System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting address information by a user; a server for receiving the address information; a server including a generative AI model for calculating a rent quote based on the address information; means for generating the calculated rent quote as evidence; and means for returning the evidence to a client.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Rental housing contracts in Japan are typically for two years, and rent prices often fluctuate during this period. However, few residents negotiate their rent when it's time to renew their contract, which creates the problem of many residents continuing to pay rents that are higher than the market rate. Furthermore, rent negotiations require a lot of effort and expertise, which places a heavy burden on residents. To solve this problem, there is a need to provide a system that makes rent negotiations easy so that residents can live at a fair rent. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. A system is provided that includes a means for a user to input address information, a server that receives the address information, a server that includes a generative AI model that calculates average rent prices based on the address information, a means for generating the calculated average rent prices as evidence, and a means for returning the evidence to a terminal. This system allows users to easily understand average rent prices and negotiate rent based on that evidence. Furthermore, by including a means for users to negotiate rent using the evidence and a means for negotiating rent on behalf of users, the effort and burden of rent negotiations can be reduced.

[0006] "User" refers to a resident who uses the system to input address information and calculate average rent prices.

[0007] "Address information" refers to information relating to the location of a rental property, and specifically includes information such as prefecture, city, ward, town, and village, and street address.

[0008] "Server" refers to a computer system that receives address information sent by the user, calculates the average rent using a generative AI model, generates evidence, and returns it to the terminal.

[0009] A "generative AI model" refers to an artificial intelligence model that calculates the average rent for a specific address based on collected rent data for surrounding properties and past trend data.

[0010] "Average rent" refers to the appropriate rent amount calculated based on specific address information.

[0011] "Evidence" refers to supporting documentation that compiles calculated market rents and related supporting data, and is provided in PDF or web format.

[0012] "Terminal" refers to the device, such as a computer or smartphone, that a User uses to enter address information and receive and view evidence.

[0013] "Rent negotiation" refers to the act of a user proposing to the owner or management company that the rent in the rental contract be revised based on the market rent calculated by the user.

[0014] "Proxy negotiation means" refers to the function in which the server uses evidence to negotiate with the owner or management company on behalf of the user to lower the rent. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

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

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0036] This invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. To achieve this, the system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0037] Enter user address information

[0038] First, the user must enter their address information. The user starts the application using a device (PC or smartphone) and enters the address of the rental property (for example, 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the input form. This input information is sent to the server by pressing the "Submit" button.

[0039] The server receives address information and calculates the average rent

[0040] The server receives the address information sent by the user. Based on this address information, a generative AI model is used to calculate the real-time market rent. The generative AI model calculates an accurate market rent by taking into account rent data for similar properties in the area and past rent trends. In this calculation process, it is important that the collected data reflects the actual market price.

[0041] Generate and provide evidence of market rents

[0042] The server generates the calculated market rent data as evidence. The evidence includes the calculated market rent data and the underlying data (for example, rent data for surrounding properties and past rent trends). The evidence is generated in PDF or web format and sent from the server to the terminal.

[0043] The terminal receives the evidence sent from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary.

[0044] Rent negotiation assistance

[0045] Users can use the generated evidence to negotiate rent when renewing a rental contract. For example, a user can inform a management company that the current rent is 350,000 yen and negotiate to lower it to 300,000 yen based on the evidence. This evidence enables persuasive negotiations with the owner and management company.

[0046] Furthermore, if the user wishes, they can use a service in which the server handles rent negotiations on their behalf. In this case, the server uses evidence to negotiate rent on the user's behalf and contacts the owner or management company. This proxy negotiation significantly reduces the time and effort required for the user to negotiate rent.

[0047] Specific examples

[0048] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address. The server receives the address information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this data as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on that, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0049] In this way, this system will be a powerful tool for residents to ensure they receive fair rent when renewing their rental contracts.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The user starts the application using a terminal. The user enters the address information of the rental property into the application's input form. Specifically, the user enters an address such as "1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0053] Step 2:

[0054] When the user presses the "Send" button, the address information is sent from the device to the server via an HTTP request.

[0055] Step 3:

[0056] The server receives the address information sent from the device, parses the received data, and prepares it for passing to the generative AI model.

[0057] Step 4:

[0058] The server calculates the market rent using a generated AI model, which takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data.

[0059] Step 5:

[0060] The server generates evidence based on the calculated market rent. The evidence includes market rent data and the underlying data (such as rent data for surrounding properties and trend graphs).

[0061] Step 6:

[0062] The server returns the generated evidence to the terminal using an HTTP response.

[0063] Step 7:

[0064] The terminal receives the evidence returned from the server and displays it on the user interface for the user to review.

[0065] Step 8:

[0066] The user uses the evidence to negotiate the rent when renewing the rental contract. Specifically, the user proposes to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence.

[0067] Step 9:

[0068] If the user wishes, they can select the proxy negotiation option, which allows the server to negotiate the rent on their behalf without the user having to negotiate directly.

[0069] Step 10:

[0070] The server uses the evidence to negotiate rent with the management company or owner on behalf of the user, and conveys the evidence and the details of the negotiation via email or telephone.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] Previously, when residents negotiated rent at the time of lease contract renewal, it was difficult to grasp the appropriate market rent, making it difficult to negotiate persuasively with management companies and owners. In particular, the inability to obtain accurate market rent data based on real-time data meant there was a lack of evidence, which meant that residents could renew their contracts on unfavorable terms. Another problem was that rent negotiations themselves were complicated, requiring a lot of time and effort.

[0074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0075] In this invention, the server includes a means for a user to input address information, a means for receiving the address information, a means including a generative AI model that calculates average rent prices based on the address information, a means for generating the calculated average rent prices as evidence, a means for returning the evidence to a terminal, a means for generating the evidence in PDF or web format, a means for calculating average rent prices in real time using the generative AI model with data on surrounding properties and past rent trends, a means for displaying the evidence on a user interface, and a means for storing the address information sent from the terminal to the server in a database. This allows residents to understand the appropriate average rent prices when renewing their rental contracts and negotiate rent based on convincing evidence. Furthermore, using a server-based service to handle rent negotiations can reduce the residents' time and effort.

[0076] "User" refers to a resident of a rental property who uses the system to negotiate rent.

[0077] "Address information" is data indicating the location of a rental property, and specifically includes information such as prefecture, city, ward, town, street name, and house number.

[0078] The "server" is a computer system that receives the user's address information via the network and calculates the average rent using a generative AI model.

[0079] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to make predictions and analyses based on input data.

[0080] "Average rent" is data that shows the average and distribution of appropriate rents in a particular area or property type.

[0081] "Evidence" refers to documents and supporting evidence provided to support rent negotiations, including calculated market rent data and the underlying data.

[0082] A "terminal" is a computing device used by a user, specifically a PC or smartphone.

[0083] A "database" is a system for efficiently storing, managing, and searching structured data.

[0084] The "user interface" is the part that provides the screen and operation means for the user to interact with the system.

[0085] "Rent negotiation" refers to the process of reviewing current rental terms and adjusting them to an appropriate rent.

[0086] "PDF" is an abbreviation for Portable Document Format, a file format for electronically distributing and displaying documents while preserving their format and layout.

[0087] "Web format" refers to a format of digital content that can be viewed and manipulated through a web browser.

[0088] The present invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. This system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0089] Hardware and software used

[0090] This system uses the following hardware and software:

[0091] Server: A central computer that processes data and runs AI models.

[0092] Terminal: A device used by a user, such as a PC or smartphone.

[0093] Generative AI models: Examples include natural language processing models such as OpenAI's GPT-3 and Google's BERT.

[0094] Database: A data management system for storing address information and rent data.

[0095] Application: Software that allows users to enter address information and verify evidence.

[0096] Explanation of program processing

[0097] First, the user launches the application using their own device (PC or smartphone) and enters address information. Specifically, the user enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the application's input form and presses the "Submit" button to send it to the server.

