System

Abstract

A system is provided.SOLUTION: The system according to claim 1, further comprising: means for extracting evidence from the generated AI and verifying the credibility of the evidence from a plurality of viewpoints; and means for outputting a result of the verification as a report and allowing a user to access the result of the verification, wherein the means for extracting evidence and the means for verifying the credibility of the evidence are included in the generated AI.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] In modern society, problems such as false accusations and bullying are serious social issues, and many of these problems stem from the difficulty of proving something "not done" or "not existing," known as "Devil's Proof." Solving these problems requires efficiently analyzing massive amounts of data and presenting reliable evidence, but conventional methods require a great deal of time and resources, making it difficult to provide reliable proof. [Means for solving the problem]

[0005] This invention provides a system that uses generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information. Specifically, it includes a simulation means for preprocessing collected data to remove noise, then analyzing it using generative AI to reproduce the target individual's past behavior. Furthermore, it provides highly reliable evidence by extracting evidence from the data reproduced by this simulation means and verifying its credibility from multiple perspectives. Furthermore, by building a system that outputs the verification results as a report and makes it easily accessible to users, it provides a means for quickly and reliably resolving issues such as false accusations and bullying.

[0006] "Generative AI" is an artificial intelligence technology that automatically generates and analyzes data for specific purposes.

[0007] "Big data" refers to a collection of information so large and complex that it requires computer analysis.

[0008] "High-speed processing" means reading data, analyzing it, and outputting results in a significantly shorter time than conventional technology.

[0009] "Prior cases" refer to previous events or data related to a particular incident or situation.

[0010] "Relevant Information" refers to data or information that relates directly or indirectly to a particular case or situation.

[0011] "Integrate" means bringing together information from multiple different data sources and processing it as a single, coherent data set.

[0012] "Preprocessing" refers to the act of preparing data to facilitate analysis by performing processes such as noise removal and data conversion before data analysis.

[0013] "Denoising" means removing unnecessary or erroneous data to improve the quality of the data.

[0014] "Analyzing data" refers to the act of extracting meaning and patterns from collected data using statistical and machine learning techniques.

[0015] "Simulation means for reproducing behavior" refers to a function that uses generative AI to virtually reproduce the behavior and events of past individuals.

[0016] "Extracting evidence" refers to the act of extracting significant information from analyzed data that supports a particular claim.

[0017] "Verifying credibility" refers to the act of verifying whether extracted evidence is based on truth using multiple perspectives and methods.

[0018] "Output as a report" means documenting the analysis results and evidence and providing them in a format that can be easily viewed and used by users.

[0019] "User-accessible means" refers to the interface or functionality that allows users to log into the system and obtain the information and reports they need. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] Specific Embodiments of the System

[0042] This patented system is a data analysis system that utilizes generative AI, where servers, terminals, and users work together. This system is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying.

[0043] Server Processing

[0044] Data collection and integration

[0045] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[0046] Data Preprocessing

[0047] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[0048] Data analysis and behavioral reproduction

[0049] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[0050] Evidence extraction and verification

[0051] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[0052] Output of results

[0053] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[0054] User operations

[0055] Accessing the system

[0056] Users log in to the system using their terminals. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[0057] Specific examples

[0058] Example 1: Proof of innocence

[0059] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. Users can download this report and use it to proceed with legal proceedings.

[0060] Example 2: Proof of being a victim of bullying

[0061] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it to help with school and legal responses.

[0062] As described above, this system makes full use of generative AI to process huge amounts of data efficiently and quickly to prove that someone "did not do it" or "did not exist," thereby helping to avoid false accusations and bullying.

[0063] The processing flow will be explained below.

[0064] Program processing steps

[0065] Step 1: Data collection

[0066] The server accesses data sources related to the incident or situation of interest.

[0067] The server downloads the surveillance camera video via the network.

[0068] The server obtains the mobile phone's location information through an API.

[0069] The server extracts the SNS message history from the database.

[0070] The server stores the collected data in temporary storage and consolidates all the data.

[0071] Step 2: Data Preprocessing

[0072] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[0073] The server performs a process to remove noise from the mobile phone's location information.

[0074] The server filters the SNS message history for important keywords and removes irrelevant data.

[0075] The server stores the pre-processed data in a new storage.

[0076] Step 3: Data analysis and behavioral reproduction

[0077] The server inputs the preprocessed data into the generation AI.

[0078] The server uses generative AI to cross-reference security camera footage with location data.

[0079] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[0080] The server visualizes the behavioral simulation results in a virtual environment.

[0081] Step 4: Evidence extraction and verification

[0082] The server extracts important evidential data from the reconstructed behavioral data.

[0083] The server cross-references the extracted evidence with information from different data sources.

[0084] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[0085] The server records the final evidence and its authenticity in a database.

[0086] Step 5: Output the results

[0087] The server generates an analysis report based on the verified evidence.

[0088] The server outputs the report in PDF format and stores it in secure storage.

[0089] Step 6: User interaction

[0090] A user logs into the system using a terminal.

[0091] The user searches through the analysis results reports and selects the report of interest.

[0092] The user downloads the selected report and checks its contents.

[0093] Users can take appropriate legal action or measures based on the contents of the report.

[0094] These are the specific processing steps of the system based on patent claims. This system allows efficient and reliable proof of non-existence or non-commitment.

[0095] Example 1

[0096] 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."

[0097] Conventional data analysis systems have the problem of making it difficult to prove false accusations, bullying, and other crimes that "did not occur" or "did not exist." The manual process of collecting, integrating, analyzing, and verifying data is extremely time-consuming. Furthermore, because much of the information contains noise, it is difficult to accurately reproduce behavior or verify the credibility of evidence. Furthermore, there are insufficient ways for users to easily access, search, and download analysis results.

[0098] 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.

[0099] In this invention, the server includes: means for using generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using generative AI and simulating the target person's past behavior; means for extracting evidence from the reproduced data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report and saving it in a secure storage device; and means for users to log in to the system using their terminals and search for and download analysis result reports of interest. This makes it possible to efficiently prove that someone did not commit or did not exist, such as a false accusation or bullying victim.

[0100] "Generative AI" refers to algorithms that use artificial intelligence techniques to process large amounts of data and generate new data and information.

[0101] "Data collection" is the process of gathering the necessary information from various data sources, including surveillance camera footage, location information, and social media message history.

[0102] "Data integration" refers to the process of centrally managing collected data and converting it into a unified format.

[0103] "Data preprocessing" refers to the data cleaning and filtering procedures used to remove noise from raw data and make it ready for analysis.

[0104] "Denoising" refers to the process of removing errors and unnecessary information from data.

[0105] "Data analysis" refers to the process of extracting useful information from collected and pre-processed data using statistical methods and artificial intelligence techniques.

[0106] "Behavioral reproduction" refers to reconstructing the past behavior of a specific person or subject as a simulation or model based on analyzed data.

[0107] "Evidence extraction" refers to the process of extracting logically significant information from replicated data and using it to support a particular conclusion.

[0108] "Verification of credibility" refers to the process of checking the reliability of the evidence obtained using different data sources and cross-referencing.

[0109] "Report output" refers to compiling the analysis and verification results in document form and making them available for viewing by users.

[0110] "Secure storage device" refers to a storage system that has security features such as authentication and encryption.

[0111] "User" refers to an individual or organization that uses this system to search for and download analysis results reports.

[0112] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[0113] "Login" refers to the authentication process required for a user to access a system.

[0114] "Search" refers to the process of locating information of interest using specific keywords and filters.

[0115] "Downloading" refers to copying data or files to your device via the Internet.

[0116] MODE FOR CARRYING OUT THE INVENTION

[0117] System Overview

[0118] This invention is a data analysis system that utilizes generative AI, and is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying. The system operates in cooperation with the server, terminals, and users.

[0119] Server Roles

[0120] The server is responsible for:

[0121] 1. Data Collection and Integration

[0122] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history. This is done by downloading data using network APIs and database queries. The collected data is first stored in temporary storage (e.g., cloud storage) and then integrated in a database system (e.g., a relational database).

[0123] 2. Data Preprocessing

[0124] The server filters and denoises the collected data. For example, it uses the OpenCV library to fill in blurry areas in security camera footage and removes low-precision data from location data. For social media messages, it uses the NLTK library to filter for important keywords.

[0125] 3. Data analysis and behavioral reproduction

[0126] The server then uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis cross-references time and location information to recreate a person's behavior at a specific time and place. The results are then visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[0127] 4. Extraction and verification of evidence

[0128] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that uses SQL queries and custom scripts.

[0129] 5. Outputting the results

[0130] The verified evidence is generated as an analysis report in PDF format, which is saved in secure storage (e.g., cloud storage). The PDF is generated using LaTeX and HTML to PDF libraries.

[0131] User Roles

[0132] The user does the following:

[0133] 1. Access to the System

[0134] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[0135] 2. Search and download analysis results reports

[0136] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[0137] Specific examples

[0138] 1. Proof of Innocent Conviction

[0139] The server collects and consolidates all data related to a false accusation case, including surveillance camera footage from the day of the crime, mobile phone location information, and transportation usage history. This data is then preprocessed and analyzed using generative AI. The analysis proves that the target person was in a different location at the time of the crime. This evidence is verified from multiple data sources and compiled into a report. Users can download this report and use it to further legal proceedings.

[0140] Example prompt sentence:

[0141] "Please tell me the results of the analysis of the incident that occurred on January 1, 2023."

[0142] 2. Proof of being a victim of bullying

[0143] In cases where bullying is suspected, the server collects school surveillance camera footage, social media message history, and testimony audio data. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying occurred. The results of this analysis are verified using different data sources and compiled into a report as reliable evidence. Users can download this report and use it for school or legal action.

[0144] Example prompt sentence:

[0145] "Please tell me the results of an analysis of bullying that occurred at a specific school on January 1, 2023."

[0146] The above is a mode for carrying out the invention, and this system makes it possible to prove false accusations and bullying victims efficiently and with high accuracy.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1: Data collection and integration

[0149] concrete action

[0150] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history, by downloading data using network APIs and database queries.

[0151] input

[0152] API access information and queries for each data source (surveillance cameras, mobile phone location information, social media messages).

[0153] Data processing and calculation

[0154] Fetch data using network APIs or SQL queries and store it in temporary storage (e.g. cloud storage).

[0155] output

[0156] Temporarily stored raw data before preprocessing.

[0157] Step 2: Data Preprocessing

[0158] concrete action

[0159] The server performs quality filtering and noise reduction on the collected data. For example, it uses the OpenCV library to fill in blurry parts of surveillance camera footage, and a Python script to remove inaccurate parts of location data. For social media messages, it uses the NLTK library to filter for important keywords.

[0160] input

[0161] Temporarily stored raw data before preprocessing.

[0162] Data processing and calculation

[0163] Generate a quality-enhanced dataset through filtering and denoising.

[0164] output

[0165] Preprocessed data with improved quality.

[0166] Step 3: Data analysis and behavioral replication

[0167] concrete action

[0168] The server uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis involves cross-referencing time and location information to simulate a person's behavior at a specific time and place. The results of this analysis are visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[0169] input

[0170] Preprocessed dataset.

[0171] Data processing and calculation

[0172] Generative AI models are used to analyze data and run simulations to reproduce specific behaviors.

[0173] output

[0174] Analysis results and behavioral simulation data.

[0175] Step 4: Evidence extraction and verification

[0176] concrete action

[0177] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that involves SQL queries and custom scripts.

[0178] input

[0179] Reproduced behavioral simulation data.

[0180] Data processing and calculation

[0181] We extract evidence and verify data through cross-referencing to confirm its authenticity.

[0182] output

[0183] Verified evidence data.

[0184] Step 5: Output the results

[0185] concrete action

[0186] The server generates a report summarizing the results in PDF format based on the evidence of the analysis and verification. This report is saved in secure storage (e.g., cloud storage). The PDF generation uses LaTeX and HTML to PDF libraries.

[0187] input

[0188] Verified evidence data.

[0189] Data processing and calculation

[0190] Generate reports and export them in PDF format.

[0191] output

[0192] Analysis results report stored in secure storage.

[0193] Step 6: Access the system

[0194] concrete action

[0195] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[0196] input

[0197] The user's authentication information.

[0198] Data processing and calculation

[0199] Uses an authentication system to verify user credentials and allow login.

[0200] output

[0201] Access rights to the system.

[0202] Step 7: Find and download the analysis report

[0203] concrete action

[0204] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[0205] input

[0206] Search keywords.

[0207] Data processing and calculation

[0208] Run a search query to filter relevant reports.

[0209] output

[0210] User downloadable analysis report.

[0211] (Application example 1)

[0212] 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."

[0213] In recent years, it has become increasingly difficult to prove false accusations and bullying, resulting in many cases of innocent people being treated unfairly. In particular, in today's world where much evidence is digitized, there is a need for efficient methods to collect, analyze, and verify the authenticity of vast amounts of data. Another issue is the lack of tools that allow users to easily prove their own actions. To solve this problem, an advanced data analysis system using generative AI is needed.

[0214] 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.

[0215] In this invention, the server includes: means for processing massive amounts of data at high speed using a generative AI and collecting and integrating past cases and related information; means for preprocessing the collected data and removing noise; simulation means for analyzing the data using a generative AI and recreating the target person's past behavior; means for extracting evidence from the recreated data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report accessible to the user; application means installed on a smartphone for automatically collecting location information, usage history, and camera footage; preprocessing means for removing noise and filtering the collected data; verification means for cross-referencing information collected from multiple data sources and checking its authenticity; and output means for generating a PDF report of the analysis results. This enables users to easily and reliably collect, analyze, and manage evidence when proving their innocence or existence.

[0216] "Generative AI" is a type of artificial intelligence that uses generative algorithms to create new data and information.

[0217] "Big data" refers to the large amount of digital data collected from a wide variety of information sources.

[0218] "Past events" refers to data or information about specific events or occurrences that have occurred in the past.

[0219] "Collection and integration" is the process of bringing together data from multiple sources and converting it into a unified format.

[0220] "Preprocessing" is a preparatory step to remove noise from the data to be analyzed and improve its quality.

[0221] "Noise reduction" is the process of eliminating meaningless data and errors.

[0222] "Analysis" refers to the process of examining data to extract and understand information.

[0223] "Simulation of past behavior" is the process of reconstructing a person's behavior at a specific time and place on a computer based on collected data.

[0224] "Evidence extraction" is the process of extracting useful information or data from the analysis results.

[0225] "Verifying credibility" is the process of confirming the accuracy and reliability of the evidence or data obtained.

[0226] A "report" refers to a document that organizes and documents the results of analysis and verification.

[0227] An "application installed on a smartphone" is software with specific functions that runs on a smartphone.

[0228] "Location information" refers to data that indicates a location at a particular point in time.

[0229] "Usage History" refers to records of how a user uses a device or application.

[0230] "Camera footage" refers to visual data captured by a digital camera.

[0231] "Noise reduction and filtering" is the process of removing unnecessary parts to improve the quality of collected data.

[0232] "Cross-referencing" refers to comparing data obtained from different sources with each other.

[0233] "PDF format" is an abbreviation for Portable Document Format developed by Adobe, and is a format for electronic documents.

[0234] Specific Embodiments of the System

[0235] This system is a data analysis system that utilizes generative AI, where the server, terminal, and user work together. This system is particularly specialized in proving that someone did not commit or exist, such as a false accusation or bullying victim.

[0236] Server Processing

[0237] Data collection and integration

[0238] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[0239] Data Preprocessing

[0240] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[0241] Data analysis and behavioral reproduction

[0242] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[0243] Evidence extraction and verification

[0244] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[0245] Output of results

[0246] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[0247] User operations

[0248] Accessing the system

[0249] Users log in to the system using a smartphone application. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[0250] Specific examples

[0251] Example 1: Proof of innocence

[0252] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. The user can download this report and use it to proceed with legal proceedings. Below is an example of a prompt for the generative AI.

[0253] "Collect and analyze data to prove that the user was in the Shinjuku Station area between 12:30 and 1:30 PM on October 1, 2023. The required data is as follows: GPS location information, SNS message history, and camera footage. Based on this data, reconstruct the user's behavioral history and generate a credible report."

[0254] Example 2: Proof of being a victim of bullying

[0255] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it for school or legal action.

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1: Data collection

[0258] The server first collects surveillance camera footage, mobile phone location information, and social media message history. This is done using the APIs of the surveillance camera system, mobile phone network, and social media platform. The input data is raw data from each source, which is then integrated and stored in temporary storage. The server then converts this data into a format that can be processed collectively.

[0259] Step 2: Data Preprocessing

[0260] The server preprocesses the collected data and removes noise. Specifically, it applies algorithms to complement blurry surveillance camera footage, improve the accuracy of location information, and extract and filter important keywords from social media messages. The input data are raw video data, location information data, and social media message data, and the output is high-quality, consistent data.

[0261] Step 3: Data analysis and behavioral replication

[0262] The server uses the preprocessed data to perform analysis using generative AI. This analysis cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The input data is the preprocessed footage, location information, and social media messages, and the output is a reproduced behavioral history. The reproduced data can be visualized in a virtual environment.

[0263] Step 4: Evidence extraction and verification

[0264] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity. Specifically, it checks whether surveillance camera footage matches the location information and performs additional cross-referencing. The input data is the reconstructed behavioral history and information from each data source, and the output is evidence whose authenticity has been confirmed.

[0265] Step 5: Output the results

[0266] The server generates a PDF report of the analysis results based on the evidence whose authenticity has been confirmed and stores it in secure storage. Users can access this report and download it as needed. The input data is the evidence whose authenticity has been confirmed, and the output is a PDF report. Users access this report through a smartphone application.

[0267] 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.

[0268] Specific Embodiments of the System

[0269] This patented system is a data analysis system that utilizes generative AI, in which a server, terminal, user, and emotion engine work together. This system specializes in proving "non-existence" and "non-existence," and furthermore, by evaluating and utilizing the user's emotional state, it provides a more accurate analysis and user experience.

[0270] Server Processing

[0271] Data collection and integration

[0272] The server accesses various data sources to collect data related to the incident or target situation. Specifically, it downloads surveillance camera footage via the network, obtains mobile phone location information via API, and extracts social media message history from a database. The collected data is stored in temporary storage and later integrated.

[0273] Data Preprocessing

[0274] The server filters and denoises the collected data. To improve the quality of surveillance camera footage, algorithms are applied to fill in blurry areas. Inaccurate data is removed from mobile phone location information, and social media message histories are filtered for important keywords.

[0275] Data analysis and behavioral reproduction

[0276] The server inputs the preprocessed data into the AI ​​generator, cross-referencing the surveillance camera footage and location data. Based on the analyzed data, a simulation is run to recreate the target person's behavior, and the results are visualized in a virtual environment.

[0277] Evidence extraction and verification

[0278] The server extracts evidence from the reconstructed behavioral data, performs cross-reference verification using information from different data sources, evaluates its credibility, and selects only highly reliable evidence, which is then recorded in a database.

[0279] Use of emotion engine

[0280] The server uses an emotion engine to recognize the user's emotions and evaluates the user's stress level and emotional state based on the analysis results. Based on the emotion engine's recognition results, the server proposes appropriate feedback and actions to the user. In addition, the emotion data is used as part of the analysis by the generative AI, enabling more accurate behavioral reproduction.

[0281] Output of results

[0282] The server generates an analysis report based on the verified evidence, which is output in PDF format and stored in secure storage.

