user is likely to perform risky behavior based on the search history acquired by the search history acquisition unit. A combination of a specific behavior pattern and search history is used as a criterion. Step 6: If the judgment unit judges that the user is likely to engage in risky behavior, the information provision unit provides the user's information to the police. The information provided includes the user ID, IP address, search history, etc.

[0133] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0134] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0135] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] For example, the prompt acquisition unit is realized by either the smart device 14 or the data processing device 12. For example, the control unit 46A of the smart device 14 acquires a prompt input by a user. The detection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and detects a crime word in the prompt. The identification unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and identifies information of the user. The search history acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and acquires a search history of the user. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and determines whether the user is a dangerous person. The provision unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and provides information of the user to the police. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0140] 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.

[0141] 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 the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0143] 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 performed in a secure state.

[0144] Fig. 4 shows an example of 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.

[0145] 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.

[0146] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0150] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] For example, the prompt acquisition unit is realized by either the smart glasses 214 or the data processing device 12. For example, the control unit 46A of the smart glasses 214 acquires a prompt input by a user. The detection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and detects a crime word in the prompt. The identification unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and identifies information of the user. The search history acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and acquires a search history of the user. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and determines whether the user is a dangerous person. The provision unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and provides information of the user to the police. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0156] 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.

[0157] 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 the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0159] 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 performed in a secure state.

[0160] 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.

[0161] 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.

[0162] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0163] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0164] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0165] 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 voice indicating a user input for 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.

[0166] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0167] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] For example, the prompt acquisition unit is realized by either the headset type terminal 314 or the data processing device 12. For example, the control unit 46A of the headset type terminal 314 acquires a prompt input by a user. The detection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and detects a crime word in the prompt. The identification unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and identifies information of the user. The search history acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and acquires a search history of the user. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and determines whether the user is a dangerous person. The provision unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and provides information of the user to the police. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0172] 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.

[0173] 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 the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0175] 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 performed in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0177] 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.

[0178] 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.

[0179] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0181] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0182] 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 a voice indicating a user input for 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.

[0183] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0184] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0185] For example, the prompt acquisition unit is realized by either the robot 414 or the data processing device 12. For example, the control unit 46A of the robot 414 acquires a prompt input by a user. The detection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and detects a crime word in the prompt. The identification unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and identifies information of the user. The search history acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and acquires a search history of the user. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and determines whether the user is a dangerous person or not. The provision unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and provides information of the user to the police. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0187] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0189] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0190] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0191] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0193] 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.

[0194] 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 Universal Serial Bus (USB) 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.

[0195] In addition, 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 upon request from the data processing device 12.

[0196] 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.