[0098] The server receives the address information sent by the user. This address information is stored in a specific database table. The server then uses a generative AI model to calculate the average rent based on the received address information, taking into account rent data for similar properties in the area and past rent trends.

[0099] Once the market rent is calculated, the server generates the results as evidence. The evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, past rent trends). The evidence is generated in PDF or web format and sent from the server to the user's device.

[0100] The user checks the received evidence on their device. The evidence is displayed on the application and can be downloaded or printed as needed. The user can use this evidence to negotiate the rent when renewing their rental contract. For example, if the current rent is 350,000 yen, the user can use the evidence to negotiate with the management company or owner to lower it to 300,000 yen.

[0101] Furthermore, if the user wishes, the server will negotiate the rent on their behalf. In this case, the server will use an automatic email sending function or API to contact the management company or owner on the user's behalf and negotiate. This reduces the user's time and effort.

[0102] Examples and prompts

[0103] For example, suppose a user named Tanaka lives in a rental property at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his lease contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address information. The server receives this information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on it, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0104] Example prompt sentence:

[0105] "Please tell me the real-time average rent for properties around 1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0106] "Please generate evidence to review my current rent of 350,000 yen to a fair price."

[0107] In this way, this system is a powerful tool that helps residents to obtain fair rent when renewing their rental contracts.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The user starts the application using a device (PC or smartphone), enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) in the address information input form, and presses the "Submit" button.

[0111] Input: Rental property address information

[0112] Output: Request with address information sent to server

[0113] What happens: A user opens the application, enters address information, and presses the submit button.

[0114] Step 2:

[0115] The server receives the address information submitted by the user, parses the HTTP request, and stores the address information in a specific database table.

[0116] Input: Address information submitted by the user

[0117] Output: Address information stored in a database

[0118] Specific operation: The server receives the HTTP request, analyzes it, and saves the extracted address information in a database.

[0119] Step 3:

[0120] The server uses a generative AI model based on the stored address information to calculate the average rent price. The generative AI model includes data on surrounding properties and past rent trends, and takes this data into account to derive the average rent price in real time.

[0121] Input: Address information stored in the database

[0122] Output: Calculated market rent data

[0123] Specific operation: The server inputs address information into a generative AI model, which then calculates the average rent.

[0124] Step 4:

[0125] The server generates evidence based on the generated market rent data. The evidence includes market rent data and its basis (e.g., data on surrounding properties, past rent trends). The evidence is generated in PDF format or web format.

[0126] Input: Calculated market rent data

[0127] Output: Generated evidence (PDF or web format)

[0128] What happens: The server formats the rent quote data and creates evidence using a PDF generation library.

[0129] Step 5:

[0130] The server sends the generated evidence to the user's device, and returns the evidence to the user as an HTTP response or provides a URL link.

[0131] Input: Generated evidence

[0132] Output: Evidence sent to the user's device

[0133] Specific operation: The server generates an evidence file and returns it in an HTTP response. In some cases, it generates a URL link and notifies the user.

[0134] Step 6:

[0135] The user checks the received evidence on the device. The evidence is displayed within the application, and the user can download or print it as needed.

[0136] Input: Evidence received from the server

[0137] Output: User interface with evidence displayed

[0138] Specific operations: The user opens the evidence confirmation screen within the application, checks the contents, and operates the download and print buttons.

[0139] Step 7:

[0140] The user can use the generated evidence to negotiate rent when renewing the rental contract. Specifically, the user submits the evidence to the management company or owner and negotiates to revise the current rent to a fair price.

[0141] Input:Evidence

[0142] Output: Rent negotiation result (e.g. rent reduction)

[0143] Specific actions: The user presents evidence in print or digital form and negotiates with the management company.

[0144] Step 8:

[0145] If the user wishes, the server will handle rent negotiations on their behalf. The server uses an automatic email sending function and API to contact the management company or owner and negotiate.

[0146] Input: User's request for negotiation

[0147] Output: Rent negotiation result (e.g. rent reduction)

[0148] Specific operation: The server receives a request for negotiation on behalf of the user and uses the automatic email sending function to send a negotiation email to the management company.

[0149] (Application example 1)

[0150] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0151] With conventional rent negotiation systems, it was difficult for residents to accurately grasp the market rent in real time, and the provision of evidence was limited, making it difficult to conduct rent negotiations effectively.In addition, support for viewing rental properties and rent negotiations using virtual reality technology was not widespread, so a more efficient and effective system was needed.

[0152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0153] In this invention, the server includes means for a user to input address information, means for receiving the address information, means including a generative AI model for calculating market rents based on the address information, means for generating the calculated market rents as evidence, means for returning the evidence to a terminal, means for viewing properties in a virtual reality environment, means for displaying the evidence in the virtual reality environment, and means for supporting rent negotiations in the virtual reality environment. This allows a user to check market rents in real time and engage in efficient and persuasive rent negotiations through the virtual reality environment.

[0154] The "means by which the user inputs address information" refers to an interface or device that allows the user to input address information for their own residence or rental property.

[0155] The "server that receives the address information" is a computer system that receives and processes the address information sent by the user.

[0156] A "server including a generative AI model that calculates average rent prices based on the address information" is a computer system that has an internal generative AI model for calculating average rent prices using address information.

[0157] "Means for generating evidence of calculated market rents" refers to the functions and processes for turning the market rents calculated by the generative AI model into evidence.

[0158] The "means for returning the evidence to the terminal" refers to a function or process for transmitting the market rent data generated as evidence to the terminal used by the user.

[0159] "Means for viewing properties in a virtual reality environment" refers to systems or technologies that allow users to view rental properties using virtual reality technology.

[0160] The "means for displaying the evidence within the virtual reality environment" refers to a system or technology for visually presenting evidence of market rent prices to a user within a virtual reality environment.

[0161] The "means for supporting rent negotiations within the virtual reality environment" refers to a system or function that supports a user when negotiating rent within the virtual reality environment.

[0162] This invention is a system that provides accurate market rent information when users negotiate rent for rental properties. It also makes it possible to more efficiently view properties and negotiate rent using a virtual reality environment.

[0163] System Configuration

[0164] 1. How users enter address information

[0165] Users use an interface to input address information using a smartphone or PC, which can be provided as an application or web form.

[0166] 2. Server that receives the address information

[0167] The server receives the address information entered by the user and stores it in a database. This reception process uses HTTP requests and REST APIs.

[0168] 3. A server containing a generative AI model that calculates market rents based on the address information.

[0169] The server uses a generative AI model to calculate average rent prices based on the address information entered by the user. This generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. The model learns from historical rent data and current market conditions to provide accurate rent prices in real time.

[0170] 4. A method for generating evidence of the calculated market rent

[0171] The server generates evidence of the calculated rent market price. This evidence is created in PDF or web page format and includes detailed data and rationale for the rent market price. Python's FPDF library is used to generate the evidence.

[0172] 5. Means for returning said evidence to the terminal

[0173] The server sends the generated evidence to the user's device using a REST API or email sending system. The user can then check the evidence on their smartphone or PC.

[0174] 6. A way to view properties in a virtual reality environment

[0175] Users can virtually view properties using a VR headset. The VR environment is built in conjunction with Unity and Unreal Engine to provide users with a 360-degree virtual experience.

[0176] 7. Means for displaying said evidence within said virtual reality environment

[0177] This is a system for displaying evidence of calculated market rents in a virtual reality environment, allowing users to check market rents in real time while viewing properties.

[0178] 8. Means for assisting in rent negotiations within said virtual reality environment

[0179] The chatbot function is used in virtual reality to support real-time rent negotiations. This chatbot uses natural language processing technology to converse with users. It can also negotiate on behalf of users, providing them with the ability to negotiate rent on their behalf.

