system

Abstract

Provide a system. 【Solution means】 Means for collecting real estate data in the neighboring area online, Means for cleaning and normalizing real estate data, Based on the cleaned and normalized real estate data, calculate the average unit price m 2 Means for calculating, Average unit price m 2 Means for estimating an appropriate rent based on the unit price, Means for generating the estimation result in a report format, Means for visually presenting the report, A system including the above.

Description

[Technical Field]

[0001] The technology disclosed herein relates to a system. [Background technology]

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, comprising the steps of: receiving a user utterance; adding the user utterance to a prompt that includes instructions relating to a description of the chatbot's character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 [Overview of the Initiative] [Problems that the invention aims to solve]

[0004] Traditional base station rent negotiations required manually collecting and analyzing nearby real estate data, which was time-consuming and labor-intensive, and also lacked the accuracy and consistency of fair rent prices. Furthermore, generating data-driven negotiation materials during rent negotiations was difficult, making it challenging to ensure price consistency nationwide. A system is needed to solve these problems and support efficient and accurate rent negotiations. [Means for solving the problem]

[0005] This invention collects neighborhood property data online, cleans and normalizes it, and then averages it. 2The system provides a method for calculating unit prices. Furthermore, it includes means for estimating appropriate rents based on collected data and generating and visually presenting the results in a report format. It also includes means for integrating and analyzing collected real estate data to calculate appropriate rents using multiple data points, and for displaying simulation results to support users in more concrete rent negotiations. This system is expected to enable efficient and accurate rent negotiations and improve price consistency nationwide.

[0006] "Neighborhood real estate data" refers to information about real estate in a specific area, including bicycle parking spaces. 2 This data includes per unit price, officially announced price, and land price.

[0007] "Methods of collecting data online" refer to methods of obtaining data in real time or periodically using the internet, such as API calls and web scraping techniques.

[0008] "Cleaning and normalization methods" refer to methods for removing incomplete or abnormal data from collected real estate data and for unifying data recorded in different formats or units.

[0009] "Average m 2 The "means of calculating unit price" refers to the method of calculating the unit price of real estate within a specific area based on cleaned and normalized data. 2 This is a method for calculating the average price per unit.

[0010] "Methods for estimating appropriate rent" refers to the average m 2 This method uses unit prices to derive appropriate rents for existing stations as numerical values, and may include integrated analysis and weighting.

[0011] "Methods for generating in report format" refer to methods for organizing calculation results and creating reports that are visually easy to understand using text, graphs, charts, etc.

[0012] "Means of visual presentation" refers to methods for displaying generated reports in a format that is easy for users to access, such as on screens or in printed materials.

[0013] "Integrated analysis" is a method for obtaining advanced analytical results by combining and analyzing multiple collected data points, and may include machine learning and statistical analysis.

[0014] "Means of supporting rent negotiations" refer to specific support tools and functions that assist in rent negotiations with existing station owners, based on calculation results and simulation data. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0016] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0017] First, let's explain the terminology used in the following explanation.

[0018] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0019] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following describes the program's processing.

[0037] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0038] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0039] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0040] Next, the server estimates an appropriate rent using the calculated average m 2 unit price. In this process, by integrating multiple data points and performing weighting, a more accurate estimate becomes possible. Statistical analysis or machine learning algorithms may also be used for estimating the appropriate rent.

[0041] After obtaining the estimated result, the terminal generates a detailed report based on it. This report describes not only the estimated result but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts for visual presentation of the data.

[0042] Finally, these reports are visually provided to the user. The user can conduct rent negotiations with the existing station owner based on the generated report. A simulation function is also incorporated in the report, enabling comparison of appropriate rents under different scenarios.

[0043] As a specific example, consider the case where an existing station owner requests a rent increase in a certain area. The server collects data on parking lots, publicized prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average m 2 unit price, and the server estimates the appropriate rent based on it. For example, if the average m 2 unit price is 5,000 yen, the publicized price is 100,000 yen / m 2 and the land price is 200,000 yen / m 2 , the server integrates these data and calculates the appropriate rent to be 50,000 yen per month. The terminal generates the result in report format and provides it to the user. The user can conduct negotiations with the owner based on this report and proceed with reliable negotiations based on the data.

[0044] It is expected that this system will achieve increased business efficiency in rent negotiations and price consistency across the country.

[0045] The processing flow will be described below.

[0046] Step 1:

[0047] The server collects data online regarding nearby bicycle parking and real estate in the target area. It uses API calls and web scraping to retrieve necessary data from public databases and real estate information websites.

[0048] Step 2:

[0049] The server stores the collected data in a database. The data stored includes the m 2 Includes attributes such as unit price, officially announced price, and land value.

[0050] Step 3:

[0051] The terminal retrieves data collected from the database and performs cleaning. Specifically, it detects missing or outlier values ​​and either fills them in or deletes them.

[0052] Step 4:

[0053] The device normalizes the cleaned data. For example, m recorded in different units. 2 Convert unit price and land price data to a unified scale.

[0054] Step 5:

[0055] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. This involves summing the values ​​of each data point and dividing by the number of data points.

[0056] Step 6:

[0057] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. We apply the estimation model using integrated analysis and weighting algorithms.

[0058] Step 7:

[0059] The server compiles the estimated appropriate rent into a detailed report. The report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0060] Step 8:

[0061] The terminal visually presents the generated report to the user. The user interface is designed to display data in a simple and easy-to-understand manner.

[0062] Step 9:

[0063] Users negotiate rent with existing station owners based on the report. They use specific scenarios for rent increases or decreases based on the data provided in the report to negotiate.

[0064] Step 10:

[0065] When a user enters the results of a negotiation into the system, the negotiation data is saved in a database. This makes it possible to use it as reference data for future negotiations.

[0066] Through these steps, this system can streamline rent negotiations and ensure price consistency across the country.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] Currently, there is a lack of adequate methods for calculating appropriate rents based on real estate information in neighboring areas and for efficiently conducting rent negotiations. This results in excessive effort in real estate management and raises concerns about the fairness and reliability of rents. Furthermore, ensuring the quality and reliability of collected data, as well as presenting the data visually, remain challenges.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for collecting real estate information for neighboring areas online, means for processing and normalizing the real estate information, and means for calculating the price per square meter based on the processed and normalized real estate information. This enables the rapid and accurate estimation of appropriate real estate rates and rent negotiations based on reliable data.

[0072] "Real estate information" refers to data related to land and buildings, including information such as their price, land value, officially announced price, and rent.

[0073] "Methods of collecting information online" refer to methods of obtaining necessary information from APIs or public databases via the internet.

[0074] "Data processing" is the process of removing unnecessary parts from acquired data and supplementing missing data.

[0075] "Normalization methods" are methods for converting data recorded in different formats or units into a consistent format or unit.

[0076] "Price per square meter" refers to a value that indicates the price per unit area of ​​the target area.

[0077] "Fair property rates" refer to fair and reasonable rents calculated based on market and area data.

[0078] "Methods of generating in report format" refer to methods of compiling calculation results and analysis results into a document, including visual elements (graphs and charts).

[0079] "Visual presentation methods" refer to ways of displaying the results of calculations and analyses in a format that is easy for users to understand, and are provided through web browsers and applications.

[0080] "Integrated analysis" is the process of integrating multiple data points and performing a comprehensive analysis.

[0081] "Simulation results" refer to the results showing estimated rents under different scenarios and conditions.

[0082] "Means to support price negotiation" refer to tools and functions that enable users to negotiate rent efficiently and effectively based on data.

[0083] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following details an embodiment of this system.

[0084] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. The server issues API calls to gather data on bicycle parking lots. 2 This involves obtaining specific data such as unit prices, officially announced prices, and land values. The APIs and databases used include publicly available APIs on the internet and government-published databases.

[0085] Next, the terminal cleans and normalizes the acquired data. This process uses data processing libraries such as Python's pandas and NumPy. First, the terminal detects missing and outlier values ​​and removes or imputes them. Then, it converts the information obtained from different data sources into a unified format and units.

[0086] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 The unit price is calculated. Specifically, the terminal extracts the necessary data from the database and calculates the average using basic statistical methods. For example, the m of the target area 2 Calculate the average unit price.

[0087] Next, the server calculates the average m 2 We will use unit prices to estimate appropriate rent. This process will utilize statistical analysis tools such as Python's scikit-learn and machine learning algorithms. The server is m 2 By integrating unit prices, official land prices, and other data points, and weighting these data points, more accurate estimates can be made.

[0088] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes visual elements such as graphs and charts created using Python's matplotlib and Seaborn.

[0089] Finally, these reports are presented to the user visually. The terminal displays the reports in a web browser or dedicated application, and the user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing users to compare appropriate rents under different scenarios.

[0090] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0091] An example of a prompt message would be: "Please collect data on bicycle parking and real estate prices in this area, estimate appropriate rents, and generate a report."

[0092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0093] Program processing steps

[0094] Step 1:

[0095] Data collection

[0096] The server collects data on nearby bicycle parking lots and real estate in the target area online. Inputs include the target area and the API or public database endpoints to be used. Specifically, the server sends an API request and receives the returned data in JSON format. The output is a dataset containing real estate data.

[0097] Step 2:

[0098] Data cleaning and normalization

[0099] The terminal cleans and normalizes the collected dataset. The input is the collected raw data, and the output is clean and normalized data. Specifically, the terminal uses pandas and NumPy to impute missing values, remove outliers, and standardize the data format.

[0100] Step 3:

[0101] average m 2 Calculation of unit price

[0102] The device uses clean and normalized data to calculate the average m for the target area. 2 Calculate the unit price. The input is organized real estate data, and the output is the calculated average price per square meter. 2 This is the unit price. Specifically, the terminal uses statistical methods to calculate the price. 2 Calculate the average unit price.

[0103] Step 4:

[0104] Estimation of appropriate rent

[0105] The server calculated average m 2 Based on the unit price, we will estimate the appropriate rent. The input is the average m 2 The data consists of unit prices and other price data (official land prices, land prices, etc.), and the output is an estimated appropriate rent. Specifically, it uses Python's scikit-learn to integrate multiple data points and perform the estimation.

[0106] Step 5:

[0107] Report generation

[0108] The terminal generates a detailed report based on the calculation results. The input is the calculated appropriate rent and the data used, and the output is a detailed report. Specifically, the terminal uses matplotlib and Seaborn to generate visual elements (graphs and charts) and creates a report that includes these elements.

[0109] Step 6:

[0110] Display the report

[0111] The terminal visually presents the generated reports to the user. Input is a detailed report, and output is a report viewable by the user. Specifically, the terminal displays the reports using a web browser or dedicated application, making them easily accessible to the user. Furthermore, users can use the simulation function to compare rental rates under different scenarios.

[0112] (Application Example 1)

[0113] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] In recent years, with the rise in security awareness, particularly in urban areas, there has been a growing need to understand local safety visually and through data. However, traditional methods require manually collecting and analyzing security-related data such as neighborhood crime rates and police patrol frequency, which is time-consuming and labor-intensive. Furthermore, there has been a lack of integrated tools for formulating appropriate crime prevention measures based on this data, making it difficult to implement crime prevention measures based on high-quality information.

[0115] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0116] In this invention, the server includes means for collecting security data from neighboring areas online, means for cleaning and normalizing the security data, and means for calculating the level of security based on the cleaned and normalized security data. This automates the entire process from data collection to analysis and reporting, enabling the development of crime prevention measures based on high-quality data. Furthermore, users can visually review the generated reports and take more appropriate measures based on the simulation results of crime prevention measures.

[0117] "Security data" refers to information related to local safety, such as crime rates in neighboring areas and the frequency of police patrols.

[0118] "Cleaning" is the process of removing missing or outlier values ​​from collected security data to improve data quality.

[0119] "Normalization" is the process of converting security data obtained from different data sources into a unified format and units, making comparative analysis easier.

[0120] "Safety level" is a numerical representation of local safety based on cleaned and normalized security data.

[0121] "Crime prevention measures" refer to public safety and crime prevention measures planned and implemented based on the level of safety in the area.

[0122] "Methods for calculation" refer to methods for performing necessary calculations based on collected data to determine appropriate countermeasures and values.

[0123] A "report" is a document that includes reports, graphs, charts, and other elements used to visually present calculation results.

[0124] "Means of visual presentation" refers to display methods and devices that provide reports and analysis results to users in an easy-to-understand format.

[0125] "Integrated analysis" is the process of analyzing multiple security data points together to derive a comprehensive view.

[0126] "Simulation results" show hypothetical outcomes of implementing security measures and are used by users to evaluate the effectiveness of those measures in advance.

[0127] This invention is a system that visually and data-drivenly assesses the safety of a neighborhood and proposes appropriate crime prevention measures. This system automates the collection, cleaning, and normalization of security data, as well as the calculation of safety levels, in order to evaluate safety.

[0128] The main components of the system are as follows:

[0129] 1. Data acquisition methods

[0130] The server uses an API to collect local security data online. This security data includes things like crime rates and police patrol frequency. This allows users to get up-to-date safety information in real time.

[0131] 2. Data cleaning and normalization measures

[0132] The server cleans the collected security data by removing missing and outlier values. Next, it normalizes the data into a unified format and units so that integrated analysis can be performed. The Python library Pandas is used in this process.

[0133] 3. Safety degree calculation method

[0134] The server quantifies safety based on cleaned and normalized data. For example, it scores areas with lower crime rates as having a higher safety rating. Python and its statistical analysis libraries are used at this stage as well.

[0135] 4. Methods for estimating crime prevention measures

[0136] The server calculates appropriate security measures based on the level of security. This process may utilize statistical analysis and machine learning algorithms. This allows users to implement effective, data-driven security measures.

[0137] 5. Report generation and visual presentation methods

[0138] The server generates a detailed report based on the calculation results and provides it to the user via the terminal. The report includes visually easy-to-understand graphs and charts. This uses the Python library Matplotlib.

[0139] By using these methods, the server enables users to quickly and accurately understand the safety of their neighborhood and take effective crime prevention measures.

[0140] As a concrete example, we will generate a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data used will be crime rates and police patrol frequency, and the report will include graphs and charts. Below are examples of prompts for the generating AI model:

[0141] Please create a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data to be used should be crime rates and police patrol frequency. The report should also include graphs and charts.

[0142] Based on this prompt, users will be able to easily run the system and conduct a detailed assessment of the safety of their surrounding area.

[0143] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0144] Step 1:

[0145] The server collects security data for the surrounding area. Specifically, it obtains data such as local crime rates and police patrol frequency online via an API. In this process, the raw data obtained from the API is used as input, and the collected dataset is output.

[0146] Step 2:

[0147] The server cleans and normalizes the collected security data. Specifically, it uses the Python Pandas library to remove missing and outlier values, improving data quality. It also converts data from different data sources into a unified format and units. The input here is the collected dataset, and the output is the cleaned and normalized dataset.

[0148] Step 3:

[0149] The server calculates safety scores based on cleaned and normalized data. Specifically, it scales the crime rate and assigns a safety score on a scale from 1 to 0. For example, it scores areas where the crime rate is lower as the safety score increases. The input here is a cleaned and normalized dataset, and the output is the safety score for each area.

[0150] Step 4:

[0151] The server estimates appropriate security measures based on the level of security. Using statistical analysis and machine learning algorithms, it proposes optimal security measures and generates estimated results based on those proposals. The input here is the security score, and the output is the estimated result of appropriate security measures.

[0152] Step 5:

[0153] The server generates the calculation results in report format and sends them to the terminal. Specifically, it uses the Matplotlib library in Python to create graphs and charts, producing a visually easy-to-understand report. In this process, the calculation results are the input, and the generated report is the output.

[0154] Step 6:

[0155] The terminal visually presents the generated report to the user. Specifically, it displays the report on the terminal screen to make it easy for the user to understand. The input for this step is the generated report, and the output is the displayed report.

[0156] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0157] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, this system dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0158] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0159] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0160] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0161] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0162] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0163] The emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how reports are presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report will be presented.

[0164] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggestion helps users conduct rent negotiations more effectively.