[0283] User operations

[0284] Accessing the system

[0285] Users log in to the system using their terminals. They can search for, select, and download analysis reports related to their interests. For example, to obtain an analysis report on a specific wrongful conviction case, users can enter the relevant time, location, and names of those involved as search keywords.

[0286] Use of emotional feedback

[0287] While the user is using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice. As a result, the system presents the analysis results and provides additional support information according to the user's stress level and emotional state. For example, easy-to-understand guidance and additional support are suggested to users in a high-stress state.

[0288] Specific examples

[0289] Example 1: Proof of innocence

[0290] In a case of false accusation, the server first collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. This data is preprocessed and analyzed by generative AI, proving that the target person was in a different location at the time of the crime. The evidence is verified from different data sources and compiled into a report as reliable evidence. The user downloads this report and proceeds with the legal process. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[0291] Example 2: Proof of being a victim of bullying

[0292] If bullying is suspected, the server collects and preprocesses surveillance camera footage from classrooms and schools, social media message history, and testimony audio data. Generative AI is used to analyze the data to confirm whether bullying has occurred. The analysis results are verified for authenticity using different data sources and output as a report. Users can download this report for reference in school or legal proceedings. During this process, the emotion engine evaluates the user's emotional state and suggests appropriate countermeasures.

[0293] The above is an embodiment of the patented system that combines an emotion engine. This system improves the accuracy of data analysis and enables flexible support that corresponds to the user's emotional state.

[0294] The processing flow will be explained below.

[0295] Program processing steps (system combining emotion engines)

[0296] Step 1: Data collection

[0297] The server accesses data sources related to the incident or situation of interest.

[0298] The server downloads the surveillance camera video via the network.

[0299] The server obtains the mobile phone's location information through an API.

[0300] The server extracts the SNS message history from the database.

[0301] The server stores the collected data in temporary storage and consolidates all the data.

[0302] Step 2: Data Preprocessing

[0303] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[0304] The server performs a process to remove noise from the mobile phone's location information.

[0305] The server filters the SNS message history for important keywords and removes irrelevant data.

[0306] The server stores the pre-processed data in a new storage.

[0307] Step 3: Data analysis and behavioral reproduction

[0308] The server inputs the preprocessed data into the generation AI.

[0309] The server uses generative AI to cross-reference security camera footage with location data.

[0310] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[0311] The server visualizes the behavioral simulation results in a virtual environment.

[0312] Step 4: Evidence extraction and verification

[0313] The server extracts important evidential data from the reconstructed behavioral data.

[0314] The server cross-references the extracted evidence with information from different data sources.

[0315] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[0316] The server records the final evidence and its authenticity in a database.

[0317] Step 5: Evaluation by the Emotion Engine

[0318] The server activates an emotion engine that recognizes the user's emotions in real time.

[0319] The server analyzes the user's facial expressions and voice data to assess their stress level and emotional state.

[0320] The server generates appropriate feedback and presents the analysis results according to the user's emotional state.

[0321] Step 6: Output the results

[0322] The server generates an analysis report based on the verified evidence.

[0323] The server outputs the report in PDF format and stores it in secure storage.

[0324] Step 7: User interaction

[0325] A user logs into the system using a terminal.

[0326] The user searches through the analysis results reports and selects the report of interest.

[0327] The user downloads the selected report and checks its contents.

[0328] Users can take appropriate legal action or measures based on the contents of the report.

[0329] Specific examples

[0330] Example 1: Proof of innocence

[0331] In step 1, the server collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the incident. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate the behavior of the target person. In step 4, evidence is extracted and verified from the recreated behavioral data. In step 5, the emotion engine evaluates the user's stress level and adjusts the presentation method of the analysis results. Finally, in step 6, an analysis result report is generated and saved, and in step 7, the user downloads this report to proceed with legal procedures.

[0332] Example 2: Proof of being a victim of bullying

[0333] In step 1, the server collects surveillance camera footage from within the school, social media message history, and testimony audio data. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate bullying behavior. In step 4, evidence is extracted and verified to confirm whether bullying behavior occurred. In step 5, the emotion engine evaluates the user's emotional state and provides appropriate feedback. Finally, in step 6, an evidence-based report is generated and saved, and in step 7, the user can download this report for use by school administrators or legal proceedings.

[0334] Through these specific processing steps, the present invention provides a system that efficiently proves "not doing something" or "not existing" and also responds to the user's emotional state.

[0335] Example 2

[0336] 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."

[0337] In recent years, the rapid increase in data volume has created a demand for effective data processing technologies. However, conventional systems require time for data collection, noise removal, analysis, and evidence extraction and verification. Furthermore, they struggle to process diverse data sources in a unified manner. Furthermore, they do not take into account the user's emotional state, resulting in a poor user experience. To address these challenges, a more advanced data analysis system is needed.

[0338] 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.

[0339] In this invention, the server includes means for using generative AI to process huge amounts of information at high speed and collect and integrate past cases and related information, means for preprocessing the collected information and removing noise, means for analyzing data using generative AI and simulating the target person's past behavior, means for extracting evidence from the reproduced information and verifying its credibility from multiple perspectives, means for recognizing the user's emotional state in real time and providing appropriate feedback based on the analysis results, and means for outputting the verification results as a report that the user can access. This enables data collection, analysis, and evidence verification to be carried out quickly and with high accuracy, and makes it possible to provide flexible support according to the user's emotional state.

[0340] "Generative AI" is an artificial intelligence technology that quickly generates and analyzes useful information from massive amounts of data.

[0341] "Information" is a general term for data collected from a variety of data sources, such as surveillance camera footage, location data of mobile devices, and message history from information exchange services.

[0342] "Noise" refers to unnecessary data or errors that should be removed during data processing and analysis.

[0343] "Simulation" is a method of virtually recreating the behavior of a target person based on collected and analyzed data.

[0344] "Evidence" is facts or information extracted from reproduced behavioral data and assessed for its veracity.

[0345] "Emotional state" refers to the psychological state of the user that is analyzed in real time from facial expressions, voice, etc.

[0346] "Feedback" refers to instructions and support information provided based on the user's emotional state and analysis results.

[0347] A "report" is a document that summarizes the analysis results and verified evidence, and is output in an electronic format such as PDF.

[0348] MODE FOR CARRYING OUT THE INVENTION

[0349] This invention is a data analysis system in which a server, a user's device, and an emotion engine work together. This system uses a generative AI model to process vast amounts of information at high speed, and collects and integrates past cases and related information. The detailed configuration is described below.

[0350] Server Processing

[0351] A server primarily uses the following hardware and software components:

[0352] Hardware: A server machine with a high-performance CPU and GPU, sufficient memory and storage.

[0353] Software: Database management systems (e.g., MySQL, PostgreSQL), API access tools, generative AI models (e.g., GPT-3, BERT), simulation engines (e.g., Unity), sentiment analysis engines.

[0354] Data collection

[0355] The server collects data from various information sources, such as surveillance footage, location information of mobile devices, and message history from information exchange services. For example, it downloads surveillance camera footage via the network, obtains mobile phone location information via an API, and extracts SNS messages from a database.

[0356] Data Preprocessing

[0357] The collected data cannot be used as is, so it is filtered and noise-removed. Specifically, surveillance camera footage is supplemented with super-resolution technology, location data accuracy is evaluated to remove inaccurate data, and social media messages are filtered using specific keywords.

[0358] Data Analysis and Simulation

[0359] The preprocessed data is input into a generative AI model for analysis. Based on the analysis results, a simulation is performed to reproduce the target person's behavior, and the simulation results are visualized in a 3D environment. This makes it possible to visually reproduce past behavior.

[0360] Evidence extraction and verification

[0361] Evidence is extracted from the reconstructed behavioral data and its veracity is verified from multiple perspectives. Data is cross-referenced with other sources, and only reliable evidence is included in the final report. This report is generated in PDF format and stored in secure storage.

[0362] Use of emotion engine

[0363] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device. Based on the analysis results, the server evaluates the user's stress level and emotional state and dynamically adjusts the system's feedback and support information.

[0364] User operations

[0365] Accessing the system

[0366] Users log in to the system using their own devices. After logging in, they can search for and download analysis results reports. For example, to obtain a report on a specific wrongful conviction case, users can enter the relevant time, place, and names of those involved as search keywords.

[0367] Use of emotional feedback

[0368] The system analyzes the user's emotional state in real time while they are using the system, and provides easy-to-understand guidance and additional support information based on the analysis results. If the user is in a high-stress state, the system will suggest appropriate measures, improving the quality of the user experience.

[0369] Specific examples

[0370] Example 1: Proof of innocence

[0371] In a case of false accusation, the server first collects surveillance footage, vehicle location information, and public transportation usage history from the day of the crime. This data is preprocessed and analyzed using a generative AI model, proving that the target was in a different location at the time of the crime. This is compiled into a report as reliable evidence, which the user can download to proceed with legal proceedings. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[0372] Example 2: Proof of being a victim of bullying

[0373] If bullying is suspected, the server collects and preprocesses classroom and school surveillance footage, social media message history, and testimony audio data. It then uses a generative AI model to analyze the data and confirm whether bullying has occurred. The analysis results, which have been verified for reliability, are output as a report that users can download and use as reference for school and legal procedures. During this process, the emotion engine assesses the user's emotional state and suggests appropriate countermeasures.

[0374] Examples of prompt statements

[0375] 1. "Analyze CCTV footage and location data related to a false accusation case to prove that the subject was somewhere else at the time of the crime."

[0376] 2. "Based on data on bullying behavior within the school, please collect evidence of bullying and prepare a report."

[0377] In this way, the system of the present invention is highly efficient and accurate in data analysis, and by combining it with an emotion engine to improve the user experience, it achieves more reliable evidence collection and report generation.

[0378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0379] Step 1:

[0380] Data collection

[0381] The server collects necessary information from data sources such as surveillance camera footage, mobile location information, and information exchange service message history. Specifically, it downloads surveillance camera footage from a specified URL using an HTTP request, obtains mobile phone location information via an API, and extracts SNS messages from a database using SQL queries.

[0382] Input: Data source URL, API key, SQL query

[0383] Output: A set of collected information

[0384] Step 2:

[0385] Data Preprocessing

[0386] The server removes noise from the collected information and formats it into a form suitable for analysis. For surveillance camera footage, super-resolution technology is applied to fill in blurry areas, for mobile phone location information, location data below a certain threshold is removed after evaluating its accuracy, and for social media messages, specific keywords are filtered.

[0387] Input: A set of collected information

[0388] Output: A set of preprocessed information

[0389] Step 3:

[0390] Data analysis

[0391] The server inputs the preprocessed information into a generative AI model for analysis. The generative AI model (e.g., GPT-3, BERT) estimates the target person's behavior based on the input data and generates a timeline.

[0392] Input: A set of preprocessed information

[0393] Output: Analysis results (timeline of estimated behavior)

[0394] Step 4:

[0395] Behavioral reproduction

[0396] The server performs a simulation to reproduce the target person's behavior based on the analysis results, and visualizes the target person's behavior in a virtual 3D environment using a simulation engine.

[0397] Input: Analysis results (estimated timeline of behavior)

[0398] Output: Visualized behavioral simulation

[0399] Step 5:

[0400] Evidence extraction and verification

[0401] The server extracts evidence from the re-created behavioral simulations and verifies its authenticity by cross-referencing it with other data sources. It compares data from different sources and selects only matching data as reliable evidence.

[0402] Input: Visualized behavioral simulations, data from other data sources

[0403] Output: A set of verified evidence

[0404] Step 6:

[0405] Use of emotion engine

[0406] The server inputs facial expression and voice data collected from the user's device into an emotion analysis engine in real time to evaluate the user's emotional state. The results of this evaluation are fed back to the generative AI model, and the system's output is adjusted based on the analysis results and the feedback.

[0407] Input: User's facial expression data, voice data

[0408] Output: Emotion evaluation results, adjusted analysis results, and feedback content

[0409] Step 7:

[0410] Output of results

[0411] The server automatically generates a report based on the verified evidence and the adjusted analysis results. The report is saved in PDF format and uploaded to secure storage. Users can download the report.

[0412] Input: Verified evidence set, adjusted analysis results

[0413] Output: Report in PDF format

[0414] Step 8:

[0415] User operations

[0416] Users log in to the system using a terminal and search, select, and download analysis results reports related to their interests.

[0417] Input: User credentials, search query

[0418] Output: Download link for analysis report

[0419] Step 9:

[0420] Use of emotional feedback

[0421] While the user is using the system, the device's camera and microphone are used to collect facial and voice data in real time, allowing the system to continuously analyze the user's emotional state and provide additional support information or guidance when necessary.

[0422] Input: Real-time facial expression data, voice data

[0423] Output: Additional supporting information and guidance

[0424] (Application example 2)

[0425] 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."

[0426] While conventional data analysis systems can efficiently process massive amounts of data and extract reliable evidence, they are unable to provide feedback that takes into account the user's emotional state or real-time warnings when an abnormality occurs. This has resulted in problems that reduce users' sense of security and satisfaction when using the system. Furthermore, they lack the functionality to remotely check surveillance camera footage and quickly detect suspicious behavior.

[0427] 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.

[0428] In this invention, the server includes: means for using a generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using the generative AI and simulating the past behavior of a target person; means for extracting evidence from the reproduced data and verifying its credibility from multiple perspectives; means for outputting the verification results as a report accessible to the user; means for recognizing the user's emotional state and providing feedback and additional support information based on the analysis results; means for the user to remotely check surveillance camera footage and detect anomalies; and means for providing a warning in real time when an anomaly is detected. This enables advanced data analysis and real-time anomaly detection while taking the user's emotional state into consideration.

[0429] "Generative AI" is an artificial intelligence technology that processes massive amounts of data quickly and efficiently, and reproduces behavior based on past cases and related information.

[0430] "Data preprocessing" refers to the process of removing noise and improving the quality of collected data before analyzing it.

[0431] "Simulation methods" are methods for recreating the target person's past behavior based on data analyzed using generative AI.

[0432] "Evidence extraction" is the process of extracting important information from the analyzed data and verifying its authenticity.

[0433] "Emotional state recognition" is a technology that analyzes a user's emotions from their facial expressions and voice and evaluates their state.

[0434] "Feedback provision means" refers to a method of presenting appropriate actions and support information to users based on the analysis results.

[0435] "Remote monitoring means" refers to a means by which a user can check surveillance camera footage from a remote location and detect abnormalities.

[0436] "Real-time warning means" refers to a method of notifying the user immediately when an abnormality is detected.

[0437] This invention is a data analysis system that utilizes generative AI, and is realized through the cooperative operation of a server, a terminal, a user, and an emotion engine. The specific configuration and operation of the system are described below.

[0438] System configuration

[0439] Hardware

[0440] server

[0441] A computer with a powerful processor and large memory capacity

[0442] Terminal

[0443] Smartphone (iOS or Android)

[0444] Surveillance cameras (network-connectable)

[0445] Camera and microphone for detecting the user's facial expressions and voice

[0446] software

[0447] Generative AI Models

[0448] For example, GPT-4

[0449] API for emotion recognition

[0450] For example, Microsoft Azure's Emotion API

[0451] Database

[0452] For example, Firebase, MySQL, etc.

[0453] Development environment

[0454] For example, Xcode, Android Studio

[0455] Server Processing

[0456] The server performs the following process.

[0457] 1. Data Collection and Integration

[0458] Use APIs to collect surveillance camera footage, location information, and social media messages.

[0459] The collected data is stored in temporary storage and later consolidated.

[0460] 2. Data Preprocessing

[0461] It runs algorithms to improve the quality of video data, remove noise from location information, and filter keywords from social media messages.

[0462] 3. Data Analysis

[0463] Preprocessed data is input into the generative AI model, and analysis and behavior reproduction are performed.

[0464] Simulations are performed based on the analyzed data and visualized in a virtual environment.

[0465] 4. Extraction and verification of evidence

[0466] Extract evidence from the reproduced data and perform cross-reference verification.

[0467] Only reliable evidence is selected and ultimately recorded in a database.

[0468] 5. Outputting the results

[0469] An analysis result report is generated based on the verified evidence and output in PDF format.

[0470] 6. Use of Emotion Engines

[0471] It recognizes the user's emotional state and provides feedback and additional support information based on the analysis results.

[0472] Terminal handling

[0473] The user uses the device to perform the following operations:

[0474] 1. Access to the System

[0475] Users log in to the system using their smartphone, search for analysis result reports, select them and download them.

[0476] 2. Check the surveillance camera footage

[0477] You can check the footage from your home or office surveillance cameras in real time from your smartphone to check for any abnormalities.

[0478] 3. Real-time alerts

[0479] If an anomaly is detected, the system will alert the user in real time.

[0480] User operations

[0481] The user uses the system by performing the following operations:

[0482] 1. Use emotional feedback

[0483] While using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice, and provides feedback based on their stress level and emotional state.

[0484] Specific examples

[0485] For example, while the user is away from home, the system can analyze suspicious behavior based on home security camera footage, mobile phone location information, and social media message history, and generate a report. If an abnormality is detected, the emotion engine will evaluate the user's stress level and provide necessary feedback.

[0486] "Recreate the target person's actions using the following data: surveillance camera footage, location information, and social media message history."

[0487] This system enables advanced data analysis and real-time anomaly detection while taking into account the user's emotional state.

[0488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0489] Step 1:

[0490] The server collects data such as surveillance camera footage, mobile phone location information, and social media message history. Input data is collected from each data source through APIs and stored in temporary storage. The output is the integrated raw data.

[0491] Step 2:

[0492] The server performs preprocessing on the collected data. Filtering is performed to improve the quality of surveillance camera footage, and noise is removed from location information. Filtering is also performed based on important keywords from SNS message history. The input data is raw data, and the output data is preprocessed data.

[0493] Step 3:

[0494] The server inputs the preprocessed data into the generative AI model and performs data analysis. The generative AI model performs the analysis and reproduces the target person's behavior. The input data is the preprocessed data, and the output data is the reproduced behavior data. In this case, the prompt used is "Please reproduce the target person's behavior based on the following data: surveillance camera footage, location information, and SNS message history."

[0495] Step 4:

[0496] The server extracts evidence from the reproduced behavioral data and cross-references its authenticity from multiple perspectives. It calculates the degree of consistency from multiple data sources and selects only highly reliable evidence. The input data is the reproduced behavioral data, and the output data is the verified evidence.

[0497] Step 5:

[0498] The server generates an analysis result report based on the verified evidence and outputs it in PDF format. The report is stored in secure storage. The input data is the verified evidence, and the output data is the PDF report.

[0499] Step 6:

[0500] Users log in to the system using a terminal, search for and download analysis result reports. The input data is the user's search keywords, and the output data is a download link for the report.

[0501] Step 7:

[0502] Users can use their devices to remotely monitor and check the surveillance camera footage in real time. The system uses an anomaly detection algorithm to provide real-time warnings when an abnormality occurs. The input data is the surveillance camera footage, and the output data is an anomaly detection warning.

[0503] Step 8:

[0504] The server recognizes the user's emotional state using an emotion engine and provides feedback and additional support information based on the analysis results. The input data is the user's facial expressions and voice, and the output data is the feedback and support information.

[0505] 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.

[0506] 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.

[0507] 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.

[0508] [Second embodiment]

[0509] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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).

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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.

[0519] 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.

