System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data related to a past unsolved case, a means for analyzing the collected data and generating the outline of the unsolved case, the details of related persons and evidence, a means for converting the generated information into a display format and displaying it on an information providing platform on the Internet, and a means for collecting additional information from a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] As time passes, information about unsolved cases fades away, making it difficult to find new clues to solve the cases. There is also a lack of efficient means to disseminate information widely and gather useful information from many people. In particular, there is an issue with minor crimes and small local crimes, which do not attract much attention and therefore do not gather enough information. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, a means for collecting data on past unsolved cases is provided. Next, a means for analyzing the collected data and generating an outline of the unsolved case, details of the people involved, and details of the evidence is provided. Finally, a means for converting the generated information into a display format and displaying it on an online information platform is provided. Furthermore, a means for collecting additional information from users is provided, and the collected information is stored in an internal database and reported to relevant authorities. In this way, a system is provided that efficiently collects new information on unsolved cases and increases the likelihood of solving the cases.

[0006] "Means of collecting data" refers to the technical elements of obtaining information about past unsolved cases from online databases and news sites.

[0007] An "unsolved case" is one that the police or other investigative agencies have been unable to solve, and the perpetrator has not yet been identified or the details of the case are unknown.

[0008] "Means of analyzing data" refers to the technical elements of analyzing collected incident information, extracting meaningful information from it, and organizing and classifying it.

[0009] "Case summary" refers to basic information about an unsolved case, such as the date and time of the incident, location, and type of incident.

[0010] "Parties" refers to people connected to an unsolved case, such as perpetrators, victims, and witnesses.

[0011] "Evidential details" refers to specific information or physical evidence that can help solve a case, such as fingerprints, video footage, or witness accounts.

[0012] "Means of generation" refers to the technical elements that analyze data and use the results to automatically create new information or text.

[0013] "Means of converting the information into a display format" refers to the technical elements that convert the generated information into a specific format (e.g., banner format) so that it is easy for the user to view.

[0014] An "information platform" refers to an online service that provides information to a wide range of users, such as online news sites and social networking sites.

[0015] "Means for collecting additional information from users" refers to technological elements that allow users to provide information they know or have seen through online forms or other interfaces.

[0016] "Internal database" refers to an information system for storing and managing collected information and generated data.

[0017] "Means of reporting to relevant authorities" refers to the technical elements that automatically or manually notify the police or other investigative authorities of any useful information collected. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0030] 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.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] 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.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating it to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0040] System configuration

[0041] This system mainly consists of the following four components:

[0042] 1. Data collection module (server)

[0043] 2. Data analysis and generation module (generative AI server)

[0044] 3. Information display module (server)

[0045] 4. User Interface (Terminal / User)

[0046] Data Collection Module

[0047] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting the latest information on unsolved robberies that occurred in City A, text data from news and public police information is obtained and stored in a database.

[0048] Data Analysis and Generation Module

[0049] The server provides the filtered data to the generation AI. The generation AI analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in City A in July 2023, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[0050] Information Display Module

[0051] The server formats the information based on the text data stored in the internal database into a format that is easy for users to view. In particular, it converts it into the Yahoo! News banner format. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery that occurred in City A in July 2023: Please provide witness information." This banner information is sent to the Yahoo! News management system and displayed at a specified time.

[0052] User Interface

[0053] When users browse Yahoo! News on their devices (PC, smartphone, etc.), they can see an overview of the unsolved case in a banner. If they are interested, they can click on the banner and be taken to a detailed information page, where they can find more detailed information about the case.

[0054] If a user has new information or witnesses about an incident, they can provide it by filling out a form on the detailed information page. The device sends the information to the server, which stores it in an internal database. The server then filters the information and, if necessary, notifies the police or other relevant authorities.

[0055] Specific examples

[0056] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the information would be processed in the following manner:

[0057] 1. The server collects and filters relevant information from news sites and police public information databases.

[0058] 2. Generate filtered data: The AI ​​module analyzes the data and automatically generates an outline of the incident, witness information, and details of the evidence.

[0059] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[0060] 4. The user clicks on the banner to access the details page and view more information about the incident.

[0061] 5. The user enters any new information or sightings they have into the form, and the device sends the information to the server.

[0062] 6. The server stores the new information in a database and notifies relevant authorities as necessary.

[0063] In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues for solving the cases.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[0067] Step 2:

[0068] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[0069] Step 3:

[0070] The server converts the filtered data into JSON format for providing to the generation AI. The converted data is passed to the generation AI module.

[0071] Step 4:

[0072] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[0073] Step 5:

[0074] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[0075] Step 6:

[0076] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[0077] Step 7:

[0078] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[0079] Step 8:

[0080] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[0081] Step 9:

[0082] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[0083] Step 10:

[0084] The terminal transmits new information and sightings entered by the user to the server.

[0085] Step 11:

[0086] The server receives the information and stores it in an internal database, where it filters the information and prepares to notify the relevant authorities.

[0087] Step 12:

[0088] The server will then report any new information collected to police and other relevant agencies as needed, which can aid in the investigation of unsolved cases.

[0089] In this way, the system of the present invention can effectively collect, analyze, and display information about unsolved cases through a series of processing steps, and efficiently provide new clues.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] The objective of this study is to solve the lack of a means to efficiently collect information on past unsolved cases, disseminate it widely, and obtain new clues. There is also a need for a method to quickly and accurately analyze the collected information and convert it into a display format.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes means for periodically collecting data on past unsolved cases, means for filtering the collected data and removing duplicate and irrelevant information, means for analyzing the filtered data and using a generative AI model to generate an outline of the unsolved case, details of the parties involved, and details of evidence, means for formatting the generated information into a banner and displaying it on an online information platform, means for collecting additional information from users and storing the collected information in an internal database, and means for reporting the collected additional information to relevant authorities as needed. This makes it possible to efficiently collect and widely disseminate information on unsolved cases and quickly obtain new clues.

[0095] "Methods of periodically collecting data on past unsolved cases" refers to crawling police public information databases and news sites at specific time intervals to collect information related to unsolved cases.

[0096] "Means of filtering collected data and removing duplicate or irrelevant information" refers to the process of removing duplicate information or information that is not relevant to the incident from collected data in order to improve accuracy.

[0097] "Using a generative AI model to analyze filtered data and generate a summary of the unsolved case, details of the people involved, and evidence" refers to a method of analyzing filtered data using an artificial intelligence model (e.g., a generative model) to automatically generate key elements of the case.

[0098] "Means for formatting the generated information into a banner format and displaying it on an information platform on the Internet" refers to the process of converting the generated text data into an easy-to-read banner format and displaying it on news sites, etc. on the Internet.

[0099] "Means for collecting additional information from users and storing that information in an internal database" refers to the internal systems used to receive and store new information provided by users.

[0100] "Means of reporting any additional information collected to relevant authorities as necessary" refers to the means by which information collected from users is deemed useful and is then notified to the police or relevant authorities.

[0101] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating that information to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0102] Data Collection Module

[0103] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). The server uses web crawling libraries such as Python's BeautifulSoup or Scrapy to collect information related to unsolved cases. The collected data is stored in a relational database such as MySQL (registered trademark) or PostgreSQL. The server then filters duplicate and irrelevant information from the collected data. Natural language processing techniques can be used in this filtering process.

[0104] Data Analysis and Generation Module

[0105] The server provides the filtered data to the generation AI (e.g., GPT-4 (registered trademark)). Examples of specific prompt sentences include the following:

[0106] "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please include location, time, and any witness information."

[0107] The AI ​​analyzes the data based on this prompt and generates text information including an overview of the incident, the people involved, and details of the evidence. The generated text data is then stored in the internal database by the server.

[0108] Information Display Module

[0109] The server formats the information into a banner based on the text data stored in its internal database. The formatting involves converting it into an easy-to-read format using HTML and CSS. The formatted banner is then displayed on Yahoo! News and other online information platforms. This process generates a banner with the message "Robbery occurred in City A in July 2023: Please provide witness information," which is displayed at the specified time.

[0110] User Interface

[0111] When users browse Yahoo! News on their devices (PCs, smartphones, etc.), they can see an overview of unsolved cases in a banner. If an interested user clicks on the banner, they are taken to a detailed information page, which provides more detailed information about the case. If a user has new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device then sends the entered information to the server, which stores the received information in an internal database and, if necessary, reports it to relevant authorities.

[0112] Specific examples

[0113] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the process would be as follows: The server collects and filters relevant information from news sites and the police's public information database. The filtered data is provided to a generation AI, which automatically generates a summary of the incident, witness information, and details of the evidence. The generated text data is formatted and sent to the Yahoo! News management system. The user clicks on the banner to access the detailed information page and view detailed information about the incident. The user enters any new information or witness information they have in a form, and the device sends the information to the server. The server saves the new information in a database and, if necessary, notifies relevant authorities. In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues to solve them.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] The server crawls news sites and police public information databases at specific intervals (e.g., 12 noon every day). The server extracts the necessary text data from web pages using Python's BeautifulSoup or Scrapy. As input, it receives a list of URLs from news sites and police public information databases, and as output, it obtains text data about unsolved cases collected from each web page.

[0117] Step 2:

[0118] The server stores the collected data in a relational database (e.g., MySQL or PostgreSQL). Before storing, it performs a filtering process to remove duplicate and irrelevant information. Specifically, it uses natural language processing technology to evaluate the similarity of text and remove duplicate data. It receives the collected raw data as input and stores the filtered, highly accurate data as output in the database.

[0119] Step 3:

[0120] The server provides the filtered data to the generation AI (e.g., GPT-4). When providing the data, it gives instructions to the AI ​​using a specific prompt. For example, the prompt might be, "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please organize it, including the location, time, and witness information." The server receives the filtered data and the prompt as input, and outputs text data containing a summary of the incident, details of the people involved, and details of the evidence.

[0121] Step 4:

[0122] The server stores the text data generated by the AI ​​in an internal database. At the same time, it formats the text data into a banner format that is easy for users to view. This formatting involves format conversion using HTML and CSS. The server receives the generated text data as input and obtains formatted banner data as output.

[0123] Step 5:

[0124] The server sends the formatted banner data to an information platform on the Internet (e.g., a news site). Specifically, it posts the banner data to the platform using a specific API endpoint and sets it to be displayed at a specified time. It receives the formatted banner data as input and displays the banner on the Internet platform as output.

[0125] Step 6:

[0126] A user is browsing a news site on their device and notices a banner that appears. When the user clicks on the banner, it takes them to a details page, which contains more detailed information about the incident. The input is an action to click on the banner, and the output is the details page.

[0127] Step 7:

[0128] The user enters new information or witnesses about the incident on the details page. The input form contains fields for describing the information and specific witnesses. The input takes the new information provided by the user and the output sends the input data for further processing.

[0129] Step 8:

[0130] The terminal sends the entered user information to the server, using the HTTPS protocol for secure data transfer, receiving the user's new information as input and sending the data to the server as output.

[0131] Step 9:

[0132] The server then filters the received user information again and stores it in an internal database. This filtering process can use natural language processing techniques to remove spam data and redundant information. It takes the information received from the user as input and stores the filtered information in an internal database as output.

[0133] Step 10:

[0134] The server then reports newly collected information to relevant authorities as needed, for example, by providing information to police or investigative agencies via email or API. It receives filtered critical information as input and reports the information to relevant authorities as output.

[0135] (Application example 1)

[0136] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0137] Existing information gathering systems for unsolved cases lack the means to efficiently collect information on past cases, analyze that information, and disseminate it widely. This makes it difficult to gather new clues or additional information from users. Furthermore, the methods for visually displaying the acquired information are limited, making it difficult to attract users' attention. Furthermore, since AI generation is not utilized when generating information on unsolved cases, the accuracy and usefulness of the information cannot be guaranteed.

[0138] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0139] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the parties involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users using a user interface, and means for generating prompt sentences using a generative AI model for information collection. This makes it possible to efficiently collect and analyze information on past unsolved cases and visually display it to gather new clues from users.

[0140] "Unsolved cases" are crimes that occurred in the past and have not been solved to date.

[0141] "Means of collecting data" are means of obtaining information about the incident from specific sources, such as news sites or police public information databases.

[0142] "Means for analyzing data" refers to the means for processing and analyzing collected information and organizing the details of the case, the people involved, and the evidence.

[0143] "Means for generating prompt sentences using a generative AI model" means means for using generative AI to generate summaries or summaries related to an incident from collected data.

[0144] The "means for converting into a display format" refers to a means for converting the generated information into a format that is easy for the user to view, specifically, a banner format or the like.

[0145] An "information platform" refers to a collection of websites and applications that provide information on the Internet.

[0146] A "user interface" is the means by which a user interacts with a system, specifically referring to devices and screens such as PCs and smartphones.

[0147] "Means for collecting additional information from the user" refers to forms or application features that allow users to enter new information, witness statements, etc. into the system.

[0148] "Internal Database" means a data storage device for storing and managing collected information and additional information provided by the User.

[0149] "Related agencies" are public or private agencies involved in resolving the case, such as the police or investigative agencies.

[0150] The present invention is a system for efficiently collecting information about unsolved cases, analyzing, generating, and displaying it using a generative AI model, and collecting additional information from users. Specific embodiments of the present invention are described below.

[0151] System configuration

[0152] This system consists of the following components:

[0153] 1. Data collection module (server)

[0154] 2. Data analysis and generation module (generative AI server)

[0155] 3. Information display module (server)

[0156] 4. User Interface (Terminal / User)

[0157] Data Collection Module

[0158] The server crawls news sites and public police information databases at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting information about unsolved cases that occurred in a specific city, text data from news and public police information is obtained and stored in a database.

[0159] Data Analysis and Generation Module

[0160] The server provides the filtered data to the generation AI, which analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in a specific city in a specific year, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[0161] Example prompt

[0162] Here are some examples of prompts for generative AI models:

[0163] Please summarize the following incident information:

[0164] Title: Robbery in a specific city

[0165] Date: 2023-07-15

[0166] Details: Two men robbed a bank in the center of a certain city. According to witnesses, the culprits were wearing black clothes and fled after stealing about 1 million yen in cash.

[0167] Information Display Module

[0168] The server uses the text data stored in the internal database to format the information in a way that is easy for users to view. In particular, it converts it into a banner format for news sites. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery occurred in a specific city in a specific year: Please provide witness information." This banner information is sent to the news site's management system and displayed at a specified time.

[0169] User Interface

[0170] When users browse a news site on their device (PC, smartphone, etc.), they can see an overview of an unsolved case in a banner. Interested users can click on the banner to go to the detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, notifies the police or relevant agencies.

[0171] Hardware and Software Use

[0172] The system uses the following hardware and software:

[0173] Hardware: High-performance servers are used for data collection, analysis, generation, and display. Users use devices such as PCs and smartphones.

[0174] Software: Generative AI models from OpenAI® are used for data analysis and generation. Web scraping libraries such as BeautifulSoup and requests are used for data collection. Database management systems (e.g., MySQL) are used for data storage and processing.

[0175] In this way, information on past unsolved cases can be efficiently collected, analyzed, and visually displayed, allowing users to gather new clues.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The server crawls news websites and police public information databases at specific time intervals. The input is the URLs of news websites and police databases, and the output is text data related to unsolved cases. The server stores the collected data in a database and filters out duplicate and irrelevant information.

[0179] Step 2:

[0180] The server analyzes the filtered data. The input for this analysis is the filtered case data, and the output is information such as an overview of the analyzed unsolved case, the people involved, and details of the evidence. The server uses a generative AI model to generate prompt sentences, which are then used to generate case information in text format.

[0181] Step 3:

[0182] The server creates banner-style display data based on the generated incident information. The input is a summary of the generated incident, and the output is visually organized banner-style data. This generated banner information is sent to an information platform on the Internet and displayed in a format that can be viewed by users.

[0183] Step 4:

[0184] A user at a terminal clicks on the banner to go to the detailed information page. The input is the user's click action, and the output is the display of the detailed information page, where the user can view more detailed information about the incident.

[0185] Step 5:

[0186] Users enter new information about the incident or witnesses using a form on the detailed information page. The input is the new information provided by the user, and the output is the transmission of the entered information to the server.

[0187] Step 6:

[0188] The server receives new information sent by the user and stores it in an internal database. The input is the new information provided by the user and the output is the information stored in the database. The server filters the new information and notifies the police or relevant authorities if necessary.

[0189] Step 7:

[0190] The server uses a generative AI model to create prompt sentences for automatically generating information. The input is the collected and filtered incident data, and the output is the prompt sentences to be input into the generative AI model.

[0191] Step 8:

[0192] The generative AI model automatically generates a summary and details of the case based on the prompt. The input is the prompt, and the output is the analyzed case information. This information is stored in a database on the server and used in the next step.

[0193] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0194] The present invention is a system for obtaining new clues by effectively collecting and disseminating information about past unsolved cases, and by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided are improved. Specific embodiments of the present invention are described below.

[0195] System configuration

[0196] The system consists of the following components:

[0197] 1. Data collection module (server)

[0198] 2. Data analysis and generation module (generative AI server)

[0199] 3. Information display module (server)

[0200] 4. User Interface (Terminal / User)

[0201] 5. Emotion engine (server)

[0202] Data Collection Module

[0203] The server periodically (for example, every day at midnight) crawls the police public information database and news sites on the Internet to collect data related to unsolved cases. The collected data is temporarily stored in a database, and duplicates and irrelevant information are filtered out. For example, a procedure may be taken to collect the latest information on unsolved theft cases that occurred in City B.

[0204] Data Analysis and Generation Module

[0205] The server converts the filtered data into JSON format to provide it to the generative AI module, which then analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generated text data is stored in an internal database.

[0206] Information Display Module

[0207] The server generates a concise summary of the information from the text data stored in the internal database and formats it into an HTML banner, which is then sent to the Yahoo! News management system and displayed at the specified time.

[0208] User Interface

[0209] When users browse Yahoo! News on their device (PC, smartphone, etc.), an overview of an unsolved case is displayed as a banner. Interested users can click on the banner to go to a detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, reports it to the police or relevant agencies.