[0165] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[0166] This system is expected to streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine will enhance the effectiveness of negotiations and improve user satisfaction.

[0167] The following describes the processing flow.

[0168] Step 1:

[0169] The server collects data online regarding nearby bicycle parking lots and real estate in the target area. Specifically, it issues API calls to retrieve data from public databases and real estate information websites. 2 Obtain data such as unit price, officially announced price, and land price.

[0170] Step 2:

[0171] The server stores the collected data in a database. This storage process also involves tagging the data and adding metadata.

[0172] Step 3:

[0173] The terminal retrieves data collected from the database and performs cleaning. For example, it detects missing or outlier values ​​and either fills in or deletes those data points.

[0174] Step 4:

[0175] The terminal normalizes the cleaned data. This is the process of unifying data recorded in different formats and units, m 2 Standardize unit prices and land price information to the same unit.

[0176] Step 5:

[0177] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. Specifically, the m of each data point. 2 The average is calculated by summing the unit prices and dividing by the number of data points.

[0178] Step 6:

[0179] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. This process uses integrated analysis and weighted algorithms, and applies numerical models.

[0180] Step 7:

[0181] The server compiles the estimated appropriate rent into a detailed report. This report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0182] Step 8:

[0183] The emotion engine recognizes the user's emotional state. For example, it analyzes facial expressions and voice through a webcam and microphone to determine the user's stress level and emotional state.

[0184] Step 9:

[0185] The device dynamically changes how reports are presented to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the report will be presented in a concise and intuitive format.

[0186] Step 10:

[0187] The emotion engine analyzes the user's emotional data and suggests the optimal timing and method for rent negotiations. It recommends negotiating when the user is relaxed or in a positive emotional state.

[0188] Step 11:

[0189] The terminal visually presents the generated report to the user. The user interface displays the data in an easy-to-understand format, allowing users to grasp the information necessary for negotiations at a glance.

[0190] Step 12:

[0191] Based on the report, users negotiate rent with existing station owners. They also consider the suggestions from the emotion engine to select the optimal negotiation timing and method.

[0192] Step 13:

[0193] Users enter the negotiation results into the system, and the negotiation data is stored in a database. In the future, this data will be used as reference data for future negotiations and setting rental rates for other base stations.

[0194] By following these steps, the system can streamline rent negotiations and provide effective, emotion-based support, thereby increasing the success rate of negotiations.

[0195] (Example 2)

[0196] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0197] Conventional rental estimate systems based on real estate data have limitations in the accuracy of the collected data and the calculation of appropriate rents, and also lack sufficient report presentation and rental negotiation support considering the emotional state of the user. Therefore, there is a need for a new system that can achieve more accurate rental estimates, reports considering the emotional state of the user, and negotiation support.

[0198] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0199] In this invention, the server includes means for online collecting real estate data of neighboring areas, means for cleaning and normalizing the real estate data, means for calculating an average unit price based on the cleaned and normalized real estate data, means for estimating an appropriate rent based on the average unit price, means for generating the estimation result in a report format, means for visually presenting the report, means for recognizing the emotional state of the user and dynamically changing the presentation method of the report, and means for analyzing the emotional state of the user and proposing an optimal timing and method for rent negotiation. Thereby, more accurate rent estimation and rental negotiation support with high user satisfaction can be achieved.

[0200] The "real estate data of neighboring areas" is a general term for data such as prices, unit prices, public notice prices, and land prices of real estate within the designated area. 2 Unit price, public notice price, land price, etc.

[0201] "Online collection" refers to an automatic data acquisition process that uses APIs and public databases via the Internet.

[0202] "Cleaning" is a data preprocessing method for removing missing values and outliers from data to enhance reliability.

[0203] "Normalization" is a process of converting information obtained from different data sources into a unified format and unit.

[0204] "Average unit price" refers to the average price per unit of real estate calculated based on cleaning and normalized real estate data. 2 It indicates the price per unit.

[0205] "Appropriate rent" is the appropriate rental price of real estate calculated using statistical analysis and machine learning algorithms based on the collected data.

[0206] "Generated in report form" means creating a document that visually represents information including trial calculation results, used data sources, and analysis methods in text, graphs, charts, etc.

[0207] "Visually presented" means displaying the generated report in a form that is easy for users to understand.

[0208] "User's emotional state" refers to what indicates the user's current psychological state obtained using wearable devices, sentiment analysis software, etc.

[0209] "Dynamically changed" means optimizing the presentation method of the report in real time according to the situation and conditions.

[0210] "Optimal timing and method for rent negotiation" refers to the most suitable timing and means for conducting rent negotiation proposed based on the user's sentiment analysis.

[0211] The system of this invention collects online real estate data of neighboring areas, calculates the appropriate rent based on it, generates a report, and visually presents it. Also, by incorporating an emotion engine, it has the function of dynamically changing the presentation method of the report according to the user's emotional state and proposing the optimal timing and method during rent negotiation.

[0212] First, the server collects nearby real estate data for the target area online. This collection is done automatically using APIs and public databases. The software used includes, for example, the Python requests library. It issues API calls to obtain data on parking lots, etc. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0213] Next, the terminal cleans and normalizes the acquired data. This process includes data preprocessing to remove missing and outlier values. Software used includes, for example, pandas in Python. Normalization transforms information obtained from different data sources into a unified format and units.

[0214] After the data is cleaned and normalized, the terminal calculates the average unit price based on that data. This is done using, for example, the statistical functions of pandas. By calculating the average unit price, it is possible to understand the general property prices in the target area.

[0215] Next, the server uses the calculated average unit price to estimate a fair rent. This process integrates and weights multiple data points to enable a more accurate estimate. Statistical analysis and machine learning algorithms, such as scikit-learn, are also used to estimate the fair rent.

[0216] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data. Specific examples include using Python's matplotlib and seaborn libraries.

[0217] Next, the emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how the report is presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report is presented. The emotion engine can be implemented using, for example, emotion analysis software or wearable devices.

[0218] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggests that the user can conduct rent negotiations more effectively. For example, it might suggest negotiating during less stressful times or periods.

[0219] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average unit price, and the server uses that to estimate a fair rent. For example, if the average unit price is 5,000 yen and the publicly announced land price is 100,000 yen / m² 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[0220] Examples of prompts for generative AI models:

[0221] "Please describe the detailed process flow of a system that, when a rent increase is requested, calculates a fair rent, and provides a report and negotiation support that takes into account the user's emotional state."

[0222] This system enables the improvement of the business efficiency of rent negotiations and price consistency across the country. Additionally, the introduction of the emotion engine is expected to further enhance the negotiation effect and improve user satisfaction.

[0223] The flow of the specific process in Example 2 will be described using FIG. 13.

[0224] Step 1:

[0225] The server collects real estate data in neighboring areas online.

[0226] Input: Specification of the target area (e.g., latitude and longitude or area name)

[0227] Specific operations:

[0228] The server sets an API endpoint (e.g., http: / / api.example.com / realestate_data).

[0229] [[ID=w28]]Using the requests library, request data with requests.get(endpoint_url).

[0230] After the request, parse the obtained data in JSON format using response.json(). <e

[0231] Output: The collected real estate data (in JSON format)

[0232] Step 2:

[0233] The terminal cleans and normalizes the obtained real estate data.

[0234] Input: The real estate data (in JSON format) collected in Step 1

[0235] Specific operations:

[0236] We use the pandas library and check for missing values ​​using data.isnull().sum().

[0237] Remove missing values ​​using data.dropna().

[0238] Statistical methods (such as z-scores) are used to detect outliers, and these are removed using `data = data[(data.zscore() < 3)]`.

[0239] To unify the units of price, perform the conversion_rate operation: data['price'] = data['price']

[0240] Output: Cleaned and normalized real estate data (in DataFrame format)

[0241] Step 3:

[0242] The device calculates the average unit price based on cleaned and normalized data.

[0243] Input: Real estate data (in DataFrame format) cleaned and normalized in Step 2.

[0244] Specific actions:

[0245] Using the statistical functions of the pandas library, we get m 2 Calculate the average unit price.

[0246] Output: Average unit price (numerical value)

[0247] Step 4:

[0248] The server estimates a fair rent based on the calculated average unit price.

[0249] Input: Average unit price (numerical value) calculated in Step 3

[0250] Specific actions:

[0251] We will use the scikit-learn library to apply a LinearRegression model to the training data.

[0252] The model is trained using `model.fit(X_train, y_train)`, and the appropriate rent is predicted using `model.predict(X_test)`.

[0253] Output: Estimated appropriate rent (numerical value)

[0254] Step 5:

[0255] The terminal generates a detailed report based on the calculation results.

[0256] Input: The appropriate rent (numerical value) calculated in Step 4.

[0257] Specific actions:

[0258] Create report templates in HTML or PDF format using a template engine (e.g., Jinja2).

[0259] Use `template.render(data)` to insert data into the template.

[0260] We use the matplotlib and seaborn libraries to generate graphs and charts.

[0261] Output: Detailed report (HTML or PDF format)

[0262] Step 6:

[0263] The emotion engine recognizes the user's emotional state and provides that data to the system.

[0264] Input: Real-time user sentiment data (e.g., obtained from a wearable device)

[0265] Specific actions:

[0266] We will use emotion analysis software to analyze the collected emotion data.

[0267] Send the analysis results to the terminal.

[0268] Output: User's emotional state (data format)

[0269] Step 7:

[0270] The device dynamically changes how reports are presented based on the user's emotional state, using emotional data obtained from the emotion engine.

[0271] Input: User's emotional state obtained from Step 6 (data format), detailed report generated in Step 5 (HTML or PDF format)

[0272] Specific actions:

[0273] If a user is experiencing stress, the displayed items in the report will be limited to make it more concise.

[0274] You can limit the items displayed by using the conditional branching function of the template engine, for example (e.g., {% if stress_level > threshold %} brief information {% else %} detailed information {% endif %}).

[0275] Output: Dynamically modified report (HTML or PDF format)

[0276] Step 8:

[0277] The device analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations.

[0278] Input: User's emotional state obtained from Step 6 (data format)

[0279] Specific actions:

[0280] Based on user sentiment data, notifications are sent to display information at the appropriate time (e.g., suggesting less stressful times).

[0281] Generate a notification such as, "The best time to negotiate is next Monday morning."

[0282] Output: Suggestions (notifications) regarding the timing and method of rent negotiations.

[0283] (Application Example 2)

[0284] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0285] Conventional rent estimation systems based on real estate data only estimated appropriate rents and generated and presented reports, failing to support rent negotiations while considering the user's emotional state. This resulted in significant psychological burden on users during rent negotiations, making it difficult to determine the optimal timing and method of negotiation. Furthermore, the fixed visual presentation method prevented flexible responses tailored to the user's understanding and circumstances. This invention aims to solve these problems and provide more effective support for rent negotiations.

[0286] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting real estate data of neighboring areas online, means for cleaning and normalizing the real estate data, and means for averaging m based on the cleaned and normalized real estate data. 2 Methods for calculating the unit price, and average m 2This includes means for calculating appropriate rent based on unit prices, means for generating the calculation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables optimal rent negotiation support tailored to the user's emotional state.

[0287] "Neighborhood real estate data" refers to diverse information about real estate acquired within a specific area.

[0288] "Means of collecting data online" refers to technologies or processes for automatically acquiring data via the internet.

[0289] "Cleaning and normalization methods" are techniques for removing missing or outlier values ​​from collected data and for standardizing data formats and units.

[0290] "Average m 2 The "means of calculating unit price" refers to the process of calculating the average property price per square meter in a specific area based on cleaned and normalized data.

[0291] "Methods for estimating appropriate rent" refers to the average m 2 This is a technique for calculating appropriate rent in a given area based on unit prices and other relevant data.

[0292] "Methods for generating calculation results in report format" refers to methods for generating reports that visually summarize the calculated data in an easy-to-understand manner.

[0293] "Means of visually presenting reports" refers to the process of presenting generated reports to users using visual elements such as graphs and charts.

[0294] "Means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data" refers to a technology that uses emotional recognition technology to analyze the user's emotions and appropriately changes the report presentation method according to the results.

[0295] "Emotional data" refers to data that indicates a user's emotional state, expressing psychological conditions such as stress, joy, and anxiety using numerical values ​​and categories.

[0296] An "emotion engine" is a technology or software that analyzes a user's emotional state in real time and performs various processes based on that information.

[0297] "A means of analyzing the user's emotional state and proposing the optimal timing and method for rent negotiation" refers to a technology that uses user emotional data to propose the optimal timing and method for conducting rent negotiations more effectively.

[0298] "Rent negotiation" refers to the process in real estate lease agreements where the tenant and landlord negotiate the rent.

[0299] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on this data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0300] The server has the means to collect data online about nearby real estate in the target area using APIs and public databases. This means is a technology for automatically retrieving data over the internet, specifically by using HTTP requests to retrieve data from APIs.

[0301] Next, the terminal has means to cleanse and normalize the acquired data. This process removes missing and outlier values ​​from the collected data and converts information obtained from different data sources into a unified format and units. Specifically, it uses Python libraries such as pandas, numpy, and scikit-learn.

[0302] Based on cleaned and normalized data, the terminals average m 2 The unit price is calculated. This allows us to calculate the average property price per square meter in a specific area. Furthermore, this average m 2 Using unit prices as basic data, the server has a means to estimate appropriate rent. This means may involve the use of statistical analysis or machine learning algorithms.

[0303] After the calculation results are obtained, the terminal has the means to generate a detailed report. This report includes graphs and charts, and describes the data sources and analysis methods used in addition to the calculation results. Specifically, it generates graphs using matplotlib.

[0304] The emotion engine has a means of recognizing the user's emotional state and providing that data to the system. This allows the terminal to dynamically change how reports are presented based on the user's emotional data. For example, if the user is feeling stressed, a more concise and easy-to-understand report format will be presented.

[0305] Furthermore, the emotion engine analyzes the user's emotional state and has the means to suggest the optimal timing and method for rent negotiations. This provides support to help users conduct more effective rent negotiations.

[0306] Specific example

[0307] For example, when collecting real estate data for Shibuya Ward and estimating appropriate rent, the server collects data using an API, and the terminal cleans and normalizes the data using Python libraries. Then, it calculates the appropriate rent and generates a report using matplotlib. The emotion engine analyzes the user's emotional state, presents a concise report if they are experiencing stress, and suggests the optimal timing for negotiation.

[0308] Example of a prompt:

[0309] "Collect real estate data for neighboring areas of Shibuya Ward and use that data to estimate appropriate rents. Also, provide a concise report if user ID 12345 is experiencing stress, and generate and provide a detailed report if they are not."

[0310] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0311] Step 1:

[0312] The server collects real estate data for the surrounding area online. Specifically, it uses API calls to retrieve real estate price information for a specified area from public databases and real estate-related data providers on the internet. 2 The system acquires data such as unit price, officially published price, and land value. This allows for the acquisition of detailed real estate information for the target area as input data. The output is real estate information as raw data.

[0313] Step 2:

[0314] The terminal cleanses and normalizes the real estate data received from the server. First, it uses the pandas library to organize the data and detect and remove missing and outlier values. Next, it uses the scikit-learn StandardScaler class to convert data from different data sources into a unified format and units. This ensures that the input data (raw data) is output as cleaned and normalized data.

[0315] Step 3:

[0316] The device uses cleansed and normalized data to calculate the average m 2 Calculate the unit price. Specifically, use the numpy library to calculate the m in the dataset. 2 Calculate the average unit price. The input for this step is cleaned and normalized real estate data, and the output is the average unit price m 2 This is the result of the unit price calculation.

[0317] Step 4:

[0318] The server calculated the average m 2 Based on the unit price, we estimate the appropriate rent. We integrate various data points and apply weighting, applying statistical analysis and machine learning algorithms as needed. For example, we use linear regression to predict the appropriate rent. The input for this step is average m 2 Based on the unit price and other relevant data, the output is the estimated appropriate rent.

[0319] Step 5:

[0320] The terminal generates calculation results in a report format, creating a visually easy-to-understand report. It uses the matplotlib library to generate graphs and charts, and also describes the calculation results, the data sources used, and the analysis methods. The input for this step is the calculated appropriate rent and data sources, and the output is a detailed report.