[0520] 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."

[0521] Specific Embodiments of the System

[0522] This patented system is a data analysis system that utilizes generative AI, where servers, terminals, and users work together. This system is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying.

[0523] Server Processing

[0524] Data collection and integration

[0525] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[0526] Data Preprocessing

[0527] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[0528] Data analysis and behavioral reproduction

[0529] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[0530] Evidence extraction and verification

[0531] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[0532] Output of results

[0533] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[0534] User operations

[0535] Accessing the system

[0536] Users log in to the system using their terminals. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[0537] Specific examples

[0538] Example 1: Proof of innocence

[0539] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. Users can download this report and use it to proceed with legal proceedings.

[0540] Example 2: Proof of being a victim of bullying

[0541] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it to help with school and legal responses.

[0542] As described above, this system makes full use of generative AI to process huge amounts of data efficiently and quickly to prove that someone "did not do it" or "did not exist," thereby helping to avoid false accusations and bullying.

[0543] The processing flow will be explained below.

[0544] Program processing steps

[0545] Step 1: Data collection

[0546] The server accesses data sources related to the incident or situation of interest.

[0547] The server downloads the surveillance camera video via the network.

[0548] The server obtains the mobile phone's location information through an API.

[0549] The server extracts the SNS message history from the database.

[0550] The server stores the collected data in temporary storage and consolidates all the data.

[0551] Step 2: Data Preprocessing

[0552] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[0553] The server performs a process to remove noise from the mobile phone's location information.

[0554] The server filters the SNS message history for important keywords and removes irrelevant data.

[0555] The server stores the pre-processed data in a new storage.

[0556] Step 3: Data analysis and behavioral reproduction

[0557] The server inputs the preprocessed data into the generation AI.

[0558] The server uses generative AI to cross-reference security camera footage with location data.

[0559] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[0560] The server visualizes the behavioral simulation results in a virtual environment.

[0561] Step 4: Evidence extraction and verification

[0562] The server extracts important evidential data from the reconstructed behavioral data.

[0563] The server cross-references the extracted evidence with information from different data sources.

[0564] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[0565] The server records the final evidence and its authenticity in a database.

[0566] Step 5: Output the results

[0567] The server generates an analysis report based on the verified evidence.

[0568] The server outputs the report in PDF format and stores it in secure storage.

[0569] Step 6: User interaction

[0570] A user logs into the system using a terminal.

[0571] The user searches through the analysis results reports and selects the report of interest.

[0572] The user downloads the selected report and checks its contents.

[0573] Users can take appropriate legal action or measures based on the contents of the report.

[0574] These are the specific processing steps of the system based on patent claims. This system allows efficient and reliable proof of non-existence or non-commitment.

[0575] Example 1

[0576] 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."

[0577] Conventional data analysis systems have the problem of making it difficult to prove false accusations, bullying, and other crimes that "did not occur" or "did not exist." The manual process of collecting, integrating, analyzing, and verifying data is extremely time-consuming. Furthermore, because much of the information contains noise, it is difficult to accurately reproduce behavior or verify the credibility of evidence. Furthermore, there are insufficient ways for users to easily access, search, and download analysis results.

[0578] 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.

[0579] In this invention, the server includes: means for using generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using generative AI and simulating the target person's past behavior; means for extracting evidence from the reproduced data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report and saving it in a secure storage device; and means for users to log in to the system using their terminals and search for and download analysis result reports of interest. This makes it possible to efficiently prove that someone did not commit or did not exist, such as a false accusation or bullying victim.

[0580] "Generative AI" refers to algorithms that use artificial intelligence techniques to process large amounts of data and generate new data and information.

[0581] "Data collection" is the process of gathering the necessary information from various data sources, including surveillance camera footage, location information, and social media message history.

[0582] "Data integration" refers to the process of centrally managing collected data and converting it into a unified format.

[0583] "Data preprocessing" refers to the data cleaning and filtering procedures used to remove noise from raw data and make it ready for analysis.

[0584] "Denoising" refers to the process of removing errors and unnecessary information from data.

[0585] "Data analysis" refers to the process of extracting useful information from collected and pre-processed data using statistical methods and artificial intelligence techniques.

[0586] "Behavioral reproduction" refers to reconstructing the past behavior of a specific person or subject as a simulation or model based on analyzed data.

[0587] "Evidence extraction" refers to the process of extracting logically significant information from replicated data and using it to support a particular conclusion.

[0588] "Verification of credibility" refers to the process of checking the reliability of the evidence obtained using different data sources and cross-referencing.

[0589] "Report output" refers to compiling the analysis and verification results in document form and making them available for viewing by users.

[0590] "Secure storage device" refers to a storage system that has security features such as authentication and encryption.

[0591] "User" refers to an individual or organization that uses this system to search for and download analysis results reports.

[0592] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[0593] "Login" refers to the authentication process required for a user to access a system.

[0594] "Search" refers to the process of locating information of interest using specific keywords and filters.

[0595] "Downloading" refers to copying data or files to your device via the Internet.

[0596] MODE FOR CARRYING OUT THE INVENTION

[0597] System Overview

[0598] This invention is a data analysis system that utilizes generative AI, and is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying. The system operates in cooperation with the server, terminals, and users.

[0599] Server Roles

[0600] The server is responsible for:

[0601] 1. Data Collection and Integration

[0602] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history. This is done by downloading data using network APIs and database queries. The collected data is first stored in temporary storage (e.g., cloud storage) and then integrated in a database system (e.g., a relational database).

[0603] 2. Data Preprocessing

[0604] The server filters and denoises the collected data. For example, it uses the OpenCV library to fill in blurry areas in security camera footage and removes low-precision data from location data. For social media messages, it uses the NLTK library to filter for important keywords.

[0605] 3. Data analysis and behavioral reproduction

[0606] The server then uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis cross-references time and location information to recreate a person's behavior at a specific time and place. The results are then visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[0607] 4. Extraction and verification of evidence

[0608] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that uses SQL queries and custom scripts.

[0609] 5. Outputting the results

[0610] The verified evidence is generated as an analysis report in PDF format, which is saved in secure storage (e.g., cloud storage). The PDF is generated using LaTeX and HTML to PDF libraries.

[0611] User Roles

[0612] The user does the following:

[0613] 1. Access to the System

[0614] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[0615] 2. Search and download analysis results reports

[0616] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[0617] Specific examples

[0618] 1. Proof of Innocent Conviction

[0619] The server collects and consolidates all data related to a false accusation case, including surveillance camera footage from the day of the crime, mobile phone location information, and transportation usage history. This data is then preprocessed and analyzed using generative AI. The analysis proves that the target person was in a different location at the time of the crime. This evidence is verified from multiple data sources and compiled into a report. Users can download this report and use it to further legal proceedings.

[0620] Example prompt sentence:

[0621] "Please tell me the results of the analysis of the incident that occurred on January 1, 2023."

[0622] 2. Proof of being a victim of bullying

[0623] In cases where bullying is suspected, the server collects school surveillance camera footage, social media message history, and testimony audio data. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying occurred. The results of this analysis are verified using different data sources and compiled into a report as reliable evidence. Users can download this report and use it for school or legal action.

[0624] Example prompt sentence:

[0625] "Please tell me the results of an analysis of bullying that occurred at a specific school on January 1, 2023."

[0626] The above is a mode for carrying out the invention, and this system makes it possible to prove false accusations and bullying victims efficiently and with high accuracy.

[0627] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0628] Step 1: Data collection and integration

[0629] concrete action

[0630] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history, by downloading data using network APIs and database queries.

[0631] input

[0632] API access information and queries for each data source (surveillance cameras, mobile phone location information, social media messages).

[0633] Data processing and calculation

[0634] Fetch data using network APIs or SQL queries and store it in temporary storage (e.g. cloud storage).

[0635] output

[0636] Temporarily stored raw data before preprocessing.

[0637] Step 2: Data Preprocessing

[0638] concrete action

[0639] The server performs quality filtering and noise reduction on the collected data. For example, it uses the OpenCV library to fill in blurry parts of surveillance camera footage, and a Python script to remove inaccurate parts of location data. For social media messages, it uses the NLTK library to filter for important keywords.

[0640] input

[0641] Temporarily stored raw data before preprocessing.

[0642] Data processing and calculation

[0643] Generate a quality-enhanced dataset through filtering and denoising.

[0644] output

[0645] Preprocessed data with improved quality.

[0646] Step 3: Data analysis and behavioral replication

[0647] concrete action

[0648] The server uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis involves cross-referencing time and location information to simulate a person's behavior at a specific time and place. The results of this analysis are visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[0649] input

[0650] Preprocessed dataset.

[0651] Data processing and calculation

[0652] Generative AI models are used to analyze data and run simulations to reproduce specific behaviors.

[0653] output

[0654] Analysis results and behavioral simulation data.

[0655] Step 4: Evidence extraction and verification

[0656] concrete action

[0657] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that involves SQL queries and custom scripts.

[0658] input

[0659] Reproduced behavioral simulation data.

[0660] Data processing and calculation

[0661] We extract evidence and verify data through cross-referencing to confirm its authenticity.

[0662] output

[0663] Verified evidence data.

[0664] Step 5: Output the results

[0665] concrete action

[0666] The server generates a report summarizing the results in PDF format based on the evidence of the analysis and verification. This report is saved in secure storage (e.g., cloud storage). The PDF generation uses LaTeX and HTML to PDF libraries.

[0667] input

[0668] Verified evidence data.

[0669] Data processing and calculation

[0670] Generate reports and export them in PDF format.

[0671] output

[0672] Analysis results report stored in secure storage.

[0673] Step 6: Access the system

[0674] concrete action

[0675] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[0676] input

[0677] The user's authentication information.

[0678] Data processing and calculation

[0679] Uses an authentication system to verify user credentials and allow login.

[0680] output

[0681] Access rights to the system.

[0682] Step 7: Find and download the analysis report

[0683] concrete action

[0684] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[0685] input

[0686] Search keywords.

[0687] Data processing and calculation

[0688] Run a search query to filter relevant reports.

[0689] output

[0690] User downloadable analysis report.

[0691] (Application example 1)

[0692] 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."

[0693] In recent years, it has become increasingly difficult to prove false accusations and bullying, resulting in many cases of innocent people being treated unfairly. In particular, in today's world where much evidence is digitized, there is a need for efficient methods to collect, analyze, and verify the authenticity of vast amounts of data. Another issue is the lack of tools that allow users to easily prove their own actions. To solve this problem, an advanced data analysis system using generative AI is needed.

[0694] 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.

[0695] In this invention, the server includes: means for processing massive amounts of data at high speed using a generative AI and collecting and integrating past cases and related information; means for preprocessing the collected data and removing noise; simulation means for analyzing the data using a generative AI and recreating the target person's past behavior; means for extracting evidence from the recreated data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report accessible to the user; application means installed on a smartphone for automatically collecting location information, usage history, and camera footage; preprocessing means for removing noise and filtering the collected data; verification means for cross-referencing information collected from multiple data sources and checking its authenticity; and output means for generating a PDF report of the analysis results. This enables users to easily and reliably collect, analyze, and manage evidence when proving their innocence or existence.

[0696] "Generative AI" is a type of artificial intelligence that uses generative algorithms to create new data and information.

[0697] "Big data" refers to the large amount of digital data collected from a wide variety of information sources.

[0698] "Past events" refers to data or information about specific events or occurrences that have occurred in the past.

[0699] "Collection and integration" is the process of bringing together data from multiple sources and converting it into a unified format.

[0700] "Preprocessing" is a preparatory step to remove noise from the data to be analyzed and improve its quality.

[0701] "Noise reduction" is the process of eliminating meaningless data and errors.

[0702] "Analysis" refers to the process of examining data to extract and understand information.

[0703] "Simulation of past behavior" is the process of reconstructing a person's behavior at a specific time and place on a computer based on collected data.

[0704] "Evidence extraction" is the process of extracting useful information or data from the analysis results.

[0705] "Verifying credibility" is the process of confirming the accuracy and reliability of the evidence or data obtained.

[0706] A "report" refers to a document that organizes and documents the results of analysis and verification.

[0707] An "application installed on a smartphone" is software with specific functions that runs on a smartphone.

[0708] "Location information" refers to data that indicates a location at a particular point in time.

[0709] "Usage History" refers to records of how a user uses a device or application.

[0710] "Camera footage" refers to visual data captured by a digital camera.

[0711] "Noise reduction and filtering" is the process of removing unnecessary parts to improve the quality of collected data.

[0712] "Cross-referencing" refers to comparing data obtained from different sources with each other.

[0713] "PDF format" is an abbreviation for Portable Document Format developed by Adobe, and is a format for electronic documents.

[0714] Specific Embodiments of the System

[0715] This system is a data analysis system that utilizes generative AI, where the server, terminal, and user work together. This system is particularly specialized in proving that someone did not commit or exist, such as a false accusation or bullying victim.

[0716] Server Processing

[0717] Data collection and integration

[0718] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[0719] Data Preprocessing

[0720] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[0721] Data analysis and behavioral reproduction

[0722] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[0723] Evidence extraction and verification

[0724] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[0725] Output of results

[0726] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[0727] User operations

[0728] Accessing the system

[0729] Users log in to the system using a smartphone application. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[0730] Specific examples

[0731] Example 1: Proof of innocence

[0732] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. The user can download this report and use it to proceed with legal proceedings. Below is an example of a prompt for the generative AI.

[0733] "Collect and analyze data to prove that the user was in the Shinjuku Station area between 12:30 and 1:30 PM on October 1, 2023. The required data is as follows: GPS location information, SNS message history, and camera footage. Based on this data, reconstruct the user's behavioral history and generate a credible report."

[0734] Example 2: Proof of being a victim of bullying

[0735] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it for school or legal action.

[0736] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0737] Step 1: Data collection

[0738] The server first collects surveillance camera footage, mobile phone location information, and social media message history. This is done using the APIs of the surveillance camera system, mobile phone network, and social media platform. The input data is raw data from each source, which is then integrated and stored in temporary storage. The server then converts this data into a format that can be processed collectively.

[0739] Step 2: Data Preprocessing

[0740] The server preprocesses the collected data and removes noise. Specifically, it applies algorithms to complement blurry surveillance camera footage, improve the accuracy of location information, and extract and filter important keywords from social media messages. The input data are raw video data, location information data, and social media message data, and the output is high-quality, consistent data.

[0741] Step 3: Data analysis and behavioral replication

[0742] The server uses the preprocessed data to perform analysis using generative AI. This analysis cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The input data is the preprocessed footage, location information, and social media messages, and the output is a reproduced behavioral history. The reproduced data can be visualized in a virtual environment.

[0743] Step 4: Evidence extraction and verification

[0744] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity. Specifically, it checks whether surveillance camera footage matches the location information and performs additional cross-referencing. The input data is the reconstructed behavioral history and information from each data source, and the output is evidence whose authenticity has been confirmed.

[0745] Step 5: Output the results

[0746] The server generates a PDF report of the analysis results based on the evidence whose authenticity has been confirmed and stores it in secure storage. Users can access this report and download it as needed. The input data is the evidence whose authenticity has been confirmed, and the output is a PDF report. Users access this report through a smartphone application.

[0747] 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.

[0748] Specific Embodiments of the System

[0749] This patented system is a data analysis system that utilizes generative AI, in which a server, terminal, user, and emotion engine work together. This system specializes in proving "non-existence" and "non-existence," and furthermore, by evaluating and utilizing the user's emotional state, it provides a more accurate analysis and user experience.

[0750] Server Processing

[0751] Data collection and integration

[0752] The server accesses various data sources to collect data related to the incident or target situation. Specifically, it downloads surveillance camera footage via the network, obtains mobile phone location information via API, and extracts social media message history from a database. The collected data is stored in temporary storage and later integrated.

[0753] Data Preprocessing

[0754] The server filters and denoises the collected data. To improve the quality of surveillance camera footage, algorithms are applied to fill in blurry areas. Inaccurate data is removed from mobile phone location information, and social media message histories are filtered for important keywords.

[0755] Data analysis and behavioral reproduction

[0756] The server inputs the preprocessed data into the AI ​​generator, cross-referencing the surveillance camera footage and location data. Based on the analyzed data, a simulation is run to recreate the target person's behavior, and the results are visualized in a virtual environment.

[0757] Evidence extraction and verification

[0758] The server extracts evidence from the reconstructed behavioral data, performs cross-reference verification using information from different data sources, evaluates its credibility, and selects only highly reliable evidence, which is then recorded in a database.

[0759] Use of emotion engine

[0760] The server uses an emotion engine to recognize the user's emotions and evaluates the user's stress level and emotional state based on the analysis results. Based on the emotion engine's recognition results, the server proposes appropriate feedback and actions to the user. In addition, the emotion data is used as part of the analysis by the generative AI, enabling more accurate behavioral reproduction.

[0761] Output of results

[0762] The server generates an analysis report based on the verified evidence, which is output in PDF format and stored in secure storage.

[0763] User operations

[0764] Accessing the system

[0765] Users log in to the system using their terminals. They can search for, select, and download analysis reports related to their interests. For example, to obtain an analysis report on a specific wrongful conviction case, users can enter the relevant time, location, and names of those involved as search keywords.

[0766] Use of emotional feedback

[0767] While the user is using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice. As a result, the system presents the analysis results and provides additional support information according to the user's stress level and emotional state. For example, easy-to-understand guidance and additional support are suggested to users in a high-stress state.

[0768] Specific examples

[0769] Example 1: Proof of innocence

[0770] In a case of false accusation, the server first collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. This data is preprocessed and analyzed by generative AI, proving that the target person was in a different location at the time of the crime. The evidence is verified from different data sources and compiled into a report as reliable evidence. The user downloads this report and proceeds with the legal process. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[0771] Example 2: Proof of being a victim of bullying

[0772] If bullying is suspected, the server collects and preprocesses surveillance camera footage from classrooms and schools, social media message history, and testimony audio data. Generative AI is used to analyze the data to confirm whether bullying has occurred. The analysis results are verified for authenticity using different data sources and output as a report. Users can download this report for reference in school or legal proceedings. During this process, the emotion engine evaluates the user's emotional state and suggests appropriate countermeasures.

[0773] The above is an embodiment of the patented system that combines an emotion engine. This system improves the accuracy of data analysis and enables flexible support that corresponds to the user's emotional state.

[0774] The processing flow will be explained below.

[0775] Program processing steps (system combining emotion engines)

[0776] Step 1: Data collection

[0777] The server accesses data sources related to the incident or situation of interest.

[0778] The server downloads the surveillance camera video via the network.

[0779] The server obtains the mobile phone's location information through an API.

[0780] The server extracts the SNS message history from the database.

[0781] The server stores the collected data in temporary storage and consolidates all the data.

[0782] Step 2: Data Preprocessing

[0783] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[0784] The server performs a process to remove noise from the mobile phone's location information.

[0785] The server filters the SNS message history for important keywords and removes irrelevant data.

[0786] The server stores the pre-processed data in a new storage.

[0787] Step 3: Data analysis and behavioral reproduction

[0788] The server inputs the preprocessed data into the generation AI.

[0789] The server uses generative AI to cross-reference security camera footage with location data.

[0790] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[0791] The server visualizes the behavioral simulation results in a virtual environment.

[0792] Step 4: Evidence extraction and verification

[0793] The server extracts important evidential data from the reconstructed behavioral data.