[0210] Adding an Emotion Engine

[0211] In the present invention, the emotion engine is utilized when the user provides information or browses detailed information. Specifically, the following processes are added:

[0212] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[0213] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[0214] 3. The server prioritizes the provided information based on the emotional data and immediately notifies the police or relevant agencies if necessary.

[0215] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[0216] Specific examples

[0217] For example, in the case of an unsolved theft that occurred in City B in July 2023, the system would operate as follows:

[0218] 1. The server collects and filters information about the incident from news sites and police public information databases.

[0219] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[0220] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[0221] 4. The user clicks on the banner to access the details page and view further details about the incident.

[0222] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[0223] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[0224] In this way, the present invention can enhance the effectiveness of gathering and disseminating information about unsolved cases by combining an emotion engine.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[0228] Step 2:

[0229] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[0230] Step 3:

[0231] The server converts the filtered data into JSON format to provide it to the generation AI module. The converted data is then passed to the generation AI module.

[0232] Step 4:

[0233] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[0234] Step 5:

[0235] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[0236] Step 6:

[0237] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[0238] Step 7:

[0239] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[0240] Step 8:

[0241] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[0242] Step 9:

[0243] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[0244] Step 10:

[0245] The emotion engine analyzes the text and voice data entered by the user into the form in real time to recognize the user's emotional state.

[0246] Step 11:

[0247] The server evaluates the credibility of the information provided by the user based on the emotion data provided by the emotion engine.

[0248] Step 12:

[0249] The device sends the input information and emotion data from the user to the server, which stores the information in its internal database.

[0250] Step 13:

[0251] The server evaluates the credibility and urgency of the information received and notifies the police or relevant authorities if necessary.

[0252] Step 14:

[0253] An emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state, for example, providing encouraging messages and engaging information if the user is feeling anxious.

[0254] In this way, the system of the present invention, by combining an emotion engine, can effectively collect information on unsolved cases and efficiently provide new clues.

[0255] Example 2

[0256] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0257] Currently, information on unsolved cases is collected and disseminated, but there is a lack of a system for evaluating the credibility and urgency of that information. As a result, collected information may not be reliably reported to relevant agencies promptly. Furthermore, since it is difficult to determine whether the provided information is true, there is a problem of low accuracy in investigations. The present invention aims to solve these problems and improve the accuracy and efficiency of information collection and dissemination of past unsolved cases.

[0258] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0259] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data to generate an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an information providing platform on the Internet, means for collecting additional information from users, means for analyzing user sentiment and evaluating the credibility and urgency of the provided information, and means for reporting the evaluated information to relevant authorities. This makes it possible to evaluate the credibility and urgency of the collected information and efficiently report it to relevant authorities.

[0260] "Past unsolved cases" refer to criminal cases that have not been solved within a certain period of time and are still under investigation.

[0261] "Data Collection Methods" refers to software and hardware features that automatically retrieve certain information from sources on the Internet.

[0262] "Means for analyzing data and generating details of open cases, people involved, and evidence" refers to the function of automatically extracting and organizing details of the case, people involved, and evidence based on collected information.

[0263] "Means for converting the generated information into a display format and displaying it on an information platform on the Internet" refers to the function of formatting the generated text and data into a visually easy-to-read format and making it available through a website or application.

[0264] "Means for collecting additional information from the user" refers to input forms and related system features that receive and store new information provided by the user.

[0265] "Means of analyzing the user's emotions and evaluating the credibility and urgency of the information provided" refers to a function that analyzes text, voice, etc. from information provided by the user and determines their emotional state.

[0266] "Means of reporting evaluated information to relevant agencies" refers to the function of promptly notifying appropriate agencies, such as the police, of information that is deemed to be highly credible or urgent.

[0267] "Means of converting into a display format" refers to the function of converting data into a form that is visually easy for users to understand (for example, HTML or banner ads).

[0268] The present invention provides a system for effectively collecting and disseminating information about past unsolved cases. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided can be improved. Specific embodiments of the present invention are described below.

[0269] System configuration

[0270] The system consists of the following components:

[0271] 1. Data collection module (server)

[0272] 2. Data analysis and generation module (generative AI server)

[0273] 3. Information display module (server)

[0274] 4. User Interface (Terminal / User)

[0275] 5. Emotion engine (server)

[0276] Data Collection Module

[0277] The server periodically (e.g., every day at midnight) crawls public police information databases and news sites on the Internet to collect data related to unsolved cases. The collected data is then temporarily stored in a database, where duplicates and irrelevant information are filtered out. This crawling is performed using web crawler software (e.g., Scrapy). For example, the procedure is to collect the latest information on unsolved theft cases that have occurred in a particular city. A natural language processing library (e.g., NLTK) is used for filtering.

[0278] Data Analysis and Generation Module

[0279] The server converts the filtered data into JSON format to provide it to the generative AI module. This conversion is performed using the Python json library. The generative AI module analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generation is performed using a generative AI model (e.g., GPT-4). The generated text data is stored in an internal database.

[0280] Information Display Module

[0281] The server generates concise information based on the text data stored in the internal database and formats it into a banner-style HTML. This HTML is generated using the Django template engine. The formatted banner information is sent to the management system of an Internet news site (e.g., Yahoo! News) and displayed at the specified time.

[0282] User Interface

[0283] Users browse a news site on their device (e.g., PC or smartphone) and see a banner with an overview of the unsolved case. Interested users can click on the banner to go to a detailed information page, where more detailed information about the case is provided using a JavaScript framework (e.g., React).

[0284] If users have any sightings or other additional information, they can provide it by filling out a form on the details page. The input from this form is sent from the device to the server, and the received information is stored in an internal database. The input information is filtered and, if necessary, reported to the relevant authorities (e.g., police).

[0285] Adding an Emotion Engine

[0286] In this invention, the emotion engine is utilized when users provide information or view detailed information. The specific process is as follows:

[0287] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[0288] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[0289] 3. The server prioritizes the provided information based on the emotion data and immediately notifies relevant authorities if necessary.

[0290] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[0291] Specific examples

[0292] For example, given an unsolved theft case that occurred in 2023 in a particular city, the system would operate as follows:

[0293] 1. The server collects and filters information about the incident from news sites and police public information databases.

[0294] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[0295] 3. The server formats the generated text data into a banner and sends it to the news site's management system.

[0296] 4. The user clicks on the banner to access the details page and view further details about the incident.

[0297] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[0298] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[0299] Example prompts for generative AI models

[0300] "Generate text based on up-to-date information about unsolved thefts that occurred in a specific city in 2023, including a summary of the case, details of the people involved, and evidence."

[0301] In this way, the present invention enables the collection and dissemination of information on unsolved cases, and improves the accuracy of information through sentiment analysis.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1:

[0304] The server starts collecting information.

[0305] Input: The crawl time set in the scheduler.

[0306] Output: Launch of crawl task.

[0307] Specific operation: Every day at midnight, the server's scheduler executes a crawl task to collect data from police public information databases and news sites on the Internet.

[0308] Step 2:

[0309] The server performs the crawl.

[0310] Input: The specified URL list.

[0311] Output: Collected data on unsolved cases.

[0312] What it does: Web crawler software (e.g., Scrapy) on the server accesses the specified URL, retrieves information related to the unsolved case, and stores it in a database.

[0313] Step 3:

[0314] The server filters the collected data.

[0315] Input: Collected cold case data.

[0316] Output: The filtered data.

[0317] What it does: Uses a natural language processing library (e.g., NLTK) to remove duplicate and irrelevant information and generate filtered data.

[0318] Step 4:

[0319] The server converts the data into JSON format.

[0320] Input: Filtered data.

[0321] Output: JSON formatted data.

[0322] Specific operation: Using Python's json library, the filtered data is converted into JSON format and passed to the generative AI module.

[0323] Step 5:

[0324] The generative AI module analyzes and generates data.

[0325] Input: JSON formatted data.

[0326] Output: Text data containing details of the incident, the people involved, and the evidence.

[0327] How it works: A generative AI model (e.g., GPT-4) generates prompt text based on the received JSON data, automatically generating a summary of the incident, details of the people involved, and details of the evidence.

[0328] Step 6:

[0329] The server formats the text into HTML.

[0330] Input: Text data generated by the generative AI module.

[0331] Output: Banner information in HTML format.

[0332] Specific behavior: Uses the Django template engine to format the generated text data into banner-style HTML.

[0333] Step 7:

[0334] The server distributes the information.

[0335] Input: Banner information in HTML format.

[0336] Output: A banner that appears on news sites on the Internet.

[0337] Specific operation: The generated banner information is sent to the news site's management system and displayed at the specified time.

[0338] Step 8:

[0339] A user browses the news.

[0340] Input: A banner displayed on a news site.

[0341] Output: Access to the more information page.

[0342] What happens: A user clicks on the banner on their device and is taken to a details page where they can view more information about the incident.

[0343] Step 9:

[0344] The user provides the information.

[0345] Input: Information entered into the form on the details page.

[0346] Output: Provided sighting and / or additional information.

[0347] Specific actions: The user enters sighting details and additional information in the form on the detailed information page and presses the submit button.

[0348] Step 10:

[0349] The terminal transmits the information.

[0350] Input: Information entered by the user.

[0351] Output: Information sent to the server.

[0352] Specific operation: Input information is sent from the terminal to the server, and the server receives it.

[0353] Step 11:

[0354] The server receives and stores the information.

[0355] Input: Information sent from the device.

[0356] Output: Information stored in an internal database.

[0357] Specific operation: The server stores the received information in a database, and prepares filtering and notification as necessary.

[0358] Step 12:

[0359] The server runs the emotion engine.

[0360] Input: Information submitted by the user.

[0361] Output: Emotion data.

[0362] Specific operation: Calls the emotion engine, analyzes the user's text and voice input, and generates emotion data.

[0363] Step 13:

[0364] The emotion engine analyzes emotions.

[0365] Input: User-provided information.

[0366] Output: Parsed emotion data.

[0367] Specific operation: The emotion engine uses natural language processing and voice emotion recognition technology to recognize the user's emotional state.

[0368] Step 14:

[0369] The server sets the priority of the information.

[0370] Input: Emotion data.

[0371] Output: Information priority.

[0372] Specific operation: The server evaluates the credibility and urgency of information based on emotional data and sets a priority.

[0373] Step 15:

[0374] The server notifies the relevant authorities.

[0375] Input: Prioritized information.

[0376] Output: Notification sent to relevant authorities.

[0377] Specific operation: The server notifies the appropriate authorities, such as the police, of high-priority information.

[0378] (Application example 2)

[0379] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0380] The challenge is to improve the efficiency of collecting and disseminating information about unsolved cases, as well as to increase the credibility of the information provided. Specifically, a system is needed that can notify passengers and drivers of autonomous vehicles of information about unsolved cases in real time, accurately collect eyewitness reports from them, and evaluate their credibility using an emotion analysis engine.

[0381] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0382] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users, means for obtaining current vehicle location information and displaying case information in real time, means for analyzing user emotions and evaluating the credibility of the information based on the emotion data, and means for reporting the information to relevant authorities as needed based on the evaluation. This makes it possible to efficiently collect information on unsolved cases and quickly report credible information to relevant authorities.

[0383] "Data collection means" refers to a device or system that has the function of collecting data related to past unsolved cases from the Internet.

[0384] "Data analysis means" means a device or system capable of analyzing collected data and generating a summary of an unsolved case, details of the parties involved, and details of evidence.

[0385] The "display conversion means" is a device or system that has the function of converting the generated information into a display format and displaying it on an information providing platform on the Internet.

[0386] An "additional information collection means" is a device or system that has the function of collecting new information from users.

[0387] The "location information acquisition means" is a device or system that has the function of acquiring information about the current location of a vehicle.

[0388] "Real-time display means" refers to a device or system that has the function of displaying incident information in real time based on the current location information of the vehicle.

[0389] The "emotion analysis means" is a device or system that has the function of analyzing the user's emotions and evaluating the credibility of information based on the emotion data.

[0390] "Automatic reporting means" refers to a device or system that has the function of automatically reporting necessary information to relevant institutions based on the evaluation results based on emotion analysis.

[0391] The present invention provides a system for efficiently collecting information on unsolved cases, evaluating the credibility of information based on eyewitness reports from users, and reporting the information to relevant authorities as necessary. Specific embodiments of the system are described below.

[0392] System Configuration

[0393] The system consists of the following components:

[0394] 1. Data collection method (server)

[0395] The server collects data on past unsolved cases from the Internet. Specifically, it crawls police public information databases and news sites to collect data on unsolved cases. The collected data is then temporarily stored in a database.

[0396] 2. Data analysis method (server)

[0397] The server analyzes the collected data and automatically generates an outline of the incident, details of the people involved, and details of the evidence using a generative AI model. The generated text data is stored in an internal database.

[0398] 3. Display conversion means (server)

[0399] The server converts the generated information into a display format and displays it on an information platform on the Internet. Specifically, it formats the generated text data into HTML banners and sends them to news sites.

[0400] 4. Additional information collection methods (devices, users)

[0401] Users can access the information platform on their own devices (such as smartphones) and check information on unsolved cases. A form is provided for interested users to provide additional information about the case, allowing users to enter witness accounts, etc. The device sends the entered information to the server, which then stores the received information in an internal database.

[0402] 5. Location information acquisition method (vehicle)

[0403] Vehicles are equipped with a device that acquires their current location information. The server constantly receives this location information and processes it in real time.

[0404] 6. Real-time display means (vehicle, terminal)

[0405] The server displays information related to unsolved cases in real time on the vehicle's or device's display based on the vehicle's current location information. For example, when a vehicle passes near the scene of a particular unsolved case, information about that case is displayed on the display.

[0406] 7. Emotion analysis means (server)

[0407] The server uses an emotion engine to analyze the user's emotions. When the user fills in the additional information form, the emotion analysis engine analyzes the input and determines the user's emotional state.

[0408] 8. Automatic reporting means (server)

[0409] Based on the results of the sentiment analysis, the credibility of the information provided is evaluated and, if necessary, the relevant authorities are notified. The server immediately notifies the police and relevant authorities of this information, facilitating a prompt response.

[0410] Hardware and software used

[0411] Hardware:

[0412] Server: Used for data collection, analysis, display conversion, sentiment analysis, and automatic reporting.

[0413] Vehicle location information acquisition device: Knows the current location of the vehicle in real time.

[0414] Devices (smartphone, vehicle display): View information, enter additional information.

[0415] software:

[0416] Generative AI model: Used to automatically generate incident information.

[0417] EmotionRecognition module: Used to analyze user emotions.

[0418] VehicleAPI: Used to obtain and display the vehicle's current location information.

[0419] Requests library: Handles HTTP requests and communicates with external APIs.

[0420] Specific examples

[0421] For example, in the case of an unsolved theft case that occurred in City B, the system operates as follows: The server collects information about the case from news sites and the police's public information database, and automatically generates details about the case using a generative AI model. The generated information is converted into banner format and displayed on the news site. When a user provides eyewitness information, the emotion engine analyzes the emotion and evaluates its credibility. Based on the evaluation results, the necessary information is immediately reported to the relevant authorities. This process enables information gathering and rapid response to unsolved cases.

[0422] Prompt Sentence Examples

[0423] "Develop an application that can collect information about unsolved cases, notify vehicles, and provide witness reports. The application will evaluate the credibility of users' witness reports using an emotion engine, and automatically notify the police and relevant agencies. The application will work in conjunction with autonomous vehicles, displaying information on the vehicle's display in real time."

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] The server collects data on past unsolved cases from public police information databases and news sites on the Internet. The input is the URL of the public police information database or news site, and the output is the collected case data. During the data collection process, the server uses a web crawler to periodically check these sites to obtain new data.

[0427] Step 2:

[0428] The server analyzes the collected data to generate a summary of the unsolved case, details of the people involved, and details of the evidence. The input is the collected case data, and the output is detailed information about the analyzed case. This analysis uses a generative AI model to analyze the input data using natural language processing (NLP) technology, automatically generating text that describes the case.

[0429] Step 3:

[0430] The server converts the generated detailed information into a display format. The input is the analyzed incident details, and the output is HTML data formatted for display. The server formats the generated text data into HTML banners and sends them to an information platform on the Internet.

[0431] Step 4:

[0432] Users can browse the information platform on their own devices (smartphones) and check information on unsolved cases. By clicking on the displayed banner, the device will be taken to a detailed information page, where a form will be displayed for users to provide further information about the case.

[0433] Step 5:

[0434] The user provides information about the sighting and other additional information. The input is the information entered by the user, and the output is the information sent to the server. The device sends the information entered by the user in the form to the server using an HTTP request.

[0435] Step 6:

[0436] The server receives information provided by the user and analyzes their emotional state. The input is the user-provided witness information and text data, and the output is the result of the emotion analysis engine. Emotion analysis is performed using the EmotionRecognition module, which identifies emotions from the user's input.

[0437] Step 7:

[0438] The server evaluates the credibility of the information based on the results of sentiment analysis. The inputs are the results of sentiment analysis and witness information, and the output is the evaluation result. Based on this evaluation result, the credibility and urgency of the provided information are judged.

[0439] Step 8:

[0440] The server will report to the relevant authorities as necessary based on the evaluation results. The input is the information whose credibility has been evaluated, and the output is the report to the relevant authorities. The server automatically notifies the police and other relevant authorities of information with a high level of importance.

[0441] Step 9:

[0442] The server obtains the vehicle's current location information and displays relevant information about unsolved cases on the vehicle's display in real time. The input is the vehicle's location information, and the output is the case information to be displayed. The server uses VehicleAPI to obtain the vehicle's current location and displays case information in real time based on that information.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0444] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0446] [Second embodiment]

[0447] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0448] 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.

[0449] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0450] 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.

[0451] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0453] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0454] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0455] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0456] 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.