[0321] Step 6:

[0322] The emotion engine recognizes the user's emotional state and provides that data to the system. Emotion recognition technology is used to analyze the user's emotional state (stress, joy, anxiety, etc.) in real time. For example, facial expressions and voice analysis are used. The input for this step is emotional data from the user, and the output is the analyzed emotional state data.

[0323] Step 7:

[0324] The device dynamically changes how reports are presented based on emotional data obtained from the emotion engine, according to the user's emotional state. For example, if the user is stressed, the report is changed to a concise and easy-to-understand format. The input for this step is emotional state data and the generated report, and the output is the dynamically modified report presented to the user.

[0325] Step 8:

[0326] The emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. It recommends the time when the user can negotiate most relaxed and effectively, and presents effective negotiation strategies. The input for this step is emotional state data, and the output is the suggested content.

[0327] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0328] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0329] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0330] [Second Embodiment]

[0331] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0332] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0333] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0334] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0335] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0336] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0337] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0338] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0339] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0340] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0341] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0342] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0343] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following describes the program's processing.

[0344] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0345] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0346] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0347] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0348] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0349] Finally, these reports are presented to the user visually. The user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing for comparison of appropriate rents under different scenarios.

[0350] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0351] This system is expected to streamline rent negotiations and ensure price consistency across the country.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server collects data online regarding nearby bicycle parking and real estate in the target area. It uses API calls and web scraping to retrieve necessary data from public databases and real estate information websites.

[0355] Step 2:

[0356] The server stores the collected data in a database. The data stored includes the m 2 Includes attributes such as unit price, officially announced price, and land value.

[0357] Step 3:

[0358] The terminal retrieves data collected from the database and performs cleaning. Specifically, it detects missing or outlier values ​​and either fills them in or deletes them.

[0359] Step 4:

[0360] The device normalizes the cleaned data. For example, m recorded in different units. 2 Convert unit price and land price data to a unified scale.

[0361] Step 5:

[0362] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. This involves summing the values ​​of each data point and dividing by the number of data points.

[0363] Step 6:

[0364] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. We apply the estimation model using integrated analysis and weighting algorithms.

[0365] Step 7:

[0366] The server compiles the estimated appropriate rent into a detailed report. The report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0367] Step 8:

[0368] The terminal visually presents the generated report to the user. The user interface is designed to display data in a simple and easy-to-understand manner.

[0369] Step 9:

[0370] Users negotiate rent with existing station owners based on the report. They use specific scenarios for rent increases or decreases based on the data provided in the report to negotiate.

[0371] Step 10:

[0372] When a user enters the results of a negotiation into the system, the negotiation data is saved in a database. This makes it possible to use it as reference data for future negotiations.

[0373] Through these steps, this system can streamline rent negotiations and ensure price consistency across the country.

[0374] (Example 1)

[0375] Next, we will describe Example 1. 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."

[0376] Currently, there is a lack of adequate methods for calculating appropriate rents based on real estate information in neighboring areas and for efficiently conducting rent negotiations. This results in excessive effort in real estate management and raises concerns about the fairness and reliability of rents. Furthermore, ensuring the quality and reliability of collected data, as well as presenting the data visually, remain challenges.

[0377] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0378] In this invention, the server includes means for collecting real estate information for neighboring areas online, means for processing and normalizing the real estate information, and means for calculating the price per square meter based on the processed and normalized real estate information. This enables the rapid and accurate estimation of appropriate real estate rates and rent negotiations based on reliable data.

[0379] "Real estate information" refers to data related to land and buildings, including information such as their price, land value, officially announced price, and rent.

[0380] "Methods of collecting information online" refer to methods of obtaining necessary information from APIs or public databases via the internet.

[0381] "Data processing" is the process of removing unnecessary parts from acquired data and supplementing missing data.

[0382] "Normalization methods" are methods for converting data recorded in different formats or units into a consistent format or unit.

[0383] "Price per square meter" refers to a value that indicates the price per unit area of ​​the target area.

[0384] "Fair property rates" refer to fair and reasonable rents calculated based on market and area data.

[0385] "Methods of generating in report format" refer to methods of compiling calculation results and analysis results into a document, including visual elements (graphs and charts).

[0386] "Visual presentation methods" refer to ways of displaying the results of calculations and analyses in a format that is easy for users to understand, and are provided through web browsers and applications.

[0387] "Integrated analysis" is the process of integrating multiple data points and performing a comprehensive analysis.

[0388] "Simulation results" refer to the results showing estimated rents under different scenarios and conditions.

[0389] "Means to support price negotiation" refer to tools and functions that enable users to negotiate rent efficiently and effectively based on data.

[0390] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following details an embodiment of this system.

[0391] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. The server issues API calls to gather data on bicycle parking lots. 2 This involves obtaining specific data such as unit prices, officially announced prices, and land values. The APIs and databases used include publicly available APIs on the internet and government-published databases.

[0392] Next, the terminal cleans and normalizes the acquired data. This process uses data processing libraries such as Python's pandas and NumPy. First, the terminal detects missing and outlier values ​​and removes or imputes them. Then, it converts the information obtained from different data sources into a unified format and units.

[0393] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 The unit price is calculated. Specifically, the terminal extracts the necessary data from the database and calculates the average using basic statistical methods. For example, the m of the target area 2 Calculate the average unit price.

[0394] Next, the server calculates the average m 2 We will use unit prices to estimate appropriate rent. This process will utilize statistical analysis tools such as Python's scikit-learn and machine learning algorithms. The server is m 2 By integrating unit prices, official land prices, and other data points, and weighting these data points, more accurate estimates can be made.

[0395] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes visual elements such as graphs and charts created using Python's matplotlib and Seaborn.

[0396] Finally, these reports are presented to the user visually. The terminal displays the reports in a web browser or dedicated application, and the user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing users to compare appropriate rents under different scenarios.

[0397] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0398] An example of a prompt message would be: "Please collect data on bicycle parking and real estate prices in this area, estimate appropriate rents, and generate a report."

[0399] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0400] Program processing steps

[0401] Step 1:

[0402] Data collection

[0403] The server collects data on nearby bicycle parking lots and real estate in the target area online. Inputs include the target area and the API or public database endpoints to be used. Specifically, the server sends an API request and receives the returned data in JSON format. The output is a dataset containing real estate data.

[0404] Step 2:

[0405] Data cleaning and normalization

[0406] The terminal cleans and normalizes the collected dataset. The input is the raw data collected, and the output is the clean and normalized data. As specific operations, the terminal uses pandas and NumPy to complete missing values, remove outliers, and unify data formats.

[0407] Step 3:

[0408] Average m 2 Calculation of unit price

[0409] Based on the clean and normalized data, the terminal calculates the average m of the target area. 2 The input is the organized real estate data, and the output is the calculated average m <00,00087>unit price. As specific operations, the terminal uses statistical methods to calculate the m 2 average value of the unit price.

[0410] Step 4:

[0411] Estimation of appropriate rent

[0412] Based on the calculated average m 2 unit price, the server estimates the appropriate rent. The input is the average m 2 unit price and other price data (public price, land price, etc.), and the output is the estimated appropriate rent. As specific operations, it uses scikit - learn in Python, etc., to integrate multiple data points for estimation.

[0413] Step 5:

[0414] Report generation

[0415] Based on the estimation results, the terminal generates a detailed report. The input is the estimated appropriate rent and the data used, and the output is a detailed report. As specific operations, the terminal uses matplotlib and Seaborn to generate visual elements (graphs and charts), and creates a report including these.

[0416] Step 6:

[0417] Display the report

[0418] The terminal visually presents the generated reports to the user. Input is a detailed report, and output is a report viewable by the user. Specifically, the terminal displays the reports using a web browser or dedicated application, making them easily accessible to the user. Furthermore, users can use the simulation function to compare rental rates under different scenarios.

[0419] (Application Example 1)

[0420] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0421] In recent years, with the rise in security awareness, particularly in urban areas, there has been a growing need to understand local safety visually and through data. However, traditional methods require manually collecting and analyzing security-related data such as neighborhood crime rates and police patrol frequency, which is time-consuming and labor-intensive. Furthermore, there has been a lack of integrated tools for formulating appropriate crime prevention measures based on this data, making it difficult to implement crime prevention measures based on high-quality information.

[0422] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0423] In this invention, the server includes means for collecting security data from neighboring areas online, means for cleaning and normalizing the security data, and means for calculating the level of security based on the cleaned and normalized security data. This automates the entire process from data collection to analysis and reporting, enabling the development of crime prevention measures based on high-quality data. Furthermore, users can visually review the generated reports and take more appropriate measures based on the simulation results of crime prevention measures.

[0424] "Security data" refers to information related to local safety, such as crime rates in neighboring areas and the frequency of police patrols.

[0425] "Cleaning" is the process of removing missing or outlier values ​​from collected security data to improve data quality.

[0426] "Normalization" is the process of converting security data obtained from different data sources into a unified format and units, making comparative analysis easier.

[0427] "Safety level" is a numerical representation of local safety based on cleaned and normalized security data.

[0428] "Crime prevention measures" refer to public safety and crime prevention measures planned and implemented based on the level of safety in the area.

[0429] "Methods for calculation" refer to methods for performing necessary calculations based on collected data to determine appropriate countermeasures and values.

[0430] A "report" is a document that includes reports, graphs, charts, and other elements used to visually present calculation results.

[0431] "Means of visual presentation" refers to display methods and devices that provide reports and analysis results to users in an easy-to-understand format.

[0432] "Integrated analysis" is the process of analyzing multiple security data points together to derive a comprehensive view.

[0433] "Simulation results" show hypothetical outcomes of implementing security measures and are used by users to evaluate the effectiveness of those measures in advance.

[0434] This invention is a system that visually and data-drivenly assesses the safety of a neighborhood and proposes appropriate crime prevention measures. This system automates the collection, cleaning, and normalization of security data, as well as the calculation of safety levels, in order to evaluate safety.

[0435] The main components of the system are as follows:

[0436] 1. Data acquisition methods

[0437] The server uses an API to collect local security data online. This security data includes things like crime rates and police patrol frequency. This allows users to get up-to-date safety information in real time.

[0438] 2. Data cleaning and normalization measures

[0439] The server cleans the collected security data by removing missing and outlier values. Next, it normalizes the data into a unified format and units so that integrated analysis can be performed. The Python library Pandas is used in this process.

[0440] 3. Safety degree calculation method

[0441] The server quantifies safety based on cleaned and normalized data. For example, it scores areas with lower crime rates as having a higher safety rating. Python and its statistical analysis libraries are used at this stage as well.

[0442] 4. Methods for estimating crime prevention measures

[0443] The server calculates appropriate security measures based on the level of security. This process may utilize statistical analysis and machine learning algorithms. This allows users to implement effective, data-driven security measures.

[0444] 5. Report generation and visual presentation methods

[0445] The server generates a detailed report based on the calculation results and provides it to the user via the terminal. The report includes visually easy-to-understand graphs and charts. This uses the Python library Matplotlib.

[0446] By using these methods, the server enables users to quickly and accurately understand the safety of their neighborhood and take effective crime prevention measures.

[0447] As a concrete example, we will generate a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data used will be crime rates and police patrol frequency, and the report will include graphs and charts. Below are examples of prompts for the generating AI model:

[0448] Please create a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data to be used should be crime rates and police patrol frequency. The report should also include graphs and charts.

[0449] Based on this prompt, users will be able to easily run the system and conduct a detailed assessment of the safety of their surrounding area.

[0450] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0451] Step 1:

[0452] The server collects security data for the surrounding area. Specifically, it obtains data such as local crime rates and police patrol frequency online via an API. In this process, the raw data obtained from the API is used as input, and the collected dataset is output.

[0453] Step 2:

[0454] The server cleans and normalizes the collected security data. Specifically, it uses the Python Pandas library to remove missing and outlier values, improving data quality. It also converts data from different data sources into a unified format and units. The input here is the collected dataset, and the output is the cleaned and normalized dataset.

[0455] Step 3:

[0456] The server calculates safety scores based on cleaned and normalized data. Specifically, it scales the crime rate and assigns a safety score on a scale from 1 to 0. For example, it scores areas where the crime rate is lower as the safety score increases. The input here is a cleaned and normalized dataset, and the output is the safety score for each area.

[0457] Step 4:

[0458] The server estimates appropriate security measures based on the level of security. Using statistical analysis and machine learning algorithms, it proposes optimal security measures and generates estimated results based on those proposals. The input here is the security score, and the output is the estimated result of appropriate security measures.

[0459] Step 5:

[0460] The server generates the calculation results in report format and sends them to the terminal. Specifically, it uses the Matplotlib library in Python to create graphs and charts, producing a visually easy-to-understand report. In this process, the calculation results are the input, and the generated report is the output.

[0461] Step 6:

[0462] The terminal visually presents the generated report to the user. Specifically, it displays the report on the terminal screen to make it easy for the user to understand. The input for this step is the generated report, and the output is the displayed report.

[0463] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0464] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, this system dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0465] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0466] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0467] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0468] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0469] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0470] The emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how reports are presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report will be presented.

[0471] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggestion helps users conduct rent negotiations more effectively.

[0472] As a specific example, consider the case where an existing property owner requests a rent increase in a certain area. The server collects data on parking lots, public prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average m 2 unit price, and the server estimates the appropriate rent based on this. For example, if the average m 2 unit price is 5,000 yen, the public price is 100,000 yen / m 2 , and the land price is 200,000 yen / m 2 , the server integrates this data and calculates the appropriate rent to be 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotion, and when the user is feeling stressed, it presents a concise report and further proposes an appropriate timing for negotiation. Based on this report and the proposal, the user can negotiate with the owner and conduct a highly reliable negotiation based on the data.

[0473] It is expected that this system will achieve the improvement of the business efficiency of rent negotiation and price consistency across the country. In addition, the introduction of the emotion engine further enhances the negotiation effect and improves the user's satisfaction.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server collects data on neighboring parking lots and real estate in the target area online. Specifically, it issues an API call to obtain data such as m 2 unit price, public price, and land price from public databases and real estate information sites.

[0477] Step 2:

[0478] The server saves the collected data in the database. This saving process also includes tagging the data and adding metadata.

[0479] Step 3:

[0480] The terminal retrieves data collected from the database and performs cleaning. For example, it detects missing or outlier values ​​and either fills in or deletes those data points.

[0481] Step 4:

[0482] The terminal normalizes the cleaned data. This is the process of unifying data recorded in different formats and units, m 2 Standardize unit prices and land price information to the same unit.

[0483] Step 5:

[0484] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. Specifically, the m of each data point. 2 The average is calculated by summing the unit prices and dividing by the number of data points.

[0485] Step 6:

[0486] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. This process uses integrated analysis and weighted algorithms, and applies numerical models.

[0487] Step 7:

[0488] The server compiles the estimated appropriate rent into a detailed report. This report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0489] Step 8:

[0490] The emotion engine recognizes the user's emotional state. For example, it analyzes facial expressions and voice through a webcam and microphone to determine the user's stress level and emotional state.

[0491] Step 9:

[0492] The device dynamically changes how reports are presented to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the report will be presented in a concise and intuitive format.

[0493] Step 10:

[0494] The emotion engine analyzes the user's emotional data and suggests the optimal timing and method for rent negotiations. It recommends negotiating when the user is relaxed or in a positive emotional state.

[0495] Step 11:

[0496] The terminal visually presents the generated report to the user. The user interface displays the data in an easy-to-understand format, allowing users to grasp the information necessary for negotiations at a glance.

[0497] Step 12:

[0498] Based on the report, users negotiate rent with existing station owners. They also consider the suggestions from the emotion engine to select the optimal negotiation timing and method.

[0499] Step 13:

[0500] Users enter the negotiation results into the system, and the negotiation data is stored in a database. In the future, this data will be used as reference data for future negotiations and setting rental rates for other base stations.

[0501] By following these steps, the system can streamline rent negotiations and provide effective, emotion-based support, thereby increasing the success rate of negotiations.