[0197] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0198] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0199] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0200] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0202] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0204] (Appendix 1) a prompt acquisition unit that acquires a prompt; a detection unit that detects crime words from the prompt acquired by the prompt acquisition unit; an identification unit that identifies information of a user who inputs a prompt including the crime word detected by the detection unit; a search history acquisition unit that acquires a search history of the user identified by the identification unit; a determination unit that determines whether or not the user is likely to perform risky behavior based on the search history acquired by the search history acquisition unit; and an information providing unit that provides information about the user to the police when the determination unit determines that the user is likely to engage in risky behavior. A system characterized by: (Appendix 2) The identification unit is At least one of the user's account and the user's network address is identified as the user's information. 2. The system of claim 1, (Appendix 3) The search history acquisition unit Acquire a search history of the user identified by the identification unit. 2. The system of claim 1, (Appendix 4) The determination unit is Based on the search history acquired by the search history acquisition unit, it is determined whether the user is a dangerous person. 2. The system of claim 1, (Appendix 5) The information providing unit is When the determination unit determines that the user is likely to engage in risky behavior, information about the user is provided to the police. 2. The system of claim 1, (Appendix 6) The prompt acquisition unit, To estimate a user's emotion and adjust a timing of receiving a prompt based on the estimated user's emotion. 2. The system of claim 1, (Appendix 7) The prompt acquisition unit, Analyze the user's past prompt input history and select the optimal acquisition method 2. The system of claim 1, (Appendix 8) The prompt acquisition unit, Filter prompts based on the user's current activity and interests when getting them 2. The system of claim 1, (Appendix 9) The prompt acquisition unit, Inferring a user's emotion and prioritizing prompts to be retrieved based on the estimated user's emotion 2. The system of claim 1, (Appendix 10) The prompt acquisition unit, When fetching prompts, the geographic location of the user is taken into account to prioritize the most relevant prompts. 2. The system of claim 1, (Appendix 11) The prompt acquisition unit, When a prompt is retrieved, the user's social media activity is analyzed to retrieve relevant prompts. 2. The system of claim 1, (Appendix 12) The detection unit is Estimating user sentiment and adjusting crime word detection criteria based on the estimated user sentiment 2. The system of claim 1, (Appendix 13) The detection unit is During detection, the context of the prompt is taken into account to improve crime word detection accuracy 2. The system of claim 1, (Appendix 14) The detection unit is During detection, apply different detection algorithms depending on the category of the prompt 2. The system of claim 1, (Appendix 15) The detection unit is Infer user emotions and adjust the way detection results are displayed based on the estimated user emotions 2. The system of claim 1, (Appendix 16) The detection unit is Upon detection, prioritize detections based on when the prompt was submitted 2. The system of claim 1, (Appendix 17) The detection unit is During detection, adjust the detection order based on prompt relevance 2. The system of claim 1, (Appendix 18) The identification unit is Inferring a user's emotion and adjusting a particular method based on the inferred user emotion 2. The system of claim 1, (Appendix 19) The identification unit is When identifying a user, the system analyzes the user's past behavior history to select the optimal identification method. 2. The system of claim 1, (Appendix 20) The identification unit is At the time of identification, customize specific measures based on the user's current activity state 2. The system of claim 1, (Appendix 21) The identification unit is Inferring a user's emotions and determining a specific priority based on the estimated user's emotions 2. The system of claim 1, (Appendix 22) The identification unit is When identifying a user, the optimal identification method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 23) The identification unit is Upon identification, analyze the user's social media activity to suggest specific measures 2. The system of claim 1, (Appendix 24) The search history acquisition unit The system estimates the user's emotions and adjusts the timing of retrieving search history based on the estimated user emotions. 2. The system of claim 1, (Appendix 25) The search history acquisition unit Analyze the user's past search history and select the optimal acquisition method 2. The system of claim 1, (Appendix 26) The search history acquisition unit When retrieving search history, filter it based on the user's current activity and interests 2. The system of claim 1, (Appendix 27) The search history acquisition unit A user's sentiment is estimated, and a priority order for search histories to be acquired is determined based on the estimated user's sentiment. 2. The system of claim 1, (Appendix 28) The search history acquisition unit When retrieving search history, the system takes into account the user's geographic location information to prioritize retrieving history that is more relevant to them. 2. The system of claim 1, (Appendix 29) The search history acquisition unit When retrieving search history, analyze the user's social media activity and retrieve related history. 2. The system of claim 1, (Appendix 30) The determination unit is To estimate a user's emotion and adjust a judgment criterion based on the estimated user's emotion. 2. The system of claim 1, (Appendix 31) The determination unit is When making a judgment, the judgment algorithm is optimized by referring to past judgment data. 2. The system of claim 1, (Appendix 32) The determination unit is When making a judgment, the user's attribute information is taken into consideration. 2. The system of claim 1, (Appendix 33) The determination unit is To estimate a user's emotion and adjust a method of displaying a judgment result based on the estimated user's emotion. 2. The system of claim 1, (Appendix 34) The determination unit is When making a decision, the user's geographic location information is taken into account. 2. The system of claim 1, (Appendix 35) The determination unit is When making a judgment, the accuracy of the judgment is improved by referring to the user's related literature. 2. The system of claim 1, (Appendix 36) The providing unit is To estimate a user's emotion and adjust a method of providing information based on the estimated user's emotion. 2. The system of claim 1, (Appendix 37) The providing unit is When providing information, the optimal method of providing information is selected by referring to the user's past provision history. 2. The system of claim 1, (Appendix 38) The providing unit is At the time of delivery, customize the delivery method based on the user's current activity 2. The system of claim 1, (Appendix 39) The providing unit is Estimate user sentiment and determine priority of offerings based on the estimated user sentiment 2. The system of claim 1, (Appendix 40) The providing unit is When providing information, the optimal method of providing the information is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 41) The providing unit is At the time of delivery, we analyze your social media activity to suggest delivery methods. 2. The system of claim 1, [Explanation of symbols]

[0205] 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 prompt acquisition unit that acquires a prompt; a detection unit that detects crime words from the prompt acquired by the prompt acquisition unit; an identification unit that identifies information of a user who inputs a prompt including the crime word detected by the detection unit; a search history acquisition unit that acquires a search history of the user identified by the identification unit; a determination unit that determines whether or not the user is likely to perform risky behavior based on the search history acquired by the search history acquisition unit; and an information providing unit that provides information about the user to the police when the determination unit determines that the user is likely to engage in risky behavior. A system characterized by:

2. The identification unit is At least one of the user's account and the user's network address is identified as the user's information.

2. The system of claim 1 .

3. The prompt acquisition unit, The user's emotion is estimated, and the timing of receiving the prompt is adjusted based on the estimated user's emotion.

2. The system of claim 1 .

4. The prompt acquisition unit, Analyze the user's past prompt input history and select the optimal acquisition method.

2. The system of claim 1 .

5. The prompt acquisition unit, When the prompts are received, they are filtered based on the user's current activities and interests.

2. The system of claim 1 .

6. The prompt acquisition unit is Estimating a feeling of the user and prioritizing prompts to be obtained based on the estimated feeling of the user.

2. The system of claim 1 .

7. The prompt acquisition unit, When acquiring the prompts, a prompt having high relevance is acquired preferentially in consideration of the geographical location information of the user.

2. The system of claim 1 .

Images