[0180] Specific examples of processing

[0181] The user views a rental property in a virtual store and enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo." The server receives the address information and calculates the average rent using a generative AI model. The result is 300,000 yen, and evidence is displayed in the virtual space. The user then begins rent negotiations with the management company via a chatbot.

[0182] Prompt Sentence Examples

[0183] "Please calculate the average rent for the following address: 1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The user enters address information. Using a smartphone or PC, the user enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo" through an application or web form. The entered address information is sent from the device to the server.

[0187] Step 2:

[0188] The server receives the address information, processes the HTTP request, and stores the address information in a database. This data is then used by the generative AI model to calculate market rents.

[0189] Step 3:

[0190] The server calculates the average rent. The server inputs the stored address information into a generative AI model to predict the average rent. This model is built using TensorFlow and PyTorch, and predicts the average rent in real time based on past data and market trends. The output is average rent data such as "300,000 yen."

[0191] Step 4:

[0192] The server generates evidence. Based on the calculated market rent data, the server creates evidence in PDF or web format. This evidence includes details of market rents and the underlying data. The PDF is generated using a library such as Python's FPDF library.

[0193] Step 5:

[0194] The server returns the evidence to the device. The generated evidence is sent back to the user's smartphone or PC via REST API or email. The user can then view this evidence on their device.

[0195] Step 6:

[0196] Users can view properties in a virtual reality environment. Users wear a VR headset and access the virtual reality environment. This environment is built using Unity and Unreal Engine, allowing users to inspect the property in detail with a 360-degree view.

[0197] Step 7:

[0198] The server displays evidence within the virtual reality environment. Rent market evidence is displayed within the user's field of vision. This display is done in real time, providing rent data and its rationale as an overlay in the virtual space.

[0199] Step 8:

[0200] Users will be provided with a means to assist in rent negotiations. Within the virtual reality environment, a chatbot will receive instructions from the user and assist in rent negotiations with the property management company in real time. The chatbot will use natural language processing technology to converse and convey the user's request for a rent reduction. If the user so desires, the chatbot can also negotiate with the property management company on their behalf.

[0201] As described above, the data input and output are clearly defined at each step, and data processing and calculations are performed based on this, allowing the system to enable users to efficiently negotiate rent in a virtual reality environment.

[0202] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0203] This invention combines a system that enables residents of rental housing to easily negotiate rent when renewing their rental contracts with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state and optimizes support for rent negotiations based on the results.

[0204] User address input and emotion recognition

[0205] First, the user launches the application using a device (PC or smartphone). The user enters the address information of the rental property into the application's input form (for example, "1-2-3 XX-cho, Shibuya-ku, Tokyo"). As the user enters the information, the emotion engine analyzes the user's input speed and facial expression, and recognizes the user's emotional state regarding the address information. This emotional information is also sent to the server.

[0206] The server receives the address information and emotion information.

[0207] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[0208] Calculating market rent

[0209] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[0210] Generating and providing evidence that takes emotional information into account

[0211] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[0212] Rent negotiation support and proxy proposals

[0213] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user can use the generated evidence to negotiate the rent when renewing the rental contract. For example, based on the evidence, the user can propose to the management company that the current rent of 350,000 yen be reduced to 300,000 yen.

[0214] The emotion engine may also suggest negotiating rent on behalf of the user depending on the user's emotional state. For example, if the server detects that the user is feeling highly stressed, it will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on their behalf. The server will then communicate the details of the negotiation along with the evidence to the owner or management company.

[0215] Specific examples

[0216] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and is due to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka requests it, the server will negotiate on his behalf.

[0217] In this way, this system supports rent negotiations while taking into account the user's emotional state, making it a powerful tool for residents to achieve a fair rent.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The user launches the application using their device. The user enters the address information of the rental property (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo") into the application's input form. As the user enters information, the emotion engine analyzes the user's input patterns and facial expression data in real time to recognize their emotional state (e.g., anxiety, stress).

[0221] Step 2:

[0222] The user presses the "Submit" button to send the address information and the detected emotion information to the server via an HTTP request.

[0223] Step 3:

[0224] The server receives the address information and emotion information sent from the device, parses the data, and passes the address information and emotion information to the appropriate processing module.

[0225] Step 4:

[0226] The server calculates the average rent using a generative AI model. The generative AI model calculates the real-time average rent (e.g., 300,000 yen) based on the address information by collecting and analyzing rent data for similar properties in the area and past rent trends.

[0227] Step 5:

[0228] The server generates evidence based on the calculated market rent. The evidence includes market rent data and related evidence (such as rent data for surrounding properties and trend graphs). Furthermore, based on the emotional information recognized by the emotion engine, negotiation support advice (e.g., "Please pay attention to these points to reduce your anxiety") is added to the user.

[0229] Step 6:

[0230] The server returns the generated evidence to the terminal using an HTTP response.

[0231] Step 7:

[0232] The terminal receives the evidence returned from the server. The terminal displays the evidence in the user interface so that the user can review it. The user can review the evidence and download or print it as a PDF.

[0233] Step 8:

[0234] Users negotiate rent based on evidence when renewing a rental contract. Based on evidence, users propose to the management company that the current rent (e.g., 350,000 yen) be lowered to a fair market price (e.g., 300,000 yen). Users can negotiate more effectively by following the advice provided by the emotion engine.

[0235] Step 9:

[0236] The emotion engine continuously monitors the user's emotional state, and if it detects that the user is experiencing high levels of stress or anxiety, it suggests proxy negotiation options, which are displayed in the user interface.

[0237] Step 10:

[0238] If the user selects the proxy negotiation option, the server will negotiate the rent on the user's behalf. The server will organize the evidence and negotiation details and contact the management company or owner. Specifically, it will send the evidence by email or phone and explain the negotiation points.

[0239] Through the above steps, the system can effectively support rent negotiations while taking into account the user's emotional state.

[0240] Example 2

[0241] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0242] Conventional rent negotiation systems have the problem that users negotiate rent without considering their own emotional state, making it difficult to negotiate effectively. In particular, emotions such as tension and anxiety often have a negative impact on the outcome of the negotiation, placing a heavy burden on users. Furthermore, many users have little experience in rent negotiations, making it difficult for them to collect appropriate evidence and implement effective approaches. Furthermore, if users feel strong stress during the negotiation process, they may be unable to achieve a fair rent.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0244] In this invention, the server includes a means for a user to input address information and recognize the user's emotional state; a server that receives the address information and emotional information; a server that includes a generative AI model that calculates the average rent price based on the address information and emotional information; a means for generating the calculated average rent price as evidence and providing advice to the user based on the emotional information; and a means for returning the evidence and advice to the terminal. This allows the system to calculate an appropriate average rent price and provide effective evidence while taking the user's emotional state into consideration, allowing the user to negotiate the rent with peace of mind. Furthermore, by offering proxy negotiations as needed, the system can reduce the user's mental burden and help them achieve a more appropriate rent price.

[0245] "User address information" is geographical information that a user inputs to identify the location of a rental property.

[0246] "Emotional state" is information that represents the user's emotions and mood, and is analyzed from input speed, facial expressions, voice, etc.

[0247] A "server" is a computer device that receives address information and emotion information sent by a user and processes and analyzes them.

[0248] A "generative AI model" is a program that uses artificial intelligence algorithms to calculate market rent prices based on specific input data (address information and emotional information).

[0249] "Evidence" refers to documents or reports containing data or supporting information to support market rents.

[0250] "Advice" is advice or suggestions provided to users based on the results of generative AI models and emotion engines.

[0251] A "terminal" is a device (such as a personal computer or smartphone) that a user uses to input information and receive evidence and advice sent from a server.

[0252] An "emotion engine" is software or a system for analyzing a user's emotional state, analyzing data such as the user's input speed, facial expressions, and voice.

[0253] "Market rent" refers to the market price of rent in a specific area or property, and is calculated using a generative AI model.