[0502] (Example 2)

[0503] Next, we will describe Example 2. 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".

[0504] Conventional rent estimation systems based on real estate data have limitations in the accuracy of the collected data and in calculating appropriate rents. Furthermore, they lacked the ability to provide reports that considered the user's emotional state and to adequately support rent negotiations. Therefore, there is a need for a new system that provides more accurate rent estimations and reports and negotiation support that take the user's emotional state into account.

[0505] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0506] In this invention, the server includes means for collecting real estate data for neighboring areas online, means for cleaning and normalizing the real estate data, means for calculating the average unit price based on the cleaned and normalized real estate data, means for estimating an appropriate rent based on the average unit price, means for generating the estimation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the way the report is presented, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables more accurate rent estimation and rent negotiation support that satisfies users.

[0507] "Neighborhood real estate data" refers to the prices of properties within a specified area, m 2 This is a general term for data such as unit price, officially announced price, and land price.

[0508] "Online data collection" refers to the automated process of acquiring data via the internet using APIs and public databases.

[0509] "Cleaning" is a data preprocessing method that removes missing or outlier values ​​from data to improve its reliability.

[0510] "Normalization" is the process of converting information obtained from different data sources into a unified format and units.

[0511] "Average unit price" refers to the average price per square meter of a property, calculated based on cleaning and normalized property data. 2 This indicates the price per unit.

[0512] "Appropriate rent" refers to the fair rental price of real estate, calculated using statistical analysis and machine learning algorithms based on collected data.

[0513] "Generating in report format" means creating a document that visually represents information such as calculation results, data sources used, and analysis methods using text, graphs, charts, and other visual aids.

[0514] "Visual presentation" means displaying the generated report in a way that is easy for the user to understand.

[0515] "User emotional state" refers to the user's current psychological state, as obtained using wearable devices, emotion analysis software, etc.

[0516] "Dynamic modification" means optimizing the way reports are presented in real time according to the situation and conditions.

[0517] "The optimal timing and method for rent negotiation" refers to the most suitable time and means for conducting rent negotiations, as suggested based on user sentiment analysis.

[0518] The system of this invention collects real estate data for the surrounding area online, calculates appropriate rent based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0519] First, the server collects nearby real estate data for the target area online. This collection is done automatically using APIs and public databases. The software used includes, for example, the Python requests library. It issues API calls to obtain data on parking lots, etc. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0520] Next, the terminal cleans and normalizes the acquired data. This process includes data preprocessing to remove missing and outlier values. Software used includes, for example, pandas in Python. Normalization transforms information obtained from different data sources into a unified format and units.

[0521] After the data is cleaned and normalized, the terminal calculates the average unit price based on that data. This is done using, for example, the statistical functions of pandas. By calculating the average unit price, it is possible to understand the general property prices in the target area.

[0522] Next, the server uses the calculated average unit price to estimate a fair rent. This process integrates and weights multiple data points to enable a more accurate estimate. Statistical analysis and machine learning algorithms, such as scikit-learn, are also used to estimate the fair rent.

[0523] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data. Specific examples include using Python's matplotlib and seaborn libraries.

[0524] Next, the emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how the report is presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report is presented. The emotion engine can be implemented using, for example, emotion analysis software or wearable devices.

[0525] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggests that the user can conduct rent negotiations more effectively. For example, it might suggest negotiating during less stressful times or periods.

[0526] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average unit price, and the server uses that to estimate a fair rent. For example, if the average unit price is 5,000 yen and the publicly announced land price is 100,000 yen / m² 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[0527] Examples of prompts for generative AI models:

[0528] "Please describe the detailed process flow of a system that, when a rent increase is requested, calculates a fair rent, and provides a report and negotiation support that takes into account the user's emotional state."

[0529] This system will streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine is expected to further enhance negotiation effectiveness and improve user satisfaction.

[0530] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0531] Step 1:

[0532] The server collects real estate data for the surrounding area online.

[0533] Input: Specify the target area (e.g., latitude and longitude or area name).

[0534] Specific actions:

[0535] The server configures the API endpoint (e.g., http: / / api.example.com / realestate_data).

[0536] The requests library is used to request data using requests.get(endpoint_url).

[0537] After the request is made, the data obtained using response.json() is parsed in JSON format.

[0538] Output: Collected real estate data (JSON format)

[0539] Step 2:

[0540] The device cleans and normalizes the acquired real estate data.

[0541] Input: Real estate data collected in Step 1 (in JSON format)

[0542] Specific actions:

[0543] We use the pandas library and check for missing values ​​using data.isnull().sum().

[0544] Remove missing values ​​using data.dropna().

[0545] Statistical methods (such as z-scores) are used to detect outliers, and these are removed using `data = data[(data.zscore() < 3)]`.

[0546] To unify the units of price, perform the conversion_rate operation: data['price'] = data['price']

[0547] Output: Cleaned and normalized real estate data (in DataFrame format)

[0548] Step 3:

[0549] The device calculates the average unit price based on cleaned and normalized data.

[0550] Input: Real estate data (in DataFrame format) cleaned and normalized in Step 2.

[0551] Specific actions:

[0552] Using the statistical functions of the pandas library, we get m 2 Calculate the average unit price.

[0553] Output: Average unit price (numerical value)

[0554] Step 4:

[0555] The server estimates a fair rent based on the calculated average unit price.

[0556] Input: Average unit price (numerical value) calculated in Step 3

[0557] Specific actions:

[0558] We will use the scikit-learn library to apply a LinearRegression model to the training data.

[0559] The model is trained using `model.fit(X_train, y_train)`, and the appropriate rent is predicted using `model.predict(X_test)`.

[0560] Output: Estimated appropriate rent (numerical value)

[0561] Step 5:

[0562] The terminal generates a detailed report based on the calculation results.

[0563] Input: The appropriate rent (numerical value) calculated in Step 4.

[0564] Specific actions:

[0565] Create report templates in HTML or PDF format using a template engine (e.g., Jinja2).

[0566] Use `template.render(data)` to insert data into the template.

[0567] We use the matplotlib and seaborn libraries to generate graphs and charts.

[0568] Output: Detailed report (HTML or PDF format)

[0569] Step 6:

[0570] The emotion engine recognizes the user's emotional state and provides that data to the system.

[0571] Input: Real-time user sentiment data (e.g., obtained from a wearable device)

[0572] Specific actions:

[0573] We will use emotion analysis software to analyze the collected emotion data.

[0574] Send the analysis results to the terminal.

[0575] Output: User's emotional state (data format)

[0576] Step 7:

[0577] The device dynamically changes how reports are presented based on the user's emotional state, using emotional data obtained from the emotion engine.

[0578] Input: User's emotional state obtained from Step 6 (data format), detailed report generated in Step 5 (HTML or PDF format)

[0579] Specific actions:

[0580] If a user is experiencing stress, the displayed items in the report will be limited to make it more concise.

[0581] You can limit the items displayed by using the conditional branching function of the template engine, for example (e.g., {% if stress_level > threshold %} brief information {% else %} detailed information {% endif %}).

[0582] Output: Dynamically modified report (HTML or PDF format)

[0583] Step 8:

[0584] The device analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations.

[0585] Input: User's emotional state obtained from Step 6 (data format)

[0586] Specific actions:

[0587] Based on user sentiment data, notifications are sent to display information at the appropriate time (e.g., suggesting less stressful times).

[0588] Generate a notification such as, "The best time to negotiate is next Monday morning."

[0589] Output: Suggestions (notifications) regarding the timing and method of rent negotiations.

[0590] (Application Example 2)

[0591] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0592] Conventional rent estimation systems based on real estate data only estimated appropriate rents and generated and presented reports, failing to support rent negotiations while considering the user's emotional state. This resulted in significant psychological burden on users during rent negotiations, making it difficult to determine the optimal timing and method of negotiation. Furthermore, the fixed visual presentation method prevented flexible responses tailored to the user's understanding and circumstances. This invention aims to solve these problems and provide more effective support for rent negotiations.

[0593] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting real estate data of neighboring areas online, means for cleaning and normalizing the real estate data, and means for averaging m based on the cleaned and normalized real estate data. 2 Methods for calculating the unit price, and average m 2 This includes means for calculating appropriate rent based on unit prices, means for generating the calculation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables optimal rent negotiation support tailored to the user's emotional state.

[0594] "Neighborhood real estate data" refers to diverse information about real estate acquired within a specific area.

[0595] "Means of collecting data online" refers to technologies or processes for automatically acquiring data via the internet.

[0596] "Cleaning and normalization methods" are techniques for removing missing or outlier values ​​from collected data and for standardizing data formats and units.

[0597] "Average m 2 The "means of calculating unit price" refers to the process of calculating the average property price per square meter in a specific area based on cleaned and normalized data.

[0598] "Methods for estimating appropriate rent" refers to the average m 2 This is a technique for calculating appropriate rent in a given area based on unit prices and other relevant data.

[0599] "Methods for generating calculation results in report format" refers to methods for generating reports that visually summarize the calculated data in an easy-to-understand manner.

[0600] "Means of visually presenting reports" refers to the process of presenting generated reports to users using visual elements such as graphs and charts.

[0601] "Means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data" refers to a technology that uses emotional recognition technology to analyze the user's emotions and appropriately changes the report presentation method according to the results.

[0602] "Emotional data" refers to data that indicates a user's emotional state, expressing psychological conditions such as stress, joy, and anxiety using numerical values ​​and categories.

[0603] An "emotion engine" is a technology or software that analyzes a user's emotional state in real time and performs various processes based on that information.

[0604] "A means of analyzing the user's emotional state and proposing the optimal timing and method for rent negotiation" refers to a technology that uses user emotional data to propose the optimal timing and method for conducting rent negotiations more effectively.

[0605] "Rent negotiation" refers to the process in real estate lease agreements where the tenant and landlord negotiate the rent.

[0606] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on this data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0607] The server has the means to collect data online about nearby real estate in the target area using APIs and public databases. This means is a technology for automatically retrieving data over the internet, specifically by using HTTP requests to retrieve data from APIs.

[0608] Next, the terminal has means to cleanse and normalize the acquired data. This process removes missing and outlier values ​​from the collected data and converts information obtained from different data sources into a unified format and units. Specifically, it uses Python libraries such as pandas, numpy, and scikit-learn.

[0609] Based on cleaned and normalized data, the terminals average m 2 The unit price is calculated. This allows us to calculate the average property price per square meter in a specific area. Furthermore, this average m 2 Using unit prices as basic data, the server has a means to estimate appropriate rent. This means may involve the use of statistical analysis or machine learning algorithms.

[0610] After the calculation results are obtained, the terminal has the means to generate a detailed report. This report includes graphs and charts, and describes the data sources and analysis methods used in addition to the calculation results. Specifically, it generates graphs using matplotlib.

[0611] The emotion engine has a means of recognizing the user's emotional state and providing that data to the system. This allows the terminal to dynamically change how reports are presented based on the user's emotional data. For example, if the user is feeling stressed, a more concise and easy-to-understand report format will be presented.

[0612] Furthermore, the emotion engine analyzes the user's emotional state and has the means to suggest the optimal timing and method for rent negotiations. This provides support to help users conduct more effective rent negotiations.

[0613] Specific example

[0614] For example, when collecting real estate data for Shibuya Ward and estimating appropriate rent, the server collects data using an API, and the terminal cleans and normalizes the data using Python libraries. Then, it calculates the appropriate rent and generates a report using matplotlib. The emotion engine analyzes the user's emotional state, presents a concise report if they are experiencing stress, and suggests the optimal timing for negotiation.

[0615] Example of a prompt:

[0616] "Collect real estate data for neighboring areas of Shibuya Ward and use that data to estimate appropriate rents. Also, provide a concise report if user ID 12345 is experiencing stress, and generate and provide a detailed report if they are not."

[0617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0618] Step 1:

[0619] The server collects real estate data for the surrounding area online. Specifically, it uses API calls to retrieve real estate price information for a specified area from public databases and real estate-related data providers on the internet. 2 The system acquires data such as unit price, officially published price, and land value. This allows for the acquisition of detailed real estate information for the target area as input data. The output is real estate information as raw data.

[0620] Step 2:

[0621] The terminal cleanses and normalizes the real estate data received from the server. First, it uses the pandas library to organize the data and detect and remove missing and outlier values. Next, it uses the scikit-learn StandardScaler class to convert data from different data sources into a unified format and units. This ensures that the input data (raw data) is output as cleaned and normalized data.

[0622] Step 3:

[0623] The device uses cleansed and normalized data to calculate the average m 2 Calculate the unit price. Specifically, use the numpy library to calculate the m in the dataset. 2 Calculate the average unit price. The input for this step is cleaned and normalized real estate data, and the output is the average unit price m 2 This is the result of the unit price calculation.

[0624] Step 4:

[0625] The server calculated the average m 2 Based on the unit price, we estimate the appropriate rent. We integrate various data points and apply weighting, applying statistical analysis and machine learning algorithms as needed. For example, we use linear regression to predict the appropriate rent. The input for this step is average m 2 Based on the unit price and other relevant data, the output is the estimated appropriate rent.

[0626] Step 5:

[0627] The terminal generates calculation results in a report format, creating a visually easy-to-understand report. It uses the matplotlib library to generate graphs and charts, and also describes the calculation results, the data sources used, and the analysis methods. The input for this step is the calculated appropriate rent and data sources, and the output is a detailed report.

[0628] Step 6:

[0629] The emotion engine recognizes the user's emotional state and provides that data to the system. Emotion recognition technology is used to analyze the user's emotional state (stress, joy, anxiety, etc.) in real time. For example, facial expressions and voice analysis are used. The input for this step is emotional data from the user, and the output is the analyzed emotional state data.

[0630] Step 7:

[0631] The device dynamically changes how reports are presented based on emotional data obtained from the emotion engine, according to the user's emotional state. For example, if the user is stressed, the report is changed to a concise and easy-to-understand format. The input for this step is emotional state data and the generated report, and the output is the dynamically modified report presented to the user.

[0632] Step 8:

[0633] The emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. It recommends the time when the user can negotiate most relaxed and effectively, and presents effective negotiation strategies. The input for this step is emotional state data, and the output is the suggested content.

[0634] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0635] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0636] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0637] [Third Embodiment]

[0638] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0639] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0640] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0641] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0642] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0643] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0644] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0645] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0646] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0647] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0648] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0649] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0650] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following describes the program's processing.

[0651] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0652] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0653] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0654] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0655] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0656] Finally, these reports are presented to the user visually. The user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing for comparison of appropriate rents under different scenarios.

[0657] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0658] This system is expected to streamline rent negotiations and ensure price consistency across the country.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The server collects data online regarding nearby bicycle parking and real estate in the target area. It uses API calls and web scraping to retrieve necessary data from public databases and real estate information websites.

[0662] Step 2:

[0663] The server stores the collected data in a database. The data stored includes the m 2 Includes attributes such as unit price, officially announced price, and land value.

[0664] Step 3:

[0665] The terminal retrieves data collected from the database and performs cleaning. Specifically, it detects missing or outlier values ​​and either fills them in or deletes them.

[0666] Step 4:

[0667] The device normalizes the cleaned data. For example, m recorded in different units. 2 Convert unit price and land price data to a unified scale.

[0668] Step 5:

[0669] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. This involves summing the values ​​of each data point and dividing by the number of data points.

[0670] Step 6:

[0671] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. We apply the estimation model using integrated analysis and weighting algorithms.

[0672] Step 7:

[0673] The server compiles the estimated appropriate rent into a detailed report. The report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0674] Step 8:

[0675] The terminal visually presents the generated report to the user. The user interface is designed to display data in a simple and easy-to-understand manner.

[0676] Step 9:

[0677] Users negotiate rent with existing station owners based on the report. They use specific scenarios for rent increases or decreases based on the data provided in the report to negotiate.

[0678] Step 10:

[0679] When a user enters the results of a negotiation into the system, the negotiation data is saved in a database. This makes it possible to use it as reference data for future negotiations.

[0680] Through these steps, this system can streamline rent negotiations and ensure price consistency across the country.

