System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting crime information in real time from a plurality of information sources on the Internet, a means for analyzing the collected crime information and predicting crime occurrence for the next one week, an interactive AI system means for proposing a consultation response or a specific countermeasure to a user on the basis of the prediction, and a means for notifying the user of the prediction result.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 recent years, petty theft and white hat crimes have been on the rise, particularly crimes that don't make the news, such as car theft, bicycle theft, and stalking. These crimes are difficult to report to the police, and new crime prevention methods are needed amid a declining number of police officers and a diversifying social environment. Furthermore, existing methods for providing citizens with crime prediction and countermeasures are limited, making it difficult to provide citizens with swift, concrete countermeasures. Citizens also find it difficult to consult the police about petty crimes. As a result, the environment in which citizens can live safely is being undermined. [Means for solving the problem]

[0005] To address the above-mentioned challenges, the present invention provides a crime prediction system that includes: means for collecting crime information in real time from multiple data sources on the Internet; means for analyzing the collected crime information and predicting crime occurrences for the next week; an interactive AI system for providing consultations and suggesting specific countermeasures to users based on the predictions; and means for notifying users of the results of the predictions. This system collects data using web scraping and API calls and uses a machine learning model to predict crime occurrences. Furthermore, it provides a function that allows users to consult with the interactive AI system and receive specific countermeasures. This allows citizens to easily consult about even minor crimes and provides an environment in which crime prevention measures can be easily implemented.

[0006] "Data sources" refer to multiple sources of crime information on the Internet, such as crime prevention maps, car theft information bureaus, and various social media platforms.

[0007] "Real-time" means that data is collected and processed immediately, the moment it is generated.

[0008] "Means of collection" refers to the technical methods used to obtain the required criminal information from data sources, including web scraping and API calls.

[0009] "Means of analysis" refers to the technical methods used to derive and predict crime trends based on collected data, such as machine learning algorithms.

[0010] "Predictive measures" are methods for estimating future crime occurrences from collected and analyzed data.

[0011] A "conversational AI system" is an artificial intelligence-based system that allows users to ask questions or ask questions in natural language and provides corresponding answers or suggestions.

[0012] "Means of notification" refers to the technical methods used to notify users of crime prediction results and specific countermeasures, including email and app notifications.

[0013] "Web scraping" is a technique for automatically extracting necessary information from websites.

[0014] "API Call" refers to the act of getting or sending data to or from other software or services using an Application Program Interface (API).

[0015] A "machine learning model" is a model that learns patterns based on large amounts of data and uses them to make predictions and classifications. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment of the system of the present invention will be described below.

[0038] Data collection implementation

[0039] First, the server collects crime information from multiple data sources on the Internet, including Yahoo! Maps crime prevention maps, car theft information bureaus, and social media sites with frequent new posts. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0040] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0041] Data Analysis Embodiments

[0042] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0043] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0044] An embodiment of an interactive AI system

[0045] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0046] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0047] Notification System Embodiments

[0048] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0049] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0050] Specific example explanation

[0051] 1. Data Collection:

[0052] The server collects new crime reports from Yahoo! Maps' crime prevention maps and social media.

[0053] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0054] 2. Data Analysis:

[0055] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0056] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0057] 3. Conversational AI systems:

[0058] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0059] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0060] 4. Notification system:

[0061] Users can set up car theft alerts in the app.

[0062] When the risk of car theft increases, the server sends a notification to the user saying, "The risk of car theft is high for the next week. Please be especially careful when parking at night."

[0063] As a result, the system according to the present invention can provide new crime prediction and countermeasures to help citizens live in peace.

[0064] The processing flow will be explained below.

[0065] Specific flow of program processing

[0066] Step 1: Start collecting data

[0067] The server will start the data collection process at the specified time interval (e.g. every hour).

[0068] The server runs a web scraping script to collect the latest crime information from multiple data sources on the Internet (e.g., crime prevention maps, car theft information bureaus, social media).

[0069] Step 2: Performing data collection

[0070] The server scans the web pages of each data source and extracts new crime report data.

[0071] The server calls the SNS API to retrieve posts containing keywords such as "car theft" and "stalking."

[0072] Step 3: Data Preprocessing

[0073] The server cleans the collected data, imputes missing values, and removes duplicate data.

[0074] The server tokenizes the text data and converts it into a format suitable for analysis.

[0075] Step 4: Analyze the data

[0076] The server inputs the cleansed data into an LSTM (long short-term memory) model and runs the machine learning algorithm.

[0077] The server then generates a prediction of crimes that may occur over the next week.

[0078] Step 5: Save the prediction results

[0079] The server stores the generated crime prediction results in a database.

[0080] Step 6: User Inquiry Processing

[0081] Users access the conversational AI system through a dedicated app or web portal.

[0082] Users input their questions or concerns into the chatbot interface. For example, they might type, "There have been a lot of bicycle thefts in my neighborhood recently. What can I do about it?"

[0083] Step 7: Parsing User Input

[0084] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[0085] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[0086] Step 8: Providing a solution

[0087] The server generates specific responses to the user's questions based on the predicted crime data.

[0088] The server will then present specific measures to the user through a chatbot, such as "We recommend installing a bicycle lock with an alarm."

[0089] Step 9: Establish notification settings

[0090] Within the app, users can set up notifications for specific crime types and geographic areas, such as car theft.

[0091] Step 10: Generate an alert

[0092] The server generates an alert based on the configured conditions, if applicable, when the risk of car theft increases.

[0093] Step 11: Sending notifications

[0094] The server sends notifications to users regarding increased crime risk.

[0095] Users receive notifications such as, "There is a high risk of car theft in your area over the next week. Please be careful when parking, especially overnight."

[0096] Through the above steps, the crime prediction system of the present invention can provide safety measures to citizens and increase crime prevention by making crime predictions in real time.

[0097] Example 1

[0098] 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."

[0099] Conventional crime prediction systems were unable to efficiently collect and analyze local crime information and provide users with appropriate crime prevention measures. It was also difficult to obtain the latest crime information in real time and make highly accurate crime predictions. This could result in citizens missing out on opportunities to take adequate crime prevention measures.

[0100] 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.

[0101] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for preprocessing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for notifying users of the prediction results. This allows citizens to collect crime information in real time and receive highly accurate crime predictions and specific crime prevention measures.

[0102] "Multiple data sources on the Internet" refers to multiple sources of information, such as websites and social media, that provide criminal information.

[0103] "Real-time" refers to constantly obtaining and processing the latest information without delay.

[0104] "Crime information" refers to detailed data and reports about crimes occurring in a particular area, such as car theft, bike theft, and stalking.

[0105] "Means of collection" refers to technology that automatically obtains criminal information from the Internet through web scraping and API calls.

[0106] "Preprocessing" refers to the process of completing missing data, eliminating duplicate data, tokenizing text data, etc. from collected data.

[0107] "Crime prediction" refers to the use of machine learning models to predict the likelihood of future crimes based on past crime data and newly collected data.

[0108] A "machine learning model" refers to an algorithm that learns from past data and makes predictions or classifications based on new data. Specifically, it includes LSTM (long short-term memory) models.

[0109] An "interactive AI system" refers to an artificial intelligence that responds to questions and inquiries through dialogue with users and provides appropriate information and solutions.

[0110] "User" refers to a person who uses an interactive AI system through a dedicated app or web portal.

[0111] "Notification means" refers to technology that sends alerts related to crime prediction results based on conditions set by the user.

[0112] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment for implementing this system will be described below.

[0113] 1. Data Collection

[0114] The server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information websites, and social media. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls. Specifically, the server runs a script every hour to check each data source and collect new crime reports.

[0115] For example, the server uses web scraping to check the latest crime prevention information and retrieves new crime information. It also uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[0116] 2. Data Preprocessing

[0117] The server pre-processes the collected criminal information. Pre-processing includes:

[0118] Imputing missing data

[0119] Eliminate duplicate data

[0120] Tokenization of text data

[0121] These processes are performed to prepare the data in a format that can be input to a machine learning model. For example, we use the Python Pandas library and SciKit-Learn's Imputer to clean the data and impute missing parts.

[0122] 3. Crime prediction

[0123] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM (long short-term memory) model trained on crime data from the past year. Newly collected data is input into this model to predict crimes that are likely to occur in the next week. Deep learning libraries such as TensorFlow and Keras are used to run the LSTM model.

[0124] 4. Conversational AI Systems

[0125] Users access the conversational AI system through a dedicated app or web portal. They input their questions or inquiries using the app's chatbot interface, which is then processed by the server. Natural language processing (NLP) technology is used to analyze the user's message and understand the intent of the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures.

[0126] 5. Notification System

[0127] Users can configure notification settings within the app to set notifications for specific areas or crime types. The server then sends alerts to users when the conditions are met. For example, if there is a high risk of car theft in a specific area, the user might receive a notification saying, "There is a high risk of car theft for the next week. Please be careful when parking, especially at night."

[0128] Specific examples

[0129] 1. Data Collection:

[0130] The server collects new crime reports from crime prevention maps and social media.

[0131] Example: A server uses web scraping technology to retrieve car theft information for a specific area.

[0132] 2. Data Preprocessing:

[0133] The server preprocesses the collected data and inputs it into a predictive model.

[0134] Example: Data cleaning and imputation using Pandas and SciKit-Learn.

[0135] 3. Crime prediction:

[0136] The server uses the LSTM model to predict crimes for the next week.

[0137] Example: Using TensorFlow to run an LSTM model to predict the likelihood of car theft in the next week.

[0138] 4. Conversational AI Systems:

[0139] A user uses the app to ask, "Car thefts are on the rise in my area. Is there anything I can do about it?"

[0140] The server analyzes it and responds, "We recommend installing surveillance cameras and an alarm system."

[0141] 5. Notification system:

[0142] Users can set up car theft alerts in the app.

[0143] When the risk of car theft increases, the server sends a notification to the user, such as "There is a high risk of car theft for the next week."

[0144] In this way, the system of the present invention provides users with real-time crime information and forecast information, aiming to realize a society in which citizens can live in peace.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] The server collects crime information from multiple data sources on the Internet. Specifically, it uses web scraping technology and API calls to retrieve crime information from Yahoo! Maps crime prevention maps, car theft information websites, and social media. The input data are new crime reports from each data source, and the output data is a list of the collected crime information. For example, the server runs an automated script every hour to parse the latest crime prevention map information using an HTML parser (e.g., BeautifulSoup) and retrieve posts that match certain criteria from social media APIs.

[0148] Step 2:

[0149] The server preprocesses the collected crime information. Specifically, it completes missing data, removes duplicate data, and tokenizes the text data. The input data is a list of collected crime information, and the output data is a preprocessed, clean dataset. For example, the server uses Python's Pandas library and SciKit-Learn's Imputer to clean the data, and NLTK to tokenize the text data.

[0150] Step 3:

[0151] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM model trained on crime data from the past year. The input data is the preprocessed dataset, and the output data is a prediction of crimes that are likely to occur in the next week. For example, new data can be input into the LSTM model using TensorFlow or Keras, and the model generates a prediction that "there is a high probability of an increase in car thefts in this area in the next week."

[0152] Step 4:

[0153] Users access the conversational AI system through a dedicated app or web portal. Specifically, when a user inputs a question or inquiry into the chatbot interface, that input is processed by the server. The input data is the question or inquiry received from the user, and the output data is the answer to that question and countermeasures. For example, if a user inputs, "Car thefts are increasing in this area, so I would like to know what to do about it," the server will analyze it using NLP technology and respond, "I recommend installing surveillance cameras and an alarm system."

[0154] Step 5:

[0155] Users configure notification settings within the app. Specifically, users set notifications for specific areas or crime types. The input data are the user's settings, and the output data is an alert notification sent at the appropriate time. For example, based on the settings, if the risk of car theft increases in a specific area, the server will send a notification saying, "There is a high risk of car theft for the next week. Please be especially careful when parking at night."

[0156] In this way, the entire system can be processed efficiently in real time, providing users with the latest crime information and predictions, as well as specific countermeasures.

[0157] (Application example 1)

[0158] 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."

[0159] Current crime prediction systems lack the ability to collect and analyze information in real time, leaving users with insufficient information to take concrete countermeasures. Additionally, there is a lack of a way to quickly notify users of alerts for specific areas or crime types using smart devices. The purpose of this invention is to solve these issues and provide an environment where citizens can live in peace of mind.

[0160] 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.

[0161] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for analyzing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for being installed on smartphones or robots to notify users of prediction results for multiple areas and send alerts for specific areas or crime types, thereby enabling users to recognize crime risks in real time and take countermeasures.

[0162] "Multiple data sources on the Internet" refers to multiple sources of information accessible via the Internet, such as various websites, social media, news feeds, and map services.

[0163] "Means of collecting crime information in real time" refers to technologies and methods for always instantly collecting the latest crime data using web scraping technology or API calls.

[0164] "Crime Information" refers to the occurrence of crimes in the relevant area, details of the incidents, the time of the incidents, and other related information.

[0165] "Means for predicting crime occurrences in the next week" refers to technologies and methods that use machine learning models and statistical analysis to predict the likelihood of crime occurring in the next week based on collected crime data.

[0166] "Interactive AI system means" refers to a system in which a user inputs a question or inquiry via text or voice, and the AI ​​provides a response based on that input.

[0167] "Means of notifying users of prediction results" refers to methods and technologies for communicating predicted crime risks and countermeasures to users via smart devices.

[0168] "Means installed on smartphones and robots" refers to systems implemented as mobile applications or robot control software and installed on these devices.

[0169] "Means for sending alerts" refers to a notification system that sends warning messages to users when certain conditions or risks occur.

[0170] "Web scraping" refers to the technique of automatically extracting data from web pages on the Internet.

[0171] "API call" refers to a method for exchanging data with other services or software using an application programming interface (API).

[0172] A "machine learning model" refers to an algorithm that uses large amounts of data to learn certain patterns and make predictions and classifications for unknown data.

[0173] The system of the present invention is designed to collect crime information in real time from multiple data sources on the Internet, predict crime occurrences for the next week, and provide consultation services and suggest specific countermeasures to users. Specific modes for carrying out the invention are described below.

[0174] Data collection methods

[0175] The server uses web scraping technology and API calls to collect crime information from multiple data sources, including crime prevention maps, social media, and car theft information services. The server periodically runs a script to retrieve new crime information.

[0176] Data analysis format

[0177] The collected crime information is preprocessed by the server. This preprocessing includes missing data imputation, duplicate data elimination, and text data tokenization. The server then uses a machine learning model (such as an LSTM model) to predict crime occurrences for the next week. This model is trained based on past crime data.

[0178] Forms of conversational AI systems

[0179] Users access the conversational AI system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or request for advice, the input is processed by the server. The server uses natural language processing technology (such as spaCy or NLTK) to analyze the input and provide the user with appropriate crime prediction data and specific countermeasures.

[0180] Notification system type

[0181] Users can configure their notification settings within the app, allowing them to receive notifications for specific areas or crime types, and the server will then send alerts to users based on the configured conditions.

[0182] Hardware and software used

[0183] Server: Used for data collection, analysis and model execution.

[0184] Web scraping: BeautifulSoup, Requests library.

[0185] API calls: Requests library.

[0186] Machine learning: TensorFlow / Keras.

[0187] Natural Language Processing: spaCy or NLTK.

[0188] Description of the Examples

[0189] The server detects reports of "car theft" from social media, preprocesses the data, and inputs it into an LSTM model to calculate the risk for the next week. Users living in areas with a high risk of car theft receive a notification saying, "Be careful when parking at night." If a user asks, "There have been a lot of car thefts in this area recently. What can I do to prevent this?" the server responds, "We recommend installing surveillance cameras and an alarm system."

[0190] Prompt Sentence Examples

[0191] "Please predict car thefts in XX region for the next week. The historical data is as follows: {Historical Data}. Based on this data, please suggest risks and specific countermeasures."

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The server uses web scraping technology and API calls to collect real-time crime information from multiple data sources on the Internet. Specifically, it periodically runs scripts to retrieve the latest crime information from crime prevention maps, social media, and car theft information services. It uses the URLs and API endpoints of the data sources as input and stores the collected crime information in a database as output.

[0195] Step 2:

[0196] The server preprocesses the collected crime information. This includes filling in missing values, eliminating duplicate data, and tokenizing text data. It uses the data collected in step 1 as input and generates a new dataset with the preprocessed data as output. Specifically, it fills in missing values ​​with the closest valid data, removes duplicate data, and tokenizes the text data to convert it into a format that is easier to analyze.

[0197] Step 3:

[0198] The server inputs the preprocessed data into a machine learning model to predict crime occurrences over the next week. The preprocessed dataset is used as input, and crime occurrence prediction results are obtained as output. Specifically, machine learning algorithms such as LSTM models are used to train this data to predict the probability of crime occurrence.

[0199] Step 4:

[0200] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or inquiries. The user's text message is used as input, and the server generates an appropriate answer as output. Specifically, the system analyzes the input question using natural language processing technology and generates an answer by referencing crime prediction data and specific countermeasures.

[0201] Step 5:

[0202] Based on the prediction results, the server sends notifications to registered users regarding specific areas and crime types. It uses the crime prediction results and user settings as input, and generates and sends notification messages to users as output. Specifically, it generates alert messages for high-risk areas and notifies users in real time via smartphones or robots.

[0203] 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.

[0204] The present invention combines a system that collects local crime information in real time and predicts crime one week in advance with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention are described below.

[0205] Data collection implementation

[0206] First, the server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information bureaus, social media, etc. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0207] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0208] Data Analysis Embodiments

[0209] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0210] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0211] An embodiment of an interactive AI system

[0212] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0213] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0214] Embodiment of Emotion Engine

[0215] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results.