[0254] This invention is a system that allows residents of rental housing to easily negotiate rent. The system uses an emotion engine and generative AI model to recognize the user's emotional state and assist with rent negotiations based on this.

[0255] First, the user launches the application using a device (such as a PC or smartphone). The user enters the address information of the rental property into the application's input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo"). At this time, an emotion engine (such as Microsoft Azure Cognitive Services Emotion API) analyzes the user's input speed, facial expressions, and voice to recognize their emotional state. The device then sends the address information and emotion information to the server.

[0256] The server receives the address and emotion information sent by the user. The received information is parsed and passed to a generative AI model (e.g., OpenAI GPT-4). The server sends the following prompt to the generative AI model:

[0257] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0258] User Sentiment: "Mild Anxiety"

[0259] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0260] Goal: "Calculate the fair market rent price"

[0261] The generative AI model calculates an appropriate market rent based on the prompt sentence, taking into account rent data for similar properties in the area and past rent trends. The server receives the market rent data calculated by the generative AI model.

[0262] Next, the server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, trend graphs, etc.). Furthermore, appropriate rent negotiation support advice is provided to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, advice to reassure them is added.

[0263] Once the evidence and advice are ready, the server generates them in PDF or web format and sends them back to the device, where the user can review the evidence and advice and download the PDF or print it as needed.

[0264] As a concrete example, consider the case where Mr. Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal. Mr. Tanaka accesses the system from his smartphone and enters his address information. At this time, the emotion engine analyzes Mr. Tanaka's facial expressions and recognizes that he is feeling anxious. The server receives the entered address information and emotion information and calculates the average rent to be 300,000 yen based on the generative AI model. The server then generates evidence based on this data and adds emotion-based advice. Mr. Tanaka uses the evidence to negotiate a reduction in his current rent of 350,000 yen to 300,000 yen.

[0265] Furthermore, if the system recognizes that Tanaka felt a great deal of stress during the negotiations, it will suggest the option of negotiating on his behalf, and if Tanaka agrees, the server will negotiate on his behalf, thereby reducing Tanaka's mental burden and helping to achieve a fair rent.

[0266] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0267] System program processing flow

[0268] 1. Divide into processing steps

[0269] 1. User address input and emotion recognition

[0270] 2. The server receives the address information and emotion information.

[0271] 3. Calculating the market rent

[0272] 4. Generating and providing evidence that takes emotional information into account

[0273] 5. Rent negotiation support and proxy proposals

[0274] 2. Explain each processing step in detail

[0275] Step 1:

[0276] The user launches the application using a device (PC or smartphone).

[0277] The user enters the address information of the rental property into the input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo").

[0278] Input: Address information

[0279] Processing: The emotion engine analyzes the user's input speed, facial expressions, and voice to recognize their emotional state.

[0280] Output: Recognized emotion information

[0281] How it works: The emotion engine (e.g., Microsoft Azure Cognitive Services Emotion API) collects data from the user's camera and microphone and analyzes their emotions in real time. Address information and emotion information are sent from the device to the server.

[0282] Step 2:

[0283] The server receives the address information and emotion information sent by the user.

[0284] Input: Address information and emotion information

[0285] Processing: Parses the received information and prepares it for passing to the generative AI model.

[0286] Output: Parsed address information and sentiment information

[0287] What it does: The server checks the data it receives and formats it as needed, standardizing addresses and sentiment information for consistency.

[0288] Step 3:

[0289] The server runs the generative AI model.

[0290] Input: Analyzed address information and sentiment information, historical data (rent trend data for the same area over the past year, average rent data for surrounding properties)

[0291] Processing: Send a prompt to the generative AI model to calculate the appropriate market rent.

[0292] Output: Calculated market rent data

[0293] Specific operation: The server sends the following prompt to the generative AI model:

[0294] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0295] User Sentiment: "Mild Anxiety"

[0296] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0297] Goal: "Calculate the fair market rent price"

[0298] A generative AI model (e.g., OpenAI GPT-4) performs calculations based on this information and outputs an appropriate market rent.

[0299] Step 4:

[0300] The server generates evidence based on the calculated market rent and provides emotion-based advice.

[0301] Input: Calculated market rent data, sentiment information

[0302] Processing: Document market rents as evidence and add emotionally informed advice.

[0303] Output: Generated evidence and advice

[0304] Specific operation: The server compiles the calculated rent market price into a PDF or web report. Taking into account emotional information, if the user is feeling anxious, it adds reassuring advice and specific negotiation steps.

[0305] Step 5:

[0306] The server returns evidence and advice to the terminal.

[0307] Input: Generated evidence and advice

[0308] Processing: Send evidence and advice to the terminal.

[0309] Output: Evidence and advice displayed on the terminal

[0310] Specific operation: The evidence and advice returned from the server arrives at the terminal and is displayed on the user interface. The user can review it and download or print the PDF as needed.

[0311] It includes specific actions at each step and provides a detailed explanation of how the system works.

[0312] (Application example 2)

[0313] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] The present invention solves the problem that the information and support provided by conventional rent negotiation support systems does not take into account the emotional state of the user, making it difficult for users to negotiate rent with confidence. Another problem is that there is a lack of personalized recommended content that corresponds to the emotional state of the user.

[0315] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's address information, means for receiving the address information, means including a generative AI model that calculates a rent market price based on the address information, means including an emotion engine that analyzes the user's emotional state, means for providing rent negotiation support optimized based on the analyzed emotional state, means for generating personalized recommended content based on the emotional state of the viewing content, means for transmitting emotion information to the server, means for generating the calculated rent market price as evidence, and means for returning the evidence to the terminal. This allows the user to receive optimal rent negotiation support that takes their emotional state into consideration, and further enables them to enjoy personalized recommended content based on their emotional state in viewing content as well.

[0316] "User" refers to the end user who uses the system to negotiate rent and view content.

[0317] "Address information" refers to data containing detailed information about the location of the property where the user lives.

[0318] "Server" refers to the computer system that receives, analyzes, and processes address information and emotion information sent by users.

[0319] A "generative AI model" refers to an artificial intelligence algorithm that calculates average rent prices based on given data.

[0320] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions, voice, etc.

[0321] "Optimized rent negotiation support" refers to advice and tools provided to facilitate rent negotiations, taking into account the user's emotional state.

[0322] "Personalized recommended content" refers to viewing content that is individually suggested based on the user's emotional state.

[0323] "Emotion information" refers to data that indicates the user's current emotional state as analyzed by the emotion engine.

[0324] "Evidence" refers to empirical materials including market rent prices and the underlying data, which users use when negotiating rent.

[0325] "Terminal" refers to a device such as a smartphone, PC, or tablet that allows a user to access the system via the Internet.

[0326] To implement this invention, a user utilizes a system that analyzes their emotional state and appropriately negotiates rent. This system consists of an application and a server that users can access via devices such as smartphones and PCs.

[0327] System Configuration

[0328] 1. User address input and emotion recognition

[0329] The user launches the application using a device such as a smartphone and enters the address information of the rental property. As the user enters the information, the emotion engine analyzes the user's typing speed, facial expression, tone of voice, etc. to obtain emotional information. This allows the system to recognize how the user feels about rent negotiations.

[0330] 2. The server receives the address information and emotion information.

[0331] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[0332] 3. Calculating the market rent

[0333] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[0334] 4. Generating and providing evidence that takes emotional information into account

[0335] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[0336] 5. Supporting users in using the service and negotiating rent

[0337] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user then uses the generated evidence to negotiate the rent when it comes time to renew the rental contract. For example, the server may suggest to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence. The emotion engine may also suggest negotiating the rent on the user's behalf, depending on the user's emotional state. For example, if the server recognizes that the user is feeling very stressed, the server will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on the user's behalf. The server then notifies the owner or management company of the details of the negotiation along with the evidence.