[0457] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0458] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0459] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating it to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0460] System configuration

[0461] This system mainly consists of the following four components:

[0462] 1. Data collection module (server)

[0463] 2. Data analysis and generation module (generative AI server)

[0464] 3. Information display module (server)

[0465] 4. User Interface (Terminal / User)

[0466] Data Collection Module

[0467] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting the latest information on unsolved robberies that occurred in City A, text data from news and public police information is obtained and stored in a database.

[0468] Data Analysis and Generation Module

[0469] The server provides the filtered data to the generation AI. The generation AI analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in City A in July 2023, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[0470] Information Display Module

[0471] The server formats the information based on the text data stored in the internal database into a format that is easy for users to view. In particular, it converts it into the Yahoo! News banner format. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery that occurred in City A in July 2023: Please provide witness information." This banner information is sent to the Yahoo! News management system and displayed at a specified time.

[0472] User Interface

[0473] When users browse Yahoo! News on their devices (PC, smartphone, etc.), they can see an overview of the unsolved case in a banner. If they are interested, they can click on the banner and be taken to a detailed information page, where they can find more detailed information about the case.

[0474] If a user has new information or witnesses about an incident, they can provide it by filling out a form on the detailed information page. The device sends the information to the server, which stores it in an internal database. The server then filters the information and, if necessary, notifies the police or other relevant authorities.

[0475] Specific examples

[0476] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the information would be processed in the following manner:

[0477] 1. The server collects and filters relevant information from news sites and police public information databases.

[0478] 2. Generate filtered data: The AI ​​module analyzes the data and automatically generates an outline of the incident, witness information, and details of the evidence.

[0479] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[0480] 4. The user clicks on the banner to access the details page and view more information about the incident.

[0481] 5. The user enters any new information or sightings they have into the form, and the device sends the information to the server.

[0482] 6. The server stores the new information in a database and notifies relevant authorities as necessary.

[0483] In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues for solving the cases.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[0487] Step 2:

[0488] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[0489] Step 3:

[0490] The server converts the filtered data into JSON format for providing to the generation AI. The converted data is passed to the generation AI module.

[0491] Step 4:

[0492] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[0493] Step 5:

[0494] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[0495] Step 6:

[0496] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[0497] Step 7:

[0498] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[0499] Step 8:

[0500] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[0501] Step 9:

[0502] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[0503] Step 10:

[0504] The terminal transmits new information and sightings entered by the user to the server.

[0505] Step 11:

[0506] The server receives the information and stores it in an internal database, where it filters the information and prepares to notify the relevant authorities.

[0507] Step 12:

[0508] The server will then report any new information collected to police and other relevant agencies as needed, which can aid in the investigation of unsolved cases.

[0509] In this way, the system of the present invention can effectively collect, analyze, and display information about unsolved cases through a series of processing steps, and efficiently provide new clues.

[0510] Example 1

[0511] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0512] The objective of this study is to solve the lack of a means to efficiently collect information on past unsolved cases, disseminate it widely, and obtain new clues. There is also a need for a method to quickly and accurately analyze the collected information and convert it into a display format.

[0513] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0514] In this invention, the server includes means for periodically collecting data on past unsolved cases, means for filtering the collected data and removing duplicate and irrelevant information, means for analyzing the filtered data and using a generative AI model to generate an outline of the unsolved case, details of the parties involved, and details of evidence, means for formatting the generated information into a banner and displaying it on an online information platform, means for collecting additional information from users and storing the collected information in an internal database, and means for reporting the collected additional information to relevant authorities as needed. This makes it possible to efficiently collect and widely disseminate information on unsolved cases and quickly obtain new clues.

[0515] "Methods of periodically collecting data on past unsolved cases" refers to crawling police public information databases and news sites at specific time intervals to collect information related to unsolved cases.

[0516] "Means of filtering collected data and removing duplicate or irrelevant information" refers to the process of removing duplicate information or information that is not relevant to the incident from collected data in order to improve accuracy.

[0517] "Using a generative AI model to analyze filtered data and generate a summary of the unsolved case, details of the people involved, and evidence" refers to a method of analyzing filtered data using an artificial intelligence model (e.g., a generative model) to automatically generate key elements of the case.

[0518] "Means for formatting the generated information into a banner format and displaying it on an information platform on the Internet" refers to the process of converting the generated text data into an easy-to-read banner format and displaying it on news sites, etc. on the Internet.

[0519] "Means for collecting additional information from users and storing that information in an internal database" refers to the internal systems used to receive and store new information provided by users.

[0520] "Means of reporting any additional information collected to relevant authorities as necessary" refers to the means by which information collected from users is deemed useful and is then notified to the police or relevant authorities.

[0521] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating that information to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0522] Data Collection Module

[0523] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). The server uses web crawling libraries such as Python's BeautifulSoup or Scrapy to collect information related to unsolved cases. The collected data is stored in a relational database such as MySQL or PostgreSQL. The server then filters out duplicates and irrelevant information from the collected data. Natural language processing techniques can be used in this filtering process.

[0524] Data Analysis and Generation Module

[0525] The server provides the filtered data to the generation AI (e.g., GPT-4). Examples of specific prompts include:

[0526] "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please include location, time, and any witness information."

[0527] The AI ​​analyzes the data based on this prompt and generates text information including an overview of the incident, the people involved, and details of the evidence. The generated text data is then stored in the internal database by the server.

[0528] Information Display Module

[0529] The server formats the information into a banner based on the text data stored in its internal database. The formatting involves converting it into an easy-to-read format using HTML and CSS. The formatted banner is then displayed on Yahoo! News and other online information platforms. This process generates a banner with the message "Robbery occurred in City A in July 2023: Please provide witness information," which is displayed at the specified time.

[0530] User Interface

[0531] When users browse Yahoo! News on their devices (PCs, smartphones, etc.), they can see an overview of unsolved cases in a banner. If an interested user clicks on the banner, they are taken to a detailed information page, which provides more detailed information about the case. If a user has new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device then sends the entered information to the server, which stores the received information in an internal database and, if necessary, reports it to relevant authorities.

[0532] Specific examples

[0533] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the process would be as follows: The server collects and filters relevant information from news sites and the police's public information database. The filtered data is provided to a generation AI, which automatically generates a summary of the incident, witness information, and details of the evidence. The generated text data is formatted and sent to the Yahoo! News management system. The user clicks on the banner to access the detailed information page and view detailed information about the incident. The user enters any new information or witness information they have in a form, and the device sends the information to the server. The server saves the new information in a database and, if necessary, notifies relevant authorities. In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues to solve them.

[0534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0535] Step 1:

[0536] The server crawls news sites and police public information databases at specific intervals (e.g., 12 noon every day). The server extracts the necessary text data from web pages using Python's BeautifulSoup or Scrapy. As input, it receives a list of URLs from news sites and police public information databases, and as output, it obtains text data about unsolved cases collected from each web page.

[0537] Step 2:

[0538] The server stores the collected data in a relational database (e.g., MySQL or PostgreSQL). Before storing, it performs a filtering process to remove duplicate and irrelevant information. Specifically, it uses natural language processing technology to evaluate the similarity of text and remove duplicate data. It receives the collected raw data as input and stores the filtered, highly accurate data as output in the database.

[0539] Step 3:

[0540] The server provides the filtered data to the generation AI (e.g., GPT-4). When providing the data, it gives instructions to the AI ​​using a specific prompt. For example, the prompt might be, "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please organize it, including the location, time, and witness information." The server receives the filtered data and the prompt as input, and outputs text data containing a summary of the incident, details of the people involved, and details of the evidence.

[0541] Step 4:

[0542] The server stores the text data generated by the AI ​​in an internal database. At the same time, it formats the text data into a banner format that is easy for users to view. This formatting involves format conversion using HTML and CSS. The server receives the generated text data as input and obtains formatted banner data as output.

[0543] Step 5:

[0544] The server sends the formatted banner data to an information platform on the Internet (e.g., a news site). Specifically, it posts the banner data to the platform using a specific API endpoint and sets it to be displayed at a specified time. It receives the formatted banner data as input and displays the banner on the Internet platform as output.

[0545] Step 6:

[0546] A user is browsing a news site on their device and notices a banner that appears. When the user clicks on the banner, it takes them to a details page, which contains more detailed information about the incident. The input is an action to click on the banner, and the output is the details page.

[0547] Step 7:

[0548] The user enters new information or witnesses about the incident on the details page. The input form contains fields for describing the information and specific witnesses. The input takes the new information provided by the user and the output sends the input data for further processing.

[0549] Step 8:

[0550] The terminal sends the entered user information to the server, using the HTTPS protocol for secure data transfer, receiving the user's new information as input and sending the data to the server as output.

[0551] Step 9:

[0552] The server then filters the received user information again and stores it in an internal database. This filtering process can use natural language processing techniques to remove spam data and redundant information. It takes the information received from the user as input and stores the filtered information in an internal database as output.

[0553] Step 10:

[0554] The server then reports newly collected information to relevant authorities as needed, for example, by providing information to police or investigative agencies via email or API. It receives filtered critical information as input and reports the information to relevant authorities as output.

[0555] (Application example 1)

[0556] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0557] Existing information gathering systems for unsolved cases lack the means to efficiently collect information on past cases, analyze that information, and disseminate it widely. This makes it difficult to gather new clues or additional information from users. Furthermore, the methods for visually displaying the acquired information are limited, making it difficult to attract users' attention. Furthermore, since AI generation is not utilized when generating information on unsolved cases, the accuracy and usefulness of the information cannot be guaranteed.

[0558] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0559] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the parties involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users using a user interface, and means for generating prompt sentences using a generative AI model for information collection. This makes it possible to efficiently collect and analyze information on past unsolved cases and visually display it to gather new clues from users.

[0560] "Unsolved cases" are crimes that occurred in the past and have not been solved to date.

[0561] "Means of collecting data" are means of obtaining information about the incident from specific sources, such as news sites or police public information databases.

[0562] "Means for analyzing data" refers to the means for processing and analyzing collected information and organizing the details of the case, the people involved, and the evidence.

[0563] "Means for generating prompt sentences using a generative AI model" means means for using generative AI to generate summaries or summaries related to an incident from collected data.

[0564] The "means for converting into a display format" refers to a means for converting the generated information into a format that is easy for the user to view, specifically, a banner format or the like.

[0565] An "information platform" refers to a collection of websites and applications that provide information on the Internet.

[0566] A "user interface" is the means by which a user interacts with a system, specifically referring to devices and screens such as PCs and smartphones.

[0567] "Means for collecting additional information from the user" refers to forms or application features that allow users to enter new information, witness statements, etc. into the system.

[0568] "Internal Database" means a data storage device for storing and managing collected information and additional information provided by the User.

[0569] "Related agencies" are public or private agencies involved in resolving the case, such as the police or investigative agencies.

[0570] The present invention is a system for efficiently collecting information about unsolved cases, analyzing, generating, and displaying it using a generative AI model, and collecting additional information from users. Specific embodiments of the present invention are described below.

[0571] System configuration

[0572] This system consists of the following components:

[0573] 1. Data collection module (server)

[0574] 2. Data analysis and generation module (generative AI server)

[0575] 3. Information display module (server)

[0576] 4. User Interface (Terminal / User)

[0577] Data Collection Module

[0578] The server crawls news sites and public police information databases at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting information about unsolved cases that occurred in a specific city, text data from news and public police information is obtained and stored in a database.

[0579] Data Analysis and Generation Module

[0580] The server provides the filtered data to the generation AI, which analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in a specific city in a specific year, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[0581] Example prompt

[0582] Here are some examples of prompts for generative AI models:

[0583] Please summarize the following incident information:

[0584] Title: Robbery in a specific city

[0585] Date: 2023-07-15

[0586] Details: Two men robbed a bank in the center of a certain city. According to witnesses, the culprits were wearing black clothes and fled after stealing about 1 million yen in cash.

[0587] Information Display Module

[0588] The server uses the text data stored in the internal database to format the information in a way that is easy for users to view. In particular, it converts it into a banner format for news sites. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery occurred in a specific city in a specific year: Please provide witness information." This banner information is sent to the news site's management system and displayed at a specified time.

[0589] User Interface

[0590] When users browse a news site on their device (PC, smartphone, etc.), they can see an overview of an unsolved case in a banner. Interested users can click on the banner to go to the detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, notifies the police or relevant agencies.

[0591] Hardware and Software Use

[0592] The system uses the following hardware and software:

[0593] Hardware: High-performance servers are used for data collection, analysis, generation, and display. Users use devices such as PCs and smartphones.

[0594] Software: OpenAI generative AI models are used for data analysis and generation. Web scraping libraries such as BeautifulSoup and requests are used for data collection. Database management systems (e.g., MySQL) are used for data storage and processing.

[0595] In this way, information on past unsolved cases can be efficiently collected, analyzed, and visually displayed, allowing users to gather new clues.

[0596] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0597] Step 1:

[0598] The server crawls news websites and police public information databases at specific time intervals. The input is the URLs of news websites and police databases, and the output is text data related to unsolved cases. The server stores the collected data in a database and filters out duplicate and irrelevant information.

[0599] Step 2:

[0600] The server analyzes the filtered data. The input for this analysis is the filtered case data, and the output is information such as an overview of the analyzed unsolved case, the people involved, and details of the evidence. The server uses a generative AI model to generate prompt sentences, which are then used to generate case information in text format.

[0601] Step 3:

[0602] The server creates banner-style display data based on the generated incident information. The input is a summary of the generated incident, and the output is visually organized banner-style data. This generated banner information is sent to an information platform on the Internet and displayed in a format that can be viewed by users.

[0603] Step 4:

[0604] A user at a terminal clicks on the banner to go to the detailed information page. The input is the user's click action, and the output is the display of the detailed information page, where the user can view more detailed information about the incident.

[0605] Step 5:

[0606] Users enter new information about the incident or witnesses using a form on the detailed information page. The input is the new information provided by the user, and the output is the transmission of the entered information to the server.

[0607] Step 6:

[0608] The server receives new information sent by the user and stores it in an internal database. The input is the new information provided by the user and the output is the information stored in the database. The server filters the new information and notifies the police or relevant authorities if necessary.

[0609] Step 7:

[0610] The server uses a generative AI model to create prompt sentences for automatically generating information. The input is the collected and filtered incident data, and the output is the prompt sentences to be input into the generative AI model.

[0611] Step 8:

[0612] The generative AI model automatically generates a summary and details of the case based on the prompt. The input is the prompt, and the output is the analyzed case information. This information is stored in a database on the server and used in the next step.

[0613] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0614] The present invention is a system for obtaining new clues by effectively collecting and disseminating information about past unsolved cases, and by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided are improved. Specific embodiments of the present invention are described below.

[0615] System configuration

[0616] The system consists of the following components:

[0617] 1. Data collection module (server)

[0618] 2. Data analysis and generation module (generative AI server)

[0619] 3. Information display module (server)

[0620] 4. User Interface (Terminal / User)

[0621] 5. Emotion engine (server)

[0622] Data Collection Module

[0623] The server periodically (for example, every day at midnight) crawls the police public information database and news sites on the Internet to collect data related to unsolved cases. The collected data is temporarily stored in a database, and duplicates and irrelevant information are filtered out. For example, a procedure may be taken to collect the latest information on unsolved theft cases that occurred in City B.

[0624] Data Analysis and Generation Module

[0625] The server converts the filtered data into JSON format to provide it to the generative AI module, which then analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generated text data is stored in an internal database.

[0626] Information Display Module

[0627] The server generates a concise summary of the information from the text data stored in the internal database and formats it into an HTML banner, which is then sent to the Yahoo! News management system and displayed at the specified time.

[0628] User Interface

[0629] When users browse Yahoo! News on their device (PC, smartphone, etc.), an overview of an unsolved case is displayed as a banner. Interested users can click on the banner to go to a detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, reports it to the police or relevant agencies.

[0630] Adding an Emotion Engine

[0631] In the present invention, the emotion engine is utilized when the user provides information or browses detailed information. Specifically, the following processes are added:

[0632] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[0633] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[0634] 3. The server prioritizes the provided information based on the emotional data and immediately notifies the police or relevant agencies if necessary.

[0635] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[0636] Specific examples

[0637] For example, in the case of an unsolved theft that occurred in City B in July 2023, the system would operate as follows:

[0638] 1. The server collects and filters information about the incident from news sites and police public information databases.

[0639] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[0640] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[0641] 4. The user clicks on the banner to access the details page and view further details about the incident.

[0642] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[0643] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[0644] In this way, the present invention can enhance the effectiveness of gathering and disseminating information about unsolved cases by combining an emotion engine.

[0645] The processing flow will be explained below.

[0646] Step 1:

[0647] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[0648] Step 2:

[0649] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[0650] Step 3:

[0651] The server converts the filtered data into JSON format to provide it to the generation AI module. The converted data is then passed to the generation AI module.

[0652] Step 4:

[0653] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[0654] Step 5:

[0655] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[0656] Step 6:

[0657] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[0658] Step 7:

[0659] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[0660] Step 8:

[0661] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[0662] Step 9:

[0663] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[0664] Step 10:

[0665] The emotion engine analyzes the text and voice data entered by the user into the form in real time to recognize the user's emotional state.

[0666] Step 11:

[0667] The server evaluates the credibility of the information provided by the user based on the emotion data provided by the emotion engine.

[0668] Step 12:

[0669] The device sends the input information and emotion data from the user to the server, which stores the information in its internal database.

[0670] Step 13:

[0671] The server evaluates the credibility and urgency of the information received and notifies the police or relevant authorities if necessary.

[0672] Step 14:

[0673] An emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state, for example, providing encouraging messages and engaging information if the user is feeling anxious.

[0674] In this way, the system of the present invention, by combining an emotion engine, can effectively collect information on unsolved cases and efficiently provide new clues.

[0675] Example 2

[0676] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0677] Currently, information on unsolved cases is collected and disseminated, but there is a lack of a system for evaluating the credibility and urgency of that information. As a result, collected information may not be reliably reported to relevant agencies promptly. Furthermore, since it is difficult to determine whether the provided information is true, there is a problem of low accuracy in investigations. The present invention aims to solve these problems and improve the accuracy and efficiency of information collection and dissemination of past unsolved cases.