[0216] For example, if a user types, "I've been scared to walk the streets at night recently," the emotion engine will detect "anxiety." Based on this, the server will suggest countermeasures to make the user feel more secure. It will provide specific measures such as, "If you feel anxious, there are more patrols in the area. We also recommend that you carry a safety alarm."

[0217] Notification System Embodiments

[0218] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0219] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0220] Specific example explanation

[0221] 1. Data Collection:

[0222] The server collects new crime reports from crime prevention maps and social media.

[0223] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0224] 2. Data Analysis:

[0225] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0226] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0227] 3. Conversational AI systems:

[0228] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0229] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0230] 4. Emotion Engine:

[0231] The user types, "Recently, I've been afraid to walk on the street at night."

[0232] The server uses an emotion engine to recognize the user's anxiety and suggests countermeasures to reassure them, such as "Patrols are increasing. We also recommend that you carry a safety alarm."

[0233] 5. Notification system:

[0234] Users can set up car theft alerts in the app.

[0235] When the risk of car theft increases, the server sends a notification to the user saying, "There is a high risk of car theft for the next week."

[0236] As a result, the system according to the present invention can not only provide new crime predictions and countermeasures to help citizens live in peace, but also respond in a detailed manner according to the user's emotions.

[0237] The processing flow will be explained below.

[0238] Specific processing flow of the embodiment

[0239] Step 1: Start collecting data

[0240] The server will start the data collection process at the specified time interval (e.g. every hour).

[0241] Step 2: Accessing the Data Source

[0242] The server uses web scraping technology and API calls to access multiple data sources on the Internet, such as crime prevention maps, car theft information bureaus, and social media.

[0243] Step 3: Collecting criminal information

[0244] The server retrieves the latest crime report data from each data source.

[0245] Example: The server retrieves the latest information on crime prevention maps and uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[0246] Step 4: Data Preprocessing

[0247] The server cleanses the collected data, completing missing data, eliminating duplicate data, and tokenizing text data.

[0248] Step 5: Perform crime predictions

[0249] The server uses a machine learning algorithm (e.g., LSTM model) to analyze the preprocessed data and make crime predictions for the coming week.

[0250] Step 6: Save the prediction results

[0251] The server stores the generated crime prediction results in a database.

[0252] Step 7: User Inquiry Processing

[0253] Users access the conversational AI system through a dedicated app or web portal.

[0254] Users input their questions or concerns into the chatbot interface. For example, they might type, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?"

[0255] Step 8: Parsing User Input

[0256] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[0257] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[0258] Step 9: Sentiment Analysis

[0259] The server uses an emotion engine to parse emotions from the user's input text.

[0260] Example: If a user inputs "I've been scared to walk on the street at night recently," the server will use the emotion engine to detect "anxiety."

[0261] Step 10: Generate emotion-based responses

[0262] The server generates more appropriate countermeasures based on the emotions recognized by the emotion engine.

[0263] Example: If the user is feeling anxious, the server may suggest reassuring measures such as, "There are increased patrols in the area. We also recommend that you carry a safety alarm."

[0264] Step 11: Provide your answers

[0265] The server presents specific countermeasures to the user based on the analyzed crime prediction data and the results of the emotion engine.

[0266] Example: The server provides the user with an answer such as "We recommend installing a bicycle lock with an alarm" via a chatbot.

[0267] Step 12: Establish notification settings

[0268] Users can configure notification settings within the app for specific areas and crime types.

[0269] Example: A user sets up notifications for car theft.

[0270] Step 13: Monitor notification conditions

[0271] The server generates notifications based on the configured notification conditions, if applicable.

[0272] Example: When the risk of car theft increases in a particular area, the server generates a notification saying, "There is a high risk of car theft in your area for the next week."

[0273] Step 14: Sending notifications

[0274] The server sends the generated notification to the user.

[0275] Users receive notifications and can take action, for example by tightening the security of their parking spot.

[0276] Through these steps, the system of the present invention can recognize the user's emotions, predict crime in real time, and provide specific countermeasures, thereby creating an environment in which users can live with greater peace of mind.

[0277] Example 2

[0278] 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."

[0279] In recent years, crime has been increasing, especially in urban areas, requiring a rapid and effective response. Currently, crime information is not collected or analyzed in real time, which often results in delayed preventative measures. It is also difficult to respond appropriately to users' feelings of anxiety and fear. For this reason, there is a need for a system that combines the rapid collection and analysis of crime information, the provision of effective preventative measures, and a response that responds to users' feelings.

[0280] 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.

[0281] In this invention, the server includes: means for collecting crime information in real time from multiple data sources on the Internet; means for preprocessing the collected crime information; means for predicting crime occurrences for the next week using a machine learning model based on the preprocessed crime information; means for accepting questions from users and analyzing them using natural language processing technology; emotion engine means for recognizing emotions from user input text and generating a response based on the results; interactive artificial intelligence system means for proposing consultation responses and specific countermeasures to the user based on the predictions; and means for notifying the user of the predictions and consultation response results. This enables the rapid collection, analysis, and prediction of crime information, and also enables detailed responses tailored to the user's emotions.

[0282] The "Internet" is an information and communications network that interconnects computer networks around the world.

[0283] A "data source" is a source of data from which information is collected.

[0284] "Crime information" refers to specific information about the location, time, and circumstances of a crime.

[0285] "Collection" is the act of obtaining necessary data from multiple data sources on the Internet.

[0286] "Preprocessing" is the act of filling in gaps in collected data, eliminating duplicates, and converting it into an analyzable format.

[0287] A "machine learning model" is an algorithm that learns patterns from past data and makes predictions about unknown data.

[0288] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0289] An "emotion engine" is a system that recognizes emotions from the user's input text and generates an appropriate response based on the results.

[0290] An "interactive artificial intelligence system" is an artificial intelligence system that interacts with users and proposes appropriate responses and solutions to their questions and inquiries.

[0291] "Notification" refers to the act of conveying information such as prediction results and countermeasures from the system to the user.

[0292] "Crime prediction" is the process of predicting in which areas crimes are likely to occur in the future based on collected crime information.

[0293] "Users" are people who use this system.

[0294] This invention combines a system that collects local crime information in real time and predicts crimes one week in advance with an emotion engine that recognizes the user's emotions. This system operates in cooperation with three parties: a server, a terminal, and the user.

[0295] Hardware and Software Configuration

[0296] The server is a high-performance computer system that collects and analyzes data, runs crime prediction models, and generates answers to user questions. The server is implemented using software such as Python, TensorFlow, and NLP libraries.

[0297] The terminal is a device used by the user, such as a smartphone or computer, that provides an interface for accessing the system through a dedicated application or a web portal. The terminal operates as a browser application or a native application and communicates with the server.

[0298] Users are people who use the system and check crime information, ask questions, and ask for advice through their terminals.

[0299] Examples of data collection

[0300] The server collects the latest crime information from data sources such as crime prevention maps, car theft information bureaus, and social media. Specifically, the server runs a script every hour to check each data source for new crime reports. For example, it checks the latest status of the crime prevention map and retrieves newly reported crime information from it. At the same time, the server uses the social media API to collect posts containing specific keywords such as "car theft" and "stalking."

[0301] Specific examples of data analysis

[0302] Based on the collected crime information, the server performs data preprocessing, such as filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict crime occurrences over the next week. For example, the server uses an LSTM model trained using crime data from the past year. By inputting newly collected data into this model, it can predict the likelihood of crimes occurring in a specific area over the next week.

[0303] Examples of conversational AI systems

[0304] Users access the conversational AI system through a dedicated app or web portal. The user opens the app and uses the chatbot interface to input a question or inquiry. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?" This input is processed by the server. The server analyzes the user's message using natural language processing (NLP) technology to understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0305] Examples of emotion engines

[0306] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results. For example, if a user inputs, "I've been afraid to walk the streets at night lately," the emotion engine detects "anxiety." Based on this, the server suggests countermeasures to make users feel more secure. It provides specific measures such as, "If you feel anxious, there have been increased patrols in this area. We also recommend that you carry a safety alarm."

[0307] Example of a notification system

[0308] Users can set up notifications within the app to receive notifications for specific areas or crime types. The server will then send alerts to users based on the set conditions. For example, if a user sets up notifications for the risk of car theft in a specific area, the server will monitor predicted car thefts in that area and, if the risk increases, send a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0309] The system of this invention not only rapidly collects and analyzes crime information and provides users with appropriate countermeasures, but also enables detailed responses that reflect the user's emotions, thereby providing new crime prediction and countermeasures that will allow citizens to live in peace.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1: Data collection

[0312] The server collects real-time crime information from multiple data sources on the Internet (such as crime prevention maps, car theft information stations, and social media). The input is the public APIs and web pages of the data sources. The server runs a script every hour to check each data source for new crime reports.

[0313] What it does: The server uses a Python script to access a crime prevention map to retrieve new crime report data, and calls social media APIs to search for posts containing specific keywords like "car theft" or "stalking," and collects the results. The output is the collected raw data.

[0314] Step 2: Data Preprocessing

[0315] The server preprocesses the collected data. The input is the collected raw data, and the output is the preprocessed clean data. Specific data preprocessing includes tokenizing text data, filling in missing data, and removing duplicate data.

[0316] What it does: The server uses NLP libraries to tokenize the text data, imputes missing items using statistical methods, and applies algorithms to detect and eliminate duplicate data, ultimately producing a clean dataset.

[0317] Step 3: Prediction using a crime prediction model

[0318] The server uses the preprocessed data to predict crime occurrences for the next week using an LSTM model. The input is the preprocessed clean data, and the output is the probability of crime occurrence for each area.

[0319] Specific operation: The server uses the TensorFlow library to run an LSTM model trained on crime data from the past year, inputs new data, and calculates the crime probability for each area. The results are then stored in a database.

[0320] Step 4: Accepting user questions

[0321] Users input questions or inquiries into the conversational AI system through a dedicated app or web portal. The input is the text entered by the user, and the output is that text data.

[0322] Specific operation: The user opens the application on their device and types a question into the chatbot interface, such as, "I've heard that bicycle thefts have been increasing recently. Are there any safety measures?"

[0323] Step 5: Analyze user emotions with the emotion engine

[0324] The server analyzes the user's input text and recognizes the user's emotions using an emotion engine. The input is text data from the user, and the output is the emotion analysis result (e.g., anxiety, fear, etc.).

[0325] How it works: The server uses NLP technology to analyze the user's input text and uses an emotion engine to identify emotions such as "anxiety" or "fear." It then adjusts the response based on the results of this emotion analysis.

[0326] Step 6: Generate response and send notification

[0327] The server responds to users based on crime prediction data and sentiment analysis results, and sends notifications as needed. The input is sentiment analysis results and crime prediction data, and the output is a response text or notification message to the user.

[0328] Specific operation: The server notifies the user through the chatbot of specific countermeasures, such as "We recommend installing a bicycle lock with an alarm." Also, when the risk of car theft increases in a specific area, it sends a notification to the app saying, "The risk of car theft is high in your area for the next week. Please be especially careful when parking at night."

[0329] Through these processing steps, the system not only quickly collects and analyzes crime information and provides users with appropriate countermeasures, but also provides detailed responses that reflect the user's emotions.

[0330] (Application example 2)

[0331] 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."

[0332] In modern society, ensuring safety and security in areas where crime is frequent or difficult to predict is an important issue. However, conventional crime prediction systems lack the ability to collect real-time data or propose countermeasures based on user sentiment, limiting their ability to provide more effective crime prevention measures. Furthermore, notification systems for users are inadequate, and a means of effectively communicating risk is needed.

[0333] 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.

[0334] In this invention, the server includes means for collecting event information in real time from multiple data sources on the Internet, means for analyzing the collected event information and predicting event occurrences for the next week, an interactive AI system for responding to inquiries from users and proposing specific countermeasures based on the predictions, means for proposing countermeasures to users based on the prediction results and emotion analysis results, and means for notifying users of the prediction results. This makes it possible to collect crime information in real time and propose appropriate crime prevention countermeasures taking into account the user's emotions.

[0335] "Event Information" refers to data about crimes and other significant events that occur in an area.

[0336] "Analysis" is the process of processing collected data and extracting meaning and trends.

[0337] "Prediction" is the estimation of the probability of future events occurring based on data obtained through analysis.

[0338] An "interactive artificial intelligence system" is a system that converses with users using natural language and proposes appropriate measures in response to questions or inquiries.

[0339] "Sentiment analysis" is a technique that processes user input text to determine the content and intensity of emotions.

[0340] "Proposal" means showing specific actions or measures to the user based on analyzed data and prediction results.

[0341] "Notification" refers to sending information from the system to the user to inform them of important events or risks.

[0342] "Harvesting" is the act of gathering necessary data from multiple data sources on the Internet.

[0343] "Web scraping" is the technique of automatically extracting information from websites.

[0344] "Application Program Interface Call" is a method of obtaining data using the API provided by the data source.

[0345] A "machine learning model" is an algorithm trained using historical data and used to predict future events.

[0346] The present invention is a system that collects local crime information in real time and provides users with crime predictions for the next week and countermeasures based on emotion analysis. Specific embodiments of the system of the present invention are described below.

[0347] Data collection methods

[0348] The server collects event information from multiple data sources on the Internet. Specifically, it uses web scraping technology and application program interface (API) calls to automatically obtain data from crime prevention maps, social media, etc. The server runs a script every hour to obtain new event information.

[0349] Data Analysis Methods

[0350] Based on the collected event information, the server performs data preprocessing. This preprocessing includes filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict event occurrences for the next week. This prediction model uses a machine learning model trained using data from the past year.

[0351] Interactive artificial intelligence system means

[0352] Users access the conversational artificial intelligence system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or inquiry, the server analyzes the input using natural language processing technology. Based on the analysis results, the server suggests appropriate countermeasures to the user. For example, in response to a question such as, "There have been a lot of car thefts in this area recently. What countermeasures should I take?" the server might respond, "I recommend installing surveillance cameras and an alarm system."

[0353] Suggestion method based on emotion analysis

[0354] The server performs sentiment analysis on the text entered by the user to recognize the user's emotions. Sentiment analysis is performed using natural language processing technologies such as SentimentIntensityAnalyzer. Based on the results of the sentiment analysis, the system suggests countermeasures that will give the user a greater sense of security. For example, if a user enters, "I've been afraid to walk the streets at night recently," the system will suggest specific countermeasures, such as, "Patrols have increased. I also recommend that you carry a safety alarm."

[0355] Notification means

[0356] The server notifies the user of predicted event information based on the notification conditions set by the user within the app. For example, if an alert is set for the risk of car theft in a specific area, the server monitors the predicted results of car theft and sends a notification saying, "The risk of car theft is high for the next week" when the risk increases.

[0357] Specific example explanation

[0358] For example:

[0359] Data collection:

[0360] The server collects new incident information from crime prevention maps and social media, for example, using web scraping technology to obtain information on reported car thefts in a specific area.

[0361] User input and interactive AI system response:

[0362] User: "There have been a lot of car thefts in this area recently. What can I do about it?"

[0363] Server: "I recommend installing security cameras and an alarm system."

[0364] User sentiment analysis and suggestions:

[0365] User: "I've been scared to walk the streets at night lately."

[0366] Server: "Patrols have been increased. We also recommend carrying a safety alarm."

[0367] In this way, the system of the present invention can provide more effective crime prevention measures by suggesting appropriate countermeasures to users while performing emotion analysis based on event information collected in real time.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] The server collects event information from multiple data sources on the Internet.

[0371] Input: The server runs a script to retrieve information from data sources such as security maps and social media.

[0372] Output: Raw data of new event information is collected.

[0373] Specific operation: The server uses web scraping technology and API calls to obtain the reported data from each data source. This operation is performed periodically (e.g., every hour).

[0374] Step 2:

[0375] The server pre-processes the collected event information.

[0376] Input: Raw data collected.

[0377] Output: Preprocessed data.

[0378] What it does: The server imputes missing values ​​in the data, removes duplicates, and tokenizes the text data, converting it into a format suitable for input into machine learning models.

[0379] Step 3:

[0380] The server uses the preprocessed data to predict the occurrence of an event.

[0381] Input: Preprocessed data.

[0382] Output: Predicted events for the next week.

[0383] How it works: The server uses the LSTM model to combine past data with newly collected data to make predictions, and provides prediction results for specific regions and event types.

[0384] Step 4:

[0385] The server responds to user questions and inquiries through an interactive artificial intelligence system.

[0386] Input: Questions or inquiries entered by the user through the app.

[0387] Output: Appropriate action or suggestion.

[0388] Specific actions: The server uses natural language processing technology to analyze the user's input and proposes the best countermeasure based on the prediction results. For example, it provides the user with specific countermeasures such as "installing surveillance cameras."

[0389] Step 5:

[0390] The server performs sentiment analysis and makes suggestions based on the user's emotions.

[0391] Input: Text that the user types into the app.

[0392] Output: Sentiment analysis results and corresponding countermeasures.

[0393] Specific operation: The server uses SentimentIntensityAnalyzer to obtain the user's emotion score, and based on the result, makes suggestions to make the user feel more secure. For example, it may make a suggestion such as "We recommend that you carry a safety alarm."

[0394] Step 6:

[0395] The server notifies the user of the prediction results.

[0396] Input: Notification conditions set by the user and event occurrence prediction results.

[0397] Output: The notification sent to the user.

[0398] Specific operation: The server monitors the notification conditions set by the user in the app and automatically sends a notification when a prediction result that matches the conditions is found. For example, a notification stating "There is a high risk of car theft" is sent via email or app notification.

[0399] The above are the processing steps of the system of the present invention, which makes it possible to collect event information in real time, perform emotion analysis, and propose appropriate countermeasures to the user.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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."

[0416] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment of the system of the present invention will be described below.