[0338] Program processing

[0339] This program uses OpenCV to capture the user's face, convert it to grayscale, and then input it into a pre-trained emotion recognition model (pre-prepared pkl file) to analyze the user's emotional state. Once the emotion is recognized, an API request is made based on the emotion to obtain recommended content information.

[0340] Hardware and software used

[0341] Hardware: Smartphone or PC camera and microphone.

[0342] Software: Python, OpenCV, sklearn, requests.

[0343] Specific examples

[0344] For example, consider a specific user named Tanaka, who lives at an address in Tokyo and is about to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka wishes, the server will negotiate on his behalf. In this way, Tanaka can proceed with the rent negotiation with peace of mind.

[0345] Prompt Sentence Examples

[0346] "I want to laugh at movies, so please recommend some movies that will put me in a good mood."

[0347] "I want to relax, so please recommend some relaxation music."

[0348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0349] Step 1:

[0350] This is a method for users to input address information. Users input the address information of rental properties into an input form on their smartphone or PC. At this time, the emotion engine analyzes the input speed, facial expression, and tone of voice. The input includes address information and biometric information (facial expression, voice, etc.), and emotional information is generated as the output.

[0351] Step 2:

[0352] The terminal sends the address information and emotion information to the server. The sent information is parsed (analyzed) on the server side and separated into address information and emotion information. The address information and emotion information are included as input, and the analyzed data is obtained as output.

[0353] Step 3:

[0354] The server uses a generative AI model to calculate the average rent based on the address information received, referencing rent data for similar properties in the area and past rent trends. The input includes the address information and data on surrounding properties, and the output is the average rent.

[0355] Step 4:

[0356] The server generates evidence for optimized rent negotiation support, taking into account the emotional information recognized by the emotion engine. The generated evidence includes market rent data and the underlying data. Market rent data and emotional information are included as inputs, and evidence is obtained as output.

[0357] Step 5:

[0358] The server sends the evidence back to the terminal. The terminal receives this evidence and displays it in a user interface. The user can view the evidence and download or print it as a PDF. The input contains the evidence, and the output is the displayed evidence.

[0359] Step 6:

[0360] The user uses the generated evidence to negotiate the rent, and if necessary, proposes to the management company to lower the current rent. The input includes the evidence, and the output is the negotiation result.

[0361] Step 7:

[0362] The emotion engine may also suggest proxy negotiation of the rent depending on the user's emotional state. For example, if the server recognizes that the user is feeling highly stressed, it will suggest a proxy negotiation option. If the user requests it, the server will negotiate the rent on their behalf. The input includes emotional information and evidence, and the output is the result of the proxy negotiation.

[0363] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0364] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0365] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0366] [Second embodiment]

[0367] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0368] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0369] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0370] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0371] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0372] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0373] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0374] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0375] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0376] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0377] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0378] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0379] This invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. To achieve this, the system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0380] Enter user address information

[0381] First, the user must enter their address information. The user starts the application using a device (PC or smartphone) and enters the address of the rental property (for example, 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the input form. This input information is sent to the server by pressing the "Submit" button.

[0382] The server receives address information and calculates the average rent

[0383] The server receives the address information sent by the user. Based on this address information, a generative AI model is used to calculate the real-time market rent. The generative AI model calculates an accurate market rent by taking into account rent data for similar properties in the area and past rent trends. In this calculation process, it is important that the collected data reflects the actual market price.

[0384] Generate and provide evidence of market rents

[0385] The server generates the calculated market rent data as evidence. The evidence includes the calculated market rent data and the underlying data (for example, rent data for surrounding properties and past rent trends). The evidence is generated in PDF or web format and sent from the server to the terminal.

[0386] The terminal receives the evidence sent from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary.

[0387] Rent negotiation assistance

[0388] Users can use the generated evidence to negotiate rent when renewing a rental contract. For example, a user can inform a management company that the current rent is 350,000 yen and negotiate to lower it to 300,000 yen based on the evidence. This evidence enables persuasive negotiations with the owner and management company.

[0389] Furthermore, if the user wishes, they can use a service in which the server handles rent negotiations on their behalf. In this case, the server uses evidence to negotiate rent on the user's behalf and contacts the owner or management company. This proxy negotiation significantly reduces the time and effort required for the user to negotiate rent.

[0390] Specific examples

[0391] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address. The server receives the address information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this data as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on that, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0392] In this way, this system will be a powerful tool for residents to ensure they receive fair rent when renewing their rental contracts.

[0393] The processing flow will be explained below.

[0394] Step 1:

[0395] The user starts the application using a terminal. The user enters the address information of the rental property into the application's input form. Specifically, the user enters an address such as "1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0396] Step 2:

[0397] When the user presses the "Send" button, the address information is sent from the device to the server via an HTTP request.

[0398] Step 3:

[0399] The server receives the address information sent from the device, parses the received data, and prepares it for passing to the generative AI model.

[0400] Step 4:

[0401] The server calculates the market rent using a generated AI model, which takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data.

[0402] Step 5:

[0403] The server generates evidence based on the calculated market rent. The evidence includes market rent data and the underlying data (such as rent data for surrounding properties and trend graphs).

[0404] Step 6:

[0405] The server returns the generated evidence to the terminal using an HTTP response.

[0406] Step 7:

[0407] The terminal receives the evidence returned from the server and displays it on the user interface for the user to review.

[0408] Step 8:

[0409] The user uses the evidence to negotiate the rent when renewing the rental contract. Specifically, the user proposes to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence.

[0410] Step 9:

[0411] If the user wishes, they can select the proxy negotiation option, which allows the server to negotiate the rent on their behalf without the user having to negotiate directly.

[0412] Step 10:

[0413] The server uses the evidence to negotiate rent with the management company or owner on behalf of the user, and conveys the evidence and the details of the negotiation via email or telephone.

[0414] Example 1

[0415] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0416] Previously, when residents negotiated rent at the time of lease contract renewal, it was difficult to grasp the appropriate market rent, making it difficult to negotiate persuasively with management companies and owners. In particular, the inability to obtain accurate market rent data based on real-time data meant there was a lack of evidence, which meant that residents could renew their contracts on unfavorable terms. Another problem was that rent negotiations themselves were complicated, requiring a lot of time and effort.

[0417] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0418] In this invention, the server includes a means for a user to input address information, a means for receiving the address information, a means including a generative AI model that calculates average rent prices based on the address information, a means for generating the calculated average rent prices as evidence, a means for returning the evidence to a terminal, a means for generating the evidence in PDF or web format, a means for calculating average rent prices in real time using the generative AI model with data on surrounding properties and past rent trends, a means for displaying the evidence on a user interface, and a means for storing the address information sent from the terminal to the server in a database. This allows residents to understand the appropriate average rent prices when renewing their rental contracts and negotiate rent based on convincing evidence. Furthermore, using a server-based service to handle rent negotiations can reduce the residents' time and effort.

[0419] "User" refers to a resident of a rental property who uses the system to negotiate rent.

[0420] "Address information" is data indicating the location of a rental property, and specifically includes information such as prefecture, city, ward, town, street name, and house number.

[0421] The "server" is a computer system that receives the user's address information via the network and calculates the average rent using a generative AI model.

[0422] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to make predictions and analyses based on input data.

[0423] "Average rent" is data that shows the average and distribution of appropriate rents in a particular area or property type.

[0424] "Evidence" refers to documents and supporting evidence provided to support rent negotiations, including calculated market rent data and the underlying data.

[0425] A "terminal" is a computing device used by a user, specifically a PC or smartphone.

[0426] A "database" is a system for efficiently storing, managing, and searching structured data.

[0427] The "user interface" is the part that provides the screen and operation means for the user to interact with the system.

[0428] "Rent negotiation" refers to the process of reviewing current rental terms and adjusting them to an appropriate rent.