[0678] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0679] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data to generate an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an information providing platform on the Internet, means for collecting additional information from users, means for analyzing user sentiment and evaluating the credibility and urgency of the provided information, and means for reporting the evaluated information to relevant authorities. This makes it possible to evaluate the credibility and urgency of the collected information and efficiently report it to relevant authorities.

[0680] "Past unsolved cases" refer to criminal cases that have not been solved within a certain period of time and are still under investigation.

[0681] "Data Collection Methods" refers to software and hardware features that automatically retrieve certain information from sources on the Internet.

[0682] "Means for analyzing data and generating details of open cases, people involved, and evidence" refers to the function of automatically extracting and organizing details of the case, people involved, and evidence based on collected information.

[0683] "Means for converting the generated information into a display format and displaying it on an information platform on the Internet" refers to the function of formatting the generated text and data into a visually easy-to-read format and making it available through a website or application.

[0684] "Means for collecting additional information from the user" refers to input forms and related system features that receive and store new information provided by the user.

[0685] "Means of analyzing the user's emotions and evaluating the credibility and urgency of the information provided" refers to a function that analyzes text, voice, etc. from information provided by the user and determines their emotional state.

[0686] "Means of reporting evaluated information to relevant agencies" refers to the function of promptly notifying appropriate agencies, such as the police, of information that is deemed to be highly credible or urgent.

[0687] "Means of converting into a display format" refers to the function of converting data into a form that is visually easy for users to understand (for example, HTML or banner ads).

[0688] The present invention provides a system for effectively collecting and disseminating information about past unsolved cases. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided can be improved. Specific embodiments of the present invention are described below.

[0689] System configuration

[0690] The system consists of the following components:

[0691] 1. Data collection module (server)

[0692] 2. Data analysis and generation module (generative AI server)

[0693] 3. Information display module (server)

[0694] 4. User Interface (Terminal / User)

[0695] 5. Emotion engine (server)

[0696] Data Collection Module

[0697] The server periodically (e.g., every day at midnight) crawls public police information databases and news sites on the Internet to collect data related to unsolved cases. The collected data is then temporarily stored in a database, where duplicates and irrelevant information are filtered out. This crawling is performed using web crawler software (e.g., Scrapy). For example, the procedure is to collect the latest information on unsolved theft cases that have occurred in a particular city. A natural language processing library (e.g., NLTK) is used for filtering.

[0698] Data Analysis and Generation Module

[0699] The server converts the filtered data into JSON format to provide it to the generative AI module. This conversion is performed using the Python json library. The generative AI module analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generation is performed using a generative AI model (e.g., GPT-4). The generated text data is stored in an internal database.

[0700] Information Display Module

[0701] The server generates concise information based on the text data stored in the internal database and formats it into a banner-style HTML. This HTML is generated using the Django template engine. The formatted banner information is sent to the management system of an Internet news site (e.g., Yahoo! News) and displayed at the specified time.

[0702] User Interface

[0703] Users browse a news site on their device (e.g., PC or smartphone) and see a banner with an overview of the unsolved case. Interested users can click on the banner to go to a detailed information page, where more detailed information about the case is provided using a JavaScript framework (e.g., React).

[0704] If users have any sightings or other additional information, they can provide it by filling out a form on the details page. The input from this form is sent from the device to the server, and the received information is stored in an internal database. The input information is filtered and, if necessary, reported to the relevant authorities (e.g., police).

[0705] Adding an Emotion Engine

[0706] In this invention, the emotion engine is utilized when users provide information or view detailed information. The specific process is as follows:

[0707] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[0708] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[0709] 3. The server prioritizes the provided information based on the emotion data and immediately notifies relevant authorities if necessary.

[0710] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[0711] Specific examples

[0712] For example, given an unsolved theft case that occurred in 2023 in a particular city, the system would operate as follows:

[0713] 1. The server collects and filters information about the incident from news sites and police public information databases.

[0714] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[0715] 3. The server formats the generated text data into a banner and sends it to the news site's management system.

[0716] 4. The user clicks on the banner to access the details page and view further details about the incident.

[0717] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[0718] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[0719] Example prompts for generative AI models

[0720] "Generate text based on up-to-date information about unsolved thefts that occurred in a specific city in 2023, including a summary of the case, details of the people involved, and evidence."

[0721] In this way, the present invention enables the collection and dissemination of information on unsolved cases, and improves the accuracy of information through sentiment analysis.

[0722] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0723] Step 1:

[0724] The server starts collecting information.

[0725] Input: The crawl time set in the scheduler.

[0726] Output: Launch of crawl task.

[0727] Specific operation: Every day at midnight, the server's scheduler executes a crawl task to collect data from police public information databases and news sites on the Internet.

[0728] Step 2:

[0729] The server performs the crawl.

[0730] Input: The specified URL list.

[0731] Output: Collected data on unsolved cases.

[0732] What it does: Web crawler software (e.g., Scrapy) on the server accesses the specified URL, retrieves information related to the unsolved case, and stores it in a database.

[0733] Step 3:

[0734] The server filters the collected data.

[0735] Input: Collected cold case data.

[0736] Output: The filtered data.

[0737] What it does: Uses a natural language processing library (e.g., NLTK) to remove duplicate and irrelevant information and generate filtered data.

[0738] Step 4:

[0739] The server converts the data into JSON format.

[0740] Input: Filtered data.

[0741] Output: JSON formatted data.

[0742] Specific operation: Using Python's json library, the filtered data is converted into JSON format and passed to the generative AI module.

[0743] Step 5:

[0744] The generative AI module analyzes and generates data.

[0745] Input: JSON formatted data.

[0746] Output: Text data containing details of the incident, the people involved, and the evidence.

[0747] How it works: A generative AI model (e.g., GPT-4) generates prompt text based on the received JSON data, automatically generating a summary of the incident, details of the people involved, and details of the evidence.

[0748] Step 6:

[0749] The server formats the text into HTML.

[0750] Input: Text data generated by the generative AI module.

[0751] Output: Banner information in HTML format.

[0752] Specific behavior: Uses the Django template engine to format the generated text data into banner-style HTML.

[0753] Step 7:

[0754] The server distributes the information.

[0755] Input: Banner information in HTML format.

[0756] Output: A banner that appears on news sites on the Internet.

[0757] Specific operation: The generated banner information is sent to the news site's management system and displayed at the specified time.

[0758] Step 8:

[0759] A user browses the news.

[0760] Input: A banner displayed on a news site.

[0761] Output: Access to the more information page.

[0762] What happens: A user clicks on the banner on their device and is taken to a details page where they can view more information about the incident.

[0763] Step 9:

[0764] The user provides the information.

[0765] Input: Information entered into the form on the details page.

[0766] Output: Provided sighting and / or additional information.

[0767] Specific actions: The user enters sighting details and additional information in the form on the detailed information page and presses the submit button.

[0768] Step 10:

[0769] The terminal transmits the information.

[0770] Input: Information entered by the user.

[0771] Output: Information sent to the server.

[0772] Specific operation: Input information is sent from the terminal to the server, and the server receives it.

[0773] Step 11:

[0774] The server receives and stores the information.

[0775] Input: Information sent from the device.

[0776] Output: Information stored in an internal database.

[0777] Specific operation: The server stores the received information in a database, and prepares filtering and notification as necessary.

[0778] Step 12:

[0779] The server runs the emotion engine.

[0780] Input: Information submitted by the user.

[0781] Output: Emotion data.

[0782] Specific operation: Calls the emotion engine, analyzes the user's text and voice input, and generates emotion data.

[0783] Step 13:

[0784] The emotion engine analyzes emotions.

[0785] Input: User-provided information.

[0786] Output: Parsed emotion data.

[0787] Specific operation: The emotion engine uses natural language processing and voice emotion recognition technology to recognize the user's emotional state.

[0788] Step 14:

[0789] The server sets the priority of the information.

[0790] Input: Emotion data.

[0791] Output: Information priority.

[0792] Specific operation: The server evaluates the credibility and urgency of information based on emotional data and sets a priority.

[0793] Step 15:

[0794] The server notifies the relevant authorities.

[0795] Input: Prioritized information.

[0796] Output: Notification sent to relevant authorities.

[0797] Specific operation: The server notifies the appropriate authorities, such as the police, of high-priority information.

[0798] (Application example 2)

[0799] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0800] The challenge is to improve the efficiency of collecting and disseminating information about unsolved cases, as well as to increase the credibility of the information provided. Specifically, a system is needed that can notify passengers and drivers of autonomous vehicles of information about unsolved cases in real time, accurately collect eyewitness reports from them, and evaluate their credibility using an emotion analysis engine.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0802] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users, means for obtaining current vehicle location information and displaying case information in real time, means for analyzing user emotions and evaluating the credibility of the information based on the emotion data, and means for reporting the information to relevant authorities as needed based on the evaluation. This makes it possible to efficiently collect information on unsolved cases and quickly report credible information to relevant authorities.

[0803] "Data collection means" refers to a device or system that has the function of collecting data related to past unsolved cases from the Internet.

[0804] "Data analysis means" means a device or system capable of analyzing collected data and generating a summary of an unsolved case, details of the parties involved, and details of evidence.

[0805] The "display conversion means" is a device or system that has the function of converting the generated information into a display format and displaying it on an information providing platform on the Internet.

[0806] An "additional information collection means" is a device or system that has the function of collecting new information from users.

[0807] The "location information acquisition means" is a device or system that has the function of acquiring information about the current location of a vehicle.

[0808] "Real-time display means" refers to a device or system that has the function of displaying incident information in real time based on the current location information of the vehicle.

[0809] The "emotion analysis means" is a device or system that has the function of analyzing the user's emotions and evaluating the credibility of information based on the emotion data.

[0810] "Automatic reporting means" refers to a device or system that has the function of automatically reporting necessary information to relevant institutions based on the evaluation results based on emotion analysis.

[0811] The present invention provides a system for efficiently collecting information on unsolved cases, evaluating the credibility of information based on eyewitness reports from users, and reporting the information to relevant authorities as necessary. Specific embodiments of the system are described below.

[0812] System Configuration

[0813] The system consists of the following components:

[0814] 1. Data collection method (server)

[0815] The server collects data on past unsolved cases from the Internet. Specifically, it crawls police public information databases and news sites to collect data on unsolved cases. The collected data is then temporarily stored in a database.

[0816] 2. Data analysis method (server)

[0817] The server analyzes the collected data and automatically generates an outline of the incident, details of the people involved, and details of the evidence using a generative AI model. The generated text data is stored in an internal database.

[0818] 3. Display conversion means (server)

[0819] The server converts the generated information into a display format and displays it on an information platform on the Internet. Specifically, it formats the generated text data into HTML banners and sends them to news sites.

[0820] 4. Additional information collection methods (devices, users)

[0821] Users can access the information platform on their own devices (such as smartphones) and check information on unsolved cases. A form is provided for interested users to provide additional information about the case, allowing users to enter witness accounts, etc. The device sends the entered information to the server, which then stores the received information in an internal database.

[0822] 5. Location information acquisition method (vehicle)

[0823] Vehicles are equipped with a device that acquires their current location information. The server constantly receives this location information and processes it in real time.

[0824] 6. Real-time display means (vehicle, terminal)

[0825] The server displays information related to unsolved cases in real time on the vehicle's or device's display based on the vehicle's current location information. For example, when a vehicle passes near the scene of a particular unsolved case, information about that case is displayed on the display.

[0826] 7. Emotion analysis means (server)

[0827] The server uses an emotion engine to analyze the user's emotions. When the user fills in the additional information form, the emotion analysis engine analyzes the input and determines the user's emotional state.

[0828] 8. Automatic reporting means (server)

[0829] Based on the results of the sentiment analysis, the credibility of the information provided is evaluated and, if necessary, the relevant authorities are notified. The server immediately notifies the police and relevant authorities of this information, facilitating a prompt response.

[0830] Hardware and software used

[0831] Hardware:

[0832] Server: Used for data collection, analysis, display conversion, sentiment analysis, and automatic reporting.

[0833] Vehicle location information acquisition device: Knows the current location of the vehicle in real time.

[0834] Devices (smartphone, vehicle display): View information, enter additional information.

[0835] software:

[0836] Generative AI model: Used to automatically generate incident information.

[0837] EmotionRecognition module: Used to analyze user emotions.

[0838] VehicleAPI: Used to obtain and display the vehicle's current location information.

[0839] Requests library: Handles HTTP requests and communicates with external APIs.

[0840] Specific examples

[0841] For example, in the case of an unsolved theft case that occurred in City B, the system operates as follows: The server collects information about the case from news sites and the police's public information database, and automatically generates details about the case using a generative AI model. The generated information is converted into banner format and displayed on the news site. When a user provides eyewitness information, the emotion engine analyzes the emotion and evaluates its credibility. Based on the evaluation results, the necessary information is immediately reported to the relevant authorities. This process enables information gathering and rapid response to unsolved cases.

[0842] Prompt Sentence Examples

[0843] "Develop an application that can collect information about unsolved cases, notify vehicles, and provide witness reports. The application will evaluate the credibility of users' witness reports using an emotion engine, and automatically notify the police and relevant agencies. The application will work in conjunction with autonomous vehicles, displaying information on the vehicle's display in real time."

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] The server collects data on past unsolved cases from public police information databases and news sites on the Internet. The input is the URL of the public police information database or news site, and the output is the collected case data. During the data collection process, the server uses a web crawler to periodically check these sites to obtain new data.

[0847] Step 2:

[0848] The server analyzes the collected data to generate a summary of the unsolved case, details of the people involved, and details of the evidence. The input is the collected case data, and the output is detailed information about the analyzed case. This analysis uses a generative AI model to analyze the input data using natural language processing (NLP) technology, automatically generating text that describes the case.

[0849] Step 3:

[0850] The server converts the generated detailed information into a display format. The input is the analyzed incident details, and the output is HTML data formatted for display. The server formats the generated text data into HTML banners and sends them to an information platform on the Internet.

[0851] Step 4:

[0852] Users can browse the information platform on their own devices (smartphones) and check information on unsolved cases. By clicking on the displayed banner, the device will be taken to a detailed information page, where a form will be displayed for users to provide further information about the case.

[0853] Step 5:

[0854] The user provides information about the sighting and other additional information. The input is the information entered by the user, and the output is the information sent to the server. The device sends the information entered by the user in the form to the server using an HTTP request.

[0855] Step 6:

[0856] The server receives information provided by the user and analyzes their emotional state. The input is the user-provided witness information and text data, and the output is the result of the emotion analysis engine. Emotion analysis is performed using the EmotionRecognition module, which identifies emotions from the user's input.

[0857] Step 7:

[0858] The server evaluates the credibility of the information based on the results of sentiment analysis. The inputs are the results of sentiment analysis and witness information, and the output is the evaluation result. Based on this evaluation result, the credibility and urgency of the provided information are judged.

[0859] Step 8:

[0860] The server will report to the relevant authorities as necessary based on the evaluation results. The input is the information whose credibility has been evaluated, and the output is the report to the relevant authorities. The server automatically notifies the police and other relevant authorities of information with a high level of importance.

[0861] Step 9:

[0862] The server obtains the vehicle's current location information and displays relevant information about unsolved cases on the vehicle's display in real time. The input is the vehicle's location information, and the output is the case information to be displayed. The server uses VehicleAPI to obtain the vehicle's current location and displays case information in real time based on that information.

[0863] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0864] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0865] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0866] [Third embodiment]

[0867] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0868] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0869] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0870] 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.

[0871] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0872] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0873] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0874] 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.

[0875] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0876] 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.

[0877] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0878] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0879] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating it to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0880] System configuration

[0881] This system mainly consists of the following four components:

[0882] 1. Data collection module (server)

[0883] 2. Data analysis and generation module (generative AI server)

[0884] 3. Information display module (server)

[0885] 4. User Interface (Terminal / User)

[0886] Data Collection Module

[0887] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting the latest information on unsolved robberies that occurred in City A, text data from news and public police information is obtained and stored in a database.

[0888] Data Analysis and Generation Module

[0889] The server provides the filtered data to the generation AI. The generation AI analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in City A in July 2023, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[0890] Information Display Module

[0891] The server formats the information based on the text data stored in the internal database into a format that is easy for users to view. In particular, it converts it into the Yahoo! News banner format. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery that occurred in City A in July 2023: Please provide witness information." This banner information is sent to the Yahoo! News management system and displayed at a specified time.

[0892] User Interface

[0893] When users browse Yahoo! News on their devices (PC, smartphone, etc.), they can see an overview of the unsolved case in a banner. If they are interested, they can click on the banner and be taken to a detailed information page, where they can find more detailed information about the case.

[0894] If a user has new information or witnesses about an incident, they can provide it by filling out a form on the detailed information page. The device sends the information to the server, which stores it in an internal database. The server then filters the information and, if necessary, notifies the police or other relevant authorities.

[0895] Specific examples

[0896] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the information would be processed in the following manner:

[0897] 1. The server collects and filters relevant information from news sites and police public information databases.

[0898] 2. Generate filtered data: The AI ​​module analyzes the data and automatically generates an outline of the incident, witness information, and details of the evidence.

[0899] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[0900] 4. The user clicks on the banner to access the details page and view more information about the incident.

[0901] 5. The user enters any new information or sightings they have into the form, and the device sends the information to the server.

[0902] 6. The server stores the new information in a database and notifies relevant authorities as necessary.

[0903] In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues for solving the cases.

[0904] The processing flow will be explained below.

[0905] Step 1:

[0906] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[0907] Step 2:

[0908] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[0909] Step 3:

[0910] The server converts the filtered data into JSON format for providing to the generation AI. The converted data is passed to the generation AI module.

[0911] Step 4:

[0912] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[0913] Step 5:

[0914] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[0915] Step 6:

[0916] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[0917] Step 7:

[0918] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[0919] Step 8:

[0920] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[0921] Step 9:

[0922] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[0923] Step 10:

[0924] The terminal transmits new information and sightings entered by the user to the server.