[0794] The server cross-references the extracted evidence with information from different data sources.

[0795] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[0796] The server records the final evidence and its authenticity in a database.

[0797] Step 5: Evaluation by the Emotion Engine

[0798] The server activates an emotion engine that recognizes the user's emotions in real time.

[0799] The server analyzes the user's facial expressions and voice data to assess their stress level and emotional state.

[0800] The server generates appropriate feedback and presents the analysis results according to the user's emotional state.

[0801] Step 6: Output the results

[0802] The server generates an analysis report based on the verified evidence.

[0803] The server outputs the report in PDF format and stores it in secure storage.

[0804] Step 7: User interaction

[0805] A user logs into the system using a terminal.

[0806] The user searches through the analysis results reports and selects the report of interest.

[0807] The user downloads the selected report and checks its contents.

[0808] Users can take appropriate legal action or measures based on the contents of the report.

[0809] Specific examples

[0810] Example 1: Proof of innocence

[0811] In step 1, the server collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the incident. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate the behavior of the target person. In step 4, evidence is extracted and verified from the recreated behavioral data. In step 5, the emotion engine evaluates the user's stress level and adjusts the presentation method of the analysis results. Finally, in step 6, an analysis result report is generated and saved, and in step 7, the user downloads this report to proceed with legal procedures.

[0812] Example 2: Proof of being a victim of bullying

[0813] In step 1, the server collects surveillance camera footage from within the school, social media message history, and testimony audio data. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate bullying behavior. In step 4, evidence is extracted and verified to confirm whether bullying behavior occurred. In step 5, the emotion engine evaluates the user's emotional state and provides appropriate feedback. Finally, in step 6, an evidence-based report is generated and saved, and in step 7, the user can download this report for use by school administrators or legal proceedings.

[0814] Through these specific processing steps, the present invention provides a system that efficiently proves "not doing something" or "not existing" and also responds to the user's emotional state.

[0815] Example 2

[0816] 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."

[0817] In recent years, the rapid increase in data volume has created a demand for effective data processing technologies. However, conventional systems require time for data collection, noise removal, analysis, and evidence extraction and verification. Furthermore, they struggle to process diverse data sources in a unified manner. Furthermore, they do not take into account the user's emotional state, resulting in a poor user experience. To address these challenges, a more advanced data analysis system is needed.

[0818] 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.

[0819] In this invention, the server includes means for using generative AI to process huge amounts of information at high speed and collect and integrate past cases and related information, means for preprocessing the collected information and removing noise, means for analyzing data using generative AI and simulating the target person's past behavior, means for extracting evidence from the reproduced information and verifying its credibility from multiple perspectives, means for recognizing the user's emotional state in real time and providing appropriate feedback based on the analysis results, and means for outputting the verification results as a report that the user can access. This enables data collection, analysis, and evidence verification to be carried out quickly and with high accuracy, and makes it possible to provide flexible support according to the user's emotional state.

[0820] "Generative AI" is an artificial intelligence technology that quickly generates and analyzes useful information from massive amounts of data.

[0821] "Information" is a general term for data collected from a variety of data sources, such as surveillance camera footage, location data of mobile devices, and message history from information exchange services.

[0822] "Noise" refers to unnecessary data or errors that should be removed during data processing and analysis.

[0823] "Simulation" is a method of virtually recreating the behavior of a target person based on collected and analyzed data.

[0824] "Evidence" is facts or information extracted from reproduced behavioral data and assessed for its veracity.

[0825] "Emotional state" refers to the psychological state of the user that is analyzed in real time from facial expressions, voice, etc.

[0826] "Feedback" refers to instructions and support information provided based on the user's emotional state and analysis results.

[0827] A "report" is a document that summarizes the analysis results and verified evidence, and is output in an electronic format such as PDF.

[0828] MODE FOR CARRYING OUT THE INVENTION

[0829] This invention is a data analysis system in which a server, a user's device, and an emotion engine work together. This system uses a generative AI model to process vast amounts of information at high speed, and collects and integrates past cases and related information. The detailed configuration is described below.

[0830] Server Processing

[0831] A server primarily uses the following hardware and software components:

[0832] Hardware: A server machine with a high-performance CPU and GPU, sufficient memory and storage.

[0833] Software: Database management systems (e.g., MySQL, PostgreSQL), API access tools, generative AI models (e.g., GPT-3, BERT), simulation engines (e.g., Unity), sentiment analysis engines.

[0834] Data collection

[0835] The server collects data from various information sources, such as surveillance footage, location information of mobile devices, and message history from information exchange services. For example, it downloads surveillance camera footage via the network, obtains mobile phone location information via an API, and extracts SNS messages from a database.

[0836] Data Preprocessing

[0837] The collected data cannot be used as is, so it is filtered and noise-removed. Specifically, surveillance camera footage is supplemented with super-resolution technology, location data accuracy is evaluated to remove inaccurate data, and social media messages are filtered using specific keywords.

[0838] Data Analysis and Simulation

[0839] The preprocessed data is input into a generative AI model for analysis. Based on the analysis results, a simulation is performed to reproduce the target person's behavior, and the simulation results are visualized in a 3D environment. This makes it possible to visually reproduce past behavior.

[0840] Evidence extraction and verification

[0841] Evidence is extracted from the reconstructed behavioral data and its veracity is verified from multiple perspectives. Data is cross-referenced with other sources, and only reliable evidence is included in the final report. This report is generated in PDF format and stored in secure storage.

[0842] Use of emotion engine

[0843] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device. Based on the analysis results, the server evaluates the user's stress level and emotional state and dynamically adjusts the system's feedback and support information.

[0844] User operations

[0845] Accessing the system

[0846] Users log in to the system using their own devices. After logging in, they can search for and download analysis results reports. For example, to obtain a report on a specific wrongful conviction case, users can enter the relevant time, place, and names of those involved as search keywords.

[0847] Use of emotional feedback

[0848] The system analyzes the user's emotional state in real time while they are using the system, and provides easy-to-understand guidance and additional support information based on the analysis results. If the user is in a high-stress state, the system will suggest appropriate measures, improving the quality of the user experience.

[0849] Specific examples

[0850] Example 1: Proof of innocence

[0851] In a case of false accusation, the server first collects surveillance footage, vehicle location information, and public transportation usage history from the day of the crime. This data is preprocessed and analyzed using a generative AI model, proving that the target was in a different location at the time of the crime. This is compiled into a report as reliable evidence, which the user can download to proceed with legal proceedings. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[0852] Example 2: Proof of being a victim of bullying

[0853] If bullying is suspected, the server collects and preprocesses classroom and school surveillance footage, social media message history, and testimony audio data. It then uses a generative AI model to analyze the data and confirm whether bullying has occurred. The analysis results, which have been verified for reliability, are output as a report that users can download and use as reference for school and legal procedures. During this process, the emotion engine assesses the user's emotional state and suggests appropriate countermeasures.

[0854] Examples of prompt statements

[0855] 1. "Analyze CCTV footage and location data related to a false accusation case to prove that the subject was somewhere else at the time of the crime."

[0856] 2. "Based on data on bullying behavior within the school, please collect evidence of bullying and prepare a report."

[0857] In this way, the system of the present invention is highly efficient and accurate in data analysis, and by combining it with an emotion engine to improve the user experience, it achieves more reliable evidence collection and report generation.

[0858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0859] Step 1:

[0860] Data collection

[0861] The server collects necessary information from data sources such as surveillance camera footage, mobile location information, and information exchange service message history. Specifically, it downloads surveillance camera footage from a specified URL using an HTTP request, obtains mobile phone location information via an API, and extracts SNS messages from a database using SQL queries.

[0862] Input: Data source URL, API key, SQL query

[0863] Output: A set of collected information

[0864] Step 2:

[0865] Data Preprocessing

[0866] The server removes noise from the collected information and formats it into a form suitable for analysis. For surveillance camera footage, super-resolution technology is applied to fill in blurry areas, for mobile phone location information, location data below a certain threshold is removed after evaluating its accuracy, and for social media messages, specific keywords are filtered.

[0867] Input: A set of collected information

[0868] Output: A set of preprocessed information

[0869] Step 3:

[0870] Data analysis

[0871] The server inputs the preprocessed information into a generative AI model for analysis. The generative AI model (e.g., GPT-3, BERT) estimates the target person's behavior based on the input data and generates a timeline.

[0872] Input: A set of preprocessed information

[0873] Output: Analysis results (timeline of estimated behavior)

[0874] Step 4:

[0875] Behavioral reproduction

[0876] The server performs a simulation to reproduce the target person's behavior based on the analysis results, and visualizes the target person's behavior in a virtual 3D environment using a simulation engine.

[0877] Input: Analysis results (estimated timeline of behavior)

[0878] Output: Visualized behavioral simulation

[0879] Step 5:

[0880] Evidence extraction and verification

[0881] The server extracts evidence from the re-created behavioral simulations and verifies its authenticity by cross-referencing it with other data sources. It compares data from different sources and selects only matching data as reliable evidence.

[0882] Input: Visualized behavioral simulations, data from other data sources

[0883] Output: A set of verified evidence

[0884] Step 6:

[0885] Use of emotion engine

[0886] The server inputs facial expression and voice data collected from the user's device into an emotion analysis engine in real time to evaluate the user's emotional state. The results of this evaluation are fed back to the generative AI model, and the system's output is adjusted based on the analysis results and the feedback.

[0887] Input: User's facial expression data, voice data

[0888] Output: Emotion evaluation results, adjusted analysis results, and feedback content

[0889] Step 7:

[0890] Output of results

[0891] The server automatically generates a report based on the verified evidence and the adjusted analysis results. The report is saved in PDF format and uploaded to secure storage. Users can download the report.

[0892] Input: Verified evidence set, adjusted analysis results

[0893] Output: Report in PDF format

[0894] Step 8:

[0895] User operations

[0896] Users log in to the system using a terminal and search, select, and download analysis results reports related to their interests.

[0897] Input: User credentials, search query

[0898] Output: Download link for analysis report

[0899] Step 9:

[0900] Use of emotional feedback

[0901] While the user is using the system, the device's camera and microphone are used to collect facial and voice data in real time, allowing the system to continuously analyze the user's emotional state and provide additional support information or guidance when necessary.

[0902] Input: Real-time facial expression data, voice data

[0903] Output: Additional supporting information and guidance

[0904] (Application example 2)

[0905] 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."

[0906] While conventional data analysis systems can efficiently process massive amounts of data and extract reliable evidence, they are unable to provide feedback that takes into account the user's emotional state or real-time warnings when an abnormality occurs. This has resulted in problems that reduce users' sense of security and satisfaction when using the system. Furthermore, they lack the functionality to remotely check surveillance camera footage and quickly detect suspicious behavior.

[0907] 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.

[0908] In this invention, the server includes: means for using a generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using the generative AI and simulating the past behavior of a target person; means for extracting evidence from the reproduced data and verifying its credibility from multiple perspectives; means for outputting the verification results as a report accessible to the user; means for recognizing the user's emotional state and providing feedback and additional support information based on the analysis results; means for the user to remotely check surveillance camera footage and detect anomalies; and means for providing a warning in real time when an anomaly is detected. This enables advanced data analysis and real-time anomaly detection while taking the user's emotional state into consideration.

[0909] "Generative AI" is an artificial intelligence technology that processes massive amounts of data quickly and efficiently, and reproduces behavior based on past cases and related information.

[0910] "Data preprocessing" refers to the process of removing noise and improving the quality of collected data before analyzing it.

[0911] "Simulation methods" are methods for recreating the target person's past behavior based on data analyzed using generative AI.

[0912] "Evidence extraction" is the process of extracting important information from the analyzed data and verifying its authenticity.

[0913] "Emotional state recognition" is a technology that analyzes a user's emotions from their facial expressions and voice and evaluates their state.

[0914] "Feedback provision means" refers to a method of presenting appropriate actions and support information to users based on the analysis results.

[0915] "Remote monitoring means" refers to a means by which a user can check surveillance camera footage from a remote location and detect abnormalities.

[0916] "Real-time warning means" refers to a method of notifying the user immediately when an abnormality is detected.

[0917] This invention is a data analysis system that utilizes generative AI, and is realized through the cooperative operation of a server, a terminal, a user, and an emotion engine. The specific configuration and operation of the system are described below.

[0918] System configuration

[0919] Hardware

[0920] server

[0921] A computer with a powerful processor and large memory capacity

[0922] Terminal

[0923] Smartphone (iOS or Android)

[0924] Surveillance cameras (network-connectable)

[0925] Camera and microphone for detecting the user's facial expressions and voice

[0926] software

[0927] Generative AI Models

[0928] For example, GPT-4

[0929] API for emotion recognition

[0930] For example, Microsoft Azure's Emotion API

[0931] Database

[0932] For example, Firebase, MySQL, etc.

[0933] Development environment

[0934] For example, Xcode, Android Studio

[0935] Server Processing

[0936] The server performs the following process.

[0937] 1. Data Collection and Integration

[0938] Use APIs to collect surveillance camera footage, location information, and social media messages.

[0939] The collected data is stored in temporary storage and later consolidated.

[0940] 2. Data Preprocessing

[0941] It runs algorithms to improve the quality of video data, remove noise from location information, and filter keywords from social media messages.

[0942] 3. Data Analysis

[0943] Preprocessed data is input into the generative AI model, and analysis and behavior reproduction are performed.

[0944] Simulations are performed based on the analyzed data and visualized in a virtual environment.

[0945] 4. Extraction and verification of evidence

[0946] Extract evidence from the reproduced data and perform cross-reference verification.

[0947] Only reliable evidence is selected and ultimately recorded in a database.

[0948] 5. Outputting the results

[0949] An analysis result report is generated based on the verified evidence and output in PDF format.

[0950] 6. Use of Emotion Engines

[0951] It recognizes the user's emotional state and provides feedback and additional support information based on the analysis results.

[0952] Terminal handling

[0953] The user uses the device to perform the following operations:

[0954] 1. Access to the System

[0955] Users log in to the system using their smartphone, search for analysis result reports, select them and download them.

[0956] 2. Check the surveillance camera footage

[0957] You can check the footage from your home or office surveillance cameras in real time from your smartphone to check for any abnormalities.

[0958] 3. Real-time alerts

[0959] If an anomaly is detected, the system will alert the user in real time.

[0960] User operations

[0961] The user uses the system by performing the following operations:

[0962] 1. Use emotional feedback

[0963] While using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice, and provides feedback based on their stress level and emotional state.

[0964] Specific examples

[0965] For example, while the user is away from home, the system can analyze suspicious behavior based on home security camera footage, mobile phone location information, and social media message history, and generate a report. If an abnormality is detected, the emotion engine will evaluate the user's stress level and provide necessary feedback.

[0966] "Recreate the target person's actions using the following data: surveillance camera footage, location information, and social media message history."

[0967] This system enables advanced data analysis and real-time anomaly detection while taking into account the user's emotional state.

[0968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0969] Step 1:

[0970] The server collects data such as surveillance camera footage, mobile phone location information, and social media message history. Input data is collected from each data source through APIs and stored in temporary storage. The output is the integrated raw data.

[0971] Step 2:

[0972] The server performs preprocessing on the collected data. Filtering is performed to improve the quality of surveillance camera footage, and noise is removed from location information. Filtering is also performed based on important keywords from SNS message history. The input data is raw data, and the output data is preprocessed data.

[0973] Step 3:

[0974] The server inputs the preprocessed data into the generative AI model and performs data analysis. The generative AI model performs the analysis and reproduces the target person's behavior. The input data is the preprocessed data, and the output data is the reproduced behavior data. In this case, the prompt used is "Please reproduce the target person's behavior based on the following data: surveillance camera footage, location information, and SNS message history."

[0975] Step 4:

[0976] The server extracts evidence from the reproduced behavioral data and cross-references its authenticity from multiple perspectives. It calculates the degree of consistency from multiple data sources and selects only highly reliable evidence. The input data is the reproduced behavioral data, and the output data is the verified evidence.

[0977] Step 5:

[0978] The server generates an analysis result report based on the verified evidence and outputs it in PDF format. The report is stored in secure storage. The input data is the verified evidence, and the output data is the PDF report.

[0979] Step 6:

[0980] Users log in to the system using a terminal, search for and download analysis result reports. The input data is the user's search keywords, and the output data is a download link for the report.

[0981] Step 7:

[0982] Users can use their devices to remotely monitor and check the surveillance camera footage in real time. The system uses an anomaly detection algorithm to provide real-time warnings when an abnormality occurs. The input data is the surveillance camera footage, and the output data is an anomaly detection warning.

[0983] Step 8:

[0984] The server recognizes the user's emotional state using an emotion engine and provides feedback and additional support information based on the analysis results. The input data is the user's facial expressions and voice, and the output data is the feedback and support information.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] [Third embodiment]

[0989] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0990] 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.

[0991] 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).

[0992] 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.

[0993] 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.

[0994] 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).

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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."

[1001] Specific Embodiments of the System

[1002] This patented system is a data analysis system that utilizes generative AI, where servers, terminals, and users work together. This system is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying.

[1003] Server Processing

[1004] Data collection and integration

[1005] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[1006] Data Preprocessing

[1007] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[1008] Data analysis and behavioral reproduction

[1009] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[1010] Evidence extraction and verification

[1011] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[1012] Output of results

[1013] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[1014] User operations

[1015] Accessing the system

[1016] Users log in to the system using their terminals. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[1017] Specific examples

[1018] Example 1: Proof of innocence

[1019] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. Users can download this report and use it to proceed with legal proceedings.

[1020] Example 2: Proof of being a victim of bullying

[1021] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it to help with school and legal responses.

[1022] As described above, this system makes full use of generative AI to process huge amounts of data efficiently and quickly to prove that someone "did not do it" or "did not exist," thereby helping to avoid false accusations and bullying.

[1023] The processing flow will be explained below.

[1024] Program processing steps

[1025] Step 1: Data collection

[1026] The server accesses data sources related to the incident or situation of interest.

[1027] The server downloads the surveillance camera video via the network.

[1028] The server obtains the mobile phone's location information through an API.

[1029] The server extracts the SNS message history from the database.

[1030] The server stores the collected data in temporary storage and consolidates all the data.

[1031] Step 2: Data Preprocessing

[1032] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[1033] The server performs a process to remove noise from the mobile phone's location information.

[1034] The server filters the SNS message history for important keywords and removes irrelevant data.

[1035] The server stores the pre-processed data in a new storage.

[1036] Step 3: Data analysis and behavioral reproduction

[1037] The server inputs the preprocessed data into the generation AI.

[1038] The server uses generative AI to cross-reference security camera footage with location data.

[1039] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[1040] The server visualizes the behavioral simulation results in a virtual environment.

[1041] Step 4: Evidence extraction and verification

[1042] The server extracts important evidential data from the reconstructed behavioral data.

[1043] The server cross-references the extracted evidence with information from different data sources.

[1044] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[1045] The server records the final evidence and its authenticity in a database.

[1046] Step 5: Output the results

[1047] The server generates an analysis report based on the verified evidence.

[1048] The server outputs the report in PDF format and stores it in secure storage.

[1049] Step 6: User interaction

[1050] A user logs into the system using a terminal.

[1051] The user searches through the analysis results reports and selects the report of interest.

[1052] The user downloads the selected report and checks its contents.

[1053] Users can take appropriate legal action or measures based on the contents of the report.