[0429] "PDF" is an abbreviation for Portable Document Format, a file format for electronically distributing and displaying documents while preserving their format and layout.

[0430] "Web format" refers to a format of digital content that can be viewed and manipulated through a web browser.

[0431] The present invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. This system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0432] Hardware and software used

[0433] This system uses the following hardware and software:

[0434] Server: A central computer that processes data and runs AI models.

[0435] Terminal: A device used by a user, such as a PC or smartphone.

[0436] Generative AI models: Examples include natural language processing models such as OpenAI's GPT-3 and Google's BERT.

[0437] Database: A data management system for storing address information and rent data.

[0438] Application: Software that allows users to enter address information and verify evidence.

[0439] Explanation of program processing

[0440] First, the user launches the application using their own device (PC or smartphone) and enters address information. Specifically, the user enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the application's input form and presses the "Submit" button to send it to the server.

[0441] The server receives the address information sent by the user. This address information is stored in a specific database table. The server then uses a generative AI model to calculate the average rent based on the received address information, taking into account rent data for similar properties in the area and past rent trends.

[0442] Once the market rent is calculated, the server generates the results as evidence. The evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, past rent trends). The evidence is generated in PDF or web format and sent from the server to the user's device.

[0443] The user checks the received evidence on their device. The evidence is displayed on the application and can be downloaded or printed as needed. The user can use this evidence to negotiate the rent when renewing their rental contract. For example, if the current rent is 350,000 yen, the user can use the evidence to negotiate with the management company or owner to lower it to 300,000 yen.

[0444] Furthermore, if the user wishes, the server will negotiate the rent on their behalf. In this case, the server will use an automatic email sending function or API to contact the management company or owner on the user's behalf and negotiate. This reduces the user's time and effort.

[0445] Examples and prompts

[0446] For example, suppose a user named Tanaka lives in a rental property at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his lease contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address information. The server receives this information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on it, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0447] Example prompt sentence:

[0448] "Please tell me the real-time average rent for properties around 1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0449] "Please generate evidence to review my current rent of 350,000 yen to a fair price."

[0450] In this way, this system is a powerful tool that helps residents to obtain fair rent when renewing their rental contracts.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1:

[0453] The user starts the application using a device (PC or smartphone), enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) in the address information input form, and presses the "Submit" button.

[0454] Input: Rental property address information

[0455] Output: Request with address information sent to server

[0456] What happens: A user opens the application, enters address information, and presses the submit button.

[0457] Step 2:

[0458] The server receives the address information submitted by the user, parses the HTTP request, and stores the address information in a specific database table.

[0459] Input: Address information submitted by the user

[0460] Output: Address information stored in a database

[0461] Specific operation: The server receives the HTTP request, analyzes it, and saves the extracted address information in a database.

[0462] Step 3:

[0463] The server uses a generative AI model based on the stored address information to calculate the average rent price. The generative AI model includes data on surrounding properties and past rent trends, and takes this data into account to derive the average rent price in real time.

[0464] Input: Address information stored in the database

[0465] Output: Calculated market rent data

[0466] Specific operation: The server inputs address information into a generative AI model, which then calculates the average rent.

[0467] Step 4:

[0468] The server generates evidence based on the generated market rent data. The evidence includes market rent data and its basis (e.g., data on surrounding properties, past rent trends). The evidence is generated in PDF format or web format.

[0469] Input: Calculated market rent data

[0470] Output: Generated evidence (PDF or web format)

[0471] What happens: The server formats the rent quote data and creates evidence using a PDF generation library.

[0472] Step 5:

[0473] The server sends the generated evidence to the user's device, and returns the evidence to the user as an HTTP response or provides a URL link.

[0474] Input: Generated evidence

[0475] Output: Evidence sent to the user's device

[0476] Specific operation: The server generates an evidence file and returns it in an HTTP response. In some cases, it generates a URL link and notifies the user.

[0477] Step 6:

[0478] The user checks the received evidence on the device. The evidence is displayed within the application, and the user can download or print it as needed.

[0479] Input: Evidence received from the server

[0480] Output: User interface with evidence displayed

[0481] Specific operations: The user opens the evidence confirmation screen within the application, checks the contents, and operates the download and print buttons.

[0482] Step 7:

[0483] The user can use the generated evidence to negotiate rent when renewing the rental contract. Specifically, the user submits the evidence to the management company or owner and negotiates to revise the current rent to a fair price.

[0484] Input:Evidence

[0485] Output: Rent negotiation result (e.g. rent reduction)

[0486] Specific actions: The user presents evidence in print or digital form and negotiates with the management company.

[0487] Step 8:

[0488] If the user wishes, the server will handle rent negotiations on their behalf. The server uses an automatic email sending function and API to contact the management company or owner and negotiate.

[0489] Input: User's request for negotiation

[0490] Output: Rent negotiation result (e.g. rent reduction)

[0491] Specific operation: The server receives a request for negotiation on behalf of the user and uses the automatic email sending function to send a negotiation email to the management company.

[0492] (Application example 1)

[0493] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0494] With conventional rent negotiation systems, it was difficult for residents to accurately grasp the market rent in real time, and the provision of evidence was limited, making it difficult to conduct rent negotiations effectively.In addition, support for viewing rental properties and rent negotiations using virtual reality technology was not widespread, so a more efficient and effective system was needed.

[0495] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0496] In this invention, the server includes means for a user to input address information, means for receiving the address information, means including a generative AI model for calculating market rents based on the address information, means for generating the calculated market rents as evidence, means for returning the evidence to a terminal, means for viewing properties in a virtual reality environment, means for displaying the evidence in the virtual reality environment, and means for supporting rent negotiations in the virtual reality environment. This allows a user to check market rents in real time and engage in efficient and persuasive rent negotiations through the virtual reality environment.

[0497] The "means by which the user inputs address information" refers to an interface or device that allows the user to input address information for their own residence or rental property.

[0498] The "server that receives the address information" is a computer system that receives and processes the address information sent by the user.

[0499] A "server including a generative AI model that calculates average rent prices based on the address information" is a computer system that has an internal generative AI model for calculating average rent prices using address information.

[0500] "Means for generating evidence of calculated market rents" refers to the functions and processes for turning the market rents calculated by the generative AI model into evidence.

[0501] The "means for returning the evidence to the terminal" refers to a function or process for transmitting the market rent data generated as evidence to the terminal used by the user.

[0502] "Means for viewing properties in a virtual reality environment" refers to systems or technologies that allow users to view rental properties using virtual reality technology.

[0503] The "means for displaying the evidence within the virtual reality environment" refers to a system or technology for visually presenting evidence of market rent prices to a user within a virtual reality environment.

[0504] The "means for supporting rent negotiations within the virtual reality environment" refers to a system or function that supports a user when negotiating rent within the virtual reality environment.

[0505] This invention is a system that provides accurate market rent information when users negotiate rent for rental properties. It also makes it possible to more efficiently view properties and negotiate rent using a virtual reality environment.

[0506] System Configuration

[0507] 1. How users enter address information

[0508] Users use an interface to input address information using a smartphone or PC, which can be provided as an application or web form.

[0509] 2. Server that receives the address information

[0510] The server receives the address information entered by the user and stores it in a database. This reception process uses HTTP requests and REST APIs.

[0511] 3. A server containing a generative AI model that calculates market rents based on the address information.

[0512] The server uses a generative AI model to calculate average rent prices based on the address information entered by the user. This generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. The model learns from historical rent data and current market conditions to provide accurate rent prices in real time.

[0513] 4. A method for generating evidence of the calculated market rent

[0514] The server generates evidence of the calculated rent market price. This evidence is created in PDF or web page format and includes detailed data and rationale for the rent market price. Python's FPDF library is used to generate the evidence.

[0515] 5. Means for returning said evidence to the terminal

[0516] The server sends the generated evidence to the user's device using a REST API or email sending system. The user can then check the evidence on their smartphone or PC.