[0925] Step 11:

[0926] The server receives the information and stores it in an internal database, where it filters the information and prepares to notify the relevant authorities.

[0927] Step 12:

[0928] The server will then report any new information collected to police and other relevant agencies as needed, which can aid in the investigation of unsolved cases.

[0929] In this way, the system of the present invention can effectively collect, analyze, and display information about unsolved cases through a series of processing steps, and efficiently provide new clues.

[0930] Example 1

[0931] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0932] The objective of this study is to solve the lack of a means to efficiently collect information on past unsolved cases, disseminate it widely, and obtain new clues. There is also a need for a method to quickly and accurately analyze the collected information and convert it into a display format.

[0933] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0934] In this invention, the server includes means for periodically collecting data on past unsolved cases, means for filtering the collected data and removing duplicate and irrelevant information, means for analyzing the filtered data and using a generative AI model to generate an outline of the unsolved case, details of the parties involved, and details of evidence, means for formatting the generated information into a banner and displaying it on an online information platform, means for collecting additional information from users and storing the collected information in an internal database, and means for reporting the collected additional information to relevant authorities as needed. This makes it possible to efficiently collect and widely disseminate information on unsolved cases and quickly obtain new clues.

[0935] "Methods of periodically collecting data on past unsolved cases" refers to crawling police public information databases and news sites at specific time intervals to collect information related to unsolved cases.

[0936] "Means of filtering collected data and removing duplicate or irrelevant information" refers to the process of removing duplicate information or information that is not relevant to the incident from collected data in order to improve accuracy.

[0937] "Using a generative AI model to analyze filtered data and generate a summary of the unsolved case, details of the people involved, and evidence" refers to a method of analyzing filtered data using an artificial intelligence model (e.g., a generative model) to automatically generate key elements of the case.

[0938] "Means for formatting the generated information into a banner format and displaying it on an information platform on the Internet" refers to the process of converting the generated text data into an easy-to-read banner format and displaying it on news sites, etc. on the Internet.

[0939] "Means for collecting additional information from users and storing that information in an internal database" refers to the internal systems used to receive and store new information provided by users.

[0940] "Means of reporting any additional information collected to relevant authorities as necessary" refers to the means by which information collected from users is deemed useful and is then notified to the police or relevant authorities.

[0941] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating that information to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[0942] Data Collection Module

[0943] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). The server uses web crawling libraries such as Python's BeautifulSoup or Scrapy to collect information related to unsolved cases. The collected data is stored in a relational database such as MySQL or PostgreSQL. The server then filters out duplicates and irrelevant information from the collected data. Natural language processing techniques can be used in this filtering process.

[0944] Data Analysis and Generation Module

[0945] The server provides the filtered data to the generation AI (e.g., GPT-4). Examples of specific prompts include:

[0946] "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please include location, time, and any witness information."

[0947] The AI ​​analyzes the data based on this prompt and generates text information including an overview of the incident, the people involved, and details of the evidence. The generated text data is then stored in the internal database by the server.

[0948] Information Display Module

[0949] The server formats the information into a banner based on the text data stored in its internal database. The formatting involves converting it into an easy-to-read format using HTML and CSS. The formatted banner is then displayed on Yahoo! News and other online information platforms. This process generates a banner with the message "Robbery occurred in City A in July 2023: Please provide witness information," which is displayed at the specified time.

[0950] User Interface

[0951] When users browse Yahoo! News on their devices (PCs, smartphones, etc.), they can see an overview of unsolved cases in a banner. If an interested user clicks on the banner, they are taken to a detailed information page, which provides more detailed information about the case. If a user has new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device then sends the entered information to the server, which stores the received information in an internal database and, if necessary, reports it to relevant authorities.

[0952] Specific examples

[0953] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the process would be as follows: The server collects and filters relevant information from news sites and the police's public information database. The filtered data is provided to a generation AI, which automatically generates a summary of the incident, witness information, and details of the evidence. The generated text data is formatted and sent to the Yahoo! News management system. The user clicks on the banner to access the detailed information page and view detailed information about the incident. The user enters any new information or witness information they have in a form, and the device sends the information to the server. The server saves the new information in a database and, if necessary, notifies relevant authorities. In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues to solve them.

[0954] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0955] Step 1:

[0956] The server crawls news sites and police public information databases at specific intervals (e.g., 12 noon every day). The server extracts the necessary text data from web pages using Python's BeautifulSoup or Scrapy. As input, it receives a list of URLs from news sites and police public information databases, and as output, it obtains text data about unsolved cases collected from each web page.

[0957] Step 2:

[0958] The server stores the collected data in a relational database (e.g., MySQL or PostgreSQL). Before storing, it performs a filtering process to remove duplicate and irrelevant information. Specifically, it uses natural language processing technology to evaluate the similarity of text and remove duplicate data. It receives the collected raw data as input and stores the filtered, highly accurate data as output in the database.

[0959] Step 3:

[0960] The server provides the filtered data to the generation AI (e.g., GPT-4). When providing the data, it gives instructions to the AI ​​using a specific prompt. For example, the prompt might be, "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please organize it, including the location, time, and witness information." The server receives the filtered data and the prompt as input, and outputs text data containing a summary of the incident, details of the people involved, and details of the evidence.

[0961] Step 4:

[0962] The server stores the text data generated by the AI ​​in an internal database. At the same time, it formats the text data into a banner format that is easy for users to view. This formatting involves format conversion using HTML and CSS. The server receives the generated text data as input and obtains formatted banner data as output.

[0963] Step 5:

[0964] The server sends the formatted banner data to an information platform on the Internet (e.g., a news site). Specifically, it posts the banner data to the platform using a specific API endpoint and sets it to be displayed at a specified time. It receives the formatted banner data as input and displays the banner on the Internet platform as output.

[0965] Step 6:

[0966] A user is browsing a news site on their device and notices a banner that appears. When the user clicks on the banner, it takes them to a details page, which contains more detailed information about the incident. The input is an action to click on the banner, and the output is the details page.

[0967] Step 7:

[0968] The user enters new information or witnesses about the incident on the details page. The input form contains fields for describing the information and specific witnesses. The input takes the new information provided by the user and the output sends the input data for further processing.

[0969] Step 8:

[0970] The terminal sends the entered user information to the server, using the HTTPS protocol for secure data transfer, receiving the user's new information as input and sending the data to the server as output.

[0971] Step 9:

[0972] The server then filters the received user information again and stores it in an internal database. This filtering process can use natural language processing techniques to remove spam data and redundant information. It takes the information received from the user as input and stores the filtered information in an internal database as output.

[0973] Step 10:

[0974] The server then reports newly collected information to relevant authorities as needed, for example, by providing information to police or investigative agencies via email or API. It receives filtered critical information as input and reports the information to relevant authorities as output.

[0975] (Application example 1)

[0976] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0977] Existing information gathering systems for unsolved cases lack the means to efficiently collect information on past cases, analyze that information, and disseminate it widely. This makes it difficult to gather new clues or additional information from users. Furthermore, the methods for visually displaying the acquired information are limited, making it difficult to attract users' attention. Furthermore, since AI generation is not utilized when generating information on unsolved cases, the accuracy and usefulness of the information cannot be guaranteed.

[0978] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0979] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the parties involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users using a user interface, and means for generating prompt sentences using a generative AI model for information collection. This makes it possible to efficiently collect and analyze information on past unsolved cases and visually display it to gather new clues from users.

[0980] "Unsolved cases" are crimes that occurred in the past and have not been solved to date.

[0981] "Means of collecting data" are means of obtaining information about the incident from specific sources, such as news sites or police public information databases.

[0982] "Means for analyzing data" refers to the means for processing and analyzing collected information and organizing the details of the case, the people involved, and the evidence.

[0983] "Means for generating prompt sentences using a generative AI model" means means for using generative AI to generate summaries or summaries related to an incident from collected data.

[0984] The "means for converting into a display format" refers to a means for converting the generated information into a format that is easy for the user to view, specifically, a banner format or the like.

[0985] An "information platform" refers to a collection of websites and applications that provide information on the Internet.

[0986] A "user interface" is the means by which a user interacts with a system, specifically referring to devices and screens such as PCs and smartphones.

[0987] "Means for collecting additional information from the user" refers to forms or application features that allow users to enter new information, witness statements, etc. into the system.

[0988] "Internal Database" means a data storage device for storing and managing collected information and additional information provided by the User.

[0989] "Related agencies" are public or private agencies involved in resolving the case, such as the police or investigative agencies.

[0990] The present invention is a system for efficiently collecting information about unsolved cases, analyzing, generating, and displaying it using a generative AI model, and collecting additional information from users. Specific embodiments of the present invention are described below.

[0991] System configuration

[0992] This system consists of the following components:

[0993] 1. Data collection module (server)

[0994] 2. Data analysis and generation module (generative AI server)

[0995] 3. Information display module (server)

[0996] 4. User Interface (Terminal / User)

[0997] Data Collection Module

[0998] The server crawls news sites and public police information databases at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting information about unsolved cases that occurred in a specific city, text data from news and public police information is obtained and stored in a database.

[0999] Data Analysis and Generation Module

[1000] The server provides the filtered data to the generation AI, which analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in a specific city in a specific year, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[1001] Example prompt

[1002] Here are some examples of prompts for generative AI models:

[1003] Please summarize the following incident information:

[1004] Title: Robbery in a specific city

[1005] Date: 2023-07-15

[1006] Details: Two men robbed a bank in the center of a certain city. According to witnesses, the culprits were wearing black clothes and fled after stealing about 1 million yen in cash.

[1007] Information Display Module

[1008] The server uses the text data stored in the internal database to format the information in a way that is easy for users to view. In particular, it converts it into a banner format for news sites. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery occurred in a specific city in a specific year: Please provide witness information." This banner information is sent to the news site's management system and displayed at a specified time.

[1009] User Interface

[1010] When users browse a news site on their device (PC, smartphone, etc.), they can see an overview of an unsolved case in a banner. Interested users can click on the banner to go to the detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, notifies the police or relevant agencies.

[1011] Hardware and Software Use

[1012] The system uses the following hardware and software:

[1013] Hardware: High-performance servers are used for data collection, analysis, generation, and display. Users use devices such as PCs and smartphones.

[1014] Software: OpenAI generative AI models are used for data analysis and generation. Web scraping libraries such as BeautifulSoup and requests are used for data collection. Database management systems (e.g., MySQL) are used for data storage and processing.

[1015] In this way, information on past unsolved cases can be efficiently collected, analyzed, and visually displayed, allowing users to gather new clues.

[1016] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1017] Step 1:

[1018] The server crawls news websites and police public information databases at specific time intervals. The input is the URLs of news websites and police databases, and the output is text data related to unsolved cases. The server stores the collected data in a database and filters out duplicate and irrelevant information.

[1019] Step 2:

[1020] The server analyzes the filtered data. The input for this analysis is the filtered case data, and the output is information such as an overview of the analyzed unsolved case, the people involved, and details of the evidence. The server uses a generative AI model to generate prompt sentences, which are then used to generate case information in text format.

[1021] Step 3:

[1022] The server creates banner-style display data based on the generated incident information. The input is a summary of the generated incident, and the output is visually organized banner-style data. This generated banner information is sent to an information platform on the Internet and displayed in a format that can be viewed by users.

[1023] Step 4:

[1024] A user at a terminal clicks on the banner to go to the detailed information page. The input is the user's click action, and the output is the display of the detailed information page, where the user can view more detailed information about the incident.

[1025] Step 5:

[1026] Users enter new information about the incident or witnesses using a form on the detailed information page. The input is the new information provided by the user, and the output is the transmission of the entered information to the server.

[1027] Step 6:

[1028] The server receives new information sent by the user and stores it in an internal database. The input is the new information provided by the user and the output is the information stored in the database. The server filters the new information and notifies the police or relevant authorities if necessary.

[1029] Step 7:

[1030] The server uses a generative AI model to create prompt sentences for automatically generating information. The input is the collected and filtered incident data, and the output is the prompt sentences to be input into the generative AI model.

[1031] Step 8:

[1032] The generative AI model automatically generates a summary and details of the case based on the prompt. The input is the prompt, and the output is the analyzed case information. This information is stored in a database on the server and used in the next step.

[1033] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1034] The present invention is a system for obtaining new clues by effectively collecting and disseminating information about past unsolved cases, and by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided are improved. Specific embodiments of the present invention are described below.

[1035] System configuration

[1036] The system consists of the following components:

[1037] 1. Data collection module (server)

[1038] 2. Data analysis and generation module (generative AI server)

[1039] 3. Information display module (server)

[1040] 4. User Interface (Terminal / User)

[1041] 5. Emotion engine (server)

[1042] Data Collection Module

[1043] The server periodically (for example, every day at midnight) crawls the police public information database and news sites on the Internet to collect data related to unsolved cases. The collected data is temporarily stored in a database, and duplicates and irrelevant information are filtered out. For example, a procedure may be taken to collect the latest information on unsolved theft cases that occurred in City B.

[1044] Data Analysis and Generation Module

[1045] The server converts the filtered data into JSON format to provide it to the generative AI module, which then analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generated text data is stored in an internal database.

[1046] Information Display Module

[1047] The server generates a concise summary of the information from the text data stored in the internal database and formats it into an HTML banner, which is then sent to the Yahoo! News management system and displayed at the specified time.

[1048] User Interface

[1049] When users browse Yahoo! News on their device (PC, smartphone, etc.), an overview of an unsolved case is displayed as a banner. Interested users can click on the banner to go to a detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, reports it to the police or relevant agencies.

[1050] Adding an Emotion Engine

[1051] In the present invention, the emotion engine is utilized when the user provides information or browses detailed information. Specifically, the following processes are added:

[1052] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[1053] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[1054] 3. The server prioritizes the provided information based on the emotional data and immediately notifies the police or relevant agencies if necessary.

[1055] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[1056] Specific examples

[1057] For example, in the case of an unsolved theft that occurred in City B in July 2023, the system would operate as follows:

[1058] 1. The server collects and filters information about the incident from news sites and police public information databases.

[1059] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[1060] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[1061] 4. The user clicks on the banner to access the details page and view further details about the incident.

[1062] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[1063] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[1064] In this way, the present invention can enhance the effectiveness of gathering and disseminating information about unsolved cases by combining an emotion engine.

[1065] The processing flow will be explained below.

[1066] Step 1:

[1067] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[1068] Step 2:

[1069] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[1070] Step 3:

[1071] The server converts the filtered data into JSON format to provide it to the generation AI module. The converted data is then passed to the generation AI module.

[1072] Step 4:

[1073] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[1074] Step 5:

[1075] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[1076] Step 6:

[1077] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[1078] Step 7:

[1079] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[1080] Step 8:

[1081] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[1082] Step 9:

[1083] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[1084] Step 10:

[1085] The emotion engine analyzes the text and voice data entered by the user into the form in real time to recognize the user's emotional state.

[1086] Step 11:

[1087] The server evaluates the credibility of the information provided by the user based on the emotion data provided by the emotion engine.

[1088] Step 12:

[1089] The device sends the input information and emotion data from the user to the server, which stores the information in its internal database.

[1090] Step 13:

[1091] The server evaluates the credibility and urgency of the information received and notifies the police or relevant authorities if necessary.

[1092] Step 14:

[1093] An emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state, for example, providing encouraging messages and engaging information if the user is feeling anxious.

[1094] In this way, the system of the present invention, by combining an emotion engine, can effectively collect information on unsolved cases and efficiently provide new clues.

[1095] Example 2

[1096] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1097] Currently, information on unsolved cases is collected and disseminated, but there is a lack of a system for evaluating the credibility and urgency of that information. As a result, collected information may not be reliably reported to relevant agencies promptly. Furthermore, since it is difficult to determine whether the provided information is true, there is a problem of low accuracy in investigations. The present invention aims to solve these problems and improve the accuracy and efficiency of information collection and dissemination of past unsolved cases.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1099] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data to generate an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an information providing platform on the Internet, means for collecting additional information from users, means for analyzing user sentiment and evaluating the credibility and urgency of the provided information, and means for reporting the evaluated information to relevant authorities. This makes it possible to evaluate the credibility and urgency of the collected information and efficiently report it to relevant authorities.

[1100] "Past unsolved cases" refer to criminal cases that have not been solved within a certain period of time and are still under investigation.

[1101] "Data Collection Methods" refers to software and hardware features that automatically retrieve certain information from sources on the Internet.

[1102] "Means for analyzing data and generating details of open cases, people involved, and evidence" refers to the function of automatically extracting and organizing details of the case, people involved, and evidence based on collected information.

[1103] "Means for converting the generated information into a display format and displaying it on an information platform on the Internet" refers to the function of formatting the generated text and data into a visually easy-to-read format and making it available through a website or application.

[1104] "Means for collecting additional information from the user" refers to input forms and related system features that receive and store new information provided by the user.

[1105] "Means of analyzing the user's emotions and evaluating the credibility and urgency of the information provided" refers to a function that analyzes text, voice, etc. from information provided by the user and determines their emotional state.

[1106] "Means of reporting evaluated information to relevant agencies" refers to the function of promptly notifying appropriate agencies, such as the police, of information that is deemed to be highly credible or urgent.

[1107] "Means of converting into a display format" refers to the function of converting data into a form that is visually easy for users to understand (for example, HTML or banner ads).

[1108] The present invention provides a system for effectively collecting and disseminating information about past unsolved cases. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided can be improved. Specific embodiments of the present invention are described below.

[1109] System configuration

[1110] The system consists of the following components:

[1111] 1. Data collection module (server)

[1112] 2. Data analysis and generation module (generative AI server)

[1113] 3. Information display module (server)

[1114] 4. User Interface (Terminal / User)

[1115] 5. Emotion engine (server)

[1116] Data Collection Module

[1117] The server periodically (e.g., every day at midnight) crawls public police information databases and news sites on the Internet to collect data related to unsolved cases. The collected data is then temporarily stored in a database, where duplicates and irrelevant information are filtered out. This crawling is performed using web crawler software (e.g., Scrapy). For example, the procedure is to collect the latest information on unsolved theft cases that have occurred in a particular city. A natural language processing library (e.g., NLTK) is used for filtering.