[0681] (Example 1)

[0682] Next, we will describe Example 1. 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."

[0683] Currently, there is a lack of adequate methods for calculating appropriate rents based on real estate information in neighboring areas and for efficiently conducting rent negotiations. This results in excessive effort in real estate management and raises concerns about the fairness and reliability of rents. Furthermore, ensuring the quality and reliability of collected data, as well as presenting the data visually, remain challenges.

[0684] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0685] In this invention, the server includes means for collecting real estate information for neighboring areas online, means for processing and normalizing the real estate information, and means for calculating the price per square meter based on the processed and normalized real estate information. This enables the rapid and accurate estimation of appropriate real estate rates and rent negotiations based on reliable data.

[0686] "Real estate information" refers to data related to land and buildings, including information such as their price, land value, officially announced price, and rent.

[0687] "Methods of collecting information online" refer to methods of obtaining necessary information from APIs or public databases via the internet.

[0688] "Data processing" is the process of removing unnecessary parts from acquired data and supplementing missing data.

[0689] "Normalization methods" are methods for converting data recorded in different formats or units into a consistent format or unit.

[0690] "Price per square meter" refers to a value that indicates the price per unit area of ​​the target area.

[0691] "Fair property rates" refer to fair and reasonable rents calculated based on market and area data.

[0692] "Methods of generating in report format" refer to methods of compiling calculation results and analysis results into a document, including visual elements (graphs and charts).

[0693] "Visual presentation methods" refer to ways of displaying the results of calculations and analyses in a format that is easy for users to understand, and are provided through web browsers and applications.

[0694] "Integrated analysis" is the process of integrating multiple data points and performing a comprehensive analysis.

[0695] "Simulation results" refer to the results showing estimated rents under different scenarios and conditions.

[0696] "Means to support price negotiation" refer to tools and functions that enable users to negotiate rent efficiently and effectively based on data.

[0697] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following details an embodiment of this system.

[0698] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. The server issues API calls to gather data on bicycle parking lots. 2 This involves obtaining specific data such as unit prices, officially announced prices, and land values. The APIs and databases used include publicly available APIs on the internet and government-published databases.

[0699] Next, the terminal cleans and normalizes the acquired data. This process uses data processing libraries such as Python's pandas and NumPy. First, the terminal detects missing and outlier values ​​and removes or imputes them. Then, it converts the information obtained from different data sources into a unified format and units.

[0700] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 The unit price is calculated. Specifically, the terminal extracts the necessary data from the database and calculates the average using basic statistical methods. For example, the m of the target area 2 Calculate the average unit price.

[0701] Next, the server calculates the average m 2 We will use unit prices to estimate appropriate rent. This process will utilize statistical analysis tools such as Python's scikit-learn and machine learning algorithms. The server is m 2 By integrating unit prices, official land prices, and other data points, and weighting these data points, more accurate estimates can be made.

[0702] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes visual elements such as graphs and charts created using Python's matplotlib and Seaborn.

[0703] Finally, these reports are presented to the user visually. The terminal displays the reports in a web browser or dedicated application, and the user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing users to compare appropriate rents under different scenarios.

[0704] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0705] An example of a prompt message would be: "Please collect data on bicycle parking and real estate prices in this area, estimate appropriate rents, and generate a report."

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Program processing steps

[0708] Step 1:

[0709] Data collection

[0710] The server collects data on nearby bicycle parking lots and real estate in the target area online. Inputs include the target area and the API or public database endpoints to be used. Specifically, the server sends an API request and receives the returned data in JSON format. The output is a dataset containing real estate data.

[0711] Step 2:

[0712] Data cleaning and normalization

[0713] The terminal cleans and normalizes the collected dataset. The input is the collected raw data, and the output is clean and normalized data. Specifically, the terminal uses pandas and NumPy to impute missing values, remove outliers, and standardize the data format.

[0714] Step 3:

[0715] average m 2 Calculation of unit price

[0716] The device uses clean and normalized data to calculate the average m for the target area. 2 Calculate the unit price. The input is organized real estate data, and the output is the calculated average price per square meter. 2 This is the unit price. Specifically, the terminal uses statistical methods to calculate the price. 2 Calculate the average unit price.

[0717] Step 4:

[0718] Estimation of appropriate rent

[0719] The server calculated average m 2 Based on the unit price, we will estimate the appropriate rent. The input is the average m 2 The data consists of unit prices and other price data (official land prices, land prices, etc.), and the output is an estimated appropriate rent. Specifically, it uses Python's scikit-learn to integrate multiple data points and perform the estimation.

[0720] Step 5:

[0721] Report generation

[0722] The terminal generates a detailed report based on the calculation results. The input is the calculated appropriate rent and the data used, and the output is a detailed report. Specifically, the terminal uses matplotlib and Seaborn to generate visual elements (graphs and charts) and creates a report that includes these elements.

[0723] Step 6:

[0724] Display the report

[0725] The terminal visually presents the generated reports to the user. Input is a detailed report, and output is a report viewable by the user. Specifically, the terminal displays the reports using a web browser or dedicated application, making them easily accessible to the user. Furthermore, users can use the simulation function to compare rental rates under different scenarios.

[0726] (Application Example 1)

[0727] Next, we will explain Application Example 1. In the following explanation, 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."

[0728] In recent years, with the rise in security awareness, particularly in urban areas, there has been a growing need to understand local safety visually and through data. However, traditional methods require manually collecting and analyzing security-related data such as neighborhood crime rates and police patrol frequency, which is time-consuming and labor-intensive. Furthermore, there has been a lack of integrated tools for formulating appropriate crime prevention measures based on this data, making it difficult to implement crime prevention measures based on high-quality information.

[0729] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0730] In this invention, the server includes means for collecting security data from neighboring areas online, means for cleaning and normalizing the security data, and means for calculating the level of security based on the cleaned and normalized security data. This automates the entire process from data collection to analysis and reporting, enabling the development of crime prevention measures based on high-quality data. Furthermore, users can visually review the generated reports and take more appropriate measures based on the simulation results of crime prevention measures.

[0731] "Security data" refers to information related to local safety, such as crime rates in neighboring areas and the frequency of police patrols.

[0732] "Cleaning" is the process of removing missing or outlier values ​​from collected security data to improve data quality.

[0733] "Normalization" is the process of converting security data obtained from different data sources into a unified format and units, making comparative analysis easier.

[0734] "Safety level" is a numerical representation of local safety based on cleaned and normalized security data.

[0735] "Crime prevention measures" refer to public safety and crime prevention measures planned and implemented based on the level of safety in the area.

[0736] "Methods for calculation" refer to methods for performing necessary calculations based on collected data to determine appropriate countermeasures and values.

[0737] A "report" is a document that includes reports, graphs, charts, and other elements used to visually present calculation results.

[0738] "Means of visual presentation" refers to display methods and devices that provide reports and analysis results to users in an easy-to-understand format.

[0739] "Integrated analysis" is the process of analyzing multiple security data points together to derive a comprehensive view.

[0740] "Simulation results" show hypothetical outcomes of implementing security measures and are used by users to evaluate the effectiveness of those measures in advance.

[0741] This invention is a system that visually and data-drivenly assesses the safety of a neighborhood and proposes appropriate crime prevention measures. This system automates the collection, cleaning, and normalization of security data, as well as the calculation of safety levels, in order to evaluate safety.

[0742] The main components of the system are as follows:

[0743] 1. Data acquisition methods

[0744] The server uses an API to collect local security data online. This security data includes things like crime rates and police patrol frequency. This allows users to get up-to-date safety information in real time.

[0745] 2. Data cleaning and normalization measures

[0746] The server cleans the collected security data by removing missing and outlier values. Next, it normalizes the data into a unified format and units so that integrated analysis can be performed. The Python library Pandas is used in this process.

[0747] 3. Safety degree calculation method

[0748] The server quantifies safety based on cleaned and normalized data. For example, it scores areas with lower crime rates as having a higher safety rating. Python and its statistical analysis libraries are used at this stage as well.

[0749] 4. Methods for estimating crime prevention measures

[0750] The server calculates appropriate security measures based on the level of security. This process may utilize statistical analysis and machine learning algorithms. This allows users to implement effective, data-driven security measures.

[0751] 5. Report generation and visual presentation methods

[0752] The server generates a detailed report based on the calculation results and provides it to the user via the terminal. The report includes visually easy-to-understand graphs and charts. This uses the Python library Matplotlib.

[0753] By using these methods, the server enables users to quickly and accurately understand the safety of their neighborhood and take effective crime prevention measures.

[0754] As a concrete example, we will generate a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data used will be crime rates and police patrol frequency, and the report will include graphs and charts. Below are examples of prompts for the generating AI model:

[0755] Please create a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data to be used should be crime rates and police patrol frequency. The report should also include graphs and charts.

[0756] Based on this prompt, users will be able to easily run the system and conduct a detailed assessment of the safety of their surrounding area.

[0757] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0758] Step 1:

[0759] The server collects security data for the surrounding area. Specifically, it obtains data such as local crime rates and police patrol frequency online via an API. In this process, the raw data obtained from the API is used as input, and the collected dataset is output.

[0760] Step 2:

[0761] The server cleans and normalizes the collected security data. Specifically, it uses the Python Pandas library to remove missing and outlier values, improving data quality. It also converts data from different data sources into a unified format and units. The input here is the collected dataset, and the output is the cleaned and normalized dataset.

[0762] Step 3:

[0763] The server calculates safety scores based on cleaned and normalized data. Specifically, it scales the crime rate and assigns a safety score on a scale from 1 to 0. For example, it scores areas where the crime rate is lower as the safety score increases. The input here is a cleaned and normalized dataset, and the output is the safety score for each area.

[0764] Step 4:

[0765] The server estimates appropriate security measures based on the level of security. Using statistical analysis and machine learning algorithms, it proposes optimal security measures and generates estimated results based on those proposals. The input here is the security score, and the output is the estimated result of appropriate security measures.

[0766] Step 5:

[0767] The server generates the calculation results in report format and sends them to the terminal. Specifically, it uses the Matplotlib library in Python to create graphs and charts, producing a visually easy-to-understand report. In this process, the calculation results are the input, and the generated report is the output.

[0768] Step 6:

[0769] The terminal visually presents the generated report to the user. Specifically, it displays the report on the terminal screen to make it easy for the user to understand. The input for this step is the generated report, and the output is the displayed report.

[0770] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0771] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, this system dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0772] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0773] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0774] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0775] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0776] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0777] The emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how reports are presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report will be presented.

[0778] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggestion helps users conduct rent negotiations more effectively.

[0779] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[0780] This system is expected to streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine will enhance the effectiveness of negotiations and improve user satisfaction.

[0781] The following describes the processing flow.

[0782] Step 1:

[0783] The server collects data online regarding nearby bicycle parking lots and real estate in the target area. Specifically, it issues API calls to retrieve data from public databases and real estate information websites. 2 Obtain data such as unit price, officially announced price, and land price.

[0784] Step 2:

[0785] The server stores the collected data in a database. This storage process also involves tagging the data and adding metadata.

[0786] Step 3:

[0787] The terminal retrieves data collected from the database and performs cleaning. For example, it detects missing or outlier values ​​and either fills in or deletes those data points.

[0788] Step 4:

[0789] The terminal normalizes the cleaned data. This is the process of unifying data recorded in different formats and units, m 2 Standardize unit prices and land price information to the same unit.

[0790] Step 5:

[0791] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. Specifically, the m of each data point. 2 The average is calculated by summing the unit prices and dividing by the number of data points.

[0792] Step 6:

[0793] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. This process uses integrated analysis and weighted algorithms, and applies numerical models.

[0794] Step 7:

[0795] The server compiles the estimated appropriate rent into a detailed report. This report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0796] Step 8:

[0797] The emotion engine recognizes the user's emotional state. For example, it analyzes facial expressions and voice through a webcam and microphone to determine the user's stress level and emotional state.

[0798] Step 9:

[0799] The device dynamically changes how reports are presented to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the report will be presented in a concise and intuitive format.

[0800] Step 10:

[0801] The emotion engine analyzes the user's emotional data and suggests the optimal timing and method for rent negotiations. It recommends negotiating when the user is relaxed or in a positive emotional state.

[0802] Step 11:

[0803] The terminal visually presents the generated report to the user. The user interface displays the data in an easy-to-understand format, allowing users to grasp the information necessary for negotiations at a glance.

[0804] Step 12:

[0805] Based on the report, users negotiate rent with existing station owners. They also consider the suggestions from the emotion engine to select the optimal negotiation timing and method.

[0806] Step 13:

[0807] Users enter the negotiation results into the system, and the negotiation data is stored in a database. In the future, this data will be used as reference data for future negotiations and setting rental rates for other base stations.

[0808] By following these steps, the system can streamline rent negotiations and provide effective, emotion-based support, thereby increasing the success rate of negotiations.

[0809] (Example 2)

[0810] Next, we will describe Example 2. 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."

[0811] Conventional rent estimation systems based on real estate data have limitations in the accuracy of the collected data and in calculating appropriate rents. Furthermore, they lacked the ability to provide reports that considered the user's emotional state and to adequately support rent negotiations. Therefore, there is a need for a new system that provides more accurate rent estimations and reports and negotiation support that take the user's emotional state into account.

[0812] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0813] In this invention, the server includes means for collecting real estate data for neighboring areas online, means for cleaning and normalizing the real estate data, means for calculating the average unit price based on the cleaned and normalized real estate data, means for estimating an appropriate rent based on the average unit price, means for generating the estimation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the way the report is presented, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables more accurate rent estimation and rent negotiation support that satisfies users.

[0814] "Neighborhood real estate data" refers to the prices of properties within a specified area, m 2 This is a general term for data such as unit price, officially announced price, and land price.

[0815] "Online data collection" refers to the automated process of acquiring data via the internet using APIs and public databases.

[0816] "Cleaning" is a data preprocessing method that removes missing or outlier values ​​from data to improve its reliability.

[0817] "Normalization" is the process of converting information obtained from different data sources into a unified format and units.

[0818] "Average unit price" refers to the average price per square meter of a property, calculated based on cleaning and normalized property data. 2 This indicates the price per unit.

[0819] "Appropriate rent" refers to the fair rental price of real estate, calculated using statistical analysis and machine learning algorithms based on collected data.

[0820] "Generating in report format" means creating a document that visually represents information such as calculation results, data sources used, and analysis methods using text, graphs, charts, and other visual aids.

[0821] "Visual presentation" means displaying the generated report in a way that is easy for the user to understand.

[0822] "User emotional state" refers to the user's current psychological state, as obtained using wearable devices, emotion analysis software, etc.

[0823] "Dynamic modification" means optimizing the way reports are presented in real time according to the situation and conditions.

[0824] "The optimal timing and method for rent negotiation" refers to the most suitable time and means for conducting rent negotiations, as suggested based on user sentiment analysis.

[0825] The system of this invention collects real estate data for the surrounding area online, calculates appropriate rent based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0826] First, the server collects nearby real estate data for the target area online. This collection is done automatically using APIs and public databases. The software used includes, for example, the Python requests library. It issues API calls to obtain data on parking lots, etc. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0827] Next, the terminal cleans and normalizes the acquired data. This process includes data preprocessing to remove missing and outlier values. Software used includes, for example, pandas in Python. Normalization transforms information obtained from different data sources into a unified format and units.

[0828] After the data is cleaned and normalized, the terminal calculates the average unit price based on that data. This is done using, for example, the statistical functions of pandas. By calculating the average unit price, it is possible to understand the general property prices in the target area.

[0829] Next, the server uses the calculated average unit price to estimate a fair rent. This process integrates and weights multiple data points to enable a more accurate estimate. Statistical analysis and machine learning algorithms, such as scikit-learn, are also used to estimate the fair rent.

[0830] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data. Specific examples include using Python's matplotlib and seaborn libraries.

[0831] Next, the emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how the report is presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report is presented. The emotion engine can be implemented using, for example, emotion analysis software or wearable devices.

[0832] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggests that the user can conduct rent negotiations more effectively. For example, it might suggest negotiating during less stressful times or periods.