[0417] Data collection implementation

[0418] First, the server collects crime information from multiple data sources on the Internet, including Yahoo! Maps crime prevention maps, car theft information bureaus, and social media sites with frequent new posts. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0419] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0420] Data Analysis Embodiments

[0421] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0422] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0423] An embodiment of an interactive AI system

[0424] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0425] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0426] Notification System Embodiments

[0427] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0428] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0429] Specific example explanation

[0430] 1. Data Collection:

[0431] The server collects new crime reports from Yahoo! Maps' crime prevention maps and social media.

[0432] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0433] 2. Data Analysis:

[0434] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0435] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0436] 3. Conversational AI systems:

[0437] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0438] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0439] 4. Notification system:

[0440] Users can set up car theft alerts in the app.

[0441] When the risk of car theft increases, the server sends a notification to the user saying, "The risk of car theft is high for the next week. Please be especially careful when parking at night."

[0442] As a result, the system according to the present invention can provide new crime prediction and countermeasures to help citizens live in peace.

[0443] The processing flow will be explained below.

[0444] Specific flow of program processing

[0445] Step 1: Start collecting data

[0446] The server will start the data collection process at the specified time interval (e.g. every hour).

[0447] The server runs a web scraping script to collect the latest crime information from multiple data sources on the Internet (e.g., crime prevention maps, car theft information bureaus, social media).

[0448] Step 2: Performing data collection

[0449] The server scans the web pages of each data source and extracts new crime report data.

[0450] The server calls the SNS API to retrieve posts containing keywords such as "car theft" and "stalking."

[0451] Step 3: Data Preprocessing

[0452] The server cleans the collected data, imputes missing values, and removes duplicate data.

[0453] The server tokenizes the text data and converts it into a format suitable for analysis.

[0454] Step 4: Analyze the data

[0455] The server inputs the cleansed data into an LSTM (long short-term memory) model and runs the machine learning algorithm.

[0456] The server then generates a prediction of crimes that may occur over the next week.

[0457] Step 5: Save the prediction results

[0458] The server stores the generated crime prediction results in a database.

[0459] Step 6: User Inquiry Processing

[0460] Users access the conversational AI system through a dedicated app or web portal.

[0461] Users input their questions or concerns into the chatbot interface. For example, they might type, "There have been a lot of bicycle thefts in my neighborhood recently. What can I do about it?"

[0462] Step 7: Parsing User Input

[0463] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[0464] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[0465] Step 8: Providing a solution

[0466] The server generates specific responses to the user's questions based on the predicted crime data.

[0467] The server will then present specific measures to the user through a chatbot, such as "We recommend installing a bicycle lock with an alarm."

[0468] Step 9: Establish notification settings

[0469] Within the app, users can set up notifications for specific crime types and geographic areas, such as car theft.

[0470] Step 10: Generate an alert

[0471] The server generates an alert based on the configured conditions, if applicable, when the risk of car theft increases.

[0472] Step 11: Sending notifications

[0473] The server sends notifications to users regarding increased crime risk.

[0474] Users receive notifications such as, "There is a high risk of car theft in your area over the next week. Please be careful when parking, especially overnight."

[0475] Through the above steps, the crime prediction system of the present invention can provide safety measures to citizens and increase crime prevention by making crime predictions in real time.

[0476] Example 1

[0477] 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."

[0478] Conventional crime prediction systems were unable to efficiently collect and analyze local crime information and provide users with appropriate crime prevention measures. It was also difficult to obtain the latest crime information in real time and make highly accurate crime predictions. This could result in citizens missing out on opportunities to take adequate crime prevention measures.

[0479] 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.

[0480] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for preprocessing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for notifying users of the prediction results. This allows citizens to collect crime information in real time and receive highly accurate crime predictions and specific crime prevention measures.

[0481] "Multiple data sources on the Internet" refers to multiple sources of information, such as websites and social media, that provide criminal information.

[0482] "Real-time" refers to constantly obtaining and processing the latest information without delay.

[0483] "Crime information" refers to detailed data and reports about crimes occurring in a particular area, such as car theft, bike theft, and stalking.

[0484] "Means of collection" refers to technology that automatically obtains criminal information from the Internet through web scraping and API calls.

[0485] "Preprocessing" refers to the process of completing missing data, eliminating duplicate data, tokenizing text data, etc. from collected data.

[0486] "Crime prediction" refers to the use of machine learning models to predict the likelihood of future crimes based on past crime data and newly collected data.

[0487] A "machine learning model" refers to an algorithm that learns from past data and makes predictions or classifications based on new data. Specifically, it includes LSTM (long short-term memory) models.

[0488] An "interactive AI system" refers to an artificial intelligence that responds to questions and inquiries through dialogue with users and provides appropriate information and solutions.

[0489] "User" refers to a person who uses an interactive AI system through a dedicated app or web portal.

[0490] "Notification means" refers to technology that sends alerts related to crime prediction results based on conditions set by the user.

[0491] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment for implementing this system will be described below.

[0492] 1. Data Collection

[0493] The server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information websites, and social media. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls. Specifically, the server runs a script every hour to check each data source and collect new crime reports.

[0494] For example, the server uses web scraping to check the latest crime prevention information and retrieves new crime information. It also uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[0495] 2. Data Preprocessing

[0496] The server pre-processes the collected criminal information. Pre-processing includes:

[0497] Imputing missing data

[0498] Eliminate duplicate data

[0499] Tokenization of text data

[0500] These processes are performed to prepare the data in a format that can be input to a machine learning model. For example, we use the Python Pandas library and SciKit-Learn's Imputer to clean the data and impute missing parts.

[0501] 3. Crime prediction

[0502] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM (long short-term memory) model trained on crime data from the past year. Newly collected data is input into this model to predict crimes that are likely to occur in the next week. Deep learning libraries such as TensorFlow and Keras are used to run the LSTM model.

[0503] 4. Conversational AI Systems

[0504] Users access the conversational AI system through a dedicated app or web portal. They input their questions or inquiries using the app's chatbot interface, which is then processed by the server. Natural language processing (NLP) technology is used to analyze the user's message and understand the intent of the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures.

[0505] 5. Notification System

[0506] Users can configure notification settings within the app to set notifications for specific areas or crime types. The server then sends alerts to users when the conditions are met. For example, if there is a high risk of car theft in a specific area, the user might receive a notification saying, "There is a high risk of car theft for the next week. Please be careful when parking, especially at night."

[0507] Specific examples

[0508] 1. Data Collection:

[0509] The server collects new crime reports from crime prevention maps and social media.

[0510] Example: A server uses web scraping technology to retrieve car theft information for a specific area.

[0511] 2. Data Preprocessing:

[0512] The server preprocesses the collected data and inputs it into a predictive model.

[0513] Example: Data cleaning and imputation using Pandas and SciKit-Learn.

[0514] 3. Crime prediction:

[0515] The server uses the LSTM model to predict crimes for the next week.

[0516] Example: Using TensorFlow to run an LSTM model to predict the likelihood of car theft in the next week.

[0517] 4. Conversational AI Systems:

[0518] A user uses the app to ask, "Car thefts are on the rise in my area. Is there anything I can do about it?"

[0519] The server analyzes it and responds, "We recommend installing surveillance cameras and an alarm system."

[0520] 5. Notification system:

[0521] Users can set up car theft alerts in the app.

[0522] When the risk of car theft increases, the server sends a notification to the user, such as "There is a high risk of car theft for the next week."

[0523] In this way, the system of the present invention provides users with real-time crime information and forecast information, aiming to realize a society in which citizens can live in peace.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The server collects crime information from multiple data sources on the Internet. Specifically, it uses web scraping technology and API calls to retrieve crime information from Yahoo! Maps crime prevention maps, car theft information websites, and social media. The input data are new crime reports from each data source, and the output data is a list of the collected crime information. For example, the server runs an automated script every hour to parse the latest crime prevention map information using an HTML parser (e.g., BeautifulSoup) and retrieve posts that match certain criteria from social media APIs.

[0527] Step 2:

[0528] The server preprocesses the collected crime information. Specifically, it completes missing data, removes duplicate data, and tokenizes the text data. The input data is a list of collected crime information, and the output data is a preprocessed, clean dataset. For example, the server uses Python's Pandas library and SciKit-Learn's Imputer to clean the data, and NLTK to tokenize the text data.

[0529] Step 3:

[0530] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM model trained on crime data from the past year. The input data is the preprocessed dataset, and the output data is a prediction of crimes that are likely to occur in the next week. For example, new data can be input into the LSTM model using TensorFlow or Keras, and the model generates a prediction that "there is a high probability of an increase in car thefts in this area in the next week."

[0531] Step 4:

[0532] Users access the conversational AI system through a dedicated app or web portal. Specifically, when a user inputs a question or inquiry into the chatbot interface, that input is processed by the server. The input data is the question or inquiry received from the user, and the output data is the answer to that question and countermeasures. For example, if a user inputs, "Car thefts are increasing in this area, so I would like to know what to do about it," the server will analyze it using NLP technology and respond, "I recommend installing surveillance cameras and an alarm system."

[0533] Step 5:

[0534] Users configure notification settings within the app. Specifically, users set notifications for specific areas or crime types. The input data are the user's settings, and the output data is an alert notification sent at the appropriate time. For example, based on the settings, if the risk of car theft increases in a specific area, the server will send a notification saying, "There is a high risk of car theft for the next week. Please be especially careful when parking at night."

[0535] In this way, the entire system can be processed efficiently in real time, providing users with the latest crime information and predictions, as well as specific countermeasures.

[0536] (Application example 1)

[0537] 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."

[0538] Current crime prediction systems lack the ability to collect and analyze information in real time, leaving users with insufficient information to take concrete countermeasures. Additionally, there is a lack of a way to quickly notify users of alerts for specific areas or crime types using smart devices. The purpose of this invention is to solve these issues and provide an environment where citizens can live in peace of mind.

[0539] 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.

[0540] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for analyzing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for being installed on smartphones or robots to notify users of prediction results for multiple areas and send alerts for specific areas or crime types, thereby enabling users to recognize crime risks in real time and take countermeasures.

[0541] "Multiple data sources on the Internet" refers to multiple sources of information accessible via the Internet, such as various websites, social media, news feeds, and map services.

[0542] "Means of collecting crime information in real time" refers to technologies and methods for always instantly collecting the latest crime data using web scraping technology or API calls.

[0543] "Crime Information" refers to the occurrence of crimes in the relevant area, details of the incidents, the time of the incidents, and other related information.

[0544] "Means for predicting crime occurrences in the next week" refers to technologies and methods that use machine learning models and statistical analysis to predict the likelihood of crime occurring in the next week based on collected crime data.

[0545] "Interactive AI system means" refers to a system in which a user inputs a question or inquiry via text or voice, and the AI ​​provides a response based on that input.

[0546] "Means of notifying users of prediction results" refers to methods and technologies for communicating predicted crime risks and countermeasures to users via smart devices.

[0547] "Means installed on smartphones and robots" refers to systems implemented as mobile applications or robot control software and installed on these devices.

[0548] "Means for sending alerts" refers to a notification system that sends warning messages to users when certain conditions or risks occur.

[0549] "Web scraping" refers to the technique of automatically extracting data from web pages on the Internet.

[0550] "API call" refers to a method for exchanging data with other services or software using an application programming interface (API).

[0551] A "machine learning model" refers to an algorithm that uses large amounts of data to learn certain patterns and make predictions and classifications for unknown data.

[0552] The system of the present invention is designed to collect crime information in real time from multiple data sources on the Internet, predict crime occurrences for the next week, and provide consultation services and suggest specific countermeasures to users. Specific modes for carrying out the invention are described below.

[0553] Data collection methods

[0554] The server uses web scraping technology and API calls to collect crime information from multiple data sources, including crime prevention maps, social media, and car theft information services. The server periodically runs a script to retrieve new crime information.

[0555] Data analysis format

[0556] The collected crime information is preprocessed by the server. This preprocessing includes missing data imputation, duplicate data elimination, and text data tokenization. The server then uses a machine learning model (such as an LSTM model) to predict crime occurrences for the next week. This model is trained based on past crime data.

[0557] Forms of conversational AI systems

[0558] Users access the conversational AI system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or request for advice, the input is processed by the server. The server uses natural language processing technology (such as spaCy or NLTK) to analyze the input and provide the user with appropriate crime prediction data and specific countermeasures.

[0559] Notification system type

[0560] Users can configure their notification settings within the app, allowing them to receive notifications for specific areas or crime types, and the server will then send alerts to users based on the configured conditions.

[0561] Hardware and software used

[0562] Server: Used for data collection, analysis and model execution.

[0563] Web scraping: BeautifulSoup, Requests library.

[0564] API calls: Requests library.

[0565] Machine learning: TensorFlow / Keras.

[0566] Natural Language Processing: spaCy or NLTK.

[0567] Description of the Examples

[0568] The server detects reports of "car theft" from social media, preprocesses the data, and inputs it into an LSTM model to calculate the risk for the next week. Users living in areas with a high risk of car theft receive a notification saying, "Be careful when parking at night." If a user asks, "There have been a lot of car thefts in this area recently. What can I do to prevent this?" the server responds, "We recommend installing surveillance cameras and an alarm system."

[0569] Prompt Sentence Examples

[0570] "Please predict car thefts in XX region for the next week. The historical data is as follows: {Historical Data}. Based on this data, please suggest risks and specific countermeasures."

[0571] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0572] Step 1:

[0573] The server uses web scraping technology and API calls to collect real-time crime information from multiple data sources on the Internet. Specifically, it periodically runs scripts to retrieve the latest crime information from crime prevention maps, social media, and car theft information services. It uses the URLs and API endpoints of the data sources as input and stores the collected crime information in a database as output.

[0574] Step 2:

[0575] The server preprocesses the collected crime information. This includes filling in missing values, eliminating duplicate data, and tokenizing text data. It uses the data collected in step 1 as input and generates a new dataset with the preprocessed data as output. Specifically, it fills in missing values ​​with the closest valid data, removes duplicate data, and tokenizes the text data to convert it into a format that is easier to analyze.

[0576] Step 3:

[0577] The server inputs the preprocessed data into a machine learning model to predict crime occurrences over the next week. The preprocessed dataset is used as input, and crime occurrence prediction results are obtained as output. Specifically, machine learning algorithms such as LSTM models are used to train this data to predict the probability of crime occurrence.

[0578] Step 4:

[0579] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or inquiries. The user's text message is used as input, and the server generates an appropriate answer as output. Specifically, the system analyzes the input question using natural language processing technology and generates an answer by referencing crime prediction data and specific countermeasures.

[0580] Step 5:

[0581] Based on the prediction results, the server sends notifications to registered users regarding specific areas and crime types. It uses the crime prediction results and user settings as input, and generates and sends notification messages to users as output. Specifically, it generates alert messages for high-risk areas and notifies users in real time via smartphones or robots.

[0582] 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.

[0583] The present invention combines a system that collects local crime information in real time and predicts crime one week in advance with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention are described below.

[0584] Data collection implementation

[0585] First, the server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information bureaus, social media, etc. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0586] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0587] Data Analysis Embodiments

[0588] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0589] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0590] An embodiment of an interactive AI system

[0591] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0592] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0593] Embodiment of Emotion Engine

[0594] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results.

[0595] For example, if a user types, "I've been scared to walk the streets at night recently," the emotion engine will detect "anxiety." Based on this, the server will suggest countermeasures to make the user feel more secure. It will provide specific measures such as, "If you feel anxious, there are more patrols in the area. We also recommend that you carry a safety alarm."

[0596] Notification System Embodiments

[0597] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0598] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0599] Specific example explanation

[0600] 1. Data Collection:

[0601] The server collects new crime reports from crime prevention maps and social media.

[0602] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0603] 2. Data Analysis:

[0604] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0605] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0606] 3. Conversational AI systems:

[0607] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0608] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0609] 4. Emotion Engine:

[0610] The user types, "Recently, I've been afraid to walk on the street at night."

[0611] The server uses an emotion engine to recognize the user's anxiety and suggests countermeasures to reassure them, such as "Patrols are increasing. We also recommend that you carry a safety alarm."

[0612] 5. Notification system:

[0613] Users can set up car theft alerts in the app.

[0614] When the risk of car theft increases, the server sends a notification to the user saying, "There is a high risk of car theft for the next week."

[0615] As a result, the system according to the present invention can not only provide new crime predictions and countermeasures to help citizens live in peace, but also respond in a detailed manner according to the user's emotions.

[0616] The processing flow will be explained below.

[0617] Specific processing flow of the embodiment

[0618] Step 1: Start collecting data

[0619] The server will start the data collection process at the specified time interval (e.g. every hour).

[0620] Step 2: Accessing the Data Source

[0621] The server uses web scraping technology and API calls to access multiple data sources on the Internet, such as crime prevention maps, car theft information bureaus, and social media.

[0622] Step 3: Collecting criminal information

[0623] The server retrieves the latest crime report data from each data source.

[0624] Example: The server retrieves the latest information on crime prevention maps and uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[0625] Step 4: Data Preprocessing

[0626] The server cleanses the collected data, completing missing data, eliminating duplicate data, and tokenizing text data.

[0627] Step 5: Perform crime predictions

[0628] The server uses a machine learning algorithm (e.g., LSTM model) to analyze the preprocessed data and make crime predictions for the coming week.

[0629] Step 6: Save the prediction results

[0630] The server stores the generated crime prediction results in a database.

[0631] Step 7: User Inquiry Processing

[0632] Users access the conversational AI system through a dedicated app or web portal.

[0633] Users input their questions or concerns into the chatbot interface. For example, they might type, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?"

[0634] Step 8: Parsing User Input

[0635] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[0636] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[0637] Step 9: Sentiment Analysis

[0638] The server uses an emotion engine to parse emotions from the user's input text.