[1054] These are the specific processing steps of the system based on patent claims. This system allows efficient and reliable proof of non-existence or non-commitment.

[1055] Example 1

[1056] 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."

[1057] Conventional data analysis systems have the problem of making it difficult to prove false accusations, bullying, and other crimes that "did not occur" or "did not exist." The manual process of collecting, integrating, analyzing, and verifying data is extremely time-consuming. Furthermore, because much of the information contains noise, it is difficult to accurately reproduce behavior or verify the credibility of evidence. Furthermore, there are insufficient ways for users to easily access, search, and download analysis results.

[1058] 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.

[1059] In this invention, the server includes: means for using generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using generative AI and simulating the target person's past behavior; means for extracting evidence from the reproduced data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report and saving it in a secure storage device; and means for users to log in to the system using their terminals and search for and download analysis result reports of interest. This makes it possible to efficiently prove that someone did not commit or did not exist, such as a false accusation or bullying victim.

[1060] "Generative AI" refers to algorithms that use artificial intelligence techniques to process large amounts of data and generate new data and information.

[1061] "Data collection" is the process of gathering the necessary information from various data sources, including surveillance camera footage, location information, and social media message history.

[1062] "Data integration" refers to the process of centrally managing collected data and converting it into a unified format.

[1063] "Data preprocessing" refers to the data cleaning and filtering procedures used to remove noise from raw data and make it ready for analysis.

[1064] "Denoising" refers to the process of removing errors and unnecessary information from data.

[1065] "Data analysis" refers to the process of extracting useful information from collected and pre-processed data using statistical methods and artificial intelligence techniques.

[1066] "Behavioral reproduction" refers to reconstructing the past behavior of a specific person or subject as a simulation or model based on analyzed data.

[1067] "Evidence extraction" refers to the process of extracting logically significant information from replicated data and using it to support a particular conclusion.

[1068] "Verification of credibility" refers to the process of checking the reliability of the evidence obtained using different data sources and cross-referencing.

[1069] "Report output" refers to compiling the analysis and verification results in document form and making them available for viewing by users.

[1070] "Secure storage device" refers to a storage system that has security features such as authentication and encryption.

[1071] "User" refers to an individual or organization that uses this system to search for and download analysis results reports.

[1072] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[1073] "Login" refers to the authentication process required for a user to access a system.

[1074] "Search" refers to the process of locating information of interest using specific keywords and filters.

[1075] "Downloading" refers to copying data or files to your device via the Internet.

[1076] MODE FOR CARRYING OUT THE INVENTION

[1077] System Overview

[1078] This invention is a data analysis system that utilizes generative AI, and is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying. The system operates in cooperation with the server, terminals, and users.

[1079] Server Roles

[1080] The server is responsible for:

[1081] 1. Data Collection and Integration

[1082] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history. This is done by downloading data using network APIs and database queries. The collected data is first stored in temporary storage (e.g., cloud storage) and then integrated in a database system (e.g., a relational database).

[1083] 2. Data Preprocessing

[1084] The server filters and denoises the collected data. For example, it uses the OpenCV library to fill in blurry areas in security camera footage and removes low-precision data from location data. For social media messages, it uses the NLTK library to filter for important keywords.

[1085] 3. Data analysis and behavioral reproduction

[1086] The server then uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis cross-references time and location information to recreate a person's behavior at a specific time and place. The results are then visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[1087] 4. Extraction and verification of evidence

[1088] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that uses SQL queries and custom scripts.

[1089] 5. Outputting the results

[1090] The verified evidence is generated as an analysis report in PDF format, which is saved in secure storage (e.g., cloud storage). The PDF is generated using LaTeX and HTML to PDF libraries.

[1091] User Roles

[1092] The user does the following:

[1093] 1. Access to the System

[1094] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[1095] 2. Search and download analysis results reports

[1096] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[1097] Specific examples

[1098] 1. Proof of Innocent Conviction

[1099] The server collects and consolidates all data related to a false accusation case, including surveillance camera footage from the day of the crime, mobile phone location information, and transportation usage history. This data is then preprocessed and analyzed using generative AI. The analysis proves that the target person was in a different location at the time of the crime. This evidence is verified from multiple data sources and compiled into a report. Users can download this report and use it to further legal proceedings.

[1100] Example prompt sentence:

[1101] "Please tell me the results of the analysis of the incident that occurred on January 1, 2023."

[1102] 2. Proof of being a victim of bullying

[1103] In cases where bullying is suspected, the server collects school surveillance camera footage, social media message history, and testimony audio data. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying occurred. The results of this analysis are verified using different data sources and compiled into a report as reliable evidence. Users can download this report and use it for school or legal action.

[1104] Example prompt sentence:

[1105] "Please tell me the results of an analysis of bullying that occurred at a specific school on January 1, 2023."

[1106] The above is a mode for carrying out the invention, and this system makes it possible to prove false accusations and bullying victims efficiently and with high accuracy.

[1107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1108] Step 1: Data collection and integration

[1109] concrete action

[1110] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history, by downloading data using network APIs and database queries.

[1111] input

[1112] API access information and queries for each data source (surveillance cameras, mobile phone location information, social media messages).

[1113] Data processing and calculation

[1114] Fetch data using network APIs or SQL queries and store it in temporary storage (e.g. cloud storage).

[1115] output

[1116] Temporarily stored raw data before preprocessing.

[1117] Step 2: Data Preprocessing

[1118] concrete action

[1119] The server performs quality filtering and noise reduction on the collected data. For example, it uses the OpenCV library to fill in blurry parts of surveillance camera footage, and a Python script to remove inaccurate parts of location data. For social media messages, it uses the NLTK library to filter for important keywords.

[1120] input

[1121] Temporarily stored raw data before preprocessing.

[1122] Data processing and calculation

[1123] Generate a quality-enhanced dataset through filtering and denoising.

[1124] output

[1125] Preprocessed data with improved quality.

[1126] Step 3: Data analysis and behavioral replication

[1127] concrete action

[1128] The server uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis involves cross-referencing time and location information to simulate a person's behavior at a specific time and place. The results of this analysis are visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[1129] input

[1130] Preprocessed dataset.

[1131] Data processing and calculation

[1132] Generative AI models are used to analyze data and run simulations to reproduce specific behaviors.

[1133] output

[1134] Analysis results and behavioral simulation data.

[1135] Step 4: Evidence extraction and verification

[1136] concrete action

[1137] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that involves SQL queries and custom scripts.

[1138] input

[1139] Reproduced behavioral simulation data.

[1140] Data processing and calculation

[1141] We extract evidence and verify data through cross-referencing to confirm its authenticity.

[1142] output

[1143] Verified evidence data.

[1144] Step 5: Output the results

[1145] concrete action

[1146] The server generates a report summarizing the results in PDF format based on the evidence of the analysis and verification. This report is saved in secure storage (e.g., cloud storage). The PDF generation uses LaTeX and HTML to PDF libraries.

[1147] input

[1148] Verified evidence data.

[1149] Data processing and calculation

[1150] Generate reports and export them in PDF format.

[1151] output

[1152] Analysis results report stored in secure storage.

[1153] Step 6: Access the system

[1154] concrete action

[1155] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[1156] input

[1157] The user's authentication information.

[1158] Data processing and calculation

[1159] Uses an authentication system to verify user credentials and allow login.

[1160] output

[1161] Access rights to the system.

[1162] Step 7: Find and download the analysis report

[1163] concrete action

[1164] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[1165] input

[1166] Search keywords.

[1167] Data processing and calculation

[1168] Run a search query to filter relevant reports.

[1169] output

[1170] User downloadable analysis report.

[1171] (Application example 1)

[1172] 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."

[1173] In recent years, it has become increasingly difficult to prove false accusations and bullying, resulting in many cases of innocent people being treated unfairly. In particular, in today's world where much evidence is digitized, there is a need for efficient methods to collect, analyze, and verify the authenticity of vast amounts of data. Another issue is the lack of tools that allow users to easily prove their own actions. To solve this problem, an advanced data analysis system using generative AI is needed.

[1174] 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.

[1175] In this invention, the server includes: means for processing massive amounts of data at high speed using a generative AI and collecting and integrating past cases and related information; means for preprocessing the collected data and removing noise; simulation means for analyzing the data using a generative AI and recreating the target person's past behavior; means for extracting evidence from the recreated data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report accessible to the user; application means installed on a smartphone for automatically collecting location information, usage history, and camera footage; preprocessing means for removing noise and filtering the collected data; verification means for cross-referencing information collected from multiple data sources and checking its authenticity; and output means for generating a PDF report of the analysis results. This enables users to easily and reliably collect, analyze, and manage evidence when proving their innocence or existence.

[1176] "Generative AI" is a type of artificial intelligence that uses generative algorithms to create new data and information.

[1177] "Big data" refers to the large amount of digital data collected from a wide variety of information sources.

[1178] "Past events" refers to data or information about specific events or occurrences that have occurred in the past.

[1179] "Collection and integration" is the process of bringing together data from multiple sources and converting it into a unified format.

[1180] "Preprocessing" is a preparatory step to remove noise from the data to be analyzed and improve its quality.

[1181] "Noise reduction" is the process of eliminating meaningless data and errors.

[1182] "Analysis" refers to the process of examining data to extract and understand information.

[1183] "Simulation of past behavior" is the process of reconstructing a person's behavior at a specific time and place on a computer based on collected data.

[1184] "Evidence extraction" is the process of extracting useful information or data from the analysis results.

[1185] "Verifying credibility" is the process of confirming the accuracy and reliability of the evidence or data obtained.

[1186] A "report" refers to a document that organizes and documents the results of analysis and verification.

[1187] An "application installed on a smartphone" is software with specific functions that runs on a smartphone.

[1188] "Location information" refers to data that indicates a location at a particular point in time.

[1189] "Usage History" refers to records of how a user uses a device or application.

[1190] "Camera footage" refers to visual data captured by a digital camera.

[1191] "Noise reduction and filtering" is the process of removing unnecessary parts to improve the quality of collected data.

[1192] "Cross-referencing" refers to comparing data obtained from different sources with each other.

[1193] "PDF format" is an abbreviation for Portable Document Format developed by Adobe, and is a format for electronic documents.

[1194] Specific Embodiments of the System

[1195] This system is a data analysis system that utilizes generative AI, where the server, terminal, and user work together. This system is particularly specialized in proving that someone did not commit or exist, such as a false accusation or bullying victim.

[1196] Server Processing

[1197] Data collection and integration

[1198] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[1199] Data Preprocessing

[1200] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[1201] Data analysis and behavioral reproduction

[1202] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[1203] Evidence extraction and verification

[1204] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[1205] Output of results

[1206] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[1207] User operations

[1208] Accessing the system

[1209] Users log in to the system using a smartphone application. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[1210] Specific examples

[1211] Example 1: Proof of innocence

[1212] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. The user can download this report and use it to proceed with legal proceedings. Below is an example of a prompt for the generative AI.

[1213] "Collect and analyze data to prove that the user was in the Shinjuku Station area between 12:30 and 1:30 PM on October 1, 2023. The required data is as follows: GPS location information, SNS message history, and camera footage. Based on this data, reconstruct the user's behavioral history and generate a credible report."

[1214] Example 2: Proof of being a victim of bullying

[1215] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it for school or legal action.

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1: Data collection

[1218] The server first collects surveillance camera footage, mobile phone location information, and social media message history. This is done using the APIs of the surveillance camera system, mobile phone network, and social media platform. The input data is raw data from each source, which is then integrated and stored in temporary storage. The server then converts this data into a format that can be processed collectively.

[1219] Step 2: Data Preprocessing

[1220] The server preprocesses the collected data and removes noise. Specifically, it applies algorithms to complement blurry surveillance camera footage, improve the accuracy of location information, and extract and filter important keywords from social media messages. The input data are raw video data, location information data, and social media message data, and the output is high-quality, consistent data.

[1221] Step 3: Data analysis and behavioral replication

[1222] The server uses the preprocessed data to perform analysis using generative AI. This analysis cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The input data is the preprocessed footage, location information, and social media messages, and the output is a reproduced behavioral history. The reproduced data can be visualized in a virtual environment.

[1223] Step 4: Evidence extraction and verification

[1224] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity. Specifically, it checks whether surveillance camera footage matches the location information and performs additional cross-referencing. The input data is the reconstructed behavioral history and information from each data source, and the output is evidence whose authenticity has been confirmed.

[1225] Step 5: Output the results

[1226] The server generates a PDF report of the analysis results based on the evidence whose authenticity has been confirmed and stores it in secure storage. Users can access this report and download it as needed. The input data is the evidence whose authenticity has been confirmed, and the output is a PDF report. Users access this report through a smartphone application.

[1227] 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.

[1228] Specific Embodiments of the System

[1229] This patented system is a data analysis system that utilizes generative AI, in which a server, terminal, user, and emotion engine work together. This system specializes in proving "non-existence" and "non-existence," and furthermore, by evaluating and utilizing the user's emotional state, it provides a more accurate analysis and user experience.

[1230] Server Processing

[1231] Data collection and integration

[1232] The server accesses various data sources to collect data related to the incident or target situation. Specifically, it downloads surveillance camera footage via the network, obtains mobile phone location information via API, and extracts social media message history from a database. The collected data is stored in temporary storage and later integrated.

[1233] Data Preprocessing

[1234] The server filters and denoises the collected data. To improve the quality of surveillance camera footage, algorithms are applied to fill in blurry areas. Inaccurate data is removed from mobile phone location information, and social media message histories are filtered for important keywords.

[1235] Data analysis and behavioral reproduction

[1236] The server inputs the preprocessed data into the AI ​​generator, cross-referencing the surveillance camera footage and location data. Based on the analyzed data, a simulation is run to recreate the target person's behavior, and the results are visualized in a virtual environment.

[1237] Evidence extraction and verification

[1238] The server extracts evidence from the reconstructed behavioral data, performs cross-reference verification using information from different data sources, evaluates its credibility, and selects only highly reliable evidence, which is then recorded in a database.

[1239] Use of emotion engine

[1240] The server uses an emotion engine to recognize the user's emotions and evaluates the user's stress level and emotional state based on the analysis results. Based on the emotion engine's recognition results, the server proposes appropriate feedback and actions to the user. In addition, the emotion data is used as part of the analysis by the generative AI, enabling more accurate behavioral reproduction.

[1241] Output of results

[1242] The server generates an analysis report based on the verified evidence, which is output in PDF format and stored in secure storage.

[1243] User operations

[1244] Accessing the system

[1245] Users log in to the system using their terminals. They can search for, select, and download analysis reports related to their interests. For example, to obtain an analysis report on a specific wrongful conviction case, users can enter the relevant time, location, and names of those involved as search keywords.

[1246] Use of emotional feedback

[1247] While the user is using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice. As a result, the system presents the analysis results and provides additional support information according to the user's stress level and emotional state. For example, easy-to-understand guidance and additional support are suggested to users in a high-stress state.

[1248] Specific examples

[1249] Example 1: Proof of innocence

[1250] In a case of false accusation, the server first collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. This data is preprocessed and analyzed by generative AI, proving that the target person was in a different location at the time of the crime. The evidence is verified from different data sources and compiled into a report as reliable evidence. The user downloads this report and proceeds with the legal process. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[1251] Example 2: Proof of being a victim of bullying

[1252] If bullying is suspected, the server collects and preprocesses surveillance camera footage from classrooms and schools, social media message history, and testimony audio data. Generative AI is used to analyze the data to confirm whether bullying has occurred. The analysis results are verified for authenticity using different data sources and output as a report. Users can download this report for reference in school or legal proceedings. During this process, the emotion engine evaluates the user's emotional state and suggests appropriate countermeasures.

[1253] The above is an embodiment of the patented system that combines an emotion engine. This system improves the accuracy of data analysis and enables flexible support that corresponds to the user's emotional state.

[1254] The processing flow will be explained below.

[1255] Program processing steps (system combining emotion engines)

[1256] Step 1: Data collection

[1257] The server accesses data sources related to the incident or situation of interest.

[1258] The server downloads the surveillance camera video via the network.

[1259] The server obtains the mobile phone's location information through an API.

[1260] The server extracts the SNS message history from the database.

[1261] The server stores the collected data in temporary storage and consolidates all the data.

[1262] Step 2: Data Preprocessing

[1263] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[1264] The server performs a process to remove noise from the mobile phone's location information.

[1265] The server filters the SNS message history for important keywords and removes irrelevant data.

[1266] The server stores the pre-processed data in a new storage.

[1267] Step 3: Data analysis and behavioral reproduction

[1268] The server inputs the preprocessed data into the generation AI.

[1269] The server uses generative AI to cross-reference security camera footage with location data.

[1270] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[1271] The server visualizes the behavioral simulation results in a virtual environment.

[1272] Step 4: Evidence extraction and verification

[1273] The server extracts important evidential data from the reconstructed behavioral data.

[1274] The server cross-references the extracted evidence with information from different data sources.

[1275] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[1276] The server records the final evidence and its authenticity in a database.

[1277] Step 5: Evaluation by the Emotion Engine

[1278] The server activates an emotion engine that recognizes the user's emotions in real time.

[1279] The server analyzes the user's facial expressions and voice data to assess their stress level and emotional state.

[1280] The server generates appropriate feedback and presents the analysis results according to the user's emotional state.

[1281] Step 6: Output the results

[1282] The server generates an analysis report based on the verified evidence.

[1283] The server outputs the report in PDF format and stores it in secure storage.

[1284] Step 7: User interaction

[1285] A user logs into the system using a terminal.

[1286] The user searches through the analysis results reports and selects the report of interest.

[1287] The user downloads the selected report and checks its contents.

[1288] Users can take appropriate legal action or measures based on the contents of the report.

[1289] Specific examples

[1290] Example 1: Proof of innocence

[1291] In step 1, the server collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the incident. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate the behavior of the target person. In step 4, evidence is extracted and verified from the recreated behavioral data. In step 5, the emotion engine evaluates the user's stress level and adjusts the presentation method of the analysis results. Finally, in step 6, an analysis result report is generated and saved, and in step 7, the user downloads this report to proceed with legal procedures.

[1292] Example 2: Proof of being a victim of bullying

[1293] In step 1, the server collects surveillance camera footage from within the school, social media message history, and testimony audio data. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate bullying behavior. In step 4, evidence is extracted and verified to confirm whether bullying behavior occurred. In step 5, the emotion engine evaluates the user's emotional state and provides appropriate feedback. Finally, in step 6, an evidence-based report is generated and saved, and in step 7, the user can download this report for use by school administrators or legal proceedings.

[1294] Through these specific processing steps, the present invention provides a system that efficiently proves "not doing something" or "not existing" and also responds to the user's emotional state.

[1295] Example 2

[1296] 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."

[1297] In recent years, the rapid increase in data volume has created a demand for effective data processing technologies. However, conventional systems require time for data collection, noise removal, analysis, and evidence extraction and verification. Furthermore, they struggle to process diverse data sources in a unified manner. Furthermore, they do not take into account the user's emotional state, resulting in a poor user experience. To address these challenges, a more advanced data analysis system is needed.

[1298] 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.

[1299] In this invention, the server includes means for using generative AI to process huge amounts of information at high speed and collect and integrate past cases and related information, means for preprocessing the collected information and removing noise, means for analyzing data using generative AI and simulating the target person's past behavior, means for extracting evidence from the reproduced information and verifying its credibility from multiple perspectives, means for recognizing the user's emotional state in real time and providing appropriate feedback based on the analysis results, and means for outputting the verification results as a report that the user can access. This enables data collection, analysis, and evidence verification to be carried out quickly and with high accuracy, and makes it possible to provide flexible support according to the user's emotional state.