[1118] Data Analysis and Generation Module

[1119] The server converts the filtered data into JSON format to provide it to the generative AI module. This conversion is performed using the Python json library. The generative AI module analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generation is performed using a generative AI model (e.g., GPT-4). The generated text data is stored in an internal database.

[1120] Information Display Module

[1121] The server generates concise information based on the text data stored in the internal database and formats it into a banner-style HTML. This HTML is generated using the Django template engine. The formatted banner information is sent to the management system of an Internet news site (e.g., Yahoo! News) and displayed at the specified time.

[1122] User Interface

[1123] Users browse a news site on their device (e.g., PC or smartphone) and see a banner with an overview of the unsolved case. Interested users can click on the banner to go to a detailed information page, where more detailed information about the case is provided using a JavaScript framework (e.g., React).

[1124] If users have any sightings or other additional information, they can provide it by filling out a form on the details page. The input from this form is sent from the device to the server, and the received information is stored in an internal database. The input information is filtered and, if necessary, reported to the relevant authorities (e.g., police).

[1125] Adding an Emotion Engine

[1126] In this invention, the emotion engine is utilized when users provide information or view detailed information. The specific process is as follows:

[1127] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[1128] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[1129] 3. The server prioritizes the provided information based on the emotion data and immediately notifies relevant authorities if necessary.

[1130] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[1131] Specific examples

[1132] For example, given an unsolved theft case that occurred in 2023 in a particular city, the system would operate as follows:

[1133] 1. The server collects and filters information about the incident from news sites and police public information databases.

[1134] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[1135] 3. The server formats the generated text data into a banner and sends it to the news site's management system.

[1136] 4. The user clicks on the banner to access the details page and view further details about the incident.

[1137] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[1138] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[1139] Example prompts for generative AI models

[1140] "Generate text based on up-to-date information about unsolved thefts that occurred in a specific city in 2023, including a summary of the case, details of the people involved, and evidence."

[1141] In this way, the present invention enables the collection and dissemination of information on unsolved cases, and improves the accuracy of information through sentiment analysis.

[1142] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1143] Step 1:

[1144] The server starts collecting information.

[1145] Input: The crawl time set in the scheduler.

[1146] Output: Launch of crawl task.

[1147] Specific operation: Every day at midnight, the server's scheduler executes a crawl task to collect data from police public information databases and news sites on the Internet.

[1148] Step 2:

[1149] The server performs the crawl.

[1150] Input: The specified URL list.

[1151] Output: Collected data on unsolved cases.

[1152] What it does: Web crawler software (e.g., Scrapy) on the server accesses the specified URL, retrieves information related to the unsolved case, and stores it in a database.

[1153] Step 3:

[1154] The server filters the collected data.

[1155] Input: Collected cold case data.

[1156] Output: The filtered data.

[1157] What it does: Uses a natural language processing library (e.g., NLTK) to remove duplicate and irrelevant information and generate filtered data.

[1158] Step 4:

[1159] The server converts the data into JSON format.

[1160] Input: Filtered data.

[1161] Output: JSON formatted data.

[1162] Specific operation: Using Python's json library, the filtered data is converted into JSON format and passed to the generative AI module.

[1163] Step 5:

[1164] The generative AI module analyzes and generates data.

[1165] Input: JSON formatted data.

[1166] Output: Text data containing details of the incident, the people involved, and the evidence.

[1167] How it works: A generative AI model (e.g., GPT-4) generates prompt text based on the received JSON data, automatically generating a summary of the incident, details of the people involved, and details of the evidence.

[1168] Step 6:

[1169] The server formats the text into HTML.

[1170] Input: Text data generated by the generative AI module.

[1171] Output: Banner information in HTML format.

[1172] Specific behavior: Uses the Django template engine to format the generated text data into banner-style HTML.

[1173] Step 7:

[1174] The server distributes the information.

[1175] Input: Banner information in HTML format.

[1176] Output: A banner that appears on news sites on the Internet.

[1177] Specific operation: The generated banner information is sent to the news site's management system and displayed at the specified time.

[1178] Step 8:

[1179] A user browses the news.

[1180] Input: A banner displayed on a news site.

[1181] Output: Access to the more information page.

[1182] What happens: A user clicks on the banner on their device and is taken to a details page where they can view more information about the incident.

[1183] Step 9:

[1184] The user provides the information.

[1185] Input: Information entered into the form on the details page.

[1186] Output: Provided sighting and / or additional information.

[1187] Specific actions: The user enters sighting details and additional information in the form on the detailed information page and presses the submit button.

[1188] Step 10:

[1189] The terminal transmits the information.

[1190] Input: Information entered by the user.

[1191] Output: Information sent to the server.

[1192] Specific operation: Input information is sent from the terminal to the server, and the server receives it.

[1193] Step 11:

[1194] The server receives and stores the information.

[1195] Input: Information sent from the device.

[1196] Output: Information stored in an internal database.

[1197] Specific operation: The server stores the received information in a database, and prepares filtering and notification as necessary.

[1198] Step 12:

[1199] The server runs the emotion engine.

[1200] Input: Information submitted by the user.

[1201] Output: Emotion data.

[1202] Specific operation: Calls the emotion engine, analyzes the user's text and voice input, and generates emotion data.

[1203] Step 13:

[1204] The emotion engine analyzes emotions.

[1205] Input: User-provided information.

[1206] Output: Parsed emotion data.

[1207] Specific operation: The emotion engine uses natural language processing and voice emotion recognition technology to recognize the user's emotional state.

[1208] Step 14:

[1209] The server sets the priority of the information.

[1210] Input: Emotion data.

[1211] Output: Information priority.

[1212] Specific operation: The server evaluates the credibility and urgency of information based on emotional data and sets a priority.

[1213] Step 15:

[1214] The server notifies the relevant authorities.

[1215] Input: Prioritized information.

[1216] Output: Notification sent to relevant authorities.

[1217] Specific operation: The server notifies the appropriate authorities, such as the police, of high-priority information.

[1218] (Application example 2)

[1219] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1220] The challenge is to improve the efficiency of collecting and disseminating information about unsolved cases, as well as to increase the credibility of the information provided. Specifically, a system is needed that can notify passengers and drivers of autonomous vehicles of information about unsolved cases in real time, accurately collect eyewitness reports from them, and evaluate their credibility using an emotion analysis engine.

[1221] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1222] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users, means for obtaining current vehicle location information and displaying case information in real time, means for analyzing user emotions and evaluating the credibility of the information based on the emotion data, and means for reporting the information to relevant authorities as needed based on the evaluation. This makes it possible to efficiently collect information on unsolved cases and quickly report credible information to relevant authorities.

[1223] "Data collection means" refers to a device or system that has the function of collecting data related to past unsolved cases from the Internet.

[1224] "Data analysis means" means a device or system capable of analyzing collected data and generating a summary of an unsolved case, details of the parties involved, and details of evidence.

[1225] The "display conversion means" is a device or system that has the function of converting the generated information into a display format and displaying it on an information providing platform on the Internet.

[1226] An "additional information collection means" is a device or system that has the function of collecting new information from users.

[1227] The "location information acquisition means" is a device or system that has the function of acquiring information about the current location of a vehicle.

[1228] "Real-time display means" refers to a device or system that has the function of displaying incident information in real time based on the current location information of the vehicle.

[1229] The "emotion analysis means" is a device or system that has the function of analyzing the user's emotions and evaluating the credibility of information based on the emotion data.

[1230] "Automatic reporting means" refers to a device or system that has the function of automatically reporting necessary information to relevant institutions based on the evaluation results based on emotion analysis.

[1231] The present invention provides a system for efficiently collecting information on unsolved cases, evaluating the credibility of information based on eyewitness reports from users, and reporting the information to relevant authorities as necessary. Specific embodiments of the system are described below.

[1232] System Configuration

[1233] The system consists of the following components:

[1234] 1. Data collection method (server)

[1235] The server collects data on past unsolved cases from the Internet. Specifically, it crawls police public information databases and news sites to collect data on unsolved cases. The collected data is then temporarily stored in a database.

[1236] 2. Data analysis method (server)

[1237] The server analyzes the collected data and automatically generates an outline of the incident, details of the people involved, and details of the evidence using a generative AI model. The generated text data is stored in an internal database.

[1238] 3. Display conversion means (server)

[1239] The server converts the generated information into a display format and displays it on an information platform on the Internet. Specifically, it formats the generated text data into HTML banners and sends them to news sites.

[1240] 4. Additional information collection methods (devices, users)

[1241] Users can access the information platform on their own devices (such as smartphones) and check information on unsolved cases. A form is provided for interested users to provide additional information about the case, allowing users to enter witness accounts, etc. The device sends the entered information to the server, which then stores the received information in an internal database.

[1242] 5. Location information acquisition method (vehicle)

[1243] Vehicles are equipped with a device that acquires their current location information. The server constantly receives this location information and processes it in real time.

[1244] 6. Real-time display means (vehicle, terminal)

[1245] The server displays information related to unsolved cases in real time on the vehicle's or device's display based on the vehicle's current location information. For example, when a vehicle passes near the scene of a particular unsolved case, information about that case is displayed on the display.

[1246] 7. Emotion analysis means (server)

[1247] The server uses an emotion engine to analyze the user's emotions. When the user fills in the additional information form, the emotion analysis engine analyzes the input and determines the user's emotional state.

[1248] 8. Automatic reporting means (server)

[1249] Based on the results of the sentiment analysis, the credibility of the information provided is evaluated and, if necessary, the relevant authorities are notified. The server immediately notifies the police and relevant authorities of this information, facilitating a prompt response.

[1250] Hardware and software used

[1251] Hardware:

[1252] Server: Used for data collection, analysis, display conversion, sentiment analysis, and automatic reporting.

[1253] Vehicle location information acquisition device: Knows the current location of the vehicle in real time.

[1254] Devices (smartphone, vehicle display): View information, enter additional information.

[1255] software:

[1256] Generative AI model: Used to automatically generate incident information.

[1257] EmotionRecognition module: Used to analyze user emotions.

[1258] VehicleAPI: Used to obtain and display the vehicle's current location information.

[1259] Requests library: Handles HTTP requests and communicates with external APIs.

[1260] Specific examples

[1261] For example, in the case of an unsolved theft case that occurred in City B, the system operates as follows: The server collects information about the case from news sites and the police's public information database, and automatically generates details about the case using a generative AI model. The generated information is converted into banner format and displayed on the news site. When a user provides eyewitness information, the emotion engine analyzes the emotion and evaluates its credibility. Based on the evaluation results, the necessary information is immediately reported to the relevant authorities. This process enables information gathering and rapid response to unsolved cases.

[1262] Prompt Sentence Examples

[1263] "Develop an application that can collect information about unsolved cases, notify vehicles, and provide witness reports. The application will evaluate the credibility of users' witness reports using an emotion engine, and automatically notify the police and relevant agencies. The application will work in conjunction with autonomous vehicles, displaying information on the vehicle's display in real time."

[1264] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1265] Step 1:

[1266] The server collects data on past unsolved cases from public police information databases and news sites on the Internet. The input is the URL of the public police information database or news site, and the output is the collected case data. During the data collection process, the server uses a web crawler to periodically check these sites to obtain new data.

[1267] Step 2:

[1268] The server analyzes the collected data to generate a summary of the unsolved case, details of the people involved, and details of the evidence. The input is the collected case data, and the output is detailed information about the analyzed case. This analysis uses a generative AI model to analyze the input data using natural language processing (NLP) technology, automatically generating text that describes the case.

[1269] Step 3:

[1270] The server converts the generated detailed information into a display format. The input is the analyzed incident details, and the output is HTML data formatted for display. The server formats the generated text data into HTML banners and sends them to an information platform on the Internet.

[1271] Step 4:

[1272] Users can browse the information platform on their own devices (smartphones) and check information on unsolved cases. By clicking on the displayed banner, the device will be taken to a detailed information page, where a form will be displayed for users to provide further information about the case.

[1273] Step 5:

[1274] The user provides information about the sighting and other additional information. The input is the information entered by the user, and the output is the information sent to the server. The device sends the information entered by the user in the form to the server using an HTTP request.

[1275] Step 6:

[1276] The server receives information provided by the user and analyzes their emotional state. The input is the user-provided witness information and text data, and the output is the result of the emotion analysis engine. Emotion analysis is performed using the EmotionRecognition module, which identifies emotions from the user's input.

[1277] Step 7:

[1278] The server evaluates the credibility of the information based on the results of sentiment analysis. The inputs are the results of sentiment analysis and witness information, and the output is the evaluation result. Based on this evaluation result, the credibility and urgency of the provided information are judged.

[1279] Step 8:

[1280] The server will report to the relevant authorities as necessary based on the evaluation results. The input is the information whose credibility has been evaluated, and the output is the report to the relevant authorities. The server automatically notifies the police and other relevant authorities of information with a high level of importance.

[1281] Step 9:

[1282] The server obtains the vehicle's current location information and displays relevant information about unsolved cases on the vehicle's display in real time. The input is the vehicle's location information, and the output is the case information to be displayed. The server uses VehicleAPI to obtain the vehicle's current location and displays case information in real time based on that information.

[1283] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1284] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1285] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1286] [Fourth embodiment]

[1287] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1288] 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.

[1289] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[1290] 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.

[1291] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1292] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1293] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1294] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1295] 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.

[1296] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1297] 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.

[1298] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1299] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1300] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating it to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[1301] System configuration

[1302] This system mainly consists of the following four components:

[1303] 1. Data collection module (server)

[1304] 2. Data analysis and generation module (generative AI server)

[1305] 3. Information display module (server)

[1306] 4. User Interface (Terminal / User)

[1307] Data Collection Module

[1308] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting the latest information on unsolved robberies that occurred in City A, text data from news and public police information is obtained and stored in a database.

[1309] Data Analysis and Generation Module

[1310] The server provides the filtered data to the generation AI. The generation AI analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in City A in July 2023, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[1311] Information Display Module

[1312] The server formats the information based on the text data stored in the internal database into a format that is easy for users to view. In particular, it converts it into the Yahoo! News banner format. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery that occurred in City A in July 2023: Please provide witness information." This banner information is sent to the Yahoo! News management system and displayed at a specified time.

[1313] User Interface

[1314] When users browse Yahoo! News on their devices (PC, smartphone, etc.), they can see an overview of the unsolved case in a banner. If they are interested, they can click on the banner and be taken to a detailed information page, where they can find more detailed information about the case.

[1315] If a user has new information or witnesses about an incident, they can provide it by filling out a form on the detailed information page. The device sends the information to the server, which stores it in an internal database. The server then filters the information and, if necessary, notifies the police or other relevant authorities.

[1316] Specific examples

[1317] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the information would be processed in the following manner:

[1318] 1. The server collects and filters relevant information from news sites and police public information databases.

[1319] 2. Generate filtered data: The AI ​​module analyzes the data and automatically generates an outline of the incident, witness information, and details of the evidence.

[1320] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[1321] 4. The user clicks on the banner to access the details page and view more information about the incident.

[1322] 5. The user enters any new information or sightings they have into the form, and the device sends the information to the server.

[1323] 6. The server stores the new information in a database and notifies relevant authorities as necessary.

[1324] In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues for solving the cases.

[1325] The processing flow will be explained below.

[1326] Step 1:

[1327] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[1328] Step 2:

[1329] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[1330] Step 3:

[1331] The server converts the filtered data into JSON format for providing to the generation AI. The converted data is passed to the generation AI module.

[1332] Step 4:

[1333] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[1334] Step 5:

[1335] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[1336] Step 6:

[1337] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[1338] Step 7:

[1339] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[1340] Step 8:

[1341] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[1342] Step 9:

[1343] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[1344] Step 10:

[1345] The terminal transmits new information and sightings entered by the user to the server.

[1346] Step 11:

[1347] The server receives the information and stores it in an internal database, where it filters the information and prepares to notify the relevant authorities.

[1348] Step 12:

[1349] The server will then report any new information collected to police and other relevant agencies as needed, which can aid in the investigation of unsolved cases.

[1350] In this way, the system of the present invention can effectively collect, analyze, and display information about unsolved cases through a series of processing steps, and efficiently provide new clues.

[1351] Example 1

[1352] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1353] The objective of this study is to solve the lack of a means to efficiently collect information on past unsolved cases, disseminate it widely, and obtain new clues. There is also a need for a method to quickly and accurately analyze the collected information and convert it into a display format.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1355] In this invention, the server includes means for periodically collecting data on past unsolved cases, means for filtering the collected data and removing duplicate and irrelevant information, means for analyzing the filtered data and using a generative AI model to generate an outline of the unsolved case, details of the parties involved, and details of evidence, means for formatting the generated information into a banner and displaying it on an online information platform, means for collecting additional information from users and storing the collected information in an internal database, and means for reporting the collected additional information to relevant authorities as needed. This makes it possible to efficiently collect and widely disseminate information on unsolved cases and quickly obtain new clues.

[1356] "Methods of periodically collecting data on past unsolved cases" refers to crawling police public information databases and news sites at specific time intervals to collect information related to unsolved cases.

[1357] "Means of filtering collected data and removing duplicate or irrelevant information" refers to the process of removing duplicate information or information that is not relevant to the incident from collected data in order to improve accuracy.

[1358] "Using a generative AI model to analyze filtered data and generate a summary of the unsolved case, details of the people involved, and evidence" refers to a method of analyzing filtered data using an artificial intelligence model (e.g., a generative model) to automatically generate key elements of the case.

[1359] "Means for formatting the generated information into a banner format and displaying it on an information platform on the Internet" refers to the process of converting the generated text data into an easy-to-read banner format and displaying it on news sites, etc. on the Internet.

[1360] "Means for collecting additional information from users and storing that information in an internal database" refers to the internal systems used to receive and store new information provided by users.

[1361] "Means of reporting any additional information collected to relevant authorities as necessary" refers to the means by which information collected from users is deemed useful and is then notified to the police or relevant authorities.