[0639] Example: If a user inputs "I've been scared to walk on the street at night recently," the server will use the emotion engine to detect "anxiety."

[0640] Step 10: Generate emotion-based responses

[0641] The server generates more appropriate countermeasures based on the emotions recognized by the emotion engine.

[0642] Example: If the user is feeling anxious, the server may suggest reassuring measures such as, "There are increased patrols in the area. We also recommend that you carry a safety alarm."

[0643] Step 11: Provide your answers

[0644] The server presents specific countermeasures to the user based on the analyzed crime prediction data and the results of the emotion engine.

[0645] Example: The server provides the user with an answer such as "We recommend installing a bicycle lock with an alarm" via a chatbot.

[0646] Step 12: Establish notification settings

[0647] Users can configure notification settings within the app for specific areas and crime types.

[0648] Example: A user sets up notifications for car theft.

[0649] Step 13: Monitor notification conditions

[0650] The server generates notifications based on the configured notification conditions, if applicable.

[0651] Example: When the risk of car theft increases in a particular area, the server generates a notification saying, "There is a high risk of car theft in your area for the next week."

[0652] Step 14: Sending notifications

[0653] The server sends the generated notification to the user.

[0654] Users receive notifications and can take action, for example by tightening the security of their parking spot.

[0655] Through these steps, the system of the present invention can recognize the user's emotions, predict crime in real time, and provide specific countermeasures, thereby creating an environment in which users can live with greater peace of mind.

[0656] Example 2

[0657] 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."

[0658] In recent years, crime has been increasing, especially in urban areas, requiring a rapid and effective response. Currently, crime information is not collected or analyzed in real time, which often results in delayed preventative measures. It is also difficult to respond appropriately to users' feelings of anxiety and fear. For this reason, there is a need for a system that combines the rapid collection and analysis of crime information, the provision of effective preventative measures, and a response that responds to users' feelings.

[0659] 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.

[0660] In this invention, the server includes: means for collecting crime information in real time from multiple data sources on the Internet; means for preprocessing the collected crime information; means for predicting crime occurrences for the next week using a machine learning model based on the preprocessed crime information; means for accepting questions from users and analyzing them using natural language processing technology; emotion engine means for recognizing emotions from user input text and generating a response based on the results; interactive artificial intelligence system means for proposing consultation responses and specific countermeasures to the user based on the predictions; and means for notifying the user of the predictions and consultation response results. This enables the rapid collection, analysis, and prediction of crime information, and also enables detailed responses tailored to the user's emotions.

[0661] The "Internet" is an information and communications network that interconnects computer networks around the world.

[0662] A "data source" is a source of data from which information is collected.

[0663] "Crime information" refers to specific information about the location, time, and circumstances of a crime.

[0664] "Collection" is the act of obtaining necessary data from multiple data sources on the Internet.

[0665] "Preprocessing" is the act of filling in gaps in collected data, eliminating duplicates, and converting it into an analyzable format.

[0666] A "machine learning model" is an algorithm that learns patterns from past data and makes predictions about unknown data.

[0667] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0668] An "emotion engine" is a system that recognizes emotions from the user's input text and generates an appropriate response based on the results.

[0669] An "interactive artificial intelligence system" is an artificial intelligence system that interacts with users and proposes appropriate responses and solutions to their questions and inquiries.

[0670] "Notification" refers to the act of conveying information such as prediction results and countermeasures from the system to the user.

[0671] "Crime prediction" is the process of predicting in which areas crimes are likely to occur in the future based on collected crime information.

[0672] "Users" are people who use this system.

[0673] This invention combines a system that collects local crime information in real time and predicts crimes one week in advance with an emotion engine that recognizes the user's emotions. This system operates in cooperation with three parties: a server, a terminal, and the user.

[0674] Hardware and Software Configuration

[0675] The server is a high-performance computer system that collects and analyzes data, runs crime prediction models, and generates answers to user questions. The server is implemented using software such as Python, TensorFlow, and NLP libraries.

[0676] The terminal is a device used by the user, such as a smartphone or computer, that provides an interface for accessing the system through a dedicated application or a web portal. The terminal operates as a browser application or a native application and communicates with the server.

[0677] Users are people who use the system and check crime information, ask questions, and ask for advice through their terminals.

[0678] Examples of data collection

[0679] The server collects the latest crime information from data sources such as crime prevention maps, car theft information bureaus, and social media. Specifically, the server runs a script every hour to check each data source for new crime reports. For example, it checks the latest status of the crime prevention map and retrieves newly reported crime information from it. At the same time, the server uses the social media API to collect posts containing specific keywords such as "car theft" and "stalking."

[0680] Specific examples of data analysis

[0681] Based on the collected crime information, the server performs data preprocessing, such as filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict crime occurrences over the next week. For example, the server uses an LSTM model trained using crime data from the past year. By inputting newly collected data into this model, it can predict the likelihood of crimes occurring in a specific area over the next week.

[0682] Examples of conversational AI systems

[0683] Users access the conversational AI system through a dedicated app or web portal. The user opens the app and uses the chatbot interface to input a question or inquiry. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?" This input is processed by the server. The server analyzes the user's message using natural language processing (NLP) technology to understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0684] Examples of emotion engines

[0685] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results. For example, if a user inputs, "I've been afraid to walk the streets at night lately," the emotion engine detects "anxiety." Based on this, the server suggests countermeasures to make users feel more secure. It provides specific measures such as, "If you feel anxious, there have been increased patrols in this area. We also recommend that you carry a safety alarm."

[0686] Example of a notification system

[0687] Users can set up notifications within the app to receive notifications for specific areas or crime types. The server will then send alerts to users based on the set conditions. For example, if a user sets up notifications for the risk of car theft in a specific area, the server will monitor predicted car thefts in that area and, if the risk increases, send a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0688] The system of this invention not only rapidly collects and analyzes crime information and provides users with appropriate countermeasures, but also enables detailed responses that reflect the user's emotions, thereby providing new crime prediction and countermeasures that will allow citizens to live in peace.

[0689] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0690] Step 1: Data collection

[0691] The server collects real-time crime information from multiple data sources on the Internet (such as crime prevention maps, car theft information stations, and social media). The input is the public APIs and web pages of the data sources. The server runs a script every hour to check each data source for new crime reports.

[0692] What it does: The server uses a Python script to access a crime prevention map to retrieve new crime report data, and calls social media APIs to search for posts containing specific keywords like "car theft" or "stalking," and collects the results. The output is the collected raw data.

[0693] Step 2: Data Preprocessing

[0694] The server preprocesses the collected data. The input is the collected raw data, and the output is the preprocessed clean data. Specific data preprocessing includes tokenizing text data, filling in missing data, and removing duplicate data.

[0695] What it does: The server uses NLP libraries to tokenize the text data, imputes missing items using statistical methods, and applies algorithms to detect and eliminate duplicate data, ultimately producing a clean dataset.

[0696] Step 3: Prediction using a crime prediction model

[0697] The server uses the preprocessed data to predict crime occurrences for the next week using an LSTM model. The input is the preprocessed clean data, and the output is the probability of crime occurrence for each area.

[0698] Specific operation: The server uses the TensorFlow library to run an LSTM model trained on crime data from the past year, inputs new data, and calculates the crime probability for each area. The results are then stored in a database.

[0699] Step 4: Accepting user questions

[0700] Users input questions or inquiries into the conversational AI system through a dedicated app or web portal. The input is the text entered by the user, and the output is that text data.

[0701] Specific operation: The user opens the application on their device and types a question into the chatbot interface, such as, "I've heard that bicycle thefts have been increasing recently. Are there any safety measures?"

[0702] Step 5: Analyze user emotions with the emotion engine

[0703] The server analyzes the user's input text and recognizes the user's emotions using an emotion engine. The input is text data from the user, and the output is the emotion analysis result (e.g., anxiety, fear, etc.).

[0704] How it works: The server uses NLP technology to analyze the user's input text and uses an emotion engine to identify emotions such as "anxiety" or "fear." It then adjusts the response based on the results of this emotion analysis.

[0705] Step 6: Generate response and send notification

[0706] The server responds to users based on crime prediction data and sentiment analysis results, and sends notifications as needed. The input is sentiment analysis results and crime prediction data, and the output is a response text or notification message to the user.

[0707] Specific operation: The server notifies the user through the chatbot of specific countermeasures, such as "We recommend installing a bicycle lock with an alarm." Also, when the risk of car theft increases in a specific area, it sends a notification to the app saying, "The risk of car theft is high in your area for the next week. Please be especially careful when parking at night."

[0708] Through these processing steps, the system not only quickly collects and analyzes crime information and provides users with appropriate countermeasures, but also provides detailed responses that reflect the user's emotions.

[0709] (Application example 2)

[0710] 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."

[0711] In modern society, ensuring safety and security in areas where crime is frequent or difficult to predict is an important issue. However, conventional crime prediction systems lack the ability to collect real-time data or propose countermeasures based on user sentiment, limiting their ability to provide more effective crime prevention measures. Furthermore, notification systems for users are inadequate, and a means of effectively communicating risk is needed.

[0712] 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.

[0713] In this invention, the server includes means for collecting event information in real time from multiple data sources on the Internet, means for analyzing the collected event information and predicting event occurrences for the next week, an interactive AI system for responding to inquiries from users and proposing specific countermeasures based on the predictions, means for proposing countermeasures to users based on the prediction results and emotion analysis results, and means for notifying users of the prediction results. This makes it possible to collect crime information in real time and propose appropriate crime prevention countermeasures taking into account the user's emotions.

[0714] "Event Information" refers to data about crimes and other significant events that occur in an area.

[0715] "Analysis" is the process of processing collected data and extracting meaning and trends.

[0716] "Prediction" is the estimation of the probability of future events occurring based on data obtained through analysis.

[0717] An "interactive artificial intelligence system" is a system that converses with users using natural language and proposes appropriate measures in response to questions or inquiries.

[0718] "Sentiment analysis" is a technique that processes user input text to determine the content and intensity of emotions.

[0719] "Proposal" means showing specific actions or measures to the user based on analyzed data and prediction results.

[0720] "Notification" refers to sending information from the system to the user to inform them of important events or risks.

[0721] "Harvesting" is the act of gathering necessary data from multiple data sources on the Internet.

[0722] "Web scraping" is the technique of automatically extracting information from websites.

[0723] "Application Program Interface Call" is a method of obtaining data using the API provided by the data source.

[0724] A "machine learning model" is an algorithm trained using historical data and used to predict future events.

[0725] The present invention is a system that collects local crime information in real time and provides users with crime predictions for the next week and countermeasures based on emotion analysis. Specific embodiments of the system of the present invention are described below.

[0726] Data collection methods

[0727] The server collects event information from multiple data sources on the Internet. Specifically, it uses web scraping technology and application program interface (API) calls to automatically obtain data from crime prevention maps, social media, etc. The server runs a script every hour to obtain new event information.

[0728] Data Analysis Methods

[0729] Based on the collected event information, the server performs data preprocessing. This preprocessing includes filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict event occurrences for the next week. This prediction model uses a machine learning model trained using data from the past year.

[0730] Interactive artificial intelligence system means

[0731] Users access the conversational artificial intelligence system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or inquiry, the server analyzes the input using natural language processing technology. Based on the analysis results, the server suggests appropriate countermeasures to the user. For example, in response to a question such as, "There have been a lot of car thefts in this area recently. What countermeasures should I take?" the server might respond, "I recommend installing surveillance cameras and an alarm system."

[0732] Suggestion method based on emotion analysis

[0733] The server performs sentiment analysis on the text entered by the user to recognize the user's emotions. Sentiment analysis is performed using natural language processing technologies such as SentimentIntensityAnalyzer. Based on the results of the sentiment analysis, the system suggests countermeasures that will give the user a greater sense of security. For example, if a user enters, "I've been afraid to walk the streets at night recently," the system will suggest specific countermeasures, such as, "Patrols have increased. I also recommend that you carry a safety alarm."

[0734] Notification means

[0735] The server notifies the user of predicted event information based on the notification conditions set by the user within the app. For example, if an alert is set for the risk of car theft in a specific area, the server monitors the predicted results of car theft and sends a notification saying, "The risk of car theft is high for the next week" when the risk increases.

[0736] Specific example explanation

[0737] For example:

[0738] Data collection:

[0739] The server collects new incident information from crime prevention maps and social media, for example, using web scraping technology to obtain information on reported car thefts in a specific area.

[0740] User input and interactive AI system response:

[0741] User: "There have been a lot of car thefts in this area recently. What can I do about it?"

[0742] Server: "I recommend installing security cameras and an alarm system."

[0743] User sentiment analysis and suggestions:

[0744] User: "I've been scared to walk the streets at night lately."

[0745] Server: "Patrols have been increased. We also recommend carrying a safety alarm."

[0746] In this way, the system of the present invention can provide more effective crime prevention measures by suggesting appropriate countermeasures to users while performing emotion analysis based on event information collected in real time.

[0747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0748] Step 1:

[0749] The server collects event information from multiple data sources on the Internet.

[0750] Input: The server runs a script to retrieve information from data sources such as security maps and social media.

[0751] Output: Raw data of new event information is collected.

[0752] Specific operation: The server uses web scraping technology and API calls to obtain the reported data from each data source. This operation is performed periodically (e.g., every hour).

[0753] Step 2:

[0754] The server pre-processes the collected event information.

[0755] Input: Raw data collected.

[0756] Output: Preprocessed data.

[0757] What it does: The server imputes missing values ​​in the data, removes duplicates, and tokenizes the text data, converting it into a format suitable for input into machine learning models.

[0758] Step 3:

[0759] The server uses the preprocessed data to predict the occurrence of an event.

[0760] Input: Preprocessed data.

[0761] Output: Predicted events for the next week.

[0762] How it works: The server uses the LSTM model to combine past data with newly collected data to make predictions, and provides prediction results for specific regions and event types.

[0763] Step 4:

[0764] The server responds to user questions and inquiries through an interactive artificial intelligence system.

[0765] Input: Questions or inquiries entered by the user through the app.

[0766] Output: Appropriate action or suggestion.

[0767] Specific actions: The server uses natural language processing technology to analyze the user's input and proposes the best countermeasure based on the prediction results. For example, it provides the user with specific countermeasures such as "installing surveillance cameras."

[0768] Step 5:

[0769] The server performs sentiment analysis and makes suggestions based on the user's emotions.

[0770] Input: Text that the user types into the app.

[0771] Output: Sentiment analysis results and corresponding countermeasures.

[0772] Specific operation: The server uses SentimentIntensityAnalyzer to obtain the user's emotion score, and based on the result, makes suggestions to make the user feel more secure. For example, it may make a suggestion such as "We recommend that you carry a safety alarm."

[0773] Step 6:

[0774] The server notifies the user of the prediction results.

[0775] Input: Notification conditions set by the user and event occurrence prediction results.

[0776] Output: The notification sent to the user.

[0777] Specific operation: The server monitors the notification conditions set by the user in the app and automatically sends a notification when a prediction result that matches the conditions is found. For example, a notification stating "There is a high risk of car theft" is sent via email or app notification.

[0778] The above are the processing steps of the system of the present invention, which makes it possible to collect event information in real time, perform emotion analysis, and propose appropriate countermeasures to the user.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] [Third embodiment]

[0783] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0784] 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.

[0785] 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).

[0786] 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.

[0787] 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.

[0788] 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).

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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."

[0795] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment of the system of the present invention will be described below.

[0796] Data collection implementation

[0797] First, the server collects crime information from multiple data sources on the Internet, including Yahoo! Maps crime prevention maps, car theft information bureaus, and social media sites with frequent new posts. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0798] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0799] Data Analysis Embodiments

[0800] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0801] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0802] An embodiment of an interactive AI system

[0803] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0804] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0805] Notification System Embodiments

[0806] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0807] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0808] Specific example explanation

[0809] 1. Data Collection:

[0810] The server collects new crime reports from Yahoo! Maps' crime prevention maps and social media.

[0811] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0812] 2. Data Analysis:

[0813] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0814] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0815] 3. Conversational AI systems:

[0816] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0817] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0818] 4. Notification system:

[0819] Users can set up car theft alerts in the app.

[0820] When the risk of car theft increases, the server sends a notification to the user saying, "The risk of car theft is high for the next week. Please be especially careful when parking at night."

[0821] As a result, the system according to the present invention can provide new crime prediction and countermeasures to help citizens live in peace.

[0822] The processing flow will be explained below.

[0823] Specific flow of program processing

[0824] Step 1: Start collecting data

[0825] The server will start the data collection process at the specified time interval (e.g. every hour).

[0826] The server runs a web scraping script to collect the latest crime information from multiple data sources on the Internet (e.g., crime prevention maps, car theft information bureaus, social media).

[0827] Step 2: Performing data collection

[0828] The server scans the web pages of each data source and extracts new crime report data.

[0829] The server calls the SNS API to retrieve posts containing keywords such as "car theft" and "stalking."

[0830] Step 3: Data Preprocessing

[0831] The server cleans the collected data, imputes missing values, and removes duplicate data.

[0832] The server tokenizes the text data and converts it into a format suitable for analysis.

[0833] Step 4: Analyze the data

[0834] The server inputs the cleansed data into an LSTM (long short-term memory) model and runs the machine learning algorithm.

[0835] The server then generates a prediction of crimes that may occur over the next week.

[0836] Step 5: Save the prediction results

[0837] The server stores the generated crime prediction results in a database.

[0838] Step 6: User Inquiry Processing

[0839] Users access the conversational AI system through a dedicated app or web portal.

[0840] Users input their questions or concerns into the chatbot interface. For example, they might type, "There have been a lot of bicycle thefts in my neighborhood recently. What can I do about it?"

[0841] Step 7: Parsing User Input

[0842] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[0843] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[0844] Step 8: Providing a solution

[0845] The server generates specific responses to the user's questions based on the predicted crime data.