[0833] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average unit price, and the server uses that to estimate a fair rent. For example, if the average unit price is 5,000 yen and the publicly announced land price is 100,000 yen / m² 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[0834] Examples of prompts for generative AI models:

[0835] "Please describe the detailed process flow of a system that, when a rent increase is requested, calculates a fair rent, and provides a report and negotiation support that takes into account the user's emotional state."

[0836] This system will streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine is expected to further enhance negotiation effectiveness and improve user satisfaction.

[0837] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0838] Step 1:

[0839] The server collects real estate data for the surrounding area online.

[0840] Input: Specify the target area (e.g., latitude and longitude or area name).

[0841] Specific actions:

[0842] The server configures the API endpoint (e.g., http: / / api.example.com / realestate_data).

[0843] The requests library is used to request data using requests.get(endpoint_url).

[0844] After the request is made, the data obtained using response.json() is parsed in JSON format.

[0845] Output: Collected real estate data (JSON format)

[0846] Step 2:

[0847] The device cleans and normalizes the acquired real estate data.

[0848] Input: Real estate data collected in Step 1 (in JSON format)

[0849] Specific actions:

[0850] We use the pandas library and check for missing values ​​using data.isnull().sum().

[0851] Remove missing values ​​using data.dropna().

[0852] Statistical methods (such as z-scores) are used to detect outliers, and these are removed using `data = data[(data.zscore() < 3)]`.

[0853] To unify the units of price, perform the conversion_rate operation: data['price'] = data['price']

[0854] Output: Cleaned and normalized real estate data (in DataFrame format)

[0855] Step 3:

[0856] The device calculates the average unit price based on cleaned and normalized data.

[0857] Input: Real estate data (in DataFrame format) cleaned and normalized in Step 2.

[0858] Specific actions:

[0859] Using the statistical functions of the pandas library, we get m 2 Calculate the average unit price.

[0860] Output: Average unit price (numerical value)

[0861] Step 4:

[0862] The server estimates a fair rent based on the calculated average unit price.

[0863] Input: Average unit price (numerical value) calculated in Step 3

[0864] Specific actions:

[0865] We will use the scikit-learn library to apply a LinearRegression model to the training data.

[0866] The model is trained using `model.fit(X_train, y_train)`, and the appropriate rent is predicted using `model.predict(X_test)`.

[0867] Output: Estimated appropriate rent (numerical value)

[0868] Step 5:

[0869] The terminal generates a detailed report based on the calculation results.

[0870] Input: The appropriate rent (numerical value) calculated in Step 4.

[0871] Specific actions:

[0872] Create report templates in HTML or PDF format using a template engine (e.g., Jinja2).

[0873] Use `template.render(data)` to insert data into the template.

[0874] We use the matplotlib and seaborn libraries to generate graphs and charts.

[0875] Output: Detailed report (HTML or PDF format)

[0876] Step 6:

[0877] The emotion engine recognizes the user's emotional state and provides that data to the system.

[0878] Input: Real-time user sentiment data (e.g., obtained from a wearable device)

[0879] Specific actions:

[0880] We will use emotion analysis software to analyze the collected emotion data.

[0881] Send the analysis results to the terminal.

[0882] Output: User's emotional state (data format)

[0883] Step 7:

[0884] The device dynamically changes how reports are presented based on the user's emotional state, using emotional data obtained from the emotion engine.

[0885] Input: User's emotional state obtained from Step 6 (data format), detailed report generated in Step 5 (HTML or PDF format)

[0886] Specific actions:

[0887] If a user is experiencing stress, the displayed items in the report will be limited to make it more concise.

[0888] You can limit the items displayed by using the conditional branching function of the template engine, for example (e.g., {% if stress_level > threshold %} brief information {% else %} detailed information {% endif %}).

[0889] Output: Dynamically modified report (HTML or PDF format)

[0890] Step 8:

[0891] The device analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations.

[0892] Input: User's emotional state obtained from Step 6 (data format)

[0893] Specific actions:

[0894] Based on user sentiment data, notifications are sent to display information at the appropriate time (e.g., suggesting less stressful times).

[0895] Generate a notification such as, "The best time to negotiate is next Monday morning."

[0896] Output: Suggestions (notifications) regarding the timing and method of rent negotiations.

[0897] (Application Example 2)

[0898] Next, we will explain application example 2. In the following explanation, 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."

[0899] Conventional rent estimation systems based on real estate data only estimated appropriate rents and generated and presented reports, failing to support rent negotiations while considering the user's emotional state. This resulted in significant psychological burden on users during rent negotiations, making it difficult to determine the optimal timing and method of negotiation. Furthermore, the fixed visual presentation method prevented flexible responses tailored to the user's understanding and circumstances. This invention aims to solve these problems and provide more effective support for rent negotiations.

[0900] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting real estate data of neighboring areas online, means for cleaning and normalizing the real estate data, and means for averaging m based on the cleaned and normalized real estate data. 2 Methods for calculating the unit price, and average m 2 This includes means for calculating appropriate rent based on unit prices, means for generating the calculation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables optimal rent negotiation support tailored to the user's emotional state.

[0901] "Neighborhood real estate data" refers to diverse information about real estate acquired within a specific area.

[0902] "Means of collecting data online" refers to technologies or processes for automatically acquiring data via the internet.

[0903] "Cleaning and normalization methods" are techniques for removing missing or outlier values ​​from collected data and for standardizing data formats and units.

[0904] "Average m 2 The "means of calculating unit price" refers to the process of calculating the average property price per square meter in a specific area based on cleaned and normalized data.

[0905] "Methods for estimating appropriate rent" refers to the average m 2 This is a technique for calculating appropriate rent in a given area based on unit prices and other relevant data.

[0906] "Methods for generating calculation results in report format" refers to methods for generating reports that visually summarize the calculated data in an easy-to-understand manner.

[0907] "Means of visually presenting reports" refers to the process of presenting generated reports to users using visual elements such as graphs and charts.

[0908] "Means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data" refers to a technology that uses emotional recognition technology to analyze the user's emotions and appropriately changes the report presentation method according to the results.

[0909] "Emotional data" refers to data that indicates a user's emotional state, expressing psychological conditions such as stress, joy, and anxiety using numerical values ​​and categories.

[0910] An "emotion engine" is a technology or software that analyzes a user's emotional state in real time and performs various processes based on that information.

[0911] "A means of analyzing the user's emotional state and proposing the optimal timing and method for rent negotiation" refers to a technology that uses user emotional data to propose the optimal timing and method for conducting rent negotiations more effectively.

[0912] "Rent negotiation" refers to the process in real estate lease agreements where the tenant and landlord negotiate the rent.

[0913] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on this data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[0914] The server has the means to collect data online about nearby real estate in the target area using APIs and public databases. This means is a technology for automatically retrieving data over the internet, specifically by using HTTP requests to retrieve data from APIs.

[0915] Next, the terminal has means to cleanse and normalize the acquired data. This process removes missing and outlier values ​​from the collected data and converts information obtained from different data sources into a unified format and units. Specifically, it uses Python libraries such as pandas, numpy, and scikit-learn.

[0916] Based on cleaned and normalized data, the terminals average m 2 The unit price is calculated. This allows us to calculate the average property price per square meter in a specific area. Furthermore, this average m 2 Using unit prices as basic data, the server has a means to estimate appropriate rent. This means may involve the use of statistical analysis or machine learning algorithms.

[0917] After the calculation results are obtained, the terminal has the means to generate a detailed report. This report includes graphs and charts, and describes the data sources and analysis methods used in addition to the calculation results. Specifically, it generates graphs using matplotlib.

[0918] The emotion engine has a means of recognizing the user's emotional state and providing that data to the system. This allows the terminal to dynamically change how reports are presented based on the user's emotional data. For example, if the user is feeling stressed, a more concise and easy-to-understand report format will be presented.

[0919] Furthermore, the emotion engine analyzes the user's emotional state and has the means to suggest the optimal timing and method for rent negotiations. This provides support to help users conduct more effective rent negotiations.

[0920] Specific example

[0921] For example, when collecting real estate data for Shibuya Ward and estimating appropriate rent, the server collects data using an API, and the terminal cleans and normalizes the data using Python libraries. Then, it calculates the appropriate rent and generates a report using matplotlib. The emotion engine analyzes the user's emotional state, presents a concise report if they are experiencing stress, and suggests the optimal timing for negotiation.

[0922] Example of a prompt:

[0923] "Collect real estate data for neighboring areas of Shibuya Ward and use that data to estimate appropriate rents. Also, provide a concise report if user ID 12345 is experiencing stress, and generate and provide a detailed report if they are not."

[0924] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0925] Step 1:

[0926] The server collects real estate data for the surrounding area online. Specifically, it uses API calls to retrieve real estate price information for a specified area from public databases and real estate-related data providers on the internet. 2 The system acquires data such as unit price, officially published price, and land value. This allows for the acquisition of detailed real estate information for the target area as input data. The output is real estate information as raw data.

[0927] Step 2:

[0928] The terminal cleanses and normalizes the real estate data received from the server. First, it uses the pandas library to organize the data and detect and remove missing and outlier values. Next, it uses the scikit-learn StandardScaler class to convert data from different data sources into a unified format and units. This ensures that the input data (raw data) is output as cleaned and normalized data.

[0929] Step 3:

[0930] The device uses cleansed and normalized data to calculate the average m 2 Calculate the unit price. Specifically, use the numpy library to calculate the m in the dataset. 2 Calculate the average unit price. The input for this step is cleaned and normalized real estate data, and the output is the average unit price m 2 This is the result of the unit price calculation.

[0931] Step 4:

[0932] The server calculated the average m 2 Based on the unit price, we estimate the appropriate rent. We integrate various data points and apply weighting, applying statistical analysis and machine learning algorithms as needed. For example, we use linear regression to predict the appropriate rent. The input for this step is average m 2 Based on the unit price and other relevant data, the output is the estimated appropriate rent.

[0933] Step 5:

[0934] The terminal generates calculation results in a report format, creating a visually easy-to-understand report. It uses the matplotlib library to generate graphs and charts, and also describes the calculation results, the data sources used, and the analysis methods. The input for this step is the calculated appropriate rent and data sources, and the output is a detailed report.

[0935] Step 6:

[0936] The emotion engine recognizes the user's emotional state and provides that data to the system. Emotion recognition technology is used to analyze the user's emotional state (stress, joy, anxiety, etc.) in real time. For example, facial expressions and voice analysis are used. The input for this step is emotional data from the user, and the output is the analyzed emotional state data.

[0937] Step 7:

[0938] The device dynamically changes how reports are presented based on emotional data obtained from the emotion engine, according to the user's emotional state. For example, if the user is stressed, the report is changed to a concise and easy-to-understand format. The input for this step is emotional state data and the generated report, and the output is the dynamically modified report presented to the user.

[0939] Step 8:

[0940] The emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. It recommends the time when the user can negotiate most relaxed and effectively, and presents effective negotiation strategies. The input for this step is emotional state data, and the output is the suggested content.

[0941] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0942] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0943] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0944] [Fourth Embodiment]

[0945] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0946] As shown in Figure 7, the 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.

[0947] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0948] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0949] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0950] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0951] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0952] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0953] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0954] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0955] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0956] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0957] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0958] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following describes the program's processing.

[0959] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[0960] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[0961] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[0962] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[0963] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[0964] Finally, these reports are presented to the user visually. The user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing for comparison of appropriate rents under different scenarios.

[0965] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[0966] This system is expected to streamline rent negotiations and ensure price consistency across the country.

[0967] The following describes the processing flow.

[0968] Step 1:

[0969] The server collects data online regarding nearby bicycle parking and real estate in the target area. It uses API calls and web scraping to retrieve necessary data from public databases and real estate information websites.

[0970] Step 2:

[0971] The server stores the collected data in a database. The data stored includes the m 2 Includes attributes such as unit price, officially announced price, and land value.

[0972] Step 3:

[0973] The terminal retrieves data collected from the database and performs cleaning. Specifically, it detects missing or outlier values ​​and either fills them in or deletes them.

[0974] Step 4:

[0975] The device normalizes the cleaned data. For example, m recorded in different units. 2 Convert unit price and land price data to a unified scale.

[0976] Step 5:

[0977] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. This involves summing the values ​​of each data point and dividing by the number of data points.

[0978] Step 6:

[0979] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. We apply the estimation model using integrated analysis and weighting algorithms.

[0980] Step 7:

[0981] The server compiles the estimated appropriate rent into a detailed report. The report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[0982] Step 8:

[0983] The terminal visually presents the generated report to the user. The user interface is designed to display data in a simple and easy-to-understand manner.

[0984] Step 9:

[0985] Users negotiate rent with existing station owners based on the report. They use specific scenarios for rent increases or decreases based on the data provided in the report to negotiate.

[0986] Step 10:

[0987] When a user enters the results of a negotiation into the system, the negotiation data is saved in a database. This makes it possible to use it as reference data for future negotiations.

[0988] Through these steps, this system can streamline rent negotiations and ensure price consistency across the country.

[0989] (Example 1)

[0990] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0991] Currently, there is a lack of adequate methods for calculating appropriate rents based on real estate information in neighboring areas and for efficiently conducting rent negotiations. This results in excessive effort in real estate management and raises concerns about the fairness and reliability of rents. Furthermore, ensuring the quality and reliability of collected data, as well as presenting the data visually, remain challenges.

[0992] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0993] In this invention, the server includes means for collecting real estate information for neighboring areas online, means for processing and normalizing the real estate information, and means for calculating the price per square meter based on the processed and normalized real estate information. This enables the rapid and accurate estimation of appropriate real estate rates and rent negotiations based on reliable data.

[0994] "Real estate information" refers to data related to land and buildings, including information such as their price, land value, officially announced price, and rent.

[0995] "Methods of collecting information online" refer to methods of obtaining necessary information from APIs or public databases via the internet.

[0996] "Data processing" is the process of removing unnecessary parts from acquired data and supplementing missing data.

[0997] "Normalization methods" are methods for converting data recorded in different formats or units into a consistent format or unit.

[0998] "Price per square meter" refers to a value that indicates the price per unit area of ​​the target area.

[0999] "Fair property rates" refer to fair and reasonable rents calculated based on market and area data.

[1000] "Methods of generating in report format" refer to methods of compiling calculation results and analysis results into a document, including visual elements (graphs and charts).

[1001] "Visual presentation methods" refer to ways of displaying the results of calculations and analyses in a format that is easy for users to understand, and are provided through web browsers and applications.

[1002] "Integrated analysis" is the process of integrating multiple data points and performing a comprehensive analysis.

[1003] "Simulation results" refer to the results showing estimated rents under different scenarios and conditions.

[1004] "Means to support price negotiation" refer to tools and functions that enable users to negotiate rent efficiently and effectively based on data.

[1005] The system of this invention collects real estate data for neighboring areas online, uses this data to estimate appropriate rents, and generates and visually presents a report. The following details an embodiment of this system.

[1006] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. The server issues API calls to gather data on bicycle parking lots. 2 This involves obtaining specific data such as unit prices, officially announced prices, and land values. The APIs and databases used include publicly available APIs on the internet and government-published databases.

[1007] Next, the terminal cleans and normalizes the acquired data. This process uses data processing libraries such as Python's pandas and NumPy. First, the terminal detects missing and outlier values ​​and removes or imputes them. Then, it converts the information obtained from different data sources into a unified format and units.

[1008] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 The unit price is calculated. Specifically, the terminal extracts the necessary data from the database and calculates the average using basic statistical methods. For example, the m of the target area 2 Calculate the average unit price.

[1009] Next, the server calculates the average m 2 We will use unit prices to estimate appropriate rent. This process will utilize statistical analysis tools such as Python's scikit-learn and machine learning algorithms. The server is m 2 By integrating unit prices, official land prices, and other data points, and weighting these data points, more accurate estimates can be made.

[1010] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes visual elements such as graphs and charts created using Python's matplotlib and Seaborn.