[0517] 6. A way to view properties in a virtual reality environment

[0518] Users can virtually view properties using a VR headset. The VR environment is built in conjunction with Unity and Unreal Engine to provide users with a 360-degree virtual experience.

[0519] 7. Means for displaying said evidence within said virtual reality environment

[0520] This is a system for displaying evidence of calculated market rents in a virtual reality environment, allowing users to check market rents in real time while viewing properties.

[0521] 8. Means for assisting in rent negotiations within said virtual reality environment

[0522] The chatbot function is used in virtual reality to support real-time rent negotiations. This chatbot uses natural language processing technology to converse with users. It can also negotiate on behalf of users, providing them with the ability to negotiate rent on their behalf.

[0523] Specific examples of processing

[0524] The user views a rental property in a virtual store and enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo." The server receives the address information and calculates the average rent using a generative AI model. The result is 300,000 yen, and evidence is displayed in the virtual space. The user then begins rent negotiations with the management company via a chatbot.

[0525] Prompt Sentence Examples

[0526] "Please calculate the average rent for the following address: 1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0527] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0528] Step 1:

[0529] The user enters address information. Using a smartphone or PC, the user enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo" through an application or web form. The entered address information is sent from the device to the server.

[0530] Step 2:

[0531] The server receives the address information, processes the HTTP request, and stores the address information in a database. This data is then used by the generative AI model to calculate market rents.

[0532] Step 3:

[0533] The server calculates the average rent. The server inputs the stored address information into a generative AI model to predict the average rent. This model is built using TensorFlow and PyTorch, and predicts the average rent in real time based on past data and market trends. The output is average rent data such as "300,000 yen."

[0534] Step 4:

[0535] The server generates evidence. Based on the calculated market rent data, the server creates evidence in PDF or web format. This evidence includes details of market rents and the underlying data. The PDF is generated using a library such as Python's FPDF library.

[0536] Step 5:

[0537] The server returns the evidence to the device. The generated evidence is sent back to the user's smartphone or PC via REST API or email. The user can then view this evidence on their device.

[0538] Step 6:

[0539] Users can view properties in a virtual reality environment. Users wear a VR headset and access the virtual reality environment. This environment is built using Unity and Unreal Engine, allowing users to inspect the property in detail with a 360-degree view.

[0540] Step 7:

[0541] The server displays evidence within the virtual reality environment. Rent market evidence is displayed within the user's field of vision. This display is done in real time, providing rent data and its rationale as an overlay in the virtual space.

[0542] Step 8:

[0543] Users will be provided with a means to assist in rent negotiations. Within the virtual reality environment, a chatbot will receive instructions from the user and assist in rent negotiations with the property management company in real time. The chatbot will use natural language processing technology to converse and convey the user's request for a rent reduction. If the user so desires, the chatbot can also negotiate with the property management company on their behalf.

[0544] As described above, the data input and output are clearly defined at each step, and data processing and calculations are performed based on this, allowing the system to enable users to efficiently negotiate rent in a virtual reality environment.

[0545] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0546] This invention combines a system that enables residents of rental housing to easily negotiate rent when renewing their rental contracts with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state and optimizes support for rent negotiations based on the results.

[0547] User address input and emotion recognition

[0548] First, the user launches the application using a device (PC or smartphone). The user enters the address information of the rental property into the application's input form (for example, "1-2-3 XX-cho, Shibuya-ku, Tokyo"). As the user enters the information, the emotion engine analyzes the user's input speed and facial expression, and recognizes the user's emotional state regarding the address information. This emotional information is also sent to the server.

[0549] The server receives the address information and emotion information.

[0550] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[0551] Calculating market rent

[0552] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[0553] Generating and providing evidence that takes emotional information into account

[0554] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[0555] Rent negotiation support and proxy proposals

[0556] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user can use the generated evidence to negotiate the rent when renewing the rental contract. For example, based on the evidence, the user can propose to the management company that the current rent of 350,000 yen be reduced to 300,000 yen.

[0557] The emotion engine may also suggest negotiating rent on behalf of the user depending on the user's emotional state. For example, if the server detects that the user is feeling highly stressed, it will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on their behalf. The server will then communicate the details of the negotiation along with the evidence to the owner or management company.

[0558] Specific examples

[0559] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and is due to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka requests it, the server will negotiate on his behalf.

[0560] In this way, this system supports rent negotiations while taking into account the user's emotional state, making it a powerful tool for residents to achieve a fair rent.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The user launches the application using their device. The user enters the address information of the rental property (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo") into the application's input form. As the user enters information, the emotion engine analyzes the user's input patterns and facial expression data in real time to recognize their emotional state (e.g., anxiety, stress).

[0564] Step 2:

[0565] The user presses the "Submit" button to send the address information and the detected emotion information to the server via an HTTP request.

[0566] Step 3:

[0567] The server receives the address information and emotion information sent from the device, parses the data, and passes the address information and emotion information to the appropriate processing module.

[0568] Step 4:

[0569] The server calculates the average rent using a generative AI model. The generative AI model calculates the real-time average rent (e.g., 300,000 yen) based on the address information by collecting and analyzing rent data for similar properties in the area and past rent trends.

[0570] Step 5:

[0571] The server generates evidence based on the calculated market rent. The evidence includes market rent data and related evidence (such as rent data for surrounding properties and trend graphs). Furthermore, based on the emotional information recognized by the emotion engine, negotiation support advice (e.g., "Please pay attention to these points to reduce your anxiety") is added to the user.

[0572] Step 6:

[0573] The server returns the generated evidence to the terminal using an HTTP response.

[0574] Step 7:

[0575] The terminal receives the evidence returned from the server. The terminal displays the evidence in the user interface so that the user can review it. The user can review the evidence and download or print it as a PDF.

[0576] Step 8:

[0577] Users negotiate rent based on evidence when renewing a rental contract. Based on evidence, users propose to the management company that the current rent (e.g., 350,000 yen) be lowered to a fair market price (e.g., 300,000 yen). Users can negotiate more effectively by following the advice provided by the emotion engine.

[0578] Step 9:

[0579] The emotion engine continuously monitors the user's emotional state, and if it detects that the user is experiencing high levels of stress or anxiety, it suggests proxy negotiation options, which are displayed in the user interface.

[0580] Step 10:

[0581] If the user selects the proxy negotiation option, the server will negotiate the rent on the user's behalf. The server will organize the evidence and negotiation details and contact the management company or owner. Specifically, it will send the evidence by email or phone and explain the negotiation points.

[0582] Through the above steps, the system can effectively support rent negotiations while taking into account the user's emotional state.

[0583] Example 2

[0584] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] Conventional rent negotiation systems have the problem that users negotiate rent without considering their own emotional state, making it difficult to negotiate effectively. In particular, emotions such as tension and anxiety often have a negative impact on the outcome of the negotiation, placing a heavy burden on users. Furthermore, many users have little experience in rent negotiations, making it difficult for them to collect appropriate evidence and implement effective approaches. Furthermore, if users feel strong stress during the negotiation process, they may be unable to achieve a fair rent.

[0586] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0587] In this invention, the server includes a means for a user to input address information and recognize the user's emotional state; a server that receives the address information and emotional information; a server that includes a generative AI model that calculates the average rent price based on the address information and emotional information; a means for generating the calculated average rent price as evidence and providing advice to the user based on the emotional information; and a means for returning the evidence and advice to the terminal. This allows the system to calculate an appropriate average rent price and provide effective evidence while taking the user's emotional state into consideration, allowing the user to negotiate the rent with peace of mind. Furthermore, by offering proxy negotiations as needed, the system can reduce the user's mental burden and help them achieve a more appropriate rent price.

[0588] "User address information" is geographical information that a user inputs to identify the location of a rental property.