[0846] The server will then present specific measures to the user through a chatbot, such as "We recommend installing a bicycle lock with an alarm."

[0847] Step 9: Establish notification settings

[0848] Within the app, users can set up notifications for specific crime types and geographic areas, such as car theft.

[0849] Step 10: Generate an alert

[0850] The server generates an alert based on the configured conditions, if applicable, when the risk of car theft increases.

[0851] Step 11: Sending notifications

[0852] The server sends notifications to users regarding increased crime risk.

[0853] Users receive notifications such as, "There is a high risk of car theft in your area over the next week. Please be careful when parking, especially overnight."

[0854] Through the above steps, the crime prediction system of the present invention can provide safety measures to citizens and increase crime prevention by making crime predictions in real time.

[0855] Example 1

[0856] 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."

[0857] Conventional crime prediction systems were unable to efficiently collect and analyze local crime information and provide users with appropriate crime prevention measures. It was also difficult to obtain the latest crime information in real time and make highly accurate crime predictions. This could result in citizens missing out on opportunities to take adequate crime prevention measures.

[0858] 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.

[0859] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for preprocessing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for notifying users of the prediction results. This allows citizens to collect crime information in real time and receive highly accurate crime predictions and specific crime prevention measures.

[0860] "Multiple data sources on the Internet" refers to multiple sources of information, such as websites and social media, that provide criminal information.

[0861] "Real-time" refers to constantly obtaining and processing the latest information without delay.

[0862] "Crime information" refers to detailed data and reports about crimes occurring in a particular area, such as car theft, bike theft, and stalking.

[0863] "Means of collection" refers to technology that automatically obtains criminal information from the Internet through web scraping and API calls.

[0864] "Preprocessing" refers to the process of completing missing data, eliminating duplicate data, tokenizing text data, etc. from collected data.

[0865] "Crime prediction" refers to the use of machine learning models to predict the likelihood of future crimes based on past crime data and newly collected data.

[0866] A "machine learning model" refers to an algorithm that learns from past data and makes predictions or classifications based on new data. Specifically, it includes LSTM (long short-term memory) models.

[0867] An "interactive AI system" refers to an artificial intelligence that responds to questions and inquiries through dialogue with users and provides appropriate information and solutions.

[0868] "User" refers to a person who uses an interactive AI system through a dedicated app or web portal.

[0869] "Notification means" refers to technology that sends alerts related to crime prediction results based on conditions set by the user.

[0870] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment for implementing this system will be described below.

[0871] 1. Data Collection

[0872] The server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information websites, and social media. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls. Specifically, the server runs a script every hour to check each data source and collect new crime reports.

[0873] For example, the server uses web scraping to check the latest crime prevention information and retrieves new crime information. It also uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[0874] 2. Data Preprocessing

[0875] The server pre-processes the collected criminal information. Pre-processing includes:

[0876] Imputing missing data

[0877] Eliminate duplicate data

[0878] Tokenization of text data

[0879] These processes are performed to prepare the data in a format that can be input to a machine learning model. For example, we use the Python Pandas library and SciKit-Learn's Imputer to clean the data and impute missing parts.

[0880] 3. Crime prediction

[0881] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM (long short-term memory) model trained on crime data from the past year. Newly collected data is input into this model to predict crimes that are likely to occur in the next week. Deep learning libraries such as TensorFlow and Keras are used to run the LSTM model.

[0882] 4. Conversational AI Systems

[0883] Users access the conversational AI system through a dedicated app or web portal. They input their questions or inquiries using the app's chatbot interface, which is then processed by the server. Natural language processing (NLP) technology is used to analyze the user's message and understand the intent of the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures.

[0884] 5. Notification System

[0885] Users can configure notification settings within the app to set notifications for specific areas or crime types. The server then sends alerts to users when the conditions are met. For example, if there is a high risk of car theft in a specific area, the user might receive a notification saying, "There is a high risk of car theft for the next week. Please be careful when parking, especially at night."

[0886] Specific examples

[0887] 1. Data Collection:

[0888] The server collects new crime reports from crime prevention maps and social media.

[0889] Example: A server uses web scraping technology to retrieve car theft information for a specific area.

[0890] 2. Data Preprocessing:

[0891] The server preprocesses the collected data and inputs it into a predictive model.

[0892] Example: Data cleaning and imputation using Pandas and SciKit-Learn.

[0893] 3. Crime prediction:

[0894] The server uses the LSTM model to predict crimes for the next week.

[0895] Example: Using TensorFlow to run an LSTM model to predict the likelihood of car theft in the next week.

[0896] 4. Conversational AI Systems:

[0897] A user uses the app to ask, "Car thefts are on the rise in my area. Is there anything I can do about it?"

[0898] The server analyzes it and responds, "We recommend installing surveillance cameras and an alarm system."

[0899] 5. Notification system:

[0900] Users can set up car theft alerts in the app.

[0901] When the risk of car theft increases, the server sends a notification to the user, such as "There is a high risk of car theft for the next week."

[0902] In this way, the system of the present invention provides users with real-time crime information and forecast information, aiming to realize a society in which citizens can live in peace.

[0903] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0904] Step 1:

[0905] The server collects crime information from multiple data sources on the Internet. Specifically, it uses web scraping technology and API calls to retrieve crime information from Yahoo! Maps crime prevention maps, car theft information websites, and social media. The input data are new crime reports from each data source, and the output data is a list of the collected crime information. For example, the server runs an automated script every hour to parse the latest crime prevention map information using an HTML parser (e.g., BeautifulSoup) and retrieve posts that match certain criteria from social media APIs.

[0906] Step 2:

[0907] The server preprocesses the collected crime information. Specifically, it completes missing data, removes duplicate data, and tokenizes the text data. The input data is a list of collected crime information, and the output data is a preprocessed, clean dataset. For example, the server uses Python's Pandas library and SciKit-Learn's Imputer to clean the data, and NLTK to tokenize the text data.

[0908] Step 3:

[0909] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM model trained on crime data from the past year. The input data is the preprocessed dataset, and the output data is a prediction of crimes that are likely to occur in the next week. For example, new data can be input into the LSTM model using TensorFlow or Keras, and the model generates a prediction that "there is a high probability of an increase in car thefts in this area in the next week."

[0910] Step 4:

[0911] Users access the conversational AI system through a dedicated app or web portal. Specifically, when a user inputs a question or inquiry into the chatbot interface, that input is processed by the server. The input data is the question or inquiry received from the user, and the output data is the answer to that question and countermeasures. For example, if a user inputs, "Car thefts are increasing in this area, so I would like to know what to do about it," the server will analyze it using NLP technology and respond, "I recommend installing surveillance cameras and an alarm system."

[0912] Step 5:

[0913] Users configure notification settings within the app. Specifically, users set notifications for specific areas or crime types. The input data are the user's settings, and the output data is an alert notification sent at the appropriate time. For example, based on the settings, if the risk of car theft increases in a specific area, the server will send a notification saying, "There is a high risk of car theft for the next week. Please be especially careful when parking at night."

[0914] In this way, the entire system can be processed efficiently in real time, providing users with the latest crime information and predictions, as well as specific countermeasures.

[0915] (Application example 1)

[0916] 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."

[0917] Current crime prediction systems lack the ability to collect and analyze information in real time, leaving users with insufficient information to take concrete countermeasures. Additionally, there is a lack of a way to quickly notify users of alerts for specific areas or crime types using smart devices. The purpose of this invention is to solve these issues and provide an environment where citizens can live in peace of mind.

[0918] 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.

[0919] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for analyzing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for being installed on smartphones or robots to notify users of prediction results for multiple areas and send alerts for specific areas or crime types, thereby enabling users to recognize crime risks in real time and take countermeasures.

[0920] "Multiple data sources on the Internet" refers to multiple sources of information accessible via the Internet, such as various websites, social media, news feeds, and map services.

[0921] "Means of collecting crime information in real time" refers to technologies and methods for always instantly collecting the latest crime data using web scraping technology or API calls.

[0922] "Crime Information" refers to the occurrence of crimes in the relevant area, details of the incidents, the time of the incidents, and other related information.

[0923] "Means for predicting crime occurrences in the next week" refers to technologies and methods that use machine learning models and statistical analysis to predict the likelihood of crime occurring in the next week based on collected crime data.

[0924] "Interactive AI system means" refers to a system in which a user inputs a question or inquiry via text or voice, and the AI ​​provides a response based on that input.

[0925] "Means of notifying users of prediction results" refers to methods and technologies for communicating predicted crime risks and countermeasures to users via smart devices.

[0926] "Means installed on smartphones and robots" refers to systems implemented as mobile applications or robot control software and installed on these devices.

[0927] "Means for sending alerts" refers to a notification system that sends warning messages to users when certain conditions or risks occur.

[0928] "Web scraping" refers to the technique of automatically extracting data from web pages on the Internet.

[0929] "API call" refers to a method for exchanging data with other services or software using an application programming interface (API).

[0930] A "machine learning model" refers to an algorithm that uses large amounts of data to learn certain patterns and make predictions and classifications for unknown data.

[0931] The system of the present invention is designed to collect crime information in real time from multiple data sources on the Internet, predict crime occurrences for the next week, and provide consultation services and suggest specific countermeasures to users. Specific modes for carrying out the invention are described below.

[0932] Data collection methods

[0933] The server uses web scraping technology and API calls to collect crime information from multiple data sources, including crime prevention maps, social media, and car theft information services. The server periodically runs a script to retrieve new crime information.

[0934] Data analysis format

[0935] The collected crime information is preprocessed by the server. This preprocessing includes missing data imputation, duplicate data elimination, and text data tokenization. The server then uses a machine learning model (such as an LSTM model) to predict crime occurrences for the next week. This model is trained based on past crime data.

[0936] Forms of conversational AI systems

[0937] Users access the conversational AI system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or request for advice, the input is processed by the server. The server uses natural language processing technology (such as spaCy or NLTK) to analyze the input and provide the user with appropriate crime prediction data and specific countermeasures.

[0938] Notification system type

[0939] Users can configure their notification settings within the app, allowing them to receive notifications for specific areas or crime types, and the server will then send alerts to users based on the configured conditions.

[0940] Hardware and software used

[0941] Server: Used for data collection, analysis and model execution.

[0942] Web scraping: BeautifulSoup, Requests library.

[0943] API calls: Requests library.

[0944] Machine learning: TensorFlow / Keras.

[0945] Natural Language Processing: spaCy or NLTK.

[0946] Description of the Examples

[0947] The server detects reports of "car theft" from social media, preprocesses the data, and inputs it into an LSTM model to calculate the risk for the next week. Users living in areas with a high risk of car theft receive a notification saying, "Be careful when parking at night." If a user asks, "There have been a lot of car thefts in this area recently. What can I do to prevent this?" the server responds, "We recommend installing surveillance cameras and an alarm system."

[0948] Prompt Sentence Examples

[0949] "Please predict car thefts in XX region for the next week. The historical data is as follows: {Historical Data}. Based on this data, please suggest risks and specific countermeasures."

[0950] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0951] Step 1:

[0952] The server uses web scraping technology and API calls to collect real-time crime information from multiple data sources on the Internet. Specifically, it periodically runs scripts to retrieve the latest crime information from crime prevention maps, social media, and car theft information services. It uses the URLs and API endpoints of the data sources as input and stores the collected crime information in a database as output.

[0953] Step 2:

[0954] The server preprocesses the collected crime information. This includes filling in missing values, eliminating duplicate data, and tokenizing text data. It uses the data collected in step 1 as input and generates a new dataset with the preprocessed data as output. Specifically, it fills in missing values ​​with the closest valid data, removes duplicate data, and tokenizes the text data to convert it into a format that is easier to analyze.

[0955] Step 3:

[0956] The server inputs the preprocessed data into a machine learning model to predict crime occurrences over the next week. The preprocessed dataset is used as input, and crime occurrence prediction results are obtained as output. Specifically, machine learning algorithms such as LSTM models are used to train this data to predict the probability of crime occurrence.

[0957] Step 4:

[0958] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or inquiries. The user's text message is used as input, and the server generates an appropriate answer as output. Specifically, the system analyzes the input question using natural language processing technology and generates an answer by referencing crime prediction data and specific countermeasures.

[0959] Step 5:

[0960] Based on the prediction results, the server sends notifications to registered users regarding specific areas and crime types. It uses the crime prediction results and user settings as input, and generates and sends notification messages to users as output. Specifically, it generates alert messages for high-risk areas and notifies users in real time via smartphones or robots.

[0961] 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.

[0962] The present invention combines a system that collects local crime information in real time and predicts crime one week in advance with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention are described below.

[0963] Data collection implementation

[0964] First, the server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information bureaus, social media, etc. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[0965] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[0966] Data Analysis Embodiments

[0967] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[0968] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[0969] An embodiment of an interactive AI system

[0970] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[0971] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[0972] Embodiment of Emotion Engine

[0973] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results.

[0974] For example, if a user types, "I've been scared to walk the streets at night recently," the emotion engine will detect "anxiety." Based on this, the server will suggest countermeasures to make the user feel more secure. It will provide specific measures such as, "If you feel anxious, there are more patrols in the area. We also recommend that you carry a safety alarm."

[0975] Notification System Embodiments

[0976] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[0977] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[0978] Specific example explanation

[0979] 1. Data Collection:

[0980] The server collects new crime reports from crime prevention maps and social media.

[0981] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[0982] 2. Data Analysis:

[0983] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[0984] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[0985] 3. Conversational AI systems:

[0986] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[0987] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[0988] 4. Emotion Engine:

[0989] The user types, "Recently, I've been afraid to walk on the street at night."

[0990] The server uses an emotion engine to recognize the user's anxiety and suggests countermeasures to reassure them, such as "Patrols are increasing. We also recommend that you carry a safety alarm."

[0991] 5. Notification system:

[0992] Users can set up car theft alerts in the app.

[0993] When the risk of car theft increases, the server sends a notification to the user saying, "There is a high risk of car theft for the next week."

[0994] As a result, the system according to the present invention can not only provide new crime predictions and countermeasures to help citizens live in peace, but also respond in a detailed manner according to the user's emotions.

[0995] The processing flow will be explained below.

[0996] Specific processing flow of the embodiment

[0997] Step 1: Start collecting data

[0998] The server will start the data collection process at the specified time interval (e.g. every hour).

[0999] Step 2: Accessing the Data Source

[1000] The server uses web scraping technology and API calls to access multiple data sources on the Internet, such as crime prevention maps, car theft information bureaus, and social media.

[1001] Step 3: Collecting criminal information

[1002] The server retrieves the latest crime report data from each data source.

[1003] Example: The server retrieves the latest information on crime prevention maps and uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[1004] Step 4: Data Preprocessing

[1005] The server cleanses the collected data, completing missing data, eliminating duplicate data, and tokenizing text data.

[1006] Step 5: Perform crime predictions

[1007] The server uses a machine learning algorithm (e.g., LSTM model) to analyze the preprocessed data and make crime predictions for the coming week.

[1008] Step 6: Save the prediction results

[1009] The server stores the generated crime prediction results in a database.

[1010] Step 7: User Inquiry Processing

[1011] Users access the conversational AI system through a dedicated app or web portal.

[1012] Users input their questions or concerns into the chatbot interface. For example, they might type, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?"

[1013] Step 8: Parsing User Input

[1014] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[1015] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[1016] Step 9: Sentiment Analysis

[1017] The server uses an emotion engine to parse emotions from the user's input text.

[1018] Example: If a user inputs "I've been scared to walk on the street at night recently," the server will use the emotion engine to detect "anxiety."

[1019] Step 10: Generate emotion-based responses

[1020] The server generates more appropriate countermeasures based on the emotions recognized by the emotion engine.

[1021] Example: If the user is feeling anxious, the server may suggest reassuring measures such as, "There are increased patrols in the area. We also recommend that you carry a safety alarm."

[1022] Step 11: Provide your answers

[1023] The server presents specific countermeasures to the user based on the analyzed crime prediction data and the results of the emotion engine.

[1024] Example: The server provides the user with an answer such as "We recommend installing a bicycle lock with an alarm" via a chatbot.

[1025] Step 12: Establish notification settings

[1026] Users can configure notification settings within the app for specific areas and crime types.

[1027] Example: A user sets up notifications for car theft.

[1028] Step 13: Monitor notification conditions

[1029] The server generates notifications based on the configured notification conditions, if applicable.

[1030] Example: When the risk of car theft increases in a particular area, the server generates a notification saying, "There is a high risk of car theft in your area for the next week."

[1031] Step 14: Sending notifications

[1032] The server sends the generated notification to the user.

[1033] Users receive notifications and can take action, for example by tightening the security of their parking spot.

[1034] Through these steps, the system of the present invention can recognize the user's emotions, predict crime in real time, and provide specific countermeasures, thereby creating an environment in which users can live with greater peace of mind.

[1035] Example 2

[1036] 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."

[1037] In recent years, crime has been increasing, especially in urban areas, requiring a rapid and effective response. Currently, crime information is not collected or analyzed in real time, which often results in delayed preventative measures. It is also difficult to respond appropriately to users' feelings of anxiety and fear. For this reason, there is a need for a system that combines the rapid collection and analysis of crime information, the provision of effective preventative measures, and a response that responds to users' feelings.

[1038] 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.

[1039] In this invention, the server includes: means for collecting crime information in real time from multiple data sources on the Internet; means for preprocessing the collected crime information; means for predicting crime occurrences for the next week using a machine learning model based on the preprocessed crime information; means for accepting questions from users and analyzing them using natural language processing technology; emotion engine means for recognizing emotions from user input text and generating a response based on the results; interactive artificial intelligence system means for proposing consultation responses and specific countermeasures to the user based on the predictions; and means for notifying the user of the predictions and consultation response results. This enables the rapid collection, analysis, and prediction of crime information, and also enables detailed responses tailored to the user's emotions.