[1011] Finally, these reports are presented to the user visually. The terminal displays the reports in a web browser or dedicated application, and the user can use the generated reports to negotiate rent with existing station owners. The reports also include a simulation function, allowing users to compare appropriate rents under different scenarios.

[1012] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The user can use this report to negotiate with the owner and conduct data-driven, reliable negotiations.

[1013] An example of a prompt message would be: "Please collect data on bicycle parking and real estate prices in this area, estimate appropriate rents, and generate a report."

[1014] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1015] Program processing steps

[1016] Step 1:

[1017] Data collection

[1018] The server collects data on nearby bicycle parking lots and real estate in the target area online. Inputs include the target area and the API or public database endpoints to be used. Specifically, the server sends an API request and receives the returned data in JSON format. The output is a dataset containing real estate data.

[1019] Step 2:

[1020] Data cleaning and normalization

[1021] The terminal cleans and normalizes the collected dataset. The input is the collected raw data, and the output is clean and normalized data. Specifically, the terminal uses pandas and NumPy to impute missing values, remove outliers, and standardize the data format.

[1022] Step 3:

[1023] average m 2 Calculation of unit price

[1024] The device uses clean and normalized data to calculate the average m for the target area. 2 Calculate the unit price. The input is organized real estate data, and the output is the calculated average price per square meter. 2 This is the unit price. Specifically, the terminal uses statistical methods to calculate the price. 2 Calculate the average unit price.

[1025] Step 4:

[1026] Estimation of appropriate rent

[1027] The server calculated average m 2 Based on the unit price, we will estimate the appropriate rent. The input is the average m 2 The data consists of unit prices and other price data (official land prices, land prices, etc.), and the output is an estimated appropriate rent. Specifically, it uses Python's scikit-learn to integrate multiple data points and perform the estimation.

[1028] Step 5:

[1029] Report generation

[1030] The terminal generates a detailed report based on the calculation results. The input is the calculated appropriate rent and the data used, and the output is a detailed report. Specifically, the terminal uses matplotlib and Seaborn to generate visual elements (graphs and charts) and creates a report that includes these elements.

[1031] Step 6:

[1032] Display the report

[1033] The terminal visually presents the generated reports to the user. Input is a detailed report, and output is a report viewable by the user. Specifically, the terminal displays the reports using a web browser or dedicated application, making them easily accessible to the user. Furthermore, users can use the simulation function to compare rental rates under different scenarios.

[1034] (Application Example 1)

[1035] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1036] In recent years, with the rise in security awareness, particularly in urban areas, there has been a growing need to understand local safety visually and through data. However, traditional methods require manually collecting and analyzing security-related data such as neighborhood crime rates and police patrol frequency, which is time-consuming and labor-intensive. Furthermore, there has been a lack of integrated tools for formulating appropriate crime prevention measures based on this data, making it difficult to implement crime prevention measures based on high-quality information.

[1037] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1038] In this invention, the server includes means for collecting security data from neighboring areas online, means for cleaning and normalizing the security data, and means for calculating the level of security based on the cleaned and normalized security data. This automates the entire process from data collection to analysis and reporting, enabling the development of crime prevention measures based on high-quality data. Furthermore, users can visually review the generated reports and take more appropriate measures based on the simulation results of crime prevention measures.

[1039] "Security data" refers to information related to local safety, such as crime rates in neighboring areas and the frequency of police patrols.

[1040] "Cleaning" is the process of removing missing or outlier values ​​from collected security data to improve data quality.

[1041] "Normalization" is the process of converting security data obtained from different data sources into a unified format and units, making comparative analysis easier.

[1042] "Safety level" is a numerical representation of local safety based on cleaned and normalized security data.

[1043] "Crime prevention measures" refer to public safety and crime prevention measures planned and implemented based on the level of safety in the area.

[1044] "Methods for calculation" refer to methods for performing necessary calculations based on collected data to determine appropriate countermeasures and values.

[1045] A "report" is a document that includes reports, graphs, charts, and other elements used to visually present calculation results.

[1046] "Means of visual presentation" refers to display methods and devices that provide reports and analysis results to users in an easy-to-understand format.

[1047] "Integrated analysis" is the process of analyzing multiple security data points together to derive a comprehensive view.

[1048] "Simulation results" show hypothetical outcomes of implementing security measures and are used by users to evaluate the effectiveness of those measures in advance.

[1049] This invention is a system that visually and data-drivenly assesses the safety of a neighborhood and proposes appropriate crime prevention measures. This system automates the collection, cleaning, and normalization of security data, as well as the calculation of safety levels, in order to evaluate safety.

[1050] The main components of the system are as follows:

[1051] 1. Data acquisition methods

[1052] The server uses an API to collect local security data online. This security data includes things like crime rates and police patrol frequency. This allows users to get up-to-date safety information in real time.

[1053] 2. Data cleaning and normalization measures

[1054] The server cleans the collected security data by removing missing and outlier values. Next, it normalizes the data into a unified format and units so that integrated analysis can be performed. The Python library Pandas is used in this process.

[1055] 3. Safety degree calculation method

[1056] The server quantifies safety based on cleaned and normalized data. For example, it scores areas with lower crime rates as having a higher safety rating. Python and its statistical analysis libraries are used at this stage as well.

[1057] 4. Methods for estimating crime prevention measures

[1058] The server calculates appropriate security measures based on the level of security. This process may utilize statistical analysis and machine learning algorithms. This allows users to implement effective, data-driven security measures.

[1059] 5. Report generation and visual presentation methods

[1060] The server generates a detailed report based on the calculation results and provides it to the user via the terminal. The report includes visually easy-to-understand graphs and charts. This uses the Python library Matplotlib.

[1061] By using these methods, the server enables users to quickly and accurately understand the safety of their neighborhood and take effective crime prevention measures.

[1062] As a concrete example, we will generate a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data used will be crime rates and police patrol frequency, and the report will include graphs and charts. Below are examples of prompts for the generating AI model:

[1063] Please create a program that collects neighborhood security information in "Tokyo," cleans and normalizes the data, calculates the level of safety, and generates a detailed report. The data to be used should be crime rates and police patrol frequency. The report should also include graphs and charts.

[1064] Based on this prompt, users will be able to easily run the system and conduct a detailed assessment of the safety of their surrounding area.

[1065] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1066] Step 1:

[1067] The server collects security data for the surrounding area. Specifically, it obtains data such as local crime rates and police patrol frequency online via an API. In this process, the raw data obtained from the API is used as input, and the collected dataset is output.

[1068] Step 2:

[1069] The server cleans and normalizes the collected security data. Specifically, it uses the Python Pandas library to remove missing and outlier values, improving data quality. It also converts data from different data sources into a unified format and units. The input here is the collected dataset, and the output is the cleaned and normalized dataset.

[1070] Step 3:

[1071] The server calculates safety scores based on cleaned and normalized data. Specifically, it scales the crime rate and assigns a safety score on a scale from 1 to 0. For example, it scores areas where the crime rate is lower as the safety score increases. The input here is a cleaned and normalized dataset, and the output is the safety score for each area.

[1072] Step 4:

[1073] The server estimates appropriate security measures based on the level of security. Using statistical analysis and machine learning algorithms, it proposes optimal security measures and generates estimated results based on those proposals. The input here is the security score, and the output is the estimated result of appropriate security measures.

[1074] Step 5:

[1075] The server generates the calculation results in report format and sends them to the terminal. Specifically, it uses the Matplotlib library in Python to create graphs and charts, producing a visually easy-to-understand report. In this process, the calculation results are the input, and the generated report is the output.

[1076] Step 6:

[1077] The terminal visually presents the generated report to the user. Specifically, it displays the report on the terminal screen to make it easy for the user to understand. The input for this step is the generated report, and the output is the displayed report.

[1078] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1079] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, this system dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[1080] First, the server collects data online about nearby bicycle parking lots and other real estate in the target area. This collection is done automatically using APIs and public databases. By issuing API calls, the server collects data about bicycle parking lots. 2 Obtain specific data such as unit price, officially announced price, and land price.

[1081] Next, the terminal cleans and normalizes the acquired data. This includes the process of removing missing and outlier values. Normalization converts information obtained from different data sources into a unified format and units.

[1082] After the data is cleaned and normalized, the terminal uses that data to make an average m 2 Calculate the unit price. Average m 2 By calculating the unit price, it is possible to understand the general real estate prices in the target area. This information serves as basic data for estimating appropriate rent.

[1083] Next, the server calculates the average m 2 A fair rent is estimated using unit prices. This process integrates and weights multiple data points to enable more accurate estimations. Statistical analysis and machine learning algorithms may also be used to estimate fair rents.

[1084] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data.

[1085] The emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how reports are presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report will be presented.

[1086] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggestion helps users conduct rent negotiations more effectively.

[1087] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land values ​​in that area, and the terminal cleans and normalizes this data. Next, the terminal averages m 2 The server calculates the unit price and then uses that to estimate the appropriate rent. For example, average m 2 The unit price is 5,000 yen, and the officially announced price is 100,000 yen / m 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[1088] This system is expected to streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine will enhance the effectiveness of negotiations and improve user satisfaction.

[1089] The following describes the processing flow.

[1090] Step 1:

[1091] The server collects data online regarding nearby bicycle parking lots and real estate in the target area. Specifically, it issues API calls to retrieve data from public databases and real estate information websites. 2 Obtain data such as unit price, officially announced price, and land price.

[1092] Step 2:

[1093] The server stores the collected data in a database. This storage process also involves tagging the data and adding metadata.

[1094] Step 3:

[1095] The terminal retrieves data collected from the database and performs cleaning. For example, it detects missing or outlier values ​​and either fills in or deletes those data points.

[1096] Step 4:

[1097] The terminal normalizes the cleaned data. This is the process of unifying data recorded in different formats and units, m 2 Standardize unit prices and land price information to the same unit.

[1098] Step 5:

[1099] The device uses cleaned and normalized data to calculate the average m² of the target area. 2 Calculate the unit price. Specifically, the m of each data point. 2 The average is calculated by summing the unit prices and dividing by the number of data points.

[1100] Step 6:

[1101] The server calculated the average m 2 We integrate unit price, officially published price, and land price data to estimate appropriate rent. This process uses integrated analysis and weighted algorithms, and applies numerical models.

[1102] Step 7:

[1103] The server compiles the estimated appropriate rent into a detailed report. This report includes the data sources used, the analysis methods, the calculation results, and graphs and charts.

[1104] Step 8:

[1105] The emotion engine recognizes the user's emotional state. For example, it analyzes facial expressions and voice through a webcam and microphone to determine the user's stress level and emotional state.

[1106] Step 9:

[1107] The device dynamically changes how reports are presented to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the report will be presented in a concise and intuitive format.

[1108] Step 10:

[1109] The emotion engine analyzes the user's emotional data and suggests the optimal timing and method for rent negotiations. It recommends negotiating when the user is relaxed or in a positive emotional state.

[1110] Step 11:

[1111] The terminal visually presents the generated report to the user. The user interface displays the data in an easy-to-understand format, allowing users to grasp the information necessary for negotiations at a glance.

[1112] Step 12:

[1113] Based on the report, users negotiate rent with existing station owners. They also consider the suggestions from the emotion engine to select the optimal negotiation timing and method.

[1114] Step 13:

[1115] Users enter the negotiation results into the system, and the negotiation data is stored in a database. In the future, this data will be used as reference data for future negotiations and setting rental rates for other base stations.

[1116] By following these steps, the system can streamline rent negotiations and provide effective, emotion-based support, thereby increasing the success rate of negotiations.

[1117] (Example 2)

[1118] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1119] Conventional rent estimation systems based on real estate data have limitations in the accuracy of the collected data and in calculating appropriate rents. Furthermore, they lacked the ability to provide reports that considered the user's emotional state and to adequately support rent negotiations. Therefore, there is a need for a new system that provides more accurate rent estimations and reports and negotiation support that take the user's emotional state into account.

[1120] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1121] In this invention, the server includes means for collecting real estate data for neighboring areas online, means for cleaning and normalizing the real estate data, means for calculating the average unit price based on the cleaned and normalized real estate data, means for estimating an appropriate rent based on the average unit price, means for generating the estimation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the way the report is presented, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables more accurate rent estimation and rent negotiation support that satisfies users.

[1122] "Neighborhood real estate data" refers to the prices of properties within a specified area, m 2 This is a general term for data such as unit price, officially announced price, and land price.

[1123] "Online data collection" refers to the automated process of acquiring data via the internet using APIs and public databases.

[1124] "Cleaning" is a data preprocessing method that removes missing or outlier values ​​from data to improve its reliability.

[1125] "Normalization" is the process of converting information obtained from different data sources into a unified format and units.

[1126] "Average unit price" refers to the average price per square meter of a property, calculated based on cleaning and normalized property data. 2 This indicates the price per unit.

[1127] "Appropriate rent" refers to the fair rental price of real estate, calculated using statistical analysis and machine learning algorithms based on collected data.

[1128] "Generating in report format" means creating a document that visually represents information such as calculation results, data sources used, and analysis methods using text, graphs, charts, and other visual aids.

[1129] "Visual presentation" means displaying the generated report in a way that is easy for the user to understand.

[1130] "User emotional state" refers to the user's current psychological state, as obtained using wearable devices, emotion analysis software, etc.

[1131] "Dynamic modification" means optimizing the way reports are presented in real time according to the situation and conditions.

[1132] "The optimal timing and method for rent negotiation" refers to the most suitable time and means for conducting rent negotiations, as suggested based on user sentiment analysis.

[1133] The system of this invention collects real estate data for the surrounding area online, calculates appropriate rent based on that data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[1134] First, the server collects nearby real estate data for the target area online. This collection is done automatically using APIs and public databases. The software used includes, for example, the Python requests library. It issues API calls to obtain data on parking lots, etc. 2 Obtain specific data such as unit price, officially announced price, and land price.

[1135] Next, the terminal cleans and normalizes the acquired data. This process includes data preprocessing to remove missing and outlier values. Software used includes, for example, pandas in Python. Normalization transforms information obtained from different data sources into a unified format and units.

[1136] After the data is cleaned and normalized, the terminal calculates the average unit price based on that data. This is done using, for example, the statistical functions of pandas. By calculating the average unit price, it is possible to understand the general property prices in the target area.

[1137] Next, the server uses the calculated average unit price to estimate a fair rent. This process integrates and weights multiple data points to enable a more accurate estimate. Statistical analysis and machine learning algorithms, such as scikit-learn, are also used to estimate the fair rent.

[1138] After obtaining the calculation results, the terminal generates a detailed report based on them. This report includes not only the calculation results but also the data sources and analysis methods used. Furthermore, the report includes graphs and charts to provide a visual presentation of the data. Specific examples include using Python's matplotlib and seaborn libraries.

[1139] Next, the emotion engine recognizes the user's emotional state and provides that data to the system. Based on the emotional data obtained from the emotion engine, the terminal dynamically changes how the report is presented according to the user's emotional state. For example, if the user is feeling stressed, a more concise and easy-to-understand report is presented. The emotion engine can be implemented using, for example, emotion analysis software or wearable devices.

[1140] Furthermore, the emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. This suggests that the user can conduct rent negotiations more effectively. For example, it might suggest negotiating during less stressful times or periods.

[1141] As a concrete example, consider a case where an existing station owner requests a rent increase in a certain area. The server collects data on bicycle parking, publicly announced land prices, and land prices in that area, and the terminal cleans and normalizes this data. Next, the terminal calculates the average unit price, and the server uses that to estimate a fair rent. For example, if the average unit price is 5,000 yen and the publicly announced land price is 100,000 yen / m² 2 The land price is 200,000 yen / m². 2 In this case, the server integrates this data and calculates a fair rent of 50,000 yen per month. The terminal generates the result in a report format and provides it to the user. The emotion engine recognizes the user's emotions, and if the user is feeling stressed, it presents a concise report and suggests the appropriate timing for negotiation. The user can use this report and suggestion to negotiate with the owner, enabling them to conduct data-driven and reliable negotiations.

[1142] Examples of prompts for generative AI models:

[1143] "Please describe the detailed process flow of a system that, when a rent increase is requested, calculates a fair rent, and provides a report and negotiation support that takes into account the user's emotional state."