[1300] "Generative AI" is an artificial intelligence technology that quickly generates and analyzes useful information from massive amounts of data.

[1301] "Information" is a general term for data collected from a variety of data sources, such as surveillance camera footage, location data of mobile devices, and message history from information exchange services.

[1302] "Noise" refers to unnecessary data or errors that should be removed during data processing and analysis.

[1303] "Simulation" is a method of virtually recreating the behavior of a target person based on collected and analyzed data.

[1304] "Evidence" is facts or information extracted from reproduced behavioral data and assessed for its veracity.

[1305] "Emotional state" refers to the psychological state of the user that is analyzed in real time from facial expressions, voice, etc.

[1306] "Feedback" refers to instructions and support information provided based on the user's emotional state and analysis results.

[1307] A "report" is a document that summarizes the analysis results and verified evidence, and is output in an electronic format such as PDF.

[1308] MODE FOR CARRYING OUT THE INVENTION

[1309] This invention is a data analysis system in which a server, a user's device, and an emotion engine work together. This system uses a generative AI model to process vast amounts of information at high speed, and collects and integrates past cases and related information. The detailed configuration is described below.

[1310] Server Processing

[1311] A server primarily uses the following hardware and software components:

[1312] Hardware: A server machine with a high-performance CPU and GPU, sufficient memory and storage.

[1313] Software: Database management systems (e.g., MySQL, PostgreSQL), API access tools, generative AI models (e.g., GPT-3, BERT), simulation engines (e.g., Unity), sentiment analysis engines.

[1314] Data collection

[1315] The server collects data from various information sources, such as surveillance footage, location information of mobile devices, and message history from information exchange services. For example, it downloads surveillance camera footage via the network, obtains mobile phone location information via an API, and extracts SNS messages from a database.

[1316] Data Preprocessing

[1317] The collected data cannot be used as is, so it is filtered and noise-removed. Specifically, surveillance camera footage is supplemented with super-resolution technology, location data accuracy is evaluated to remove inaccurate data, and social media messages are filtered using specific keywords.

[1318] Data Analysis and Simulation

[1319] The preprocessed data is input into a generative AI model for analysis. Based on the analysis results, a simulation is performed to reproduce the target person's behavior, and the simulation results are visualized in a 3D environment. This makes it possible to visually reproduce past behavior.

[1320] Evidence extraction and verification

[1321] Evidence is extracted from the reconstructed behavioral data and its veracity is verified from multiple perspectives. Data is cross-referenced with other sources, and only reliable evidence is included in the final report. This report is generated in PDF format and stored in secure storage.

[1322] Use of emotion engine

[1323] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device. Based on the analysis results, the server evaluates the user's stress level and emotional state and dynamically adjusts the system's feedback and support information.

[1324] User operations

[1325] Accessing the system

[1326] Users log in to the system using their own devices. After logging in, they can search for and download analysis results reports. For example, to obtain a report on a specific wrongful conviction case, users can enter the relevant time, place, and names of those involved as search keywords.

[1327] Use of emotional feedback

[1328] The system analyzes the user's emotional state in real time while they are using the system, and provides easy-to-understand guidance and additional support information based on the analysis results. If the user is in a high-stress state, the system will suggest appropriate measures, improving the quality of the user experience.

[1329] Specific examples

[1330] Example 1: Proof of innocence

[1331] In a case of false accusation, the server first collects surveillance footage, vehicle location information, and public transportation usage history from the day of the crime. This data is preprocessed and analyzed using a generative AI model, proving that the target was in a different location at the time of the crime. This is compiled into a report as reliable evidence, which the user can download to proceed with legal proceedings. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[1332] Example 2: Proof of being a victim of bullying

[1333] If bullying is suspected, the server collects and preprocesses classroom and school surveillance footage, social media message history, and testimony audio data. It then uses a generative AI model to analyze the data and confirm whether bullying has occurred. The analysis results, which have been verified for reliability, are output as a report that users can download and use as reference for school and legal procedures. During this process, the emotion engine assesses the user's emotional state and suggests appropriate countermeasures.

[1334] Examples of prompt statements

[1335] 1. "Analyze CCTV footage and location data related to a false accusation case to prove that the subject was somewhere else at the time of the crime."

[1336] 2. "Based on data on bullying behavior within the school, please collect evidence of bullying and prepare a report."

[1337] In this way, the system of the present invention is highly efficient and accurate in data analysis, and by combining it with an emotion engine to improve the user experience, it achieves more reliable evidence collection and report generation.

[1338] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1339] Step 1:

[1340] Data collection

[1341] The server collects necessary information from data sources such as surveillance camera footage, mobile location information, and information exchange service message history. Specifically, it downloads surveillance camera footage from a specified URL using an HTTP request, obtains mobile phone location information via an API, and extracts SNS messages from a database using SQL queries.

[1342] Input: Data source URL, API key, SQL query

[1343] Output: A set of collected information

[1344] Step 2:

[1345] Data Preprocessing

[1346] The server removes noise from the collected information and formats it into a form suitable for analysis. For surveillance camera footage, super-resolution technology is applied to fill in blurry areas, for mobile phone location information, location data below a certain threshold is removed after evaluating its accuracy, and for social media messages, specific keywords are filtered.

[1347] Input: A set of collected information

[1348] Output: A set of preprocessed information

[1349] Step 3:

[1350] Data analysis

[1351] The server inputs the preprocessed information into a generative AI model for analysis. The generative AI model (e.g., GPT-3, BERT) estimates the target person's behavior based on the input data and generates a timeline.

[1352] Input: A set of preprocessed information

[1353] Output: Analysis results (timeline of estimated behavior)

[1354] Step 4:

[1355] Behavioral reproduction

[1356] The server performs a simulation to reproduce the target person's behavior based on the analysis results, and visualizes the target person's behavior in a virtual 3D environment using a simulation engine.

[1357] Input: Analysis results (estimated timeline of behavior)

[1358] Output: Visualized behavioral simulation

[1359] Step 5:

[1360] Evidence extraction and verification

[1361] The server extracts evidence from the re-created behavioral simulations and verifies its authenticity by cross-referencing it with other data sources. It compares data from different sources and selects only matching data as reliable evidence.

[1362] Input: Visualized behavioral simulations, data from other data sources

[1363] Output: A set of verified evidence

[1364] Step 6:

[1365] Use of emotion engine

[1366] The server inputs facial expression and voice data collected from the user's device into an emotion analysis engine in real time to evaluate the user's emotional state. The results of this evaluation are fed back to the generative AI model, and the system's output is adjusted based on the analysis results and the feedback.

[1367] Input: User's facial expression data, voice data

[1368] Output: Emotion evaluation results, adjusted analysis results, and feedback content

[1369] Step 7:

[1370] Output of results

[1371] The server automatically generates a report based on the verified evidence and the adjusted analysis results. The report is saved in PDF format and uploaded to secure storage. Users can download the report.

[1372] Input: Verified evidence set, adjusted analysis results

[1373] Output: Report in PDF format

[1374] Step 8:

[1375] User operations

[1376] Users log in to the system using a terminal and search, select, and download analysis results reports related to their interests.

[1377] Input: User credentials, search query

[1378] Output: Download link for analysis report

[1379] Step 9:

[1380] Use of emotional feedback

[1381] While the user is using the system, the device's camera and microphone are used to collect facial and voice data in real time, allowing the system to continuously analyze the user's emotional state and provide additional support information or guidance when necessary.

[1382] Input: Real-time facial expression data, voice data

[1383] Output: Additional supporting information and guidance

[1384] (Application example 2)

[1385] 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."

[1386] While conventional data analysis systems can efficiently process massive amounts of data and extract reliable evidence, they are unable to provide feedback that takes into account the user's emotional state or real-time warnings when an abnormality occurs. This has resulted in problems that reduce users' sense of security and satisfaction when using the system. Furthermore, they lack the functionality to remotely check surveillance camera footage and quickly detect suspicious behavior.

[1387] 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.

[1388] In this invention, the server includes: means for using a generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using the generative AI and simulating the past behavior of a target person; means for extracting evidence from the reproduced data and verifying its credibility from multiple perspectives; means for outputting the verification results as a report accessible to the user; means for recognizing the user's emotional state and providing feedback and additional support information based on the analysis results; means for the user to remotely check surveillance camera footage and detect anomalies; and means for providing a warning in real time when an anomaly is detected. This enables advanced data analysis and real-time anomaly detection while taking the user's emotional state into consideration.

[1389] "Generative AI" is an artificial intelligence technology that processes massive amounts of data quickly and efficiently, and reproduces behavior based on past cases and related information.

[1390] "Data preprocessing" refers to the process of removing noise and improving the quality of collected data before analyzing it.

[1391] "Simulation methods" are methods for recreating the target person's past behavior based on data analyzed using generative AI.

[1392] "Evidence extraction" is the process of extracting important information from the analyzed data and verifying its authenticity.

[1393] "Emotional state recognition" is a technology that analyzes a user's emotions from their facial expressions and voice and evaluates their state.

[1394] "Feedback provision means" refers to a method of presenting appropriate actions and support information to users based on the analysis results.

[1395] "Remote monitoring means" refers to a means by which a user can check surveillance camera footage from a remote location and detect abnormalities.

[1396] "Real-time warning means" refers to a method of notifying the user immediately when an abnormality is detected.

[1397] This invention is a data analysis system that utilizes generative AI, and is realized through the cooperative operation of a server, a terminal, a user, and an emotion engine. The specific configuration and operation of the system are described below.

[1398] System configuration

[1399] Hardware

[1400] server

[1401] A computer with a powerful processor and large memory capacity

[1402] Terminal

[1403] Smartphone (iOS or Android)

[1404] Surveillance cameras (network-connectable)

[1405] Camera and microphone for detecting the user's facial expressions and voice

[1406] software

[1407] Generative AI Models

[1408] For example, GPT-4

[1409] API for emotion recognition

[1410] For example, Microsoft Azure's Emotion API

[1411] Database

[1412] For example, Firebase, MySQL, etc.

[1413] Development environment

[1414] For example, Xcode, Android Studio

[1415] Server Processing

[1416] The server performs the following process.

[1417] 1. Data Collection and Integration

[1418] Use APIs to collect surveillance camera footage, location information, and social media messages.

[1419] The collected data is stored in temporary storage and later consolidated.

[1420] 2. Data Preprocessing

[1421] It runs algorithms to improve the quality of video data, remove noise from location information, and filter keywords from social media messages.

[1422] 3. Data Analysis

[1423] Preprocessed data is input into the generative AI model, and analysis and behavior reproduction are performed.

[1424] Simulations are performed based on the analyzed data and visualized in a virtual environment.

[1425] 4. Extraction and verification of evidence

[1426] Extract evidence from the reproduced data and perform cross-reference verification.

[1427] Only reliable evidence is selected and ultimately recorded in a database.

[1428] 5. Outputting the results

[1429] An analysis result report is generated based on the verified evidence and output in PDF format.

[1430] 6. Use of Emotion Engines

[1431] It recognizes the user's emotional state and provides feedback and additional support information based on the analysis results.

[1432] Terminal handling

[1433] The user uses the device to perform the following operations:

[1434] 1. Access to the System

[1435] Users log in to the system using their smartphone, search for analysis result reports, select them and download them.

[1436] 2. Check the surveillance camera footage

[1437] You can check the footage from your home or office surveillance cameras in real time from your smartphone to check for any abnormalities.

[1438] 3. Real-time alerts

[1439] If an anomaly is detected, the system will alert the user in real time.

[1440] User operations

[1441] The user uses the system by performing the following operations:

[1442] 1. Use emotional feedback

[1443] While using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice, and provides feedback based on their stress level and emotional state.

[1444] Specific examples

[1445] For example, while the user is away from home, the system can analyze suspicious behavior based on home security camera footage, mobile phone location information, and social media message history, and generate a report. If an abnormality is detected, the emotion engine will evaluate the user's stress level and provide necessary feedback.

[1446] "Recreate the target person's actions using the following data: surveillance camera footage, location information, and social media message history."

[1447] This system enables advanced data analysis and real-time anomaly detection while taking into account the user's emotional state.

[1448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1449] Step 1:

[1450] The server collects data such as surveillance camera footage, mobile phone location information, and social media message history. Input data is collected from each data source through APIs and stored in temporary storage. The output is the integrated raw data.

[1451] Step 2:

[1452] The server performs preprocessing on the collected data. Filtering is performed to improve the quality of surveillance camera footage, and noise is removed from location information. Filtering is also performed based on important keywords from SNS message history. The input data is raw data, and the output data is preprocessed data.

[1453] Step 3:

[1454] The server inputs the preprocessed data into the generative AI model and performs data analysis. The generative AI model performs the analysis and reproduces the target person's behavior. The input data is the preprocessed data, and the output data is the reproduced behavior data. In this case, the prompt used is "Please reproduce the target person's behavior based on the following data: surveillance camera footage, location information, and SNS message history."

[1455] Step 4:

[1456] The server extracts evidence from the reproduced behavioral data and cross-references its authenticity from multiple perspectives. It calculates the degree of consistency from multiple data sources and selects only highly reliable evidence. The input data is the reproduced behavioral data, and the output data is the verified evidence.

[1457] Step 5:

[1458] The server generates an analysis result report based on the verified evidence and outputs it in PDF format. The report is stored in secure storage. The input data is the verified evidence, and the output data is the PDF report.

[1459] Step 6:

[1460] Users log in to the system using a terminal, search for and download analysis result reports. The input data is the user's search keywords, and the output data is a download link for the report.

[1461] Step 7:

[1462] Users can use their devices to remotely monitor and check the surveillance camera footage in real time. The system uses an anomaly detection algorithm to provide real-time warnings when an abnormality occurs. The input data is the surveillance camera footage, and the output data is an anomaly detection warning.

[1463] Step 8:

[1464] The server recognizes the user's emotional state using an emotion engine and provides feedback and additional support information based on the analysis results. The input data is the user's facial expressions and voice, and the output data is the feedback and support information.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] [Fourth embodiment]

[1469] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1470] 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.

[1471] 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).

[1472] 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.

[1473] 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.

[1474] 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).

[1475] 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.

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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."

[1482] Specific Embodiments of the System

[1483] This patented system is a data analysis system that utilizes generative AI, where servers, terminals, and users work together. This system is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying.

[1484] Server Processing

[1485] Data collection and integration

[1486] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[1487] Data Preprocessing

[1488] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[1489] Data analysis and behavioral reproduction

[1490] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[1491] Evidence extraction and verification

[1492] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[1493] Output of results

[1494] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[1495] User operations

[1496] Accessing the system

[1497] Users log in to the system using their terminals. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[1498] Specific examples

[1499] Example 1: Proof of innocence

[1500] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. Users can download this report and use it to proceed with legal proceedings.

[1501] Example 2: Proof of being a victim of bullying

[1502] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it to help with school and legal responses.

[1503] As described above, this system makes full use of generative AI to process huge amounts of data efficiently and quickly to prove that someone "did not do it" or "did not exist," thereby helping to avoid false accusations and bullying.

[1504] The processing flow will be explained below.

[1505] Program processing steps

[1506] Step 1: Data collection

[1507] The server accesses data sources related to the incident or situation of interest.

[1508] The server downloads the surveillance camera video via the network.

[1509] The server obtains the mobile phone's location information through an API.

[1510] The server extracts the SNS message history from the database.

[1511] The server stores the collected data in temporary storage and consolidates all the data.

[1512] Step 2: Data Preprocessing

[1513] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[1514] The server performs a process to remove noise from the mobile phone's location information.

[1515] The server filters the SNS message history for important keywords and removes irrelevant data.

[1516] The server stores the pre-processed data in a new storage.

[1517] Step 3: Data analysis and behavioral reproduction

[1518] The server inputs the preprocessed data into the generation AI.

[1519] The server uses generative AI to cross-reference security camera footage with location data.

[1520] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[1521] The server visualizes the behavioral simulation results in a virtual environment.

[1522] Step 4: Evidence extraction and verification

[1523] The server extracts important evidential data from the reconstructed behavioral data.

[1524] The server cross-references the extracted evidence with information from different data sources.

[1525] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[1526] The server records the final evidence and its authenticity in a database.

[1527] Step 5: Output the results

[1528] The server generates an analysis report based on the verified evidence.

[1529] The server outputs the report in PDF format and stores it in secure storage.

[1530] Step 6: User interaction

[1531] A user logs into the system using a terminal.

[1532] The user searches through the analysis results reports and selects the report of interest.

[1533] The user downloads the selected report and checks its contents.

[1534] Users can take appropriate legal action or measures based on the contents of the report.

[1535] These are the specific processing steps of the system based on patent claims. This system allows efficient and reliable proof of non-existence or non-commitment.

[1536] Example 1

[1537] 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."

[1538] Conventional data analysis systems have the problem of making it difficult to prove false accusations, bullying, and other crimes that "did not occur" or "did not exist." The manual process of collecting, integrating, analyzing, and verifying data is extremely time-consuming. Furthermore, because much of the information contains noise, it is difficult to accurately reproduce behavior or verify the credibility of evidence. Furthermore, there are insufficient ways for users to easily access, search, and download analysis results.

[1539] 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.

[1540] In this invention, the server includes: means for using generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using generative AI and simulating the target person's past behavior; means for extracting evidence from the reproduced data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report and saving it in a secure storage device; and means for users to log in to the system using their terminals and search for and download analysis result reports of interest. This makes it possible to efficiently prove that someone did not commit or did not exist, such as a false accusation or bullying victim.

[1541] "Generative AI" refers to algorithms that use artificial intelligence techniques to process large amounts of data and generate new data and information.

[1542] "Data collection" is the process of gathering the necessary information from various data sources, including surveillance camera footage, location information, and social media message history.

[1543] "Data integration" refers to the process of centrally managing collected data and converting it into a unified format.

[1544] "Data preprocessing" refers to the data cleaning and filtering procedures used to remove noise from raw data and make it ready for analysis.

[1545] "Denoising" refers to the process of removing errors and unnecessary information from data.

[1546] "Data analysis" refers to the process of extracting useful information from collected and pre-processed data using statistical methods and artificial intelligence techniques.

[1547] "Behavioral reproduction" refers to reconstructing the past behavior of a specific person or subject as a simulation or model based on analyzed data.

[1548] "Evidence extraction" refers to the process of extracting logically significant information from replicated data and using it to support a particular conclusion.

[1549] "Verification of credibility" refers to the process of checking the reliability of the evidence obtained using different data sources and cross-referencing.

[1550] "Report output" refers to compiling the analysis and verification results in document form and making them available for viewing by users.

[1551] "Secure storage device" refers to a storage system that has security features such as authentication and encryption.

[1552] "User" refers to an individual or organization that uses this system to search for and download analysis results reports.

[1553] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[1554] "Login" refers to the authentication process required for a user to access a system.

[1555] "Search" refers to the process of locating information of interest using specific keywords and filters.

[1556] "Downloading" refers to copying data or files to your device via the Internet.

[1557] MODE FOR CARRYING OUT THE INVENTION

[1558] System Overview

[1559] This invention is a data analysis system that utilizes generative AI, and is particularly specialized in proving that something did not happen or did not exist, such as false accusations or bullying. The system operates in cooperation with the server, terminals, and users.