[1362] The present invention provides a system for efficiently collecting information about past unsolved cases and widely disseminating that information to obtain new clues for solving the cases. Specific embodiments of the system are described below.

[1363] Data Collection Module

[1364] The server crawls police public information databases and news sites at specific time intervals (e.g., 12 noon every day). The server uses web crawling libraries such as Python's BeautifulSoup or Scrapy to collect information related to unsolved cases. The collected data is stored in a relational database such as MySQL or PostgreSQL. The server then filters out duplicates and irrelevant information from the collected data. Natural language processing techniques can be used in this filtering process.

[1365] Data Analysis and Generation Module

[1366] The server provides the filtered data to the generation AI (e.g., GPT-4). Examples of specific prompts include:

[1367] "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please include location, time, and any witness information."

[1368] The AI ​​analyzes the data based on this prompt and generates text information including an overview of the incident, the people involved, and details of the evidence. The generated text data is then stored in the internal database by the server.

[1369] Information Display Module

[1370] The server formats the information into a banner based on the text data stored in its internal database. The formatting involves converting it into an easy-to-read format using HTML and CSS. The formatted banner is then displayed on Yahoo! News and other online information platforms. This process generates a banner with the message "Robbery occurred in City A in July 2023: Please provide witness information," which is displayed at the specified time.

[1371] User Interface

[1372] When users browse Yahoo! News on their devices (PCs, smartphones, etc.), they can see an overview of unsolved cases in a banner. If an interested user clicks on the banner, they are taken to a detailed information page, which provides more detailed information about the case. If a user has new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device then sends the entered information to the server, which stores the received information in an internal database and, if necessary, reports it to relevant authorities.

[1373] Specific examples

[1374] For example, in the case of an unsolved robbery that occurred in City A in July 2023, the process would be as follows: The server collects and filters relevant information from news sites and the police's public information database. The filtered data is provided to a generation AI, which automatically generates a summary of the incident, witness information, and details of the evidence. The generated text data is formatted and sent to the Yahoo! News management system. The user clicks on the banner to access the detailed information page and view detailed information about the incident. The user enters any new information or witness information they have in a form, and the device sends the information to the server. The server saves the new information in a database and, if necessary, notifies relevant authorities. In this way, the present invention can widely disseminate information about unsolved cases and effectively gather new clues to solve them.

[1375] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1376] Step 1:

[1377] The server crawls news sites and police public information databases at specific intervals (e.g., 12 noon every day). The server extracts the necessary text data from web pages using Python's BeautifulSoup or Scrapy. As input, it receives a list of URLs from news sites and police public information databases, and as output, it obtains text data about unsolved cases collected from each web page.

[1378] Step 2:

[1379] The server stores the collected data in a relational database (e.g., MySQL or PostgreSQL). Before storing, it performs a filtering process to remove duplicate and irrelevant information. Specifically, it uses natural language processing technology to evaluate the similarity of text and remove duplicate data. It receives the collected raw data as input and stores the filtered, highly accurate data as output in the database.

[1380] Step 3:

[1381] The server provides the filtered data to the generation AI (e.g., GPT-4). When providing the data, it gives instructions to the AI ​​using a specific prompt. For example, the prompt might be, "Based on the data below, please create a summary of an unsolved robbery that occurred in City A in July 2023. Please organize it, including the location, time, and witness information." The server receives the filtered data and the prompt as input, and outputs text data containing a summary of the incident, details of the people involved, and details of the evidence.

[1382] Step 4:

[1383] The server stores the text data generated by the AI ​​in an internal database. At the same time, it formats the text data into a banner format that is easy for users to view. This formatting involves format conversion using HTML and CSS. The server receives the generated text data as input and obtains formatted banner data as output.

[1384] Step 5:

[1385] The server sends the formatted banner data to an information platform on the Internet (e.g., a news site). Specifically, it posts the banner data to the platform using a specific API endpoint and sets it to be displayed at a specified time. It receives the formatted banner data as input and displays the banner on the Internet platform as output.

[1386] Step 6:

[1387] A user is browsing a news site on their device and notices a banner that appears. When the user clicks on the banner, it takes them to a details page, which contains more detailed information about the incident. The input is an action to click on the banner, and the output is the details page.

[1388] Step 7:

[1389] The user enters new information or witnesses about the incident on the details page. The input form contains fields for describing the information and specific witnesses. The input takes the new information provided by the user and the output sends the input data for further processing.

[1390] Step 8:

[1391] The terminal sends the entered user information to the server, using the HTTPS protocol for secure data transfer, receiving the user's new information as input and sending the data to the server as output.

[1392] Step 9:

[1393] The server then filters the received user information again and stores it in an internal database. This filtering process can use natural language processing techniques to remove spam data and redundant information. It takes the information received from the user as input and stores the filtered information in an internal database as output.

[1394] Step 10:

[1395] The server then reports newly collected information to relevant authorities as needed, for example, by providing information to police or investigative agencies via email or API. It receives filtered critical information as input and reports the information to relevant authorities as output.

[1396] (Application example 1)

[1397] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1398] Existing information gathering systems for unsolved cases lack the means to efficiently collect information on past cases, analyze that information, and disseminate it widely. This makes it difficult to gather new clues or additional information from users. Furthermore, the methods for visually displaying the acquired information are limited, making it difficult to attract users' attention. Furthermore, since AI generation is not utilized when generating information on unsolved cases, the accuracy and usefulness of the information cannot be guaranteed.

[1399] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1400] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the parties involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users using a user interface, and means for generating prompt sentences using a generative AI model for information collection. This makes it possible to efficiently collect and analyze information on past unsolved cases and visually display it to gather new clues from users.

[1401] "Unsolved cases" are crimes that occurred in the past and have not been solved to date.

[1402] "Means of collecting data" are means of obtaining information about the incident from specific sources, such as news sites or police public information databases.

[1403] "Means for analyzing data" refers to the means for processing and analyzing collected information and organizing the details of the case, the people involved, and the evidence.

[1404] "Means for generating prompt sentences using a generative AI model" means means for using generative AI to generate summaries or summaries related to an incident from collected data.

[1405] The "means for converting into a display format" refers to a means for converting the generated information into a format that is easy for the user to view, specifically, a banner format or the like.

[1406] An "information platform" refers to a collection of websites and applications that provide information on the Internet.

[1407] A "user interface" is the means by which a user interacts with a system, specifically referring to devices and screens such as PCs and smartphones.

[1408] "Means for collecting additional information from the user" refers to forms or application features that allow users to enter new information, witness statements, etc. into the system.

[1409] "Internal Database" means a data storage device for storing and managing collected information and additional information provided by the User.

[1410] "Related agencies" are public or private agencies involved in resolving the case, such as the police or investigative agencies.

[1411] The present invention is a system for efficiently collecting information about unsolved cases, analyzing, generating, and displaying it using a generative AI model, and collecting additional information from users. Specific embodiments of the present invention are described below.

[1412] System configuration

[1413] This system consists of the following components:

[1414] 1. Data collection module (server)

[1415] 2. Data analysis and generation module (generative AI server)

[1416] 3. Information display module (server)

[1417] 4. User Interface (Terminal / User)

[1418] Data Collection Module

[1419] The server crawls news sites and public police information databases at specific time intervals (e.g., 12 noon every day). During this crawling process, information related to unsolved cases is collected. The collected data is temporarily stored in a database, and duplicate or irrelevant information is filtered out. For example, when collecting information about unsolved cases that occurred in a specific city, text data from news and public police information is obtained and stored in a database.

[1420] Data Analysis and Generation Module

[1421] The server provides the filtered data to the generation AI, which analyzes the data and generates a text summary of the incident, details of the people involved, and evidence. For example, for an incident that occurred in a specific city in a specific year, the AI ​​will organize the location, time, witness information, etc., and write a summary of the incident. This generated text data is stored in an internal database.

[1422] Example prompt

[1423] Here are some examples of prompts for generative AI models:

[1424] Please summarize the following incident information:

[1425] Title: Robbery in a specific city

[1426] Date: 2023-07-15

[1427] Details: Two men robbed a bank in the center of a certain city. According to witnesses, the culprits were wearing black clothes and fled after stealing about 1 million yen in cash.

[1428] Information Display Module

[1429] The server uses the text data stored in the internal database to format the information in a way that is easy for users to view. In particular, it converts it into a banner format for news sites. For example, it generates a banner that briefly summarizes the generated incident, such as "Robbery occurred in a specific city in a specific year: Please provide witness information." This banner information is sent to the news site's management system and displayed at a specified time.

[1430] User Interface

[1431] When users browse a news site on their device (PC, smartphone, etc.), they can see an overview of an unsolved case in a banner. Interested users can click on the banner to go to the detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, notifies the police or relevant agencies.

[1432] Hardware and Software Use

[1433] The system uses the following hardware and software:

[1434] Hardware: High-performance servers are used for data collection, analysis, generation, and display. Users use devices such as PCs and smartphones.

[1435] Software: OpenAI generative AI models are used for data analysis and generation. Web scraping libraries such as BeautifulSoup and requests are used for data collection. Database management systems (e.g., MySQL) are used for data storage and processing.

[1436] In this way, information on past unsolved cases can be efficiently collected, analyzed, and visually displayed, allowing users to gather new clues.

[1437] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1438] Step 1:

[1439] The server crawls news websites and police public information databases at specific time intervals. The input is the URLs of news websites and police databases, and the output is text data related to unsolved cases. The server stores the collected data in a database and filters out duplicate and irrelevant information.

[1440] Step 2:

[1441] The server analyzes the filtered data. The input for this analysis is the filtered case data, and the output is information such as an overview of the analyzed unsolved case, the people involved, and details of the evidence. The server uses a generative AI model to generate prompt sentences, which are then used to generate case information in text format.

[1442] Step 3:

[1443] The server creates banner-style display data based on the generated incident information. The input is a summary of the generated incident, and the output is visually organized banner-style data. This generated banner information is sent to an information platform on the Internet and displayed in a format that can be viewed by users.

[1444] Step 4:

[1445] A user at a terminal clicks on the banner to go to the detailed information page. The input is the user's click action, and the output is the display of the detailed information page, where the user can view more detailed information about the incident.

[1446] Step 5:

[1447] Users enter new information about the incident or witnesses using a form on the detailed information page. The input is the new information provided by the user, and the output is the transmission of the entered information to the server.

[1448] Step 6:

[1449] The server receives new information sent by the user and stores it in an internal database. The input is the new information provided by the user and the output is the information stored in the database. The server filters the new information and notifies the police or relevant authorities if necessary.

[1450] Step 7:

[1451] The server uses a generative AI model to create prompt sentences for automatically generating information. The input is the collected and filtered incident data, and the output is the prompt sentences to be input into the generative AI model.

[1452] Step 8:

[1453] The generative AI model automatically generates a summary and details of the case based on the prompt. The input is the prompt, and the output is the analyzed case information. This information is stored in a database on the server and used in the next step.

[1454] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1455] The present invention is a system for obtaining new clues by effectively collecting and disseminating information about past unsolved cases, and by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided are improved. Specific embodiments of the present invention are described below.

[1456] System configuration

[1457] The system consists of the following components:

[1458] 1. Data collection module (server)

[1459] 2. Data analysis and generation module (generative AI server)

[1460] 3. Information display module (server)

[1461] 4. User Interface (Terminal / User)

[1462] 5. Emotion engine (server)

[1463] Data Collection Module

[1464] The server periodically (for example, every day at midnight) crawls the police public information database and news sites on the Internet to collect data related to unsolved cases. The collected data is temporarily stored in a database, and duplicates and irrelevant information are filtered out. For example, a procedure may be taken to collect the latest information on unsolved theft cases that occurred in City B.

[1465] Data Analysis and Generation Module

[1466] The server converts the filtered data into JSON format to provide it to the generative AI module, which then analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generated text data is stored in an internal database.

[1467] Information Display Module

[1468] The server generates a concise summary of the information from the text data stored in the internal database and formats it into an HTML banner, which is then sent to the Yahoo! News management system and displayed at the specified time.

[1469] User Interface

[1470] When users browse Yahoo! News on their device (PC, smartphone, etc.), an overview of an unsolved case is displayed as a banner. Interested users can click on the banner to go to a detailed information page, which provides more detailed information about the case. If users have new information or witness reports about the case, they can provide them by filling out a form on the detailed information page. The device sends the entered information to a server, which stores the received information in an internal database. The server filters the information and, if necessary, reports it to the police or relevant agencies.

[1471] Adding an Emotion Engine

[1472] In the present invention, the emotion engine is utilized when the user provides information or browses detailed information. Specifically, the following processes are added:

[1473] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[1474] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[1475] 3. The server prioritizes the provided information based on the emotional data and immediately notifies the police or relevant agencies if necessary.

[1476] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[1477] Specific examples

[1478] For example, in the case of an unsolved theft that occurred in City B in July 2023, the system would operate as follows:

[1479] 1. The server collects and filters information about the incident from news sites and police public information databases.

[1480] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[1481] 3. The server formats the generated text data into banner format and sends it to the Yahoo! News management system.

[1482] 4. The user clicks on the banner to access the details page and view further details about the incident.

[1483] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[1484] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[1485] In this way, the present invention can enhance the effectiveness of gathering and disseminating information about unsolved cases by combining an emotion engine.

[1486] The processing flow will be explained below.

[1487] Step 1:

[1488] The server periodically (for example, at midnight every day) crawls police public information databases and news sites on the Internet to collect data related to unsolved cases.

[1489] Step 2:

[1490] The server filters the collected data to remove duplicates and irrelevant information, and stores the filtered data in an internal database.

[1491] Step 3:

[1492] The server converts the filtered data into JSON format to provide it to the generation AI module. The converted data is then passed to the generation AI module.

[1493] Step 4:

[1494] The generative AI module analyzes the provided data and generates a summary of the unsolved case, details of the people involved, and details of the evidence. This generated text data is stored in the server's internal database.

[1495] Step 5:

[1496] The server generates information that briefly summarizes the incident based on the text data stored in the internal database and formats it into banner-style HTML.

[1497] Step 6:

[1498] The server sends the generated banner information to the Yahoo! News management system, where it is displayed in the designated banner area.

[1499] Step 7:

[1500] When a user browses Yahoo! News on their device (PC, smartphone, etc.), they see a banner displaying an overview of an unsolved case.

[1501] Step 8:

[1502] The user clicks on a banner that interests them. The device transitions to a detailed information page based on the clicked link.

[1503] Step 9:

[1504] The user views further details about the incident on the details page. If necessary, the user can provide witness information or new information using the input form on the details page.

[1505] Step 10:

[1506] The emotion engine analyzes the text and voice data entered by the user into the form in real time to recognize the user's emotional state.

[1507] Step 11:

[1508] The server evaluates the credibility of the information provided by the user based on the emotion data provided by the emotion engine.

[1509] Step 12:

[1510] The device sends the input information and emotion data from the user to the server, which stores the information in its internal database.

[1511] Step 13:

[1512] The server evaluates the credibility and urgency of the information received and notifies the police or relevant authorities if necessary.

[1513] Step 14:

[1514] An emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state, for example, providing encouraging messages and engaging information if the user is feeling anxious.

[1515] In this way, the system of the present invention, by combining an emotion engine, can effectively collect information on unsolved cases and efficiently provide new clues.

[1516] Example 2

[1517] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1518] Currently, information on unsolved cases is collected and disseminated, but there is a lack of a system for evaluating the credibility and urgency of that information. As a result, collected information may not be reliably reported to relevant agencies promptly. Furthermore, since it is difficult to determine whether the provided information is true, there is a problem of low accuracy in investigations. The present invention aims to solve these problems and improve the accuracy and efficiency of information collection and dissemination of past unsolved cases.

[1519] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1520] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data to generate an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an information providing platform on the Internet, means for collecting additional information from users, means for analyzing user sentiment and evaluating the credibility and urgency of the provided information, and means for reporting the evaluated information to relevant authorities. This makes it possible to evaluate the credibility and urgency of the collected information and efficiently report it to relevant authorities.

[1521] "Past unsolved cases" refer to criminal cases that have not been solved within a certain period of time and are still under investigation.

[1522] "Data Collection Methods" refers to software and hardware features that automatically retrieve certain information from sources on the Internet.

[1523] "Means for analyzing data and generating details of open cases, people involved, and evidence" refers to the function of automatically extracting and organizing details of the case, people involved, and evidence based on collected information.

[1524] "Means for converting the generated information into a display format and displaying it on an information platform on the Internet" refers to the function of formatting the generated text and data into a visually easy-to-read format and making it available through a website or application.

[1525] "Means for collecting additional information from the user" refers to input forms and related system features that receive and store new information provided by the user.

[1526] "Means of analyzing the user's emotions and evaluating the credibility and urgency of the information provided" refers to a function that analyzes text, voice, etc. from information provided by the user and determines their emotional state.

[1527] "Means of reporting evaluated information to relevant agencies" refers to the function of promptly notifying appropriate agencies, such as the police, of information that is deemed to be highly credible or urgent.

[1528] "Means of converting into a display format" refers to the function of converting data into a form that is visually easy for users to understand (for example, HTML or banner ads).

[1529] The present invention provides a system for effectively collecting and disseminating information about past unsolved cases. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the accuracy and credibility of the information provided can be improved. Specific embodiments of the present invention are described below.

[1530] System configuration

[1531] The system consists of the following components:

[1532] 1. Data collection module (server)

[1533] 2. Data analysis and generation module (generative AI server)

[1534] 3. Information display module (server)

[1535] 4. User Interface (Terminal / User)

[1536] 5. Emotion engine (server)

[1537] Data Collection Module

[1538] The server periodically (e.g., every day at midnight) crawls public police information databases and news sites on the Internet to collect data related to unsolved cases. The collected data is then temporarily stored in a database, where duplicates and irrelevant information are filtered out. This crawling is performed using web crawler software (e.g., Scrapy). For example, the procedure is to collect the latest information on unsolved theft cases that have occurred in a particular city. A natural language processing library (e.g., NLTK) is used for filtering.