[1144] This system will streamline rent negotiations and ensure nationwide price consistency. Furthermore, the introduction of an emotional engine is expected to further enhance negotiation effectiveness and improve user satisfaction.

[1145] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1146] Step 1:

[1147] The server collects real estate data for the surrounding area online.

[1148] Input: Specify the target area (e.g., latitude and longitude or area name).

[1149] Specific actions:

[1150] The server configures the API endpoint (e.g., http: / / api.example.com / realestate_data).

[1151] The requests library is used to request data using requests.get(endpoint_url).

[1152] After the request is made, the data obtained using response.json() is parsed in JSON format.

[1153] Output: Collected real estate data (JSON format)

[1154] Step 2:

[1155] The device cleans and normalizes the acquired real estate data.

[1156] Input: Real estate data collected in Step 1 (in JSON format)

[1157] Specific actions:

[1158] We use the pandas library and check for missing values ​​using data.isnull().sum().

[1159] Remove missing values ​​using data.dropna().

[1160] Statistical methods (such as z-scores) are used to detect outliers, and these are removed using `data = data[(data.zscore() < 3)]`.

[1161] To unify the units of price, perform the conversion_rate operation: data['price'] = data['price']

[1162] Output: Cleaned and normalized real estate data (in DataFrame format)

[1163] Step 3:

[1164] The device calculates the average unit price based on cleaned and normalized data.

[1165] Input: Real estate data (in DataFrame format) cleaned and normalized in Step 2.

[1166] Specific actions:

[1167] Using the statistical functions of the pandas library, we get m 2 Calculate the average unit price.

[1168] Output: Average unit price (numerical value)

[1169] Step 4:

[1170] The server estimates a fair rent based on the calculated average unit price.

[1171] Input: Average unit price (numerical value) calculated in Step 3

[1172] Specific actions:

[1173] We will use the scikit-learn library to apply a LinearRegression model to the training data.

[1174] The model is trained using `model.fit(X_train, y_train)`, and the appropriate rent is predicted using `model.predict(X_test)`.

[1175] Output: Estimated appropriate rent (numerical value)

[1176] Step 5:

[1177] The terminal generates a detailed report based on the calculation results.

[1178] Input: The appropriate rent (numerical value) calculated in Step 4.

[1179] Specific actions:

[1180] Create report templates in HTML or PDF format using a template engine (e.g., Jinja2).

[1181] Use `template.render(data)` to insert data into the template.

[1182] We use the matplotlib and seaborn libraries to generate graphs and charts.

[1183] Output: Detailed report (HTML or PDF format)

[1184] Step 6:

[1185] The emotion engine recognizes the user's emotional state and provides that data to the system.

[1186] Input: Real-time user sentiment data (e.g., obtained from a wearable device)

[1187] Specific actions:

[1188] We will use emotion analysis software to analyze the collected emotion data.

[1189] Send the analysis results to the terminal.

[1190] Output: User's emotional state (data format)

[1191] Step 7:

[1192] The device dynamically changes how reports are presented based on the user's emotional state, using emotional data obtained from the emotion engine.

[1193] Input: User's emotional state obtained from Step 6 (data format), detailed report generated in Step 5 (HTML or PDF format)

[1194] Specific actions:

[1195] If a user is experiencing stress, the displayed items in the report will be limited to make it more concise.

[1196] You can limit the items displayed by using the conditional branching function of the template engine, for example (e.g., {% if stress_level > threshold %} brief information {% else %} detailed information {% endif %}).

[1197] Output: Dynamically modified report (HTML or PDF format)

[1198] Step 8:

[1199] The device analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations.

[1200] Input: User's emotional state obtained from Step 6 (data format)

[1201] Specific actions:

[1202] Based on user sentiment data, notifications are sent to display information at the appropriate time (e.g., suggesting less stressful times).

[1203] Generate a notification such as, "The best time to negotiate is next Monday morning."

[1204] Output: Suggestions (notifications) regarding the timing and method of rent negotiations.

[1205] (Application Example 2)

[1206] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1207] Conventional rent estimation systems based on real estate data only estimated appropriate rents and generated and presented reports, failing to support rent negotiations while considering the user's emotional state. This resulted in significant psychological burden on users during rent negotiations, making it difficult to determine the optimal timing and method of negotiation. Furthermore, the fixed visual presentation method prevented flexible responses tailored to the user's understanding and circumstances. This invention aims to solve these problems and provide more effective support for rent negotiations.

[1208] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting real estate data of neighboring areas online, means for cleaning and normalizing the real estate data, and means for averaging m based on the cleaned and normalized real estate data. 2 Methods for calculating the unit price, and average m 2 This includes means for calculating appropriate rent based on unit prices, means for generating the calculation results in report format, means for visually presenting the report, means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data, and means for analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiation. This enables optimal rent negotiation support tailored to the user's emotional state.

[1209] "Neighborhood real estate data" refers to diverse information about real estate acquired within a specific area.

[1210] "Means of collecting data online" refers to technologies or processes for automatically acquiring data via the internet.

[1211] "Cleaning and normalization methods" are techniques for removing missing or outlier values ​​from collected data and for standardizing data formats and units.

[1212] "Average m 2 The "means of calculating unit price" refers to the process of calculating the average property price per square meter in a specific area based on cleaned and normalized data.

[1213] "Methods for estimating appropriate rent" refers to the average m 2 This is a technique for calculating appropriate rent in a given area based on unit prices and other relevant data.

[1214] "Methods for generating calculation results in report format" refers to methods for generating reports that visually summarize the calculated data in an easy-to-understand manner.

[1215] "Means of visually presenting reports" refers to the process of presenting generated reports to users using visual elements such as graphs and charts.

[1216] "Means for recognizing the user's emotional state and dynamically changing the report presentation method based on emotional data" refers to a technology that uses emotional recognition technology to analyze the user's emotions and appropriately changes the report presentation method according to the results.

[1217] "Emotional data" refers to data that indicates a user's emotional state, expressing psychological conditions such as stress, joy, and anxiety using numerical values ​​and categories.

[1218] An "emotion engine" is a technology or software that analyzes a user's emotional state in real time and performs various processes based on that information.

[1219] "A means of analyzing the user's emotional state and proposing the optimal timing and method for rent negotiation" refers to a technology that uses user emotional data to propose the optimal timing and method for conducting rent negotiations more effectively.

[1220] "Rent negotiation" refers to the process in real estate lease agreements where the tenant and landlord negotiate the rent.

[1221] The system of this invention collects real estate data for neighboring areas online, calculates appropriate rents based on this data, and generates and visually presents a report. Furthermore, by incorporating an emotion engine, it dynamically changes the way the report is presented according to the user's emotional state and has the function of suggesting the optimal timing and method for rent negotiations.

[1222] The server has the means to collect data online about nearby real estate in the target area using APIs and public databases. This means is a technology for automatically retrieving data over the internet, specifically by using HTTP requests to retrieve data from APIs.

[1223] Next, the terminal has means to cleanse and normalize the acquired data. This process removes missing and outlier values ​​from the collected data and converts information obtained from different data sources into a unified format and units. Specifically, it uses Python libraries such as pandas, numpy, and scikit-learn.

[1224] Based on cleaned and normalized data, the terminals average m 2 The unit price is calculated. This allows us to calculate the average property price per square meter in a specific area. Furthermore, this average m 2 Using unit prices as basic data, the server has a means to estimate appropriate rent. This means may involve the use of statistical analysis or machine learning algorithms.

[1225] After the calculation results are obtained, the terminal has the means to generate a detailed report. This report includes graphs and charts, and describes the data sources and analysis methods used in addition to the calculation results. Specifically, it generates graphs using matplotlib.

[1226] The emotion engine has a means of recognizing the user's emotional state and providing that data to the system. This allows the terminal to dynamically change how reports are presented based on the user's emotional data. For example, if the user is feeling stressed, a more concise and easy-to-understand report format will be presented.

[1227] Furthermore, the emotion engine analyzes the user's emotional state and has the means to suggest the optimal timing and method for rent negotiations. This provides support to help users conduct more effective rent negotiations.

[1228] Specific example

[1229] For example, when collecting real estate data for Shibuya Ward and estimating appropriate rent, the server collects data using an API, and the terminal cleans and normalizes the data using Python libraries. Then, it calculates the appropriate rent and generates a report using matplotlib. The emotion engine analyzes the user's emotional state, presents a concise report if they are experiencing stress, and suggests the optimal timing for negotiation.

[1230] Example of a prompt:

[1231] "Collect real estate data for neighboring areas of Shibuya Ward and use that data to estimate appropriate rents. Also, provide a concise report if user ID 12345 is experiencing stress, and generate and provide a detailed report if they are not."

[1232] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1233] Step 1:

[1234] The server collects real estate data for the surrounding area online. Specifically, it uses API calls to retrieve real estate price information for a specified area from public databases and real estate-related data providers on the internet. 2 The system acquires data such as unit price, officially published price, and land value. This allows for the acquisition of detailed real estate information for the target area as input data. The output is real estate information as raw data.

[1235] Step 2:

[1236] The terminal cleanses and normalizes the real estate data received from the server. First, it uses the pandas library to organize the data and detect and remove missing and outlier values. Next, it uses the scikit-learn StandardScaler class to convert data from different data sources into a unified format and units. This ensures that the input data (raw data) is output as cleaned and normalized data.

[1237] Step 3:

[1238] The device uses cleansed and normalized data to calculate the average m 2 Calculate the unit price. Specifically, use the numpy library to calculate the m in the dataset. 2 Calculate the average unit price. The input for this step is cleaned and normalized real estate data, and the output is the average unit price m 2 This is the result of the unit price calculation.

[1239] Step 4:

[1240] The server calculated the average m 2 Based on the unit price, we estimate the appropriate rent. We integrate various data points and apply weighting, applying statistical analysis and machine learning algorithms as needed. For example, we use linear regression to predict the appropriate rent. The input for this step is average m 2 Based on the unit price and other relevant data, the output is the estimated appropriate rent.

[1241] Step 5:

[1242] The terminal generates calculation results in a report format, creating a visually easy-to-understand report. It uses the matplotlib library to generate graphs and charts, and also describes the calculation results, the data sources used, and the analysis methods. The input for this step is the calculated appropriate rent and data sources, and the output is a detailed report.

[1243] Step 6:

[1244] The emotion engine recognizes the user's emotional state and provides that data to the system. Emotion recognition technology is used to analyze the user's emotional state (stress, joy, anxiety, etc.) in real time. For example, facial expressions and voice analysis are used. The input for this step is emotional data from the user, and the output is the analyzed emotional state data.

[1245] Step 7:

[1246] The device dynamically changes how reports are presented based on emotional data obtained from the emotion engine, according to the user's emotional state. For example, if the user is stressed, the report is changed to a concise and easy-to-understand format. The input for this step is emotional state data and the generated report, and the output is the dynamically modified report presented to the user.

[1247] Step 8:

[1248] The emotion engine analyzes the user's emotional state and suggests the optimal timing and method for rent negotiations. It recommends the time when the user can negotiate most relaxed and effectively, and presents effective negotiation strategies. The input for this step is emotional state data, and the output is the suggested content.

[1249] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1250] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1251] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1252] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1253] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1254] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1255] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1256] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1257] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1258] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1259] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1260] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1261] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1262] 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.

[1263] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1264] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1265] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1266] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1267] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1268] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1269] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1270] The following is further disclosed regarding the embodiments described above.

[1271] (Claim 1)

[1272] Means of collecting real estate data for neighboring areas online,

[1273] Means for cleaning and normalizing real estate data,

[1274] Based on cleaned and normalized real estate data, average m 2 Methods for calculating the unit price,

[1275] average m 2 A method for estimating appropriate rent based on unit price,

[1276] A means of generating the calculation results in report format,

[1277] Means of presenting reports visually,

[1278] A system that includes this.

[1279] (Claim 2)

[1280] The system according to claim 1, comprising means for integrating and analyzing collected real estate data and calculating appropriate rent using multiple data points.

[1281] (Claim 3)

[1282] The system according to claim 1, which includes means for displaying the results of a simulation of appropriate rent and assisting the user in rent negotiation.

[1283] "Example 1"

[1284] (Claim 1)

[1285] Methods for collecting real estate information in the surrounding area online,

[1286] Methods for processing and normalizing real estate information,

[1287] A means for calculating the price per square meter based on processed and normalized real estate information,

[1288] A method for estimating appropriate real estate rates based on the price per square meter,

[1289] A means of generating the calculation results in a report format,

[1290] Means of presenting reports visually,

[1291] A system that includes this.

[1292] (Claim 2)

[1293] The system according to claim 1, comprising means for integrating and analyzing collected real estate information and calculating an appropriate price using multiple data points.

[1294] (Claim 3)

[1295] The system according to claim 1, which includes means for displaying the results of a simulation of appropriate fees and assisting the user in negotiating fees.

[1296] "Application Example 1"

[1297] (Claim 1)

[1298] A means of collecting security data from neighboring areas online,

[1299] Means for cleaning and normalizing security data,

[1300] A means of calculating security based on cleaned and normalized security data,

[1301] A method for estimating appropriate crime prevention measures based on the level of safety,

[1302] A means of generating the calculation results in report format,

[1303] Means of presenting reports visually,

[1304] A system that includes this.

[1305] (Claim 2)

[1306] The system according to claim 1, comprising means for integrating and analyzing collected security data and estimating appropriate crime prevention measures using multiple data points.

[1307] (Claim 3)

[1308] The system according to claim 1, which includes means for displaying the simulation results of appropriate crime prevention measures and for the user to support crime prevention measures.

[1309] "Example 2 of combining an emotion engine"

[1310] (Claim 1)

[1311] Means of collecting real estate data for neighboring areas online,

[1312] Means for cleaning and normalizing real estate data,

[1313] A method for calculating the average unit price based on cleaning and normalized real estate data,

[1314] A method for estimating appropriate rent based on average unit price,

[1315] A means of generating the calculation results in report format,

[1316] Means of presenting reports visually,

[1317] A means to recognize the user's emotional state and dynamically change how reports are presented,

[1318] A method to analyze the user's emotional state and suggest the optimal timing and method for rent negotiations,

[1319] A system that includes this.

[1320] (Claim 2)

[1321] The system according to claim 1, comprising means for integrating and analyzing collected real estate data and calculating appropriate rent using multiple data points.

[1322] (Claim 3)

[1323] The system according to claim 1, which includes means for displaying the results of a simulation of appropriate rent and assisting the user in rent negotiation.

[1324] "Application example 2 when combining with an emotional engine"

[1325] (Claim 1)

[1326] Means of collecting real estate data for neighboring areas online,

[1327] Means for cleaning and normalizing real estate data,

[1328] Based on cleaned and normalized real estate data, average m 2 Methods for calculating the unit price,

[1329] average m 2 A method for estimating appropriate rent based on unit price,

[1330] A means of generating the calculation results in report format,

[1331] Means of presenting reports visually,

[1332] A means of recognizing the user's emotional state and dynamically changing the way reports are presented based on emotional data,

[1333] A means of analyzing the user's emotional state and suggesting the optimal timing and method for rent negotiations,

[1334] A system that includes this.

[1335] (Claim 2)

[1336] The system according to claim 1, comprising means for integrating and analyzing collected real estate data and calculating appropriate rent using multiple data points.

[1337] (Claim 3)

[1338] The system according to claim 1, which includes means for displaying the results of a simulation of appropriate rent and assisting the user in rent negotiation. [Explanation of Symbols]

[1339] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting real estate data for neighboring areas online, Means for cleaning and normalizing real estate data, Based on cleaned and normalized real estate data, average m 2 Methods for calculating the unit price, average m 2 A method for estimating appropriate rent based on unit price, A means of generating the calculation results in report format, Means of presenting reports visually, A system that includes this.

2. The system according to claim 1, comprising means for integrating and analyzing collected real estate data and calculating appropriate rent using multiple data points.

3. The system according to claim 1, which includes means for displaying the results of a simulation of appropriate rent and assisting the user in rent negotiation.

Images