[1560] Server Roles

[1561] The server is responsible for:

[1562] 1. Data Collection and Integration

[1563] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history. This is done by downloading data using network APIs and database queries. The collected data is first stored in temporary storage (e.g., cloud storage) and then integrated in a database system (e.g., a relational database).

[1564] 2. Data Preprocessing

[1565] The server filters and denoises the collected data. For example, it uses the OpenCV library to fill in blurry areas in security camera footage and removes low-precision data from location data. For social media messages, it uses the NLTK library to filter for important keywords.

[1566] 3. Data analysis and behavioral reproduction

[1567] The server then uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis cross-references time and location information to recreate a person's behavior at a specific time and place. The results are then visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[1568] 4. Extraction and verification of evidence

[1569] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that uses SQL queries and custom scripts.

[1570] 5. Outputting the results

[1571] The verified evidence is generated as an analysis report in PDF format, which is saved in secure storage (e.g., cloud storage). The PDF is generated using LaTeX and HTML to PDF libraries.

[1572] User Roles

[1573] The user does the following:

[1574] 1. Access to the System

[1575] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[1576] 2. Search and download analysis results reports

[1577] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[1578] Specific examples

[1579] 1. Proof of Innocent Conviction

[1580] The server collects and consolidates all data related to a false accusation case, including surveillance camera footage from the day of the crime, mobile phone location information, and transportation usage history. This data is then preprocessed and analyzed using generative AI. The analysis proves that the target person was in a different location at the time of the crime. This evidence is verified from multiple data sources and compiled into a report. Users can download this report and use it to further legal proceedings.

[1581] Example prompt sentence:

[1582] "Please tell me the results of the analysis of the incident that occurred on January 1, 2023."

[1583] 2. Proof of being a victim of bullying

[1584] In cases where bullying is suspected, the server collects school surveillance camera footage, social media message history, and testimony audio data. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying occurred. The results of this analysis are verified using different data sources and compiled into a report as reliable evidence. Users can download this report and use it for school or legal action.

[1585] Example prompt sentence:

[1586] "Please tell me the results of an analysis of bullying that occurred at a specific school on January 1, 2023."

[1587] The above is a mode for carrying out the invention, and this system makes it possible to prove false accusations and bullying victims efficiently and with high accuracy.

[1588] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1589] Step 1: Data collection and integration

[1590] concrete action

[1591] The server collects relevant data from multiple data sources, such as surveillance camera footage, mobile phone location information, and social media message history, by downloading data using network APIs and database queries.

[1592] input

[1593] API access information and queries for each data source (surveillance cameras, mobile phone location information, social media messages).

[1594] Data processing and calculation

[1595] Fetch data using network APIs or SQL queries and store it in temporary storage (e.g. cloud storage).

[1596] output

[1597] Temporarily stored raw data before preprocessing.

[1598] Step 2: Data Preprocessing

[1599] concrete action

[1600] The server performs quality filtering and noise reduction on the collected data. For example, it uses the OpenCV library to fill in blurry parts of surveillance camera footage, and a Python script to remove inaccurate parts of location data. For social media messages, it uses the NLTK library to filter for important keywords.

[1601] input

[1602] Temporarily stored raw data before preprocessing.

[1603] Data processing and calculation

[1604] Generate a quality-enhanced dataset through filtering and denoising.

[1605] output

[1606] Preprocessed data with improved quality.

[1607] Step 3: Data analysis and behavioral replication

[1608] concrete action

[1609] The server uses the preprocessed data to perform analysis using a generative AI model (e.g., GPT-3.5). The analysis involves cross-referencing time and location information to simulate a person's behavior at a specific time and place. The results of this analysis are visualized in a virtual environment using 3D modeling software such as Unity or Blender.

[1610] input

[1611] Preprocessed dataset.

[1612] Data processing and calculation

[1613] Generative AI models are used to analyze data and run simulations to reproduce specific behaviors.

[1614] output

[1615] Analysis results and behavioral simulation data.

[1616] Step 4: Evidence extraction and verification

[1617] concrete action

[1618] The server extracts useful evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, a process that involves SQL queries and custom scripts.

[1619] input

[1620] Reproduced behavioral simulation data.

[1621] Data processing and calculation

[1622] We extract evidence and verify data through cross-referencing to confirm its authenticity.

[1623] output

[1624] Verified evidence data.

[1625] Step 5: Output the results

[1626] concrete action

[1627] The server generates a report summarizing the results in PDF format based on the evidence of the analysis and verification. This report is saved in secure storage (e.g., cloud storage). The PDF generation uses LaTeX and HTML to PDF libraries.

[1628] input

[1629] Verified evidence data.

[1630] Data processing and calculation

[1631] Generate reports and export them in PDF format.

[1632] output

[1633] Analysis results report stored in secure storage.

[1634] Step 6: Access the system

[1635] concrete action

[1636] Users log in to the system using their devices, and the authentication process uses OAuth and two-factor authentication.

[1637] input

[1638] The user's authentication information.

[1639] Data processing and calculation

[1640] Uses an authentication system to verify user credentials and allow login.

[1641] output

[1642] Access rights to the system.

[1643] Step 7: Find and download the analysis report

[1644] concrete action

[1645] Users search for analysis reports using specific keywords (e.g., case number, location, names of involved parties), select the appropriate report from the search results, and download it.

[1646] input

[1647] Search keywords.

[1648] Data processing and calculation

[1649] Run a search query to filter relevant reports.

[1650] output

[1651] User downloadable analysis report.

[1652] (Application example 1)

[1653] 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."

[1654] In recent years, it has become increasingly difficult to prove false accusations and bullying, resulting in many cases of innocent people being treated unfairly. In particular, in today's world where much evidence is digitized, there is a need for efficient methods to collect, analyze, and verify the authenticity of vast amounts of data. Another issue is the lack of tools that allow users to easily prove their own actions. To solve this problem, an advanced data analysis system using generative AI is needed.

[1655] 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.

[1656] In this invention, the server includes: means for processing massive amounts of data at high speed using a generative AI and collecting and integrating past cases and related information; means for preprocessing the collected data and removing noise; simulation means for analyzing the data using a generative AI and recreating the target person's past behavior; means for extracting evidence from the recreated data and verifying its authenticity from multiple perspectives; means for outputting the verification results as a report accessible to the user; application means installed on a smartphone for automatically collecting location information, usage history, and camera footage; preprocessing means for removing noise and filtering the collected data; verification means for cross-referencing information collected from multiple data sources and checking its authenticity; and output means for generating a PDF report of the analysis results. This enables users to easily and reliably collect, analyze, and manage evidence when proving their innocence or existence.

[1657] "Generative AI" is a type of artificial intelligence that uses generative algorithms to create new data and information.

[1658] "Big data" refers to the large amount of digital data collected from a wide variety of information sources.

[1659] "Past events" refers to data or information about specific events or occurrences that have occurred in the past.

[1660] "Collection and integration" is the process of bringing together data from multiple sources and converting it into a unified format.

[1661] "Preprocessing" is a preparatory step to remove noise from the data to be analyzed and improve its quality.

[1662] "Noise reduction" is the process of eliminating meaningless data and errors.

[1663] "Analysis" refers to the process of examining data to extract and understand information.

[1664] "Simulation of past behavior" is the process of reconstructing a person's behavior at a specific time and place on a computer based on collected data.

[1665] "Evidence extraction" is the process of extracting useful information or data from the analysis results.

[1666] "Verifying credibility" is the process of confirming the accuracy and reliability of the evidence or data obtained.

[1667] A "report" refers to a document that organizes and documents the results of analysis and verification.

[1668] An "application installed on a smartphone" is software with specific functions that runs on a smartphone.

[1669] "Location information" refers to data that indicates a location at a particular point in time.

[1670] "Usage History" refers to records of how a user uses a device or application.

[1671] "Camera footage" refers to visual data captured by a digital camera.

[1672] "Noise reduction and filtering" is the process of removing unnecessary parts to improve the quality of collected data.

[1673] "Cross-referencing" refers to comparing data obtained from different sources with each other.

[1674] "PDF format" is an abbreviation for Portable Document Format developed by Adobe, and is a format for electronic documents.

[1675] Specific Embodiments of the System

[1676] This system is a data analysis system that utilizes generative AI, where the server, terminal, and user work together. This system is particularly specialized in proving that someone did not commit or exist, such as a false accusation or bullying victim.

[1677] Server Processing

[1678] Data collection and integration

[1679] The server accesses multiple data sources to collect relevant data. Specifically, it downloads surveillance camera footage from the network, obtains mobile phone location information via API, and extracts social media message history from a database. This collected data is first stored in temporary storage and then integrated.

[1680] Data Preprocessing

[1681] The server then filters and denoises the collected data. For example, to improve the quality of surveillance camera footage, it applies algorithms to fill in blurry areas and removes low-precision data from mobile phone location information. In particular, it filters social media message histories for important keywords.

[1682] Data analysis and behavioral reproduction

[1683] The server then uses the pre-processed data to perform analysis using generative AI. For example, it cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The results of this analysis are visualized in a virtual environment.

[1684] Evidence extraction and verification

[1685] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity, for example by checking whether surveillance camera footage matches with location information.

[1686] Output of results

[1687] Evidence of the completed verification is generated as an analysis result report in PDF format and stored in secure storage.

[1688] User operations

[1689] Accessing the system

[1690] Users log in to the system using a smartphone application. They can search for analysis results reports related to their interests, select them, and download them. For example, to obtain an analysis results report for a specific wrongful conviction case, users simply enter the relevant time, location, and names of those involved as search keywords.

[1691] Specific examples

[1692] Example 1: Proof of innocence

[1693] In a false accusation case, the server first collects and integrates surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. Next, this data is preprocessed and analyzed using generative AI. The analysis results prove that the target person was in a different location at the time of the crime. The evidence is verified from multiple data sources, and finally, a report is output. The user can download this report and use it to proceed with legal proceedings. Below is an example of a prompt for the generative AI.

[1694] "Collect and analyze data to prove that the user was in the Shinjuku Station area between 12:30 and 1:30 PM on October 1, 2023. The required data is as follows: GPS location information, SNS message history, and camera footage. Based on this data, reconstruct the user's behavioral history and generate a credible report."

[1695] Example 2: Proof of being a victim of bullying

[1696] In cases where bullying is suspected, the server collects surveillance camera footage from classrooms and schools, social media message history, and audio testimony. After preprocessing the data, generative AI is used to analyze it and confirm whether bullying has occurred. The analysis results are verified using different data sources, and evidence that has been confirmed to be credible is output as a report. Users can download this report and use it for school or legal action.

[1697] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1698] Step 1: Data collection

[1699] The server first collects surveillance camera footage, mobile phone location information, and social media message history. This is done using the APIs of the surveillance camera system, mobile phone network, and social media platform. The input data is raw data from each source, which is then integrated and stored in temporary storage. The server then converts this data into a format that can be processed collectively.

[1700] Step 2: Data Preprocessing

[1701] The server preprocesses the collected data and removes noise. Specifically, it applies algorithms to complement blurry surveillance camera footage, improve the accuracy of location information, and extract and filter important keywords from social media messages. The input data are raw video data, location information data, and social media message data, and the output is high-quality, consistent data.

[1702] Step 3: Data analysis and behavioral replication

[1703] The server uses the preprocessed data to perform analysis using generative AI. This analysis cross-references surveillance camera footage with location data to simulate where a person was at a specific time. The input data is the preprocessed footage, location information, and social media messages, and the output is a reproduced behavioral history. The reproduced data can be visualized in a virtual environment.

[1704] Step 4: Evidence extraction and verification

[1705] The server extracts key evidence from the reconstructed behavioral data and cross-references information from different data sources to verify its authenticity. Specifically, it checks whether surveillance camera footage matches the location information and performs additional cross-referencing. The input data is the reconstructed behavioral history and information from each data source, and the output is evidence whose authenticity has been confirmed.

[1706] Step 5: Output the results

[1707] The server generates a PDF report of the analysis results based on the evidence whose authenticity has been confirmed and stores it in secure storage. Users can access this report and download it as needed. The input data is the evidence whose authenticity has been confirmed, and the output is a PDF report. Users access this report through a smartphone application.

[1708] 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.

[1709] Specific Embodiments of the System

[1710] This patented system is a data analysis system that utilizes generative AI, in which a server, terminal, user, and emotion engine work together. This system specializes in proving "non-existence" and "non-existence," and furthermore, by evaluating and utilizing the user's emotional state, it provides a more accurate analysis and user experience.

[1711] Server Processing

[1712] Data collection and integration

[1713] The server accesses various data sources to collect data related to the incident or target situation. Specifically, it downloads surveillance camera footage via the network, obtains mobile phone location information via API, and extracts social media message history from a database. The collected data is stored in temporary storage and later integrated.

[1714] Data Preprocessing

[1715] The server filters and denoises the collected data. To improve the quality of surveillance camera footage, algorithms are applied to fill in blurry areas. Inaccurate data is removed from mobile phone location information, and social media message histories are filtered for important keywords.

[1716] Data analysis and behavioral reproduction

[1717] The server inputs the preprocessed data into the AI ​​generator, cross-referencing the surveillance camera footage and location data. Based on the analyzed data, a simulation is run to recreate the target person's behavior, and the results are visualized in a virtual environment.

[1718] Evidence extraction and verification

[1719] The server extracts evidence from the reconstructed behavioral data, performs cross-reference verification using information from different data sources, evaluates its credibility, and selects only highly reliable evidence, which is then recorded in a database.

[1720] Use of emotion engine

[1721] The server uses an emotion engine to recognize the user's emotions and evaluates the user's stress level and emotional state based on the analysis results. Based on the emotion engine's recognition results, the server proposes appropriate feedback and actions to the user. In addition, the emotion data is used as part of the analysis by the generative AI, enabling more accurate behavioral reproduction.

[1722] Output of results

[1723] The server generates an analysis report based on the verified evidence, which is output in PDF format and stored in secure storage.

[1724] User operations

[1725] Accessing the system

[1726] Users log in to the system using their terminals. They can search for, select, and download analysis reports related to their interests. For example, to obtain an analysis report on a specific wrongful conviction case, users can enter the relevant time, location, and names of those involved as search keywords.

[1727] Use of emotional feedback

[1728] While the user is using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice. As a result, the system presents the analysis results and provides additional support information according to the user's stress level and emotional state. For example, easy-to-understand guidance and additional support are suggested to users in a high-stress state.

[1729] Specific examples

[1730] Example 1: Proof of innocence

[1731] In a case of false accusation, the server first collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the crime. This data is preprocessed and analyzed by generative AI, proving that the target person was in a different location at the time of the crime. The evidence is verified from different data sources and compiled into a report as reliable evidence. The user downloads this report and proceeds with the legal process. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[1732] Example 2: Proof of being a victim of bullying

[1733] If bullying is suspected, the server collects and preprocesses surveillance camera footage from classrooms and schools, social media message history, and testimony audio data. Generative AI is used to analyze the data to confirm whether bullying has occurred. The analysis results are verified for authenticity using different data sources and output as a report. Users can download this report for reference in school or legal proceedings. During this process, the emotion engine evaluates the user's emotional state and suggests appropriate countermeasures.

[1734] The above is an embodiment of the patented system that combines an emotion engine. This system improves the accuracy of data analysis and enables flexible support that corresponds to the user's emotional state.

[1735] The processing flow will be explained below.

[1736] Program processing steps (system combining emotion engines)

[1737] Step 1: Data collection

[1738] The server accesses data sources related to the incident or situation of interest.

[1739] The server downloads the surveillance camera video via the network.

[1740] The server obtains the mobile phone's location information through an API.

[1741] The server extracts the SNS message history from the database.

[1742] The server stores the collected data in temporary storage and consolidates all the data.

[1743] Step 2: Data Preprocessing

[1744] The server analyzes the surveillance camera footage and applies an algorithm to fill in any blurry areas.

[1745] The server performs a process to remove noise from the mobile phone's location information.

[1746] The server filters the SNS message history for important keywords and removes irrelevant data.

[1747] The server stores the pre-processed data in a new storage.

[1748] Step 3: Data analysis and behavioral reproduction

[1749] The server inputs the preprocessed data into the generation AI.

[1750] The server uses generative AI to cross-reference security camera footage with location data.

[1751] The server performs a simulation to reproduce the target person's behavior based on the analyzed data.

[1752] The server visualizes the behavioral simulation results in a virtual environment.

[1753] Step 4: Evidence extraction and verification

[1754] The server extracts important evidential data from the reconstructed behavioral data.

[1755] The server cross-references the extracted evidence with information from different data sources.

[1756] The server evaluates the credibility of the evidence and selects only highly reliable evidence.

[1757] The server records the final evidence and its authenticity in a database.

[1758] Step 5: Evaluation by the Emotion Engine

[1759] The server activates an emotion engine that recognizes the user's emotions in real time.

[1760] The server analyzes the user's facial expressions and voice data to assess their stress level and emotional state.

[1761] The server generates appropriate feedback and presents the analysis results according to the user's emotional state.

[1762] Step 6: Output the results

[1763] The server generates an analysis report based on the verified evidence.

[1764] The server outputs the report in PDF format and stores it in secure storage.

[1765] Step 7: User interaction

[1766] A user logs into the system using a terminal.

[1767] The user searches through the analysis results reports and selects the report of interest.

[1768] The user downloads the selected report and checks its contents.

[1769] Users can take appropriate legal action or measures based on the contents of the report.

[1770] Specific examples

[1771] Example 1: Proof of innocence

[1772] In step 1, the server collects surveillance camera footage, mobile phone location information, and transportation usage history from the day of the incident. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate the behavior of the target person. In step 4, evidence is extracted and verified from the recreated behavioral data. In step 5, the emotion engine evaluates the user's stress level and adjusts the presentation method of the analysis results. Finally, in step 6, an analysis result report is generated and saved, and in step 7, the user downloads this report to proceed with legal procedures.

[1773] Example 2: Proof of being a victim of bullying

[1774] In step 1, the server collects surveillance camera footage from within the school, social media message history, and testimony audio data. In step 2, this data is preprocessed, and in step 3, it is analyzed by generative AI to recreate bullying behavior. In step 4, evidence is extracted and verified to confirm whether bullying behavior occurred. In step 5, the emotion engine evaluates the user's emotional state and provides appropriate feedback. Finally, in step 6, an evidence-based report is generated and saved, and in step 7, the user can download this report for use by school administrators or legal proceedings.

[1775] Through these specific processing steps, the present invention provides a system that efficiently proves "not doing something" or "not existing" and also responds to the user's emotional state.

[1776] Example 2

[1777] 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."

[1778] In recent years, the rapid increase in data volume has created a demand for effective data processing technologies. However, conventional systems require time for data collection, noise removal, analysis, and evidence extraction and verification. Furthermore, they struggle to process diverse data sources in a unified manner. Furthermore, they do not take into account the user's emotional state, resulting in a poor user experience. To address these challenges, a more advanced data analysis system is needed.

[1779] 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.

[1780] In this invention, the server includes means for using generative AI to process huge amounts of information at high speed and collect and integrate past cases and related information, means for preprocessing the collected information and removing noise, means for analyzing data using generative AI and simulating the target person's past behavior, means for extracting evidence from the reproduced information and verifying its credibility from multiple perspectives, means for recognizing the user's emotional state in real time and providing appropriate feedback based on the analysis results, and means for outputting the verification results as a report that the user can access. This enables data collection, analysis, and evidence verification to be carried out quickly and with high accuracy, and makes it possible to provide flexible support according to the user's emotional state.