[1040] The "Internet" is an information and communications network that interconnects computer networks around the world.

[1041] A "data source" is a source of data from which information is collected.

[1042] "Crime information" refers to specific information about the location, time, and circumstances of a crime.

[1043] "Collection" is the act of obtaining necessary data from multiple data sources on the Internet.

[1044] "Preprocessing" is the act of filling in gaps in collected data, eliminating duplicates, and converting it into an analyzable format.

[1045] A "machine learning model" is an algorithm that learns patterns from past data and makes predictions about unknown data.

[1046] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1047] An "emotion engine" is a system that recognizes emotions from the user's input text and generates an appropriate response based on the results.

[1048] An "interactive artificial intelligence system" is an artificial intelligence system that interacts with users and proposes appropriate responses and solutions to their questions and inquiries.

[1049] "Notification" refers to the act of conveying information such as prediction results and countermeasures from the system to the user.

[1050] "Crime prediction" is the process of predicting in which areas crimes are likely to occur in the future based on collected crime information.

[1051] "Users" are people who use this system.

[1052] This invention combines a system that collects local crime information in real time and predicts crimes one week in advance with an emotion engine that recognizes the user's emotions. This system operates in cooperation with three parties: a server, a terminal, and the user.

[1053] Hardware and Software Configuration

[1054] The server is a high-performance computer system that collects and analyzes data, runs crime prediction models, and generates answers to user questions. The server is implemented using software such as Python, TensorFlow, and NLP libraries.

[1055] The terminal is a device used by the user, such as a smartphone or computer, that provides an interface for accessing the system through a dedicated application or a web portal. The terminal operates as a browser application or a native application and communicates with the server.

[1056] Users are people who use the system and check crime information, ask questions, and ask for advice through their terminals.

[1057] Examples of data collection

[1058] The server collects the latest crime information from data sources such as crime prevention maps, car theft information bureaus, and social media. Specifically, the server runs a script every hour to check each data source for new crime reports. For example, it checks the latest status of the crime prevention map and retrieves newly reported crime information from it. At the same time, the server uses the social media API to collect posts containing specific keywords such as "car theft" and "stalking."

[1059] Specific examples of data analysis

[1060] Based on the collected crime information, the server performs data preprocessing, such as filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict crime occurrences over the next week. For example, the server uses an LSTM model trained using crime data from the past year. By inputting newly collected data into this model, it can predict the likelihood of crimes occurring in a specific area over the next week.

[1061] Examples of conversational AI systems

[1062] Users access the conversational AI system through a dedicated app or web portal. The user opens the app and uses the chatbot interface to input a question or inquiry. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?" This input is processed by the server. The server analyzes the user's message using natural language processing (NLP) technology to understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[1063] Examples of emotion engines

[1064] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results. For example, if a user inputs, "I've been afraid to walk the streets at night lately," the emotion engine detects "anxiety." Based on this, the server suggests countermeasures to make users feel more secure. It provides specific measures such as, "If you feel anxious, there have been increased patrols in this area. We also recommend that you carry a safety alarm."

[1065] Example of a notification system

[1066] Users can set up notifications within the app to receive notifications for specific areas or crime types. The server will then send alerts to users based on the set conditions. For example, if a user sets up notifications for the risk of car theft in a specific area, the server will monitor predicted car thefts in that area and, if the risk increases, send a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[1067] The system of this invention not only rapidly collects and analyzes crime information and provides users with appropriate countermeasures, but also enables detailed responses that reflect the user's emotions, thereby providing new crime prediction and countermeasures that will allow citizens to live in peace.

[1068] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1069] Step 1: Data collection

[1070] The server collects real-time crime information from multiple data sources on the Internet (such as crime prevention maps, car theft information stations, and social media). The input is the public APIs and web pages of the data sources. The server runs a script every hour to check each data source for new crime reports.

[1071] What it does: The server uses a Python script to access a crime prevention map to retrieve new crime report data, and calls social media APIs to search for posts containing specific keywords like "car theft" or "stalking," and collects the results. The output is the collected raw data.

[1072] Step 2: Data Preprocessing

[1073] The server preprocesses the collected data. The input is the collected raw data, and the output is the preprocessed clean data. Specific data preprocessing includes tokenizing text data, filling in missing data, and removing duplicate data.

[1074] What it does: The server uses NLP libraries to tokenize the text data, imputes missing items using statistical methods, and applies algorithms to detect and eliminate duplicate data, ultimately producing a clean dataset.

[1075] Step 3: Prediction using a crime prediction model

[1076] The server uses the preprocessed data to predict crime occurrences for the next week using an LSTM model. The input is the preprocessed clean data, and the output is the probability of crime occurrence for each area.

[1077] Specific operation: The server uses the TensorFlow library to run an LSTM model trained on crime data from the past year, inputs new data, and calculates the crime probability for each area. The results are then stored in a database.

[1078] Step 4: Accepting user questions

[1079] Users input questions or inquiries into the conversational AI system through a dedicated app or web portal. The input is the text entered by the user, and the output is that text data.

[1080] Specific operation: The user opens the application on their device and types a question into the chatbot interface, such as, "I've heard that bicycle thefts have been increasing recently. Are there any safety measures?"

[1081] Step 5: Analyze user emotions with the emotion engine

[1082] The server analyzes the user's input text and recognizes the user's emotions using an emotion engine. The input is text data from the user, and the output is the emotion analysis result (e.g., anxiety, fear, etc.).

[1083] How it works: The server uses NLP technology to analyze the user's input text and uses an emotion engine to identify emotions such as "anxiety" or "fear." It then adjusts the response based on the results of this emotion analysis.

[1084] Step 6: Generate response and send notification

[1085] The server responds to users based on crime prediction data and sentiment analysis results, and sends notifications as needed. The input is sentiment analysis results and crime prediction data, and the output is a response text or notification message to the user.

[1086] Specific operation: The server notifies the user through the chatbot of specific countermeasures, such as "We recommend installing a bicycle lock with an alarm." Also, when the risk of car theft increases in a specific area, it sends a notification to the app saying, "The risk of car theft is high in your area for the next week. Please be especially careful when parking at night."

[1087] Through these processing steps, the system not only quickly collects and analyzes crime information and provides users with appropriate countermeasures, but also provides detailed responses that reflect the user's emotions.

[1088] (Application example 2)

[1089] 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."

[1090] In modern society, ensuring safety and security in areas where crime is frequent or difficult to predict is an important issue. However, conventional crime prediction systems lack the ability to collect real-time data or propose countermeasures based on user sentiment, limiting their ability to provide more effective crime prevention measures. Furthermore, notification systems for users are inadequate, and a means of effectively communicating risk is needed.

[1091] 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.

[1092] In this invention, the server includes means for collecting event information in real time from multiple data sources on the Internet, means for analyzing the collected event information and predicting event occurrences for the next week, an interactive AI system for responding to inquiries from users and proposing specific countermeasures based on the predictions, means for proposing countermeasures to users based on the prediction results and emotion analysis results, and means for notifying users of the prediction results. This makes it possible to collect crime information in real time and propose appropriate crime prevention countermeasures taking into account the user's emotions.

[1093] "Event Information" refers to data about crimes and other significant events that occur in an area.

[1094] "Analysis" is the process of processing collected data and extracting meaning and trends.

[1095] "Prediction" is the estimation of the probability of future events occurring based on data obtained through analysis.

[1096] An "interactive artificial intelligence system" is a system that converses with users using natural language and proposes appropriate measures in response to questions or inquiries.

[1097] "Sentiment analysis" is a technique that processes user input text to determine the content and intensity of emotions.

[1098] "Proposal" means showing specific actions or measures to the user based on analyzed data and prediction results.

[1099] "Notification" refers to sending information from the system to the user to inform them of important events or risks.

[1100] "Harvesting" is the act of gathering necessary data from multiple data sources on the Internet.

[1101] "Web scraping" is the technique of automatically extracting information from websites.

[1102] "Application Program Interface Call" is a method of obtaining data using the API provided by the data source.

[1103] A "machine learning model" is an algorithm trained using historical data and used to predict future events.

[1104] The present invention is a system that collects local crime information in real time and provides users with crime predictions for the next week and countermeasures based on emotion analysis. Specific embodiments of the system of the present invention are described below.

[1105] Data collection methods

[1106] The server collects event information from multiple data sources on the Internet. Specifically, it uses web scraping technology and application program interface (API) calls to automatically obtain data from crime prevention maps, social media, etc. The server runs a script every hour to obtain new event information.

[1107] Data Analysis Methods

[1108] Based on the collected event information, the server performs data preprocessing. This preprocessing includes filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict event occurrences for the next week. This prediction model uses a machine learning model trained using data from the past year.

[1109] Interactive artificial intelligence system means

[1110] Users access the conversational artificial intelligence system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or inquiry, the server analyzes the input using natural language processing technology. Based on the analysis results, the server suggests appropriate countermeasures to the user. For example, in response to a question such as, "There have been a lot of car thefts in this area recently. What countermeasures should I take?" the server might respond, "I recommend installing surveillance cameras and an alarm system."

[1111] Suggestion method based on emotion analysis

[1112] The server performs sentiment analysis on the text entered by the user to recognize the user's emotions. Sentiment analysis is performed using natural language processing technologies such as SentimentIntensityAnalyzer. Based on the results of the sentiment analysis, the system suggests countermeasures that will give the user a greater sense of security. For example, if a user enters, "I've been afraid to walk the streets at night recently," the system will suggest specific countermeasures, such as, "Patrols have increased. I also recommend that you carry a safety alarm."

[1113] Notification means

[1114] The server notifies the user of predicted event information based on the notification conditions set by the user within the app. For example, if an alert is set for the risk of car theft in a specific area, the server monitors the predicted results of car theft and sends a notification saying, "The risk of car theft is high for the next week" when the risk increases.

[1115] Specific example explanation

[1116] For example:

[1117] Data collection:

[1118] The server collects new incident information from crime prevention maps and social media, for example, using web scraping technology to obtain information on reported car thefts in a specific area.

[1119] User input and interactive AI system response:

[1120] User: "There have been a lot of car thefts in this area recently. What can I do about it?"

[1121] Server: "I recommend installing security cameras and an alarm system."

[1122] User sentiment analysis and suggestions:

[1123] User: "I've been scared to walk the streets at night lately."

[1124] Server: "Patrols have been increased. We also recommend carrying a safety alarm."

[1125] In this way, the system of the present invention can provide more effective crime prevention measures by suggesting appropriate countermeasures to users while performing emotion analysis based on event information collected in real time.

[1126] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1127] Step 1:

[1128] The server collects event information from multiple data sources on the Internet.

[1129] Input: The server runs a script to retrieve information from data sources such as security maps and social media.

[1130] Output: Raw data of new event information is collected.

[1131] Specific operation: The server uses web scraping technology and API calls to obtain the reported data from each data source. This operation is performed periodically (e.g., every hour).

[1132] Step 2:

[1133] The server pre-processes the collected event information.

[1134] Input: Raw data collected.

[1135] Output: Preprocessed data.

[1136] What it does: The server imputes missing values ​​in the data, removes duplicates, and tokenizes the text data, converting it into a format suitable for input into machine learning models.

[1137] Step 3:

[1138] The server uses the preprocessed data to predict the occurrence of an event.

[1139] Input: Preprocessed data.

[1140] Output: Predicted events for the next week.

[1141] How it works: The server uses the LSTM model to combine past data with newly collected data to make predictions, and provides prediction results for specific regions and event types.

[1142] Step 4:

[1143] The server responds to user questions and inquiries through an interactive artificial intelligence system.

[1144] Input: Questions or inquiries entered by the user through the app.

[1145] Output: Appropriate action or suggestion.

[1146] Specific actions: The server uses natural language processing technology to analyze the user's input and proposes the best countermeasure based on the prediction results. For example, it provides the user with specific countermeasures such as "installing surveillance cameras."

[1147] Step 5:

[1148] The server performs sentiment analysis and makes suggestions based on the user's emotions.

[1149] Input: Text that the user types into the app.

[1150] Output: Sentiment analysis results and corresponding countermeasures.

[1151] Specific operation: The server uses SentimentIntensityAnalyzer to obtain the user's emotion score, and based on the result, makes suggestions to make the user feel more secure. For example, it may make a suggestion such as "We recommend that you carry a safety alarm."

[1152] Step 6:

[1153] The server notifies the user of the prediction results.

[1154] Input: Notification conditions set by the user and event occurrence prediction results.

[1155] Output: The notification sent to the user.

[1156] Specific operation: The server monitors the notification conditions set by the user in the app and automatically sends a notification when a prediction result that matches the conditions is found. For example, a notification stating "There is a high risk of car theft" is sent via email or app notification.

[1157] The above are the processing steps of the system of the present invention, which makes it possible to collect event information in real time, perform emotion analysis, and propose appropriate countermeasures to the user.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] [Fourth embodiment]

[1162] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1163] 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.

[1164] 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).

[1165] 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.

[1166] 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.

[1167] 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).

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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."

[1175] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment of the system of the present invention will be described below.

[1176] Data collection implementation

[1177] First, the server collects crime information from multiple data sources on the Internet, including Yahoo! Maps crime prevention maps, car theft information bureaus, and social media sites with frequent new posts. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[1178] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[1179] Data Analysis Embodiments

[1180] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[1181] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[1182] An embodiment of an interactive AI system

[1183] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[1184] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[1185] Notification System Embodiments

[1186] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[1187] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[1188] Specific example explanation

[1189] 1. Data Collection:

[1190] The server collects new crime reports from Yahoo! Maps' crime prevention maps and social media.

[1191] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[1192] 2. Data Analysis:

[1193] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[1194] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[1195] 3. Conversational AI systems:

[1196] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[1197] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[1198] 4. Notification system:

[1199] Users can set up car theft alerts in the app.

[1200] When the risk of car theft increases, the server sends a notification to the user saying, "The risk of car theft is high for the next week. Please be especially careful when parking at night."

[1201] As a result, the system according to the present invention can provide new crime prediction and countermeasures to help citizens live in peace.

[1202] The processing flow will be explained below.

[1203] Specific flow of program processing

[1204] Step 1: Start collecting data

[1205] The server will start the data collection process at the specified time interval (e.g. every hour).

[1206] The server runs a web scraping script to collect the latest crime information from multiple data sources on the Internet (e.g., crime prevention maps, car theft information bureaus, social media).

[1207] Step 2: Performing data collection

[1208] The server scans the web pages of each data source and extracts new crime report data.

[1209] The server calls the SNS API to retrieve posts containing keywords such as "car theft" and "stalking."

[1210] Step 3: Data Preprocessing

[1211] The server cleans the collected data, imputes missing values, and removes duplicate data.

[1212] The server tokenizes the text data and converts it into a format suitable for analysis.

[1213] Step 4: Analyze the data

[1214] The server inputs the cleansed data into an LSTM (long short-term memory) model and runs the machine learning algorithm.

[1215] The server then generates a prediction of crimes that may occur over the next week.

[1216] Step 5: Save the prediction results

[1217] The server stores the generated crime prediction results in a database.

[1218] Step 6: User Inquiry Processing

[1219] Users access the conversational AI system through a dedicated app or web portal.

[1220] Users input their questions or concerns into the chatbot interface. For example, they might type, "There have been a lot of bicycle thefts in my neighborhood recently. What can I do about it?"

[1221] Step 7: Parsing User Input

[1222] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[1223] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[1224] Step 8: Providing a solution

[1225] The server generates specific responses to the user's questions based on the predicted crime data.

[1226] The server will then present specific measures to the user through a chatbot, such as "We recommend installing a bicycle lock with an alarm."

[1227] Step 9: Establish notification settings

[1228] Within the app, users can set up notifications for specific crime types and geographic areas, such as car theft.

[1229] Step 10: Generate an alert

[1230] The server generates an alert based on the configured conditions, if applicable, when the risk of car theft increases.

[1231] Step 11: Sending notifications

[1232] The server sends notifications to users regarding increased crime risk.

[1233] Users receive notifications such as, "There is a high risk of car theft in your area over the next week. Please be careful when parking, especially overnight."

[1234] Through the above steps, the crime prediction system of the present invention can provide safety measures to citizens and increase crime prevention by making crime predictions in real time.

[1235] Example 1

[1236] 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."

[1237] Conventional crime prediction systems were unable to efficiently collect and analyze local crime information and provide users with appropriate crime prevention measures. It was also difficult to obtain the latest crime information in real time and make highly accurate crime predictions. This could result in citizens missing out on opportunities to take adequate crime prevention measures.

[1238] 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.

[1239] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for preprocessing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for notifying users of the prediction results. This allows citizens to collect crime information in real time and receive highly accurate crime predictions and specific crime prevention measures.

[1240] "Multiple data sources on the Internet" refers to multiple sources of information, such as websites and social media, that provide criminal information.

[1241] "Real-time" refers to constantly obtaining and processing the latest information without delay.

[1242] "Crime information" refers to detailed data and reports about crimes occurring in a particular area, such as car theft, bike theft, and stalking.

[1243] "Means of collection" refers to technology that automatically obtains criminal information from the Internet through web scraping and API calls.

[1244] "Preprocessing" refers to the process of completing missing data, eliminating duplicate data, tokenizing text data, etc. from collected data.

[1245] "Crime prediction" refers to the use of machine learning models to predict the likelihood of future crimes based on past crime data and newly collected data.

[1246] A "machine learning model" refers to an algorithm that learns from past data and makes predictions or classifications based on new data. Specifically, it includes LSTM (long short-term memory) models.

[1247] An "interactive AI system" refers to an artificial intelligence that responds to questions and inquiries through dialogue with users and provides appropriate information and solutions.