[1539] Data Analysis and Generation Module

[1540] The server converts the filtered data into JSON format to provide it to the generative AI module. This conversion is performed using the Python json library. The generative AI module analyzes the data and automatically generates a summary of the incident, details of the people involved, and details of the evidence. This generation is performed using a generative AI model (e.g., GPT-4). The generated text data is stored in an internal database.

[1541] Information Display Module

[1542] The server generates concise information based on the text data stored in the internal database and formats it into a banner-style HTML. This HTML is generated using the Django template engine. The formatted banner information is sent to the management system of an Internet news site (e.g., Yahoo! News) and displayed at the specified time.

[1543] User Interface

[1544] Users browse a news site on their device (e.g., PC or smartphone) and see a banner with an overview of the unsolved case. Interested users can click on the banner to go to a detailed information page, where more detailed information about the case is provided using a JavaScript framework (e.g., React).

[1545] If users have any sightings or other additional information, they can provide it by filling out a form on the details page. The input from this form is sent from the device to the server, and the received information is stored in an internal database. The input information is filtered and, if necessary, reported to the relevant authorities (e.g., police).

[1546] Adding an Emotion Engine

[1547] In this invention, the emotion engine is utilized when users provide information or view detailed information. The specific process is as follows:

[1548] 1. When a user fills out an information form, the emotion engine analyzes the user's text and voice input and recognizes their emotions. This analysis uses natural language processing (NLP) and voice emotion recognition technology.

[1549] 2. The server evaluates the credibility of the input information based on the emotional data obtained from the emotion engine. For example, if the user is excited, it determines that the information may be urgent.

[1550] 3. The server prioritizes the provided information based on the emotion data and immediately notifies relevant authorities if necessary.

[1551] 4. The emotion engine dynamically changes the content and format of the information displayed based on the user's emotional state. For example, if the user is feeling anxious, it will provide more encouraging messages and information that will increase engagement.

[1552] Specific examples

[1553] For example, given an unsolved theft case that occurred in 2023 in a particular city, the system would operate as follows:

[1554] 1. The server collects and filters information about the incident from news sites and police public information databases.

[1555] 2. The generative AI module analyzes the filtered data and automatically generates an incident summary, witness information, and evidence details.

[1556] 3. The server formats the generated text data into a banner and sends it to the news site's management system.

[1557] 4. The user clicks on the banner to access the details page and view further details about the incident.

[1558] 5. When a user provides information about an eyewitness incident, the emotion engine analyzes the user's emotions and evaluates their credibility.

[1559] 6. The server prioritizes the information based on the credibility evaluation results and reports it to relevant authorities as necessary.

[1560] Example prompts for generative AI models

[1561] "Generate text based on up-to-date information about unsolved thefts that occurred in a specific city in 2023, including a summary of the case, details of the people involved, and evidence."

[1562] In this way, the present invention enables the collection and dissemination of information on unsolved cases, and improves the accuracy of information through sentiment analysis.

[1563] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1564] Step 1:

[1565] The server starts collecting information.

[1566] Input: The crawl time set in the scheduler.

[1567] Output: Launch of crawl task.

[1568] Specific operation: Every day at midnight, the server's scheduler executes a crawl task to collect data from police public information databases and news sites on the Internet.

[1569] Step 2:

[1570] The server performs the crawl.

[1571] Input: The specified URL list.

[1572] Output: Collected data on unsolved cases.

[1573] What it does: Web crawler software (e.g., Scrapy) on the server accesses the specified URL, retrieves information related to the unsolved case, and stores it in a database.

[1574] Step 3:

[1575] The server filters the collected data.

[1576] Input: Collected cold case data.

[1577] Output: The filtered data.

[1578] What it does: Uses a natural language processing library (e.g., NLTK) to remove duplicate and irrelevant information and generate filtered data.

[1579] Step 4:

[1580] The server converts the data into JSON format.

[1581] Input: Filtered data.

[1582] Output: JSON formatted data.

[1583] Specific operation: Using Python's json library, the filtered data is converted into JSON format and passed to the generative AI module.

[1584] Step 5:

[1585] The generative AI module analyzes and generates data.

[1586] Input: JSON formatted data.

[1587] Output: Text data containing details of the incident, the people involved, and the evidence.

[1588] How it works: A generative AI model (e.g., GPT-4) generates prompt text based on the received JSON data, automatically generating a summary of the incident, details of the people involved, and details of the evidence.

[1589] Step 6:

[1590] The server formats the text into HTML.

[1591] Input: Text data generated by the generative AI module.

[1592] Output: Banner information in HTML format.

[1593] Specific behavior: Uses the Django template engine to format the generated text data into banner-style HTML.

[1594] Step 7:

[1595] The server distributes the information.

[1596] Input: Banner information in HTML format.

[1597] Output: A banner that appears on news sites on the Internet.

[1598] Specific operation: The generated banner information is sent to the news site's management system and displayed at the specified time.

[1599] Step 8:

[1600] A user browses the news.

[1601] Input: A banner displayed on a news site.

[1602] Output: Access to the more information page.

[1603] What happens: A user clicks on the banner on their device and is taken to a details page where they can view more information about the incident.

[1604] Step 9:

[1605] The user provides the information.

[1606] Input: Information entered into the form on the details page.

[1607] Output: Provided sighting and / or additional information.

[1608] Specific actions: The user enters sighting details and additional information in the form on the detailed information page and presses the submit button.

[1609] Step 10:

[1610] The terminal transmits the information.

[1611] Input: Information entered by the user.

[1612] Output: Information sent to the server.

[1613] Specific operation: Input information is sent from the terminal to the server, and the server receives it.

[1614] Step 11:

[1615] The server receives and stores the information.

[1616] Input: Information sent from the device.

[1617] Output: Information stored in an internal database.

[1618] Specific operation: The server stores the received information in a database, and prepares filtering and notification as necessary.

[1619] Step 12:

[1620] The server runs the emotion engine.

[1621] Input: Information submitted by the user.

[1622] Output: Emotion data.

[1623] Specific operation: Calls the emotion engine, analyzes the user's text and voice input, and generates emotion data.

[1624] Step 13:

[1625] The emotion engine analyzes emotions.

[1626] Input: User-provided information.

[1627] Output: Parsed emotion data.

[1628] Specific operation: The emotion engine uses natural language processing and voice emotion recognition technology to recognize the user's emotional state.

[1629] Step 14:

[1630] The server sets the priority of the information.

[1631] Input: Emotion data.

[1632] Output: Information priority.

[1633] Specific operation: The server evaluates the credibility and urgency of information based on emotional data and sets a priority.

[1634] Step 15:

[1635] The server notifies the relevant authorities.

[1636] Input: Prioritized information.

[1637] Output: Notification sent to relevant authorities.

[1638] Specific operation: The server notifies the appropriate authorities, such as the police, of high-priority information.

[1639] (Application example 2)

[1640] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1641] The challenge is to improve the efficiency of collecting and disseminating information about unsolved cases, as well as to increase the credibility of the information provided. Specifically, a system is needed that can notify passengers and drivers of autonomous vehicles of information about unsolved cases in real time, accurately collect eyewitness reports from them, and evaluate their credibility using an emotion analysis engine.

[1642] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1643] In this invention, the server includes means for collecting data on past unsolved cases, means for analyzing the collected data and generating an outline of the unsolved case, details of the people involved, and details of evidence, means for converting the generated information into a display format and displaying it on an online information platform, means for collecting additional information from users, means for obtaining current vehicle location information and displaying case information in real time, means for analyzing user emotions and evaluating the credibility of the information based on the emotion data, and means for reporting the information to relevant authorities as needed based on the evaluation. This makes it possible to efficiently collect information on unsolved cases and quickly report credible information to relevant authorities.

[1644] "Data collection means" refers to a device or system that has the function of collecting data related to past unsolved cases from the Internet.

[1645] "Data analysis means" means a device or system capable of analyzing collected data and generating a summary of an unsolved case, details of the parties involved, and details of evidence.

[1646] The "display conversion means" is a device or system that has the function of converting the generated information into a display format and displaying it on an information providing platform on the Internet.

[1647] An "additional information collection means" is a device or system that has the function of collecting new information from users.

[1648] The "location information acquisition means" is a device or system that has the function of acquiring information about the current location of a vehicle.

[1649] "Real-time display means" refers to a device or system that has the function of displaying incident information in real time based on the current location information of the vehicle.

[1650] The "emotion analysis means" is a device or system that has the function of analyzing the user's emotions and evaluating the credibility of information based on the emotion data.

[1651] "Automatic reporting means" refers to a device or system that has the function of automatically reporting necessary information to relevant institutions based on the evaluation results based on emotion analysis.

[1652] The present invention provides a system for efficiently collecting information on unsolved cases, evaluating the credibility of information based on eyewitness reports from users, and reporting the information to relevant authorities as necessary. Specific embodiments of the system are described below.

[1653] System Configuration

[1654] The system consists of the following components:

[1655] 1. Data collection method (server)

[1656] The server collects data on past unsolved cases from the Internet. Specifically, it crawls police public information databases and news sites to collect data on unsolved cases. The collected data is then temporarily stored in a database.

[1657] 2. Data analysis method (server)

[1658] The server analyzes the collected data and automatically generates an outline of the incident, details of the people involved, and details of the evidence using a generative AI model. The generated text data is stored in an internal database.

[1659] 3. Display conversion means (server)

[1660] The server converts the generated information into a display format and displays it on an information platform on the Internet. Specifically, it formats the generated text data into HTML banners and sends them to news sites.

[1661] 4. Additional information collection methods (devices, users)

[1662] Users can access the information platform on their own devices (such as smartphones) and check information on unsolved cases. A form is provided for interested users to provide additional information about the case, allowing users to enter witness accounts, etc. The device sends the entered information to the server, which then stores the received information in an internal database.

[1663] 5. Location information acquisition method (vehicle)

[1664] Vehicles are equipped with a device that acquires their current location information. The server constantly receives this location information and processes it in real time.

[1665] 6. Real-time display means (vehicle, terminal)

[1666] The server displays information related to unsolved cases in real time on the vehicle's or device's display based on the vehicle's current location information. For example, when a vehicle passes near the scene of a particular unsolved case, information about that case is displayed on the display.

[1667] 7. Emotion analysis means (server)

[1668] The server uses an emotion engine to analyze the user's emotions. When the user fills in the additional information form, the emotion analysis engine analyzes the input and determines the user's emotional state.

[1669] 8. Automatic reporting means (server)

[1670] Based on the results of the sentiment analysis, the credibility of the information provided is evaluated and, if necessary, the relevant authorities are notified. The server immediately notifies the police and relevant authorities of this information, facilitating a prompt response.

[1671] Hardware and software used

[1672] Hardware:

[1673] Server: Used for data collection, analysis, display conversion, sentiment analysis, and automatic reporting.

[1674] Vehicle location information acquisition device: Knows the current location of the vehicle in real time.

[1675] Devices (smartphone, vehicle display): View information, enter additional information.

[1676] software:

[1677] Generative AI model: Used to automatically generate incident information.

[1678] EmotionRecognition module: Used to analyze user emotions.

[1679] VehicleAPI: Used to obtain and display the vehicle's current location information.

[1680] Requests library: Handles HTTP requests and communicates with external APIs.

[1681] Specific examples

[1682] For example, in the case of an unsolved theft case that occurred in City B, the system operates as follows: The server collects information about the case from news sites and the police's public information database, and automatically generates details about the case using a generative AI model. The generated information is converted into banner format and displayed on the news site. When a user provides eyewitness information, the emotion engine analyzes the emotion and evaluates its credibility. Based on the evaluation results, the necessary information is immediately reported to the relevant authorities. This process enables information gathering and rapid response to unsolved cases.

[1683] Prompt Sentence Examples

[1684] "Develop an application that can collect information about unsolved cases, notify vehicles, and provide witness reports. The application will evaluate the credibility of users' witness reports using an emotion engine, and automatically notify the police and relevant agencies. The application will work in conjunction with autonomous vehicles, displaying information on the vehicle's display in real time."

[1685] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1686] Step 1:

[1687] The server collects data on past unsolved cases from public police information databases and news sites on the Internet. The input is the URL of the public police information database or news site, and the output is the collected case data. During the data collection process, the server uses a web crawler to periodically check these sites to obtain new data.

[1688] Step 2:

[1689] The server analyzes the collected data to generate a summary of the unsolved case, details of the people involved, and details of the evidence. The input is the collected case data, and the output is detailed information about the analyzed case. This analysis uses a generative AI model to analyze the input data using natural language processing (NLP) technology, automatically generating text that describes the case.

[1690] Step 3:

[1691] The server converts the generated detailed information into a display format. The input is the analyzed incident details, and the output is HTML data formatted for display. The server formats the generated text data into HTML banners and sends them to an information platform on the Internet.

[1692] Step 4:

[1693] Users can browse the information platform on their own devices (smartphones) and check information on unsolved cases. By clicking on the displayed banner, the device will be taken to a detailed information page, where a form will be displayed for users to provide further information about the case.

[1694] Step 5:

[1695] The user provides information about the sighting and other additional information. The input is the information entered by the user, and the output is the information sent to the server. The device sends the information entered by the user in the form to the server using an HTTP request.

[1696] Step 6:

[1697] The server receives information provided by the user and analyzes their emotional state. The input is the user-provided witness information and text data, and the output is the result of the emotion analysis engine. Emotion analysis is performed using the EmotionRecognition module, which identifies emotions from the user's input.

[1698] Step 7:

[1699] The server evaluates the credibility of the information based on the results of sentiment analysis. The inputs are the results of sentiment analysis and witness information, and the output is the evaluation result. Based on this evaluation result, the credibility and urgency of the provided information are judged.

[1700] Step 8:

[1701] The server will report to the relevant authorities as necessary based on the evaluation results. The input is the information whose credibility has been evaluated, and the output is the report to the relevant authorities. The server automatically notifies the police and other relevant authorities of information with a high level of importance.

[1702] Step 9:

[1703] The server obtains the vehicle's current location information and displays relevant information about unsolved cases on the vehicle's display in real time. The input is the vehicle's location information, and the output is the case information to be displayed. The server uses VehicleAPI to obtain the vehicle's current location and displays case information in real time based on that information.

[1704] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1705] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1706] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1707] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1708] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1709] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1710] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1711] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1712] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1713] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1714] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1715] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1716] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1717] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1718] 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.

[1719] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1720] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1721] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1722] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1723] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1724] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1725] The following is further disclosed regarding the above embodiment.

[1726] (Claim 1)

[1727] a means of collecting data on past unsolved cases;

[1728] A means of analyzing the collected data to generate a summary of the cold case, details of the people involved, and evidence;

[1729] means for converting the generated information into a display format and displaying it on an information providing platform on the Internet;

[1730] means of collecting additional information from users; and

[1731] A system including:

[1732] (Claim 2)

[1733] 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

[1734] (Claim 3)

[1735] 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to relevant authorities.

[1736] "Example 1"

[1737] (Claim 1)

[1738] a means of periodically collecting data on past unsolved cases;

[1739] A means of filtering the collected data to remove duplicate or irrelevant information;

[1740] Using generative AI models to analyze the filtered data and generate cold case summaries, actors, and evidence details; and

[1741] A means for formatting the generated information into a banner format and displaying it on an information providing platform on the Internet;

[1742] means of collecting additional information from users and storing such information in an internal database;

[1743] A means of reporting any additional information collected to relevant authorities as necessary;

[1744] A system including:

[1745] (Claim 2)

[1746] 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

[1747] (Claim 3)

[1748] 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to relevant authorities.

[1749] "Application Example 1"

[1750] (Claim 1)

[1751] a means of collecting data on past unsolved cases;

[1752] A means of analyzing the collected data to generate a summary of the cold case, details of the people involved, and evidence;

[1753] means for converting the generated information into a display format and displaying it on an information providing platform on the Internet;

[1754] a means for collecting additional information from the user using the user interface;

[1755] a means for generating prompt sentences using a generative AI model for information gathering;

[1756] A system including:

[1757] (Claim 2)

[1758] 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

[1759] (Claim 3)

[1760] 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to relevant authorities.

[1761] "Example 2: Combining Emotion Engines"

[1762] (Claim 1)

[1763] a means of collecting data on past unsolved cases;

[1764] A means of analyzing the collected data to generate a summary of the cold case, details of the people involved, and evidence;

[1765] means for converting the generated information into a display format and displaying it on an information providing platform on the Internet;

[1766] means of collecting additional information from users; and

[1767] A means of analyzing user sentiment and assessing the credibility and urgency of the information provided;

[1768] means of reporting the assessed information to relevant authorities;

[1769] A system including:

[1770] (Claim 2)

[1771] 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

[1772] (Claim 3)

[1773] 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to relevant authorities.

[1774] "Application example 2 when combining emotion engines"

[1775] (Claim 1)

[1776] a means of collecting data on past unsolved cases;

[1777] A means of analyzing the collected data to generate a summary of the cold case, details of the people involved, and evidence;

[1778] means for converting the generated information into a display format and displaying it on an information providing platform on the Internet;

[1779] means of collecting additional information from users; and

[1780] A means for obtaining current vehicle location information and displaying incident information in real time;

[1781] A means of analyzing user emotions and evaluating the credibility of information based on the emotional data;

[1782] means for reporting such information to relevant authorities as necessary based on such assessment;

[1783] A system including:

[1784] (Claim 2)

[1785] 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

[1786] (Claim 3)

[1787] 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to relevant authorities. [Explanation of symbols]

[1788] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data on past unsolved cases; A means of analyzing the collected data to generate a summary of the cold case, details of the people involved, and evidence; means for converting the generated information into a display format and displaying it on an information providing platform on the Internet; means of collecting additional information from users; and A system including:

2. 2. The system according to claim 1, wherein the means for converting the generated information into a display format converts the information into a banner format for a news site on the Internet.

3. 10. The system of claim 1, further comprising means for receiving additional information from the user, storing the information in an internal database, and reporting the information to appropriate authorities.

Images