[1781] "Generative AI" is an artificial intelligence technology that quickly generates and analyzes useful information from massive amounts of data.

[1782] "Information" is a general term for data collected from a variety of data sources, such as surveillance camera footage, location data of mobile devices, and message history from information exchange services.

[1783] "Noise" refers to unnecessary data or errors that should be removed during data processing and analysis.

[1784] "Simulation" is a method of virtually recreating the behavior of a target person based on collected and analyzed data.

[1785] "Evidence" is facts or information extracted from reproduced behavioral data and assessed for its veracity.

[1786] "Emotional state" refers to the psychological state of the user that is analyzed in real time from facial expressions, voice, etc.

[1787] "Feedback" refers to instructions and support information provided based on the user's emotional state and analysis results.

[1788] A "report" is a document that summarizes the analysis results and verified evidence, and is output in an electronic format such as PDF.

[1789] MODE FOR CARRYING OUT THE INVENTION

[1790] This invention is a data analysis system in which a server, a user's device, and an emotion engine work together. This system uses a generative AI model to process vast amounts of information at high speed, and collects and integrates past cases and related information. The detailed configuration is described below.

[1791] Server Processing

[1792] A server primarily uses the following hardware and software components:

[1793] Hardware: A server machine with a high-performance CPU and GPU, sufficient memory and storage.

[1794] Software: Database management systems (e.g., MySQL, PostgreSQL), API access tools, generative AI models (e.g., GPT-3, BERT), simulation engines (e.g., Unity), sentiment analysis engines.

[1795] Data collection

[1796] The server collects data from various information sources, such as surveillance footage, location information of mobile devices, and message history from information exchange services. For example, it downloads surveillance camera footage via the network, obtains mobile phone location information via an API, and extracts SNS messages from a database.

[1797] Data Preprocessing

[1798] The collected data cannot be used as is, so it is filtered and noise-removed. Specifically, surveillance camera footage is supplemented with super-resolution technology, location data accuracy is evaluated to remove inaccurate data, and social media messages are filtered using specific keywords.

[1799] Data Analysis and Simulation

[1800] The preprocessed data is input into a generative AI model for analysis. Based on the analysis results, a simulation is performed to reproduce the target person's behavior, and the simulation results are visualized in a 3D environment. This makes it possible to visually reproduce past behavior.

[1801] Evidence extraction and verification

[1802] Evidence is extracted from the reconstructed behavioral data and its veracity is verified from multiple perspectives. Data is cross-referenced with other sources, and only reliable evidence is included in the final report. This report is generated in PDF format and stored in secure storage.

[1803] Use of emotion engine

[1804] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device. Based on the analysis results, the server evaluates the user's stress level and emotional state and dynamically adjusts the system's feedback and support information.

[1805] User operations

[1806] Accessing the system

[1807] Users log in to the system using their own devices. After logging in, they can search for and download analysis results reports. For example, to obtain a report on a specific wrongful conviction case, users can enter the relevant time, place, and names of those involved as search keywords.

[1808] Use of emotional feedback

[1809] The system analyzes the user's emotional state in real time while they are using the system, and provides easy-to-understand guidance and additional support information based on the analysis results. If the user is in a high-stress state, the system will suggest appropriate measures, improving the quality of the user experience.

[1810] Specific examples

[1811] Example 1: Proof of innocence

[1812] In a case of false accusation, the server first collects surveillance footage, vehicle location information, and public transportation usage history from the day of the crime. This data is preprocessed and analyzed using a generative AI model, proving that the target was in a different location at the time of the crime. This is compiled into a report as reliable evidence, which the user can download to proceed with legal proceedings. During this process, the emotion engine evaluates the user's emotional state and provides appropriate feedback.

[1813] Example 2: Proof of being a victim of bullying

[1814] If bullying is suspected, the server collects and preprocesses classroom and school surveillance footage, social media message history, and testimony audio data. It then uses a generative AI model to analyze the data and confirm whether bullying has occurred. The analysis results, which have been verified for reliability, are output as a report that users can download and use as reference for school and legal procedures. During this process, the emotion engine assesses the user's emotional state and suggests appropriate countermeasures.

[1815] Examples of prompt statements

[1816] 1. "Analyze CCTV footage and location data related to a false accusation case to prove that the subject was somewhere else at the time of the crime."

[1817] 2. "Based on data on bullying behavior within the school, please collect evidence of bullying and prepare a report."

[1818] In this way, the system of the present invention is highly efficient and accurate in data analysis, and by combining it with an emotion engine to improve the user experience, it achieves more reliable evidence collection and report generation.

[1819] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1820] Step 1:

[1821] Data collection

[1822] The server collects necessary information from data sources such as surveillance camera footage, mobile location information, and information exchange service message history. Specifically, it downloads surveillance camera footage from a specified URL using an HTTP request, obtains mobile phone location information via an API, and extracts SNS messages from a database using SQL queries.

[1823] Input: Data source URL, API key, SQL query

[1824] Output: A set of collected information

[1825] Step 2:

[1826] Data Preprocessing

[1827] The server removes noise from the collected information and formats it into a form suitable for analysis. For surveillance camera footage, super-resolution technology is applied to fill in blurry areas, for mobile phone location information, location data below a certain threshold is removed after evaluating its accuracy, and for social media messages, specific keywords are filtered.

[1828] Input: A set of collected information

[1829] Output: A set of preprocessed information

[1830] Step 3:

[1831] Data analysis

[1832] The server inputs the preprocessed information into a generative AI model for analysis. The generative AI model (e.g., GPT-3, BERT) estimates the target person's behavior based on the input data and generates a timeline.

[1833] Input: A set of preprocessed information

[1834] Output: Analysis results (timeline of estimated behavior)

[1835] Step 4:

[1836] Behavioral reproduction

[1837] The server performs a simulation to reproduce the target person's behavior based on the analysis results, and visualizes the target person's behavior in a virtual 3D environment using a simulation engine.

[1838] Input: Analysis results (estimated timeline of behavior)

[1839] Output: Visualized behavioral simulation

[1840] Step 5:

[1841] Evidence extraction and verification

[1842] The server extracts evidence from the re-created behavioral simulations and verifies its authenticity by cross-referencing it with other data sources. It compares data from different sources and selects only matching data as reliable evidence.

[1843] Input: Visualized behavioral simulations, data from other data sources

[1844] Output: A set of verified evidence

[1845] Step 6:

[1846] Use of emotion engine

[1847] The server inputs facial expression and voice data collected from the user's device into an emotion analysis engine in real time to evaluate the user's emotional state. The results of this evaluation are fed back to the generative AI model, and the system's output is adjusted based on the analysis results and the feedback.

[1848] Input: User's facial expression data, voice data

[1849] Output: Emotion evaluation results, adjusted analysis results, and feedback content

[1850] Step 7:

[1851] Output of results

[1852] The server automatically generates a report based on the verified evidence and the adjusted analysis results. The report is saved in PDF format and uploaded to secure storage. Users can download the report.

[1853] Input: Verified evidence set, adjusted analysis results

[1854] Output: Report in PDF format

[1855] Step 8:

[1856] User operations

[1857] Users log in to the system using a terminal and search, select, and download analysis results reports related to their interests.

[1858] Input: User credentials, search query

[1859] Output: Download link for analysis report

[1860] Step 9:

[1861] Use of emotional feedback

[1862] While the user is using the system, the device's camera and microphone are used to collect facial and voice data in real time, allowing the system to continuously analyze the user's emotional state and provide additional support information or guidance when necessary.

[1863] Input: Real-time facial expression data, voice data

[1864] Output: Additional supporting information and guidance

[1865] (Application example 2)

[1866] 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."

[1867] While conventional data analysis systems can efficiently process massive amounts of data and extract reliable evidence, they are unable to provide feedback that takes into account the user's emotional state or real-time warnings when an abnormality occurs. This has resulted in problems that reduce users' sense of security and satisfaction when using the system. Furthermore, they lack the functionality to remotely check surveillance camera footage and quickly detect suspicious behavior.

[1868] 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.

[1869] In this invention, the server includes: means for using a generative AI to process massive amounts of data at high speed and collect and integrate past cases and related information; means for preprocessing the collected data and removing noise; means for analyzing the data using the generative AI and simulating the past behavior of a target person; means for extracting evidence from the reproduced data and verifying its credibility from multiple perspectives; means for outputting the verification results as a report accessible to the user; means for recognizing the user's emotional state and providing feedback and additional support information based on the analysis results; means for the user to remotely check surveillance camera footage and detect anomalies; and means for providing a warning in real time when an anomaly is detected. This enables advanced data analysis and real-time anomaly detection while taking the user's emotional state into consideration.

[1870] "Generative AI" is an artificial intelligence technology that processes massive amounts of data quickly and efficiently, and reproduces behavior based on past cases and related information.

[1871] "Data preprocessing" refers to the process of removing noise and improving the quality of collected data before analyzing it.

[1872] "Simulation methods" are methods for recreating the target person's past behavior based on data analyzed using generative AI.

[1873] "Evidence extraction" is the process of extracting important information from the analyzed data and verifying its authenticity.

[1874] "Emotional state recognition" is a technology that analyzes a user's emotions from their facial expressions and voice and evaluates their state.

[1875] "Feedback provision means" refers to a method of presenting appropriate actions and support information to users based on the analysis results.

[1876] "Remote monitoring means" refers to a means by which a user can check surveillance camera footage from a remote location and detect abnormalities.

[1877] "Real-time warning means" refers to a method of notifying the user immediately when an abnormality is detected.

[1878] This invention is a data analysis system that utilizes generative AI, and is realized through the cooperative operation of a server, a terminal, a user, and an emotion engine. The specific configuration and operation of the system are described below.

[1879] System configuration

[1880] Hardware

[1881] server

[1882] A computer with a powerful processor and large memory capacity

[1883] Terminal

[1884] Smartphone (iOS or Android)

[1885] Surveillance cameras (network-connectable)

[1886] Camera and microphone for detecting the user's facial expressions and voice

[1887] software

[1888] Generative AI Models

[1889] For example, GPT-4

[1890] API for emotion recognition

[1891] For example, Microsoft Azure's Emotion API

[1892] Database

[1893] For example, Firebase, MySQL, etc.

[1894] Development environment

[1895] For example, Xcode, Android Studio

[1896] Server Processing

[1897] The server performs the following process.

[1898] 1. Data Collection and Integration

[1899] Use APIs to collect surveillance camera footage, location information, and social media messages.

[1900] The collected data is stored in temporary storage and later consolidated.

[1901] 2. Data Preprocessing

[1902] It runs algorithms to improve the quality of video data, remove noise from location information, and filter keywords from social media messages.

[1903] 3. Data Analysis

[1904] Preprocessed data is input into the generative AI model, and analysis and behavior reproduction are performed.

[1905] Simulations are performed based on the analyzed data and visualized in a virtual environment.

[1906] 4. Extraction and verification of evidence

[1907] Extract evidence from the reproduced data and perform cross-reference verification.

[1908] Only reliable evidence is selected and ultimately recorded in a database.

[1909] 5. Outputting the results

[1910] An analysis result report is generated based on the verified evidence and output in PDF format.

[1911] 6. Use of Emotion Engines

[1912] It recognizes the user's emotional state and provides feedback and additional support information based on the analysis results.

[1913] Terminal handling

[1914] The user uses the device to perform the following operations:

[1915] 1. Access to the System

[1916] Users log in to the system using their smartphone, search for analysis result reports, select them and download them.

[1917] 2. Check the surveillance camera footage

[1918] You can check the footage from your home or office surveillance cameras in real time from your smartphone to check for any abnormalities.

[1919] 3. Real-time alerts

[1920] If an anomaly is detected, the system will alert the user in real time.

[1921] User operations

[1922] The user uses the system by performing the following operations:

[1923] 1. Use emotional feedback

[1924] While using the system, the emotion engine analyzes the user's emotions in real time from their facial expressions and voice, and provides feedback based on their stress level and emotional state.

[1925] Specific examples

[1926] For example, while the user is away from home, the system can analyze suspicious behavior based on home security camera footage, mobile phone location information, and social media message history, and generate a report. If an abnormality is detected, the emotion engine will evaluate the user's stress level and provide necessary feedback.

[1927] "Recreate the target person's actions using the following data: surveillance camera footage, location information, and social media message history."

[1928] This system enables advanced data analysis and real-time anomaly detection while taking into account the user's emotional state.

[1929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1930] Step 1:

[1931] The server collects data such as surveillance camera footage, mobile phone location information, and social media message history. Input data is collected from each data source through APIs and stored in temporary storage. The output is the integrated raw data.

[1932] Step 2:

[1933] The server performs preprocessing on the collected data. Filtering is performed to improve the quality of surveillance camera footage, and noise is removed from location information. Filtering is also performed based on important keywords from SNS message history. The input data is raw data, and the output data is preprocessed data.

[1934] Step 3:

[1935] The server inputs the preprocessed data into the generative AI model and performs data analysis. The generative AI model performs the analysis and reproduces the target person's behavior. The input data is the preprocessed data, and the output data is the reproduced behavior data. In this case, the prompt used is "Please reproduce the target person's behavior based on the following data: surveillance camera footage, location information, and SNS message history."

[1936] Step 4:

[1937] The server extracts evidence from the reproduced behavioral data and cross-references its authenticity from multiple perspectives. It calculates the degree of consistency from multiple data sources and selects only highly reliable evidence. The input data is the reproduced behavioral data, and the output data is the verified evidence.

[1938] Step 5:

[1939] The server generates an analysis result report based on the verified evidence and outputs it in PDF format. The report is stored in secure storage. The input data is the verified evidence, and the output data is the PDF report.

[1940] Step 6:

[1941] Users log in to the system using a terminal, search for and download analysis result reports. The input data is the user's search keywords, and the output data is a download link for the report.

[1942] Step 7:

[1943] Users can use their devices to remotely monitor and check the surveillance camera footage in real time. The system uses an anomaly detection algorithm to provide real-time warnings when an abnormality occurs. The input data is the surveillance camera footage, and the output data is an anomaly detection warning.

[1944] Step 8:

[1945] The server recognizes the user's emotional state using an emotion engine and provides feedback and additional support information based on the analysis results. The input data is the user's facial expressions and voice, and the output data is the feedback and support information.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] 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.

[1952] 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).

[1953] 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.

[1954] 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."

[1955] 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.

[1956] 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).

[1957] 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.

[1958] 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.

[1959] 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.

[1960] 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.

[1961] 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.

[1962] 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.

[1963] 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.

[1964] 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.

[1965] 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.

[1966] 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.

[1967] The following is further disclosed regarding the above embodiment.

[1968] (Claim 1)

[1969] Using generative AI, we will process huge amounts of data at high speed, collect and integrate past cases and related information, and

[1970] a means for preprocessing and denoising the collected data;

[1971] A simulation method that analyzes data using generative AI and reproduces the target person's past behavior;

[1972] A means to extract evidence from the reproduced data and verify its authenticity from multiple perspectives;

[1973] A system that outputs the verified results as a report and includes a means for users to access it.

[1974] (Claim 2)

[1975] The system of claim 1, wherein the collected data includes at least one of surveillance camera footage, mobile phone location information, and SNS message history.

[1976] (Claim 3)

[1977] 10. The system of claim 1, wherein information from different data sources is cross-referenced in verifying the analysis results.

[1978] "Example 1"

[1979] (Claim 1)

[1980] Using generative AI, we will process huge amounts of data at high speed, collect and integrate past cases and related information, and

[1981] a means for preprocessing and denoising the collected data;

[1982] A simulation method that analyzes data using generative AI and reproduces the target person's past behavior;

[1983] A means to extract evidence from the reproduced data and verify its authenticity from multiple perspectives;

[1984] means for outputting the verified results as a report and storing the report in a secure storage device;

[1985] A means by which users can log in to the system using a terminal and search for and download analysis result reports of interest;

[1986] A system including:

[1987] (Claim 2)

[1988] 10. The system of claim 1, wherein the data collection includes at least one of surveillance camera footage, mobile phone location information, and social media message history.

[1989] (Claim 3)

[1990] 10. The system of claim 1, wherein information from different data sources is cross-referenced in verifying the analysis results.

[1991] "Application Example 1"

[1992] (Claim 1)

[1993] Using generative AI, we will process huge amounts of data at high speed, collect and integrate past cases and related information, and

[1994] a means for preprocessing and denoising the collected data;

[1995] A simulation method that analyzes data using generative AI and reproduces the target person's past behavior;

[1996] A means to extract evidence from the reproduced data and verify its authenticity from multiple perspectives;

[1997] The verified results are output as a report and made accessible to users.

[1998] An application means that is installed on a smartphone and automatically collects location information, usage history, and camera footage;

[1999] pre-processing means for denoising and filtering the collected data;

[2000] A verification method to cross-reference information collected from multiple data sources and check its authenticity;

[2001] A system including an output means for generating a report of the analysis results in PDF format.

[2002] (Claim 2)

[2003] The system of claim 1, wherein the collected data includes at least one of surveillance camera footage, mobile phone location information, and SNS message history.

[2004] (Claim 3)

[2005] 10. The system of claim 1, wherein information from different data sources is cross-referenced in verifying the analysis results.

[2006] "Example 2: Combining Emotion Engines"

[2007] (Claim 1)

[2008] Using generative AI, we will rapidly process huge amounts of information and collect and integrate past cases and related information.

[2009] a means for preprocessing and denoising the collected information;

[2010] A simulation method that analyzes data using generative AI and reproduces the target person's past behavior;

[2011] A means of extracting evidence from the reproduced information and verifying its authenticity from multiple perspectives;

[2012] A means of recognizing the user's emotional state in real time and providing appropriate feedback based on the analysis results;

[2013] A system that outputs the verified results as a report and includes a means for users to access it.

[2014] (Claim 2)

[2015] 2. The system according to claim 1, wherein the collected information includes at least one of surveillance device video, mobile object location information, and information exchange service message history.

[2016] (Claim 3)

[2017] 10. The system of claim 1, wherein information from different sources is cross-referenced when verifying analysis results.

[2018] "Application example 2 when combining emotion engines"

[2019] (Claim 1)

[2020] Using generative AI, we will process huge amounts of data at high speed, collect and integrate past cases and related information, and

[2021] a means for preprocessing and denoising the collected data;

[2022] A simulation method that analyzes data using generative AI and reproduces the target person's past behavior;

[2023] A means to extract evidence from the reproduced data and verify its authenticity from multiple perspectives;

[2024] The verified results are output as a report and made accessible to users.

[2025] A means of recognizing the user's emotional state and providing feedback and additional support information based ...

Claims

1. Using generative AI, we will process huge amounts of data at high speed, and collect and integrate past cases and related information. a means for preprocessing and denoising the collected data; A simulation method that analyzes data using generative AI and reproduces the target person's past behavior; A means to extract evidence from the reproduced data and verify its authenticity from multiple perspectives; A system that outputs the verified results as a report and includes a means for users to access it.

2. The system of claim 1, wherein the collected data includes at least one of surveillance camera footage, mobile phone location information, and SNS message history.

3. 10. The system of claim 1, wherein information from different data sources is cross-referenced in verifying the analysis results.

Images