[1248] "User" refers to a person who uses an interactive AI system through a dedicated app or web portal.

[1249] "Notification means" refers to technology that sends alerts related to crime prediction results based on conditions set by the user.

[1250] The system of the present invention collects local crime information in real time and predicts crimes one week in advance. A specific embodiment for implementing this system will be described below.

[1251] 1. Data Collection

[1252] The server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information websites, and social media. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls. Specifically, the server runs a script every hour to check each data source and collect new crime reports.

[1253] For example, the server uses web scraping to check the latest crime prevention information and retrieves new crime information. It also uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[1254] 2. Data Preprocessing

[1255] The server pre-processes the collected criminal information. Pre-processing includes:

[1256] Imputing missing data

[1257] Eliminate duplicate data

[1258] Tokenization of text data

[1259] These processes are performed to prepare the data in a format that can be input to a machine learning model. For example, we use the Python Pandas library and SciKit-Learn's Imputer to clean the data and impute missing parts.

[1260] 3. Crime prediction

[1261] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM (long short-term memory) model trained on crime data from the past year. Newly collected data is input into this model to predict crimes that are likely to occur in the next week. Deep learning libraries such as TensorFlow and Keras are used to run the LSTM model.

[1262] 4. Conversational AI Systems

[1263] Users access the conversational AI system through a dedicated app or web portal. They input their questions or inquiries using the app's chatbot interface, which is then processed by the server. Natural language processing (NLP) technology is used to analyze the user's message and understand the intent of the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures.

[1264] 5. Notification System

[1265] Users can configure notification settings within the app to set notifications for specific areas or crime types. The server then sends alerts to users when the conditions are met. For example, if there is a high risk of car theft in a specific area, the user might receive a notification saying, "There is a high risk of car theft for the next week. Please be careful when parking, especially at night."

[1266] Specific examples

[1267] 1. Data Collection:

[1268] The server collects new crime reports from crime prevention maps and social media.

[1269] Example: A server uses web scraping technology to retrieve car theft information for a specific area.

[1270] 2. Data Preprocessing:

[1271] The server preprocesses the collected data and inputs it into a predictive model.

[1272] Example: Data cleaning and imputation using Pandas and SciKit-Learn.

[1273] 3. Crime prediction:

[1274] The server uses the LSTM model to predict crimes for the next week.

[1275] Example: Using TensorFlow to run an LSTM model to predict the likelihood of car theft in the next week.

[1276] 4. Conversational AI Systems:

[1277] A user uses the app to ask, "Car thefts are on the rise in my area. Is there anything I can do about it?"

[1278] The server analyzes it and responds, "We recommend installing surveillance cameras and an alarm system."

[1279] 5. Notification system:

[1280] Users can set up car theft alerts in the app.

[1281] When the risk of car theft increases, the server sends a notification to the user, such as "There is a high risk of car theft for the next week."

[1282] In this way, the system of the present invention provides users with real-time crime information and forecast information, aiming to realize a society in which citizens can live in peace.

[1283] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1284] Step 1:

[1285] The server collects crime information from multiple data sources on the Internet. Specifically, it uses web scraping technology and API calls to retrieve crime information from Yahoo! Maps crime prevention maps, car theft information websites, and social media. The input data are new crime reports from each data source, and the output data is a list of the collected crime information. For example, the server runs an automated script every hour to parse the latest crime prevention map information using an HTML parser (e.g., BeautifulSoup) and retrieve posts that match certain criteria from social media APIs.

[1286] Step 2:

[1287] The server preprocesses the collected crime information. Specifically, it completes missing data, removes duplicate data, and tokenizes the text data. The input data is a list of collected crime information, and the output data is a preprocessed, clean dataset. For example, the server uses Python's Pandas library and SciKit-Learn's Imputer to clean the data, and NLTK to tokenize the text data.

[1288] Step 3:

[1289] The server uses the preprocessed data to make crime predictions. Specifically, it uses an LSTM model trained on crime data from the past year. The input data is the preprocessed dataset, and the output data is a prediction of crimes that are likely to occur in the next week. For example, new data can be input into the LSTM model using TensorFlow or Keras, and the model generates a prediction that "there is a high probability of an increase in car thefts in this area in the next week."

[1290] Step 4:

[1291] Users access the conversational AI system through a dedicated app or web portal. Specifically, when a user inputs a question or inquiry into the chatbot interface, that input is processed by the server. The input data is the question or inquiry received from the user, and the output data is the answer to that question and countermeasures. For example, if a user inputs, "Car thefts are increasing in this area, so I would like to know what to do about it," the server will analyze it using NLP technology and respond, "I recommend installing surveillance cameras and an alarm system."

[1292] Step 5:

[1293] Users configure notification settings within the app. Specifically, users set notifications for specific areas or crime types. The input data are the user's settings, and the output data is an alert notification sent at the appropriate time. For example, based on the settings, if the risk of car theft increases in a specific area, the server will send a notification saying, "There is a high risk of car theft for the next week. Please be especially careful when parking at night."

[1294] In this way, the entire system can be processed efficiently in real time, providing users with the latest crime information and predictions, as well as specific countermeasures.

[1295] (Application example 1)

[1296] 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."

[1297] Current crime prediction systems lack the ability to collect and analyze information in real time, leaving users with insufficient information to take concrete countermeasures. Additionally, there is a lack of a way to quickly notify users of alerts for specific areas or crime types using smart devices. The purpose of this invention is to solve these issues and provide an environment where citizens can live in peace of mind.

[1298] 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.

[1299] In this invention, the server includes means for collecting crime information in real time from multiple data sources on the Internet, means for analyzing the collected crime information and predicting crime occurrences for the next week, an interactive AI system means for providing consultation to users and proposing specific countermeasures based on the predictions, and means for being installed on smartphones or robots to notify users of prediction results for multiple areas and send alerts for specific areas or crime types, thereby enabling users to recognize crime risks in real time and take countermeasures.

[1300] "Multiple data sources on the Internet" refers to multiple sources of information accessible via the Internet, such as various websites, social media, news feeds, and map services.

[1301] "Means of collecting crime information in real time" refers to technologies and methods for always instantly collecting the latest crime data using web scraping technology or API calls.

[1302] "Crime Information" refers to the occurrence of crimes in the relevant area, details of the incidents, the time of the incidents, and other related information.

[1303] "Means for predicting crime occurrences in the next week" refers to technologies and methods that use machine learning models and statistical analysis to predict the likelihood of crime occurring in the next week based on collected crime data.

[1304] "Interactive AI system means" refers to a system in which a user inputs a question or inquiry via text or voice, and the AI ​​provides a response based on that input.

[1305] "Means of notifying users of prediction results" refers to methods and technologies for communicating predicted crime risks and countermeasures to users via smart devices.

[1306] "Means installed on smartphones and robots" refers to systems implemented as mobile applications or robot control software and installed on these devices.

[1307] "Means for sending alerts" refers to a notification system that sends warning messages to users when certain conditions or risks occur.

[1308] "Web scraping" refers to the technique of automatically extracting data from web pages on the Internet.

[1309] "API call" refers to a method for exchanging data with other services or software using an application programming interface (API).

[1310] A "machine learning model" refers to an algorithm that uses large amounts of data to learn certain patterns and make predictions and classifications for unknown data.

[1311] The system of the present invention is designed to collect crime information in real time from multiple data sources on the Internet, predict crime occurrences for the next week, and provide consultation services and suggest specific countermeasures to users. Specific modes for carrying out the invention are described below.

[1312] Data collection methods

[1313] The server uses web scraping technology and API calls to collect crime information from multiple data sources, including crime prevention maps, social media, and car theft information services. The server periodically runs a script to retrieve new crime information.

[1314] Data analysis format

[1315] The collected crime information is preprocessed by the server. This preprocessing includes missing data imputation, duplicate data elimination, and text data tokenization. The server then uses a machine learning model (such as an LSTM model) to predict crime occurrences for the next week. This model is trained based on past crime data.

[1316] Forms of conversational AI systems

[1317] Users access the conversational AI system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or request for advice, the input is processed by the server. The server uses natural language processing technology (such as spaCy or NLTK) to analyze the input and provide the user with appropriate crime prediction data and specific countermeasures.

[1318] Notification system type

[1319] Users can configure their notification settings within the app, allowing them to receive notifications for specific areas or crime types, and the server will then send alerts to users based on the configured conditions.

[1320] Hardware and software used

[1321] Server: Used for data collection, analysis and model execution.

[1322] Web scraping: BeautifulSoup, Requests library.

[1323] API calls: Requests library.

[1324] Machine learning: TensorFlow / Keras.

[1325] Natural Language Processing: spaCy or NLTK.

[1326] Description of the Examples

[1327] The server detects reports of "car theft" from social media, preprocesses the data, and inputs it into an LSTM model to calculate the risk for the next week. Users living in areas with a high risk of car theft receive a notification saying, "Be careful when parking at night." If a user asks, "There have been a lot of car thefts in this area recently. What can I do to prevent this?" the server responds, "We recommend installing surveillance cameras and an alarm system."

[1328] Prompt Sentence Examples

[1329] "Please predict car thefts in XX region for the next week. The historical data is as follows: {Historical Data}. Based on this data, please suggest risks and specific countermeasures."

[1330] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1331] Step 1:

[1332] The server uses web scraping technology and API calls to collect real-time crime information from multiple data sources on the Internet. Specifically, it periodically runs scripts to retrieve the latest crime information from crime prevention maps, social media, and car theft information services. It uses the URLs and API endpoints of the data sources as input and stores the collected crime information in a database as output.

[1333] Step 2:

[1334] The server preprocesses the collected crime information. This includes filling in missing values, eliminating duplicate data, and tokenizing text data. It uses the data collected in step 1 as input and generates a new dataset with the preprocessed data as output. Specifically, it fills in missing values ​​with the closest valid data, removes duplicate data, and tokenizes the text data to convert it into a format that is easier to analyze.

[1335] Step 3:

[1336] The server inputs the preprocessed data into a machine learning model to predict crime occurrences over the next week. The preprocessed dataset is used as input, and crime occurrence prediction results are obtained as output. Specifically, machine learning algorithms such as LSTM models are used to train this data to predict the probability of crime occurrence.

[1337] Step 4:

[1338] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or inquiries. The user's text message is used as input, and the server generates an appropriate answer as output. Specifically, the system analyzes the input question using natural language processing technology and generates an answer by referencing crime prediction data and specific countermeasures.

[1339] Step 5:

[1340] Based on the prediction results, the server sends notifications to registered users regarding specific areas and crime types. It uses the crime prediction results and user settings as input, and generates and sends notification messages to users as output. Specifically, it generates alert messages for high-risk areas and notifies users in real time via smartphones or robots.

[1341] 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.

[1342] The present invention combines a system that collects local crime information in real time and predicts crime one week in advance with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention are described below.

[1343] Data collection implementation

[1344] First, the server collects crime information from multiple data sources on the Internet, including crime prevention maps, car theft information bureaus, social media, etc. The server periodically retrieves the necessary crime information from these data sources using web scraping technology and API calls.

[1345] Specifically, the server runs a script every hour to check each data source for new crime reports. For example, the server checks the latest crime prevention map and retrieves newly reported crime information. At the same time, the server uses social media APIs to collect posts containing specific keywords, such as "car theft" or "stalking."

[1346] Data Analysis Embodiments

[1347] Based on the collected crime information, the server performs data preprocessing, which includes filling in missing data, eliminating duplicate data, and tokenizing text data, and then uses machine learning models to predict crime occurrences for the next week.

[1348] For example, the server uses a long short-term memory (LSTM) model trained using crime data from the past year, and by inputting newly collected data, the model predicts the likelihood of crimes occurring in a particular area over the next week.

[1349] An embodiment of an interactive AI system

[1350] Users access the conversational AI system through a dedicated app or web portal. They open the app and use the chatbot interface to input their questions or concerns. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures in place?"

[1351] This input is processed by the server, which uses natural language processing (NLP) technology to analyze the user's message and understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[1352] Embodiment of Emotion Engine

[1353] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results.

[1354] For example, if a user types, "I've been scared to walk the streets at night recently," the emotion engine will detect "anxiety." Based on this, the server will suggest countermeasures to make the user feel more secure. It will provide specific measures such as, "If you feel anxious, there are more patrols in the area. We also recommend that you carry a safety alarm."

[1355] Notification System Embodiments

[1356] Users can configure their notification settings within the app to receive notifications for specific areas or crime types, and the server will then send an alert to the user when the conditions are met.

[1357] For example, if a user sets up notifications for the risk of car theft in a particular area, the server monitors the predicted results of car theft in that area and, when the risk increases, sends a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[1358] Specific example explanation

[1359] 1. Data Collection:

[1360] The server collects new crime reports from crime prevention maps and social media.

[1361] For example, the server uses web scraping technology to retrieve information about reported car thefts in a particular area.

[1362] 2. Data Analysis:

[1363] The server preprocesses the collected data and inputs it into a machine learning model to predict crime for the next week.

[1364] For example, the server might use an LSTM model to predict the likelihood of an increase in car thefts in a particular area.

[1365] 3. Conversational AI systems:

[1366] Using the app, users can ask the AI ​​questions such as, "There have been a lot of car thefts in this area recently. Please tell me what to do."

[1367] The server analyzes the question and responds, "We recommend installing surveillance cameras and an alarm system."

[1368] 4. Emotion Engine:

[1369] The user types, "Recently, I've been afraid to walk on the street at night."

[1370] The server uses an emotion engine to recognize the user's anxiety and suggests countermeasures to reassure them, such as "Patrols are increasing. We also recommend that you carry a safety alarm."

[1371] 5. Notification system:

[1372] Users can set up car theft alerts in the app.

[1373] When the risk of car theft increases, the server sends a notification to the user saying, "There is a high risk of car theft for the next week."

[1374] As a result, the system according to the present invention can not only provide new crime predictions and countermeasures to help citizens live in peace, but also respond in a detailed manner according to the user's emotions.

[1375] The processing flow will be explained below.

[1376] Specific processing flow of the embodiment

[1377] Step 1: Start collecting data

[1378] The server will start the data collection process at the specified time interval (e.g. every hour).

[1379] Step 2: Accessing the Data Source

[1380] The server uses web scraping technology and API calls to access multiple data sources on the Internet, such as crime prevention maps, car theft information bureaus, and social media.

[1381] Step 3: Collecting criminal information

[1382] The server retrieves the latest crime report data from each data source.

[1383] Example: The server retrieves the latest information on crime prevention maps and uses social media APIs to collect posts containing specific keywords such as "car theft" or "stalking."

[1384] Step 4: Data Preprocessing

[1385] The server cleanses the collected data, completing missing data, eliminating duplicate data, and tokenizing text data.

[1386] Step 5: Perform crime predictions

[1387] The server uses a machine learning algorithm (e.g., LSTM model) to analyze the preprocessed data and make crime predictions for the coming week.

[1388] Step 6: Save the prediction results

[1389] The server stores the generated crime prediction results in a database.

[1390] Step 7: User Inquiry Processing

[1391] Users access the conversational AI system through a dedicated app or web portal.

[1392] Users input their questions or concerns into the chatbot interface. For example, they might type, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?"

[1393] Step 8: Parsing User Input

[1394] The server receives the user's input and analyzes it using natural language processing (NLP) techniques.

[1395] The server tokenizes the user's question and classifies it into the appropriate category (e.g., bicycle theft).

[1396] Step 9: Sentiment Analysis

[1397] The server uses an emotion engine to parse emotions from the user's input text.

[1398] Example: If a user inputs "I've been scared to walk on the street at night recently," the server will use the emotion engine to detect "anxiety."

[1399] Step 10: Generate emotion-based responses

[1400] The server generates more appropriate countermeasures based on the emotions recognized by the emotion engine.

[1401] Example: If the user is feeling anxious, the server may suggest reassuring measures such as, "There are increased patrols in the area. We also recommend that you carry a safety alarm."

[1402] Step 11: Provide your answers

[1403] The server presents specific countermeasures to the user based on the analyzed crime prediction data and the results of the emotion engine.

[1404] Example: The server provides the user with an answer such as "We recommend installing a bicycle lock with an alarm" via a chatbot.

[1405] Step 12: Establish notification settings

[1406] Users can configure notification settings within the app for specific areas and crime types.

[1407] Example: A user sets up notifications for car theft.

[1408] Step 13: Monitor notification conditions

[1409] The server generates notifications based on the configured notification conditions, if applicable.

[1410] Example: When the risk of car theft increases in a particular area, the server generates a notification saying, "There is a high risk of car theft in your area for the next week."

[1411] Step 14: Sending notifications

[1412] The server sends the generated notification to the user.

[1413] Users receive notifications and can take action, for example by tightening the security of their parking spot.

[1414] Through these steps, the system of the present invention can recognize the user's emotions, predict crime in real time, and provide specific countermeasures, thereby creating an environment in which users can live with greater peace of mind.

[1415] Example 2

[1416] 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."

[1417] In recent years, crime has been increasing, especially in urban areas, requiring a rapid and effective response. Currently, crime information is not collected or analyzed in real time, which often results in delayed preventative measures. It is also difficult to respond appropriately to users' feelings of anxiety and fear. For this reason, there is a need for a system that combines the rapid collection and analysis of crime information, the provision of effective preventative measures, and a response that responds to users' feelings.

[1418] 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.

[1419] In this invention, the server includes: means for collecting crime information in real time from multiple data sources on the Internet; means for preprocessing the collected crime information; means for predicting crime occurrences for the next week using a machine learning model based on the preprocessed crime information; means for accepting questions from users and analyzing them using natural language processing technology; emotion engine means for recognizing emotions from user input text and generating a response based on the results; interactive artificial intelligence system means for proposing consultation responses and specific countermeasures to the user based on the predictions; and means for notifying the user of the predictions and consultation response results. This enables the rapid collection, analysis, and prediction of crime information, and also enables detailed responses tailored to the user's emotions.

[1420] The "Internet" is an information and communications network that interconnects computer networks around the world.

[1421] A "data source" is a source of data from which information is collected.

[1422] "Crime information" refers to specific information about the location, time, and circumstances of a crime.

[1423] "Collection" is the act of obtaining necessary data from multiple data sources on the Internet.

[1424] "Preprocessing" is the act of filling in gaps in collected data, eliminating duplicates, and converting it into an analyzable format.

[1425] A "machine learning model" is an algorithm that learns patterns from past data and makes predictions about unknown data.

[1426] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1427] An "emotion engine" is a system that recognizes emotions from the user's input text and generates an appropriate response based on the results.

[1428] An "interactive artificial intelligence system" is an artificial intelligence system that interacts with users and proposes appropriate responses and solutions to their questions and inquiries.

[1429] "Notification" refers to the act of conveying information such as prediction results and countermeasures from the system to the user.

[1430] "Crime prediction" is the process of predicting in which areas crimes are likely to occur in the future based on collected crime information.

[1431] "Users" are people who use this system.

[1432] This invention combines a system that collects local crime information in real time and predicts crimes one week in advance with an emotion engine that recognizes the user's emotions. This system operates in cooperation with three parties: a server, a terminal, and the user.

[1433] Hardware and Software Configuration

[1434] The server is a high-performance computer system that collects and analyzes data, runs crime prediction models, and generates answers to user questions. The server is implemented using software such as Python, TensorFlow, and NLP libraries.

[1435] The terminal is a device used by the user, such as a smartphone or computer, that provides an interface for accessing the system through a dedicated application or a web portal. The terminal operates as a browser application or a native application and communicates with the server.

[1436] Users are people who use the system and check crime information, ask questions, and ask for advice through their terminals.

[1437] Examples of data collection

[1438] The server collects the latest crime information from data sources such as crime prevention maps, car theft information bureaus, and social media. Specifically, the server runs a script every hour to check each data source for new crime reports. For example, it checks the latest status of the crime prevention map and retrieves newly reported crime information from it. At the same time, the server uses the social media API to collect posts containing specific keywords such as "car theft" and "stalking."

[1439] Specific examples of data analysis

[1440] Based on the collected crime information, the server performs data preprocessing, such as filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict crime occurrences over the next week. For example, the server uses an LSTM model trained using crime data from the past year. By inputting newly collected data into this model, it can predict the likelihood of crimes occurring in a specific area over the next week.

[1441] Examples of conversational AI systems

[1442] Users access the conversational AI system through a dedicated app or web portal. The user opens the app and uses the chatbot interface to input a question or inquiry. For example, they might ask, "I've heard there have been a lot of bicycle thefts in my neighborhood recently. Are there any safety measures?" This input is processed by the server. The server analyzes the user's message using natural language processing (NLP) technology to understand the question. Based on the results of the analysis, the server then provides the user with appropriate crime prediction data and specific countermeasures. For example, the server might respond, "We recommend installing a bicycle lock with an alarm."

[1443] Examples of emotion engines

[1444] When a user asks a question or asks for advice through the conversational AI system, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions (e.g., anxiety, anger, sadness, etc.) from the user's input text and adjusts the system's response based on the results. For example, if a user inputs, "I've been afraid to walk the streets at night lately," the emotion engine detects "anxiety." Based on this, the server suggests countermeasures to make users feel more secure. It provides specific measures such as, "If you feel anxious, there have been increased patrols in this area. We also recommend that you carry a safety alarm."

[1445] Example of a notification system

[1446] Users can set up notifications within the app to receive notifications for specific areas or crime types. The server will then send alerts to users based on the set conditions. For example, if a user sets up notifications for the risk of car theft in a specific area, the server will monitor predicted car thefts in that area and, if the risk increases, send a notification saying, "There is a high risk of car theft in your area for the next week. Please be careful when parking, especially at night."

[1447] The system of this invention not only rapidly collects and analyzes crime information and provides users with appropriate countermeasures, but also enables detailed responses that reflect the user's emotions, thereby providing new crime prediction and countermeasures that will allow citizens to live in peace.

[1448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1449] Step 1: Data collection

[1450] The server collects real-time crime information from multiple data sources on the Internet (such as crime prevention maps, car theft information stations, and social media). The input is the public APIs and web pages of the data sources. The server runs a script every hour to check each data source for new crime reports.

[1451] What it does: The server uses a Python script to access a crime prevention map to retrieve new crime report data, and calls social media APIs to search for posts containing specific keywords like "car theft" or "stalking," and collects the results. The output is the collected raw data.

[1452] Step 2: Data Preprocessing

[1453] The server preprocesses the collected data. The input is the collected raw data, and the output is the preprocessed clean data. Specific data preprocessing includes tokenizing text data, filling in missing data, and removing duplicate data.

[1454] What it does: The server uses NLP libraries to tokenize the text data, imputes missing items using statistical methods, and applies algorithms to detect and eliminate duplicate data, ultimately producing a clean dataset.

[1455] Step 3: Prediction using a crime prediction model

[1456] The server uses the preprocessed data to predict crime occurrences for the next week using an LSTM model. The input is the preprocessed clean data, and the output is the probability of crime occurrence for each area.

[1457] Specific operation: The server uses the TensorFlow library to run an LSTM model trained on crime data from the past year, inputs new data, and calculates the crime probability for each area. The results are then stored in a database.

[1458] Step 4: Accepting user questions

[1459] Users input questions or inquiries into the conversational AI system through a dedicated app or web portal. The input is the text entered by the user, and the output is that text data.

[1460] Specific operation: The user opens the application on their device and types a question into the chatbot interface, such as, "I've heard that bicycle thefts have been increasing recently. Are there any safety measures?"

[1461] Step 5: Analyze user emotions with the emotion engine

[1462] The server analyzes the user's input text and recognizes the user's emotions using an emotion engine. The input is text data from the user, and the output is the emotion analysis result (e.g., anxiety, fear, etc.).

[1463] How it works: The server uses NLP technology to analyze the user's input text and uses an emotion engine to identify emotions such as "anxiety" or "fear." It then adjusts the response based on the results of this emotion analysis.

[1464] Step 6: Generate response and send notification

[1465] The server responds to users based on crime prediction data and sentiment analysis results, and sends notifications as needed. The input is sentiment analysis results and crime prediction data, and the output is a response text or notification message to the user.

[1466] Specific operation: The server notifies the user through the chatbot of specific countermeasures, such as "We recommend installing a bicycle lock with an alarm." Also, when the risk of car theft increases in a specific area, it sends a notification to the app saying, "The risk of car theft is high in your area for the next week. Please be especially careful when parking at night."

[1467] Through these processing steps, the system not only quickly collects and analyzes crime information and provides users with appropriate countermeasures, but also provides detailed responses that reflect the user's emotions.

[1468] (Application example 2)

[1469] 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."

[1470] In modern society, ensuring safety and security in areas where crime is frequent or difficult to predict is an important issue. However, conventional crime prediction systems lack the ability to collect real-time data or propose countermeasures based on user sentiment, limiting their ability to provide more effective crime prevention measures. Furthermore, notification systems for users are inadequate, and a means of effectively communicating risk is needed.

[1471] 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.

[1472] In this invention, the server includes means for collecting event information in real time from multiple data sources on the Internet, means for analyzing the collected event information and predicting event occurrences for the next week, an interactive AI system for responding to inquiries from users and proposing specific countermeasures based on the predictions, means for proposing countermeasures to users based on the prediction results and emotion analysis results, and means for notifying users of the prediction results. This makes it possible to collect crime information in real time and propose appropriate crime prevention countermeasures taking into account the user's emotions.

[1473] "Event Information" refers to data about crimes and other significant events that occur in an area.

[1474] "Analysis" is the process of processing collected data and extracting meaning and trends.

[1475] "Prediction" is the estimation of the probability of future events occurring based on data obtained through analysis.

[1476] An "interactive artificial intelligence system" is a system that converses with users using natural language and proposes appropriate measures in response to questions or inquiries.

[1477] "Sentiment analysis" is a technique that processes user input text to determine the content and intensity of emotions.

[1478] "Proposal" means showing specific actions or measures to the user based on analyzed data and prediction results.

[1479] "Notification" refers to sending information from the system to the user to inform them of important events or risks.

[1480] "Harvesting" is the act of gathering necessary data from multiple data sources on the Internet.

[1481] "Web scraping" is the technique of automatically extracting information from websites.

[1482] "Application Program Interface Call" is a method of obtaining data using the API provided by the data source.

[1483] A "machine learning model" is an algorithm trained using historical data and used to predict future events.

[1484] The present invention is a system that collects local crime information in real time and provides users with crime predictions for the next week and countermeasures based on emotion analysis. Specific embodiments of the system of the present invention are described below.

[1485] Data collection methods

[1486] The server collects event information from multiple data sources on the Internet. Specifically, it uses web scraping technology and application program interface (API) calls to automatically obtain data from crime prevention maps, social media, etc. The server runs a script every hour to obtain new event information.

[1487] Data Analysis Methods

[1488] Based on the collected event information, the server performs data preprocessing. This preprocessing includes filling in missing data, eliminating duplicate data, and tokenizing text data. The server then uses an LSTM (long short-term memory) model to predict event occurrences for the next week. This prediction model uses a machine learning model trained using data from the past year.

[1489] Interactive artificial intelligence system means

[1490] Users access the conversational artificial intelligence system through a dedicated app or web portal. When a user opens the app and uses the chatbot interface to input a question or inquiry, the server analyzes the input using natural language processing technology. Based on the analysis results, the server suggests appropriate countermeasures to the user. For example, in response to a question such as, "There have been a lot of car thefts in this area recently. What countermeasures should I take?" the server might respond, "I recommend installing surveillance cameras and an alarm system."

[1491] Suggestion method based on emotion analysis

[1492] The server performs sentiment analysis on the text entered by the user to recognize the user's emotions. Sentiment analysis is performed using natural language processing technologies such as SentimentIntensityAnalyzer. Based on the results of the sentiment analysis, the system suggests countermeasures that will give the user a greater sense of security. For example, if a user enters, "I've been afraid to walk the streets at night recently," the system will suggest specific countermeasures, such as, "Patrols have increased. I also recommend that you carry a safety alarm."

[1493] Notification means

[1494] The server notifies the user of predicted event information based on the notification conditions set by the user within the app. For example, if an alert is set for the risk of car theft in a specific area, the server monitors the predicted results of car theft and sends a notification saying, "The risk of car theft is high for the next week" when the risk increases.

[1495] Specific example explanation

[1496] For example:

[1497] Data collection:

[1498] The server collects new incident information from crime prevention maps and social media, for example, using web scraping technology to obtain information on reported car thefts in a specific area.

[1499] User input and interactive AI system response:

[1500] User: "There have been a lot of car thefts in this area recently. What can I do about it?"

[1501] Server: "I recommend installing security cameras and an alarm system."

[1502] User sentiment analysis and suggestions:

[1503] User: "I've been scared to walk the streets at night lately."

[1504] Server: "Patrols have been increased. We also recommend carrying a safety alarm."

[1505] In this way, the system of the present invention can provide more effective crime prevention measures by suggesting appropriate countermeasures to users while performing emotion analysis based on event information collected in real time.

[1506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1507] Step 1:

[1508] The server collects event information from multiple data sources on the Internet.

[1509] Input: The server runs a script to retrieve information from data sources such as security maps and social media.

[1510] Output: Raw data of new event information is collected.

[1511] Specific operation: The server uses web scraping technology and API calls to obtain the reported data from each data source. This operation is performed periodically (e.g., every hour).

[1512] Step 2:

[1513] The server pre-processes the collected event information.

[1514] Input: Raw data collected.

[1515] Output: Preprocessed data.

[1516] What it does: The server imputes missing values ​​in the data, removes duplicates, and tokenizes the text data, converting it into a format suitable for input into machine learning models.

[1517] Step 3:

[1518] The server uses the preprocessed data to predict the occurrence of an event.

[1519] Input: Preprocessed data.

[1520] Output: Predicted events for the next week.

[1521] How it works: The server uses the LSTM model to combine past data with newly collected data to make predictions, and provides prediction results for specific regions and event types.

[1522] Step 4:

[1523] The server responds to user questions and inquiries through an interactive artificial intelligence system.

[1524] Input: Questions or inquiries entered by the user through the app.

[1525] Output: Appropriate action or suggestion.

[1526] Specific actions: The server uses natural language processing technology to analyze the user's input and proposes the best countermeasure based on the prediction results. For example, it provides the user with specific countermeasures such as "installing surveillance cameras."

[1527] Step 5:

[1528] The server performs sentiment analysis and makes suggestions based on the user's emotions.

[1529] Input: Text that the user types into the app.

[1530] Output: Sentiment analysis results and corresponding countermeasures.

[1531] Specific operation: The server uses SentimentIntensityAnalyzer to obtain the user's emotion score, and based on the result, makes suggestions to make the user feel more secure. For example, it may make a suggestion such as "We recommend that you carry a safety alarm."

[1532] Step 6:

[1533] The server notifies the user of the prediction results.

[1534] Input: Notification conditions set by the user and event occurrence prediction results.

[1535] Output: The notification sent to the user.

[1536] Specific operation: The server monitors the notification conditions set by the user in the app and automatically sends a notification when a prediction result that matches the conditions is found. For example, a notification stating "There is a high risk of car theft" is sent via email or app notification.

[1537] The above are the processing steps of the system of the present invention, which makes it possible to collect event information in real time, perform emotion analysis, and propose appropriate countermeasures to the user.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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).

[1545] 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.

[1546] 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."

[1547] 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.

[1548] 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).

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] The following is further disclosed regarding the above embodiment.

[1560] (Claim 1)

[1561] A means of collecting crime information in real time from multiple data sources on the Internet;

[1562] A method for analyzing collected crime information and predicting crime occurrences for the next week,

[1563] An interactive AI system means for proposing consultation responses and specific measures to the user based on the prediction;

[1564] means for notifying a user of the prediction result;

[1565] A system including:

[1566] (Claim 2)

[1567] The system of claim 1 , wherein the collecting means includes web scraping and API calls.

[1568] (Claim 3)

[1569] The system of claim 1 , wherein the analysis means uses a machine learning model.

[1570] "Example 1"

[1571] (Claim 1)

[1572] A means of collecting crime information in real time from multiple data sources on the Internet;

[1573] A method for preprocessing the collected crime information and predicting crime occurrences for the next week.

[1574] An interactive AI system means for proposing consultation responses and specific measures to the user based on the prediction;

[1575] means for notifying a user of the prediction result;

[1576] A system including:

[1577] (Claim 2)

[1578] The system of claim 1 , wherein the collecting means includes web scraping and API calls.

[1579] (Claim 3)

[1580] The system of claim 1 , wherein the analysis means includes means for predicting crimes using a machine learning model.

[1581] "Application Example 1"

[1582] (Claim 1)

[1583] A means of collecting crime information in real time from multiple data sources on the Internet;

[1584] A method for analyzing collected crime information and predicting crime occurrences for the next week,

[1585] An interactive AI system means for proposing consultation responses and specific measures to the user based on the prediction;

[1586] means for notifying a user of the prediction result;

[1587] A means to be installed on a smartphone or robot to notify users of prediction results for multiple areas and send alerts for specific areas or crime types;

[1588] A system including:

[1589] (Claim 2)

[1590] The system of claim 1 , wherein the collecting means includes web scraping and API calls.

[1591] (Claim 3)

[1592] The system of claim 1 , wherein the analysis means uses a machine learning model.

[1593] "Example 2: Combining Emotion Engines"

[1594] (Claim 1)

[1595] A means of collecting crime information in real time from multiple data sources on the Internet;

[1596] a means for pre-processing the collected criminal information;

[1597] A method for predicting crime occurrences in the coming week using a machine learning model based on preprocessed crime information;

[1598] A means for accepting questions from users and analyzing them using natural language processing technology;

[1599] an emotion engine means for recognizing emotions from a user's input text and generating a response based on the recognition result;

[1600] an interactive artificial intelligence system means for proposing consultation responses and specific measures to the user based on the prediction;

[1601] means for notifying the user of the prediction result and the consultation response result;

[1602] A system including:

[1603] (Claim 2)

[1604] 10. The system of claim 1, wherein the means for collecting includes data collection techniques and application programming interface calls.

[1605] (Claim 3)

[1606] 2. The system of claim 1, wherein the analysis means uses a generative AI model.

[1607] "Application example 2 when combining emotion engines"

[1608] (Claim 1)

[1609] a means for collecting event information in real time from multiple data sources on the Internet;

[1610] A means of analyzing the collected event information and predicting the occurrence of events in the next week,

[1611] an interactive artificial intelligence system means for proposing consultation responses and specific measures to the user based on the prediction;

[1612] means for suggesting measures to a user based on the prediction result and the emotion analysis result;

[1613] means for notifying a user of the prediction result;

[1614] A system including:

[1615] (Claim 2)

[1616] The system of claim 1 , wherein the collecting means includes web scraping and application program interface calls.

[1617] (Claim 3)

[1618] 10. The system of claim 1, wherein the analyzing means uses machine learning models and natural language processing techniques. [Explanation of symbols]

[1619] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting crime information in real time from multiple data sources on the Internet; A method for analyzing collected crime information and predicting crime occurrences for the next week, An interactive AI system means for proposing consultation responses and specific measures to the user based on the prediction; means for notifying a user of the prediction result; A system including:

2. The system of claim 1 , wherein the means for collecting includes web scraping and API calls.

3. The system of claim 1 , wherein the analysis means uses a machine learning model.

Images