[0589] "Emotional state" is information that represents the user's emotions and mood, and is analyzed from input speed, facial expressions, voice, etc.

[0590] A "server" is a computer device that receives address information and emotion information sent by a user and processes and analyzes them.

[0591] A "generative AI model" is a program that uses artificial intelligence algorithms to calculate market rent prices based on specific input data (address information and emotional information).

[0592] "Evidence" refers to documents or reports containing data or supporting information to support market rents.

[0593] "Advice" is advice or suggestions provided to users based on the results of generative AI models and emotion engines.

[0594] A "terminal" is a device (such as a personal computer or smartphone) that a user uses to input information and receive evidence and advice sent from a server.

[0595] An "emotion engine" is software or a system for analyzing a user's emotional state, analyzing data such as the user's input speed, facial expressions, and voice.

[0596] "Market rent" refers to the market price of rent in a specific area or property, and is calculated using a generative AI model.

[0597] This invention is a system that allows residents of rental housing to easily negotiate rent. The system uses an emotion engine and generative AI model to recognize the user's emotional state and assist with rent negotiations based on this.

[0598] First, the user launches the application using a device (such as a PC or smartphone). The user enters the address information of the rental property into the application's input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo"). At this time, an emotion engine (such as Microsoft Azure Cognitive Services Emotion API) analyzes the user's input speed, facial expressions, and voice to recognize their emotional state. The device then sends the address information and emotion information to the server.

[0599] The server receives the address and emotion information sent by the user. The received information is parsed and passed to a generative AI model (e.g., OpenAI GPT-4). The server sends the following prompt to the generative AI model:

[0600] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0601] User Sentiment: "Mild Anxiety"

[0602] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0603] Goal: "Calculate the fair market rent price"

[0604] The generative AI model calculates an appropriate market rent based on the prompt sentence, taking into account rent data for similar properties in the area and past rent trends. The server receives the market rent data calculated by the generative AI model.

[0605] Next, the server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, trend graphs, etc.). Furthermore, appropriate rent negotiation support advice is provided to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, advice to reassure them is added.

[0606] Once the evidence and advice are ready, the server generates them in PDF or web format and sends them back to the device, where the user can review the evidence and advice and download the PDF or print it as needed.

[0607] As a concrete example, consider the case where Mr. Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal. Mr. Tanaka accesses the system from his smartphone and enters his address information. At this time, the emotion engine analyzes Mr. Tanaka's facial expressions and recognizes that he is feeling anxious. The server receives the entered address information and emotion information and calculates the average rent to be 300,000 yen based on the generative AI model. The server then generates evidence based on this data and adds emotion-based advice. Mr. Tanaka uses the evidence to negotiate a reduction in his current rent of 350,000 yen to 300,000 yen.

[0608] Furthermore, if the system recognizes that Tanaka felt a great deal of stress during the negotiations, it will suggest the option of negotiating on his behalf, and if Tanaka agrees, the server will negotiate on his behalf, thereby reducing Tanaka's mental burden and helping to achieve a fair rent.

[0609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0610] System program processing flow

[0611] 1. Divide into processing steps

[0612] 1. User address input and emotion recognition

[0613] 2. The server receives the address information and emotion information.

[0614] 3. Calculating the market rent

[0615] 4. Generating and providing evidence that takes emotional information into account

[0616] 5. Rent negotiation support and proxy proposals

[0617] 2. Explain each processing step in detail

[0618] Step 1:

[0619] The user launches the application using a device (PC or smartphone).

[0620] The user enters the address information of the rental property into the input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo").

[0621] Input: Address information

[0622] Processing: The emotion engine analyzes the user's input speed, facial expressions, and voice to recognize their emotional state.

[0623] Output: Recognized emotion information

[0624] How it works: The emotion engine (e.g., Microsoft Azure Cognitive Services Emotion API) collects data from the user's camera and microphone and analyzes their emotions in real time. Address information and emotion information are sent from the device to the server.

[0625] Step 2:

[0626] The server receives the address information and emotion information sent by the user.

[0627] Input: Address information and emotion information

[0628] Processing: Parses the received information and prepares it for passing to the generative AI model.

[0629] Output: Parsed address information and sentiment information

[0630] What it does: The server checks the data it receives and formats it as needed, standardizing addresses and sentiment information for consistency.

[0631] Step 3:

[0632] The server runs the generative AI model.

[0633] Input: Analyzed address information and sentiment information, historical data (rent trend data for the same area over the past year, average rent data for surrounding properties)

[0634] Processing: Send a prompt to the generative AI model to calculate the appropriate market rent.

[0635] Output: Calculated market rent data

[0636] Specific operation: The server sends the following prompt to the generative AI model:

[0637] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0638] User Sentiment: "Mild Anxiety"

[0639] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0640] Goal: "Calculate the fair market rent price"

[0641] A generative AI model (e.g., OpenAI GPT-4) performs calculations based on this information and outputs an appropriate market rent.

[0642] Step 4:

[0643] The server generates evidence based on the calculated market rent and provides emotion-based advice.

[0644] Input: Calculated market rent data, sentiment information

[0645] Processing: Document market rents as evidence and add emotionally informed advice.

[0646] Output: Generated evidence and advice

[0647] Specific operation: The server compiles the calculated rent market price into a PDF or web report. Taking into account emotional information, if the user is feeling anxious, it adds reassuring advice and specific negotiation steps.

[0648] Step 5:

[0649] The server returns evidence and advice to the terminal.

[0650] Input: Generated evidence and advice

[0651] Processing: Send evidence and advice to the terminal.

[0652] Output: Evidence and advice displayed on the terminal

[0653] Specific operation: The evidence and advice returned from the server arrives at the terminal and is displayed on the user interface. The user can review it and download or print the PDF as needed.

[0654] It includes specific actions at each step and provides a detailed explanation of how the system works.

[0655] (Application example 2)

[0656] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0657] The present invention solves the problem that the information and support provided by conventional rent negotiation support systems does not take into account the emotional state of the user, making it difficult for users to negotiate rent with confidence. Another problem is that there is a lack of personalized recommended content that corresponds to the emotional state of the user.

[0658] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's address information, means for receiving the address information, means including a generative AI model that calculates a rent market price based on the address information, means including an emotion engine that analyzes the user's emotional state, means for providing rent negotiation support optimized based on the analyzed emotional state, means for generating personalized recommended content based on the emotional state of the viewing content, means for transmitting emotion information to the server, means for generating the calculated rent market price as evidence, and means for returning the evidence to the terminal. This allows the user to receive optimal rent negotiation support that takes their emotional state into consideration, and further enables them to enjoy personalized recommended content based on their emotional state in viewing content as well.

[0659] "User" refers to the end user who uses the system to negotiate rent and view content.

[0660] "Address information" refers to data containing detailed information about the location of the property where the user lives.

[0661] "Server" refers to the computer system that receives, analyzes, and processes address information and emotion information sent by users.

[0662] A "generative AI model" refers to an artificial intelligence algorithm that calculates average rent prices based on given data.

[0663] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions, voice, etc.

[0664] "Optimized rent negotiation support" refers to advice and tools provided to facilitate rent negotiations, taking into account the user's emotional state.

[0665] "Personalized recommended content" refers to viewing content that is individually suggested based on the user's emotional state.

[0666] "Emotion information" refers to data that indicates the user's current emotional state as analyzed by the emotion engine.

[0667] "Evidence" refers to empirical materials including market rent prices and the underlying data, which users use when negotiating rent.

[0668] "Terminal" refers to a device such as a smartphone, PC, or tablet that allows a user to access the system via the Internet.

[0669] To implement this invention, a user utilizes a system that analyzes their emotional state and appropriately negotiates rent. This system consists of an application and a server that users can access via devices such as smartphones and PCs.

[0670] System Configuration

[0671] 1. User address input and emotion recognition

[0672] The user launches the application using a device such as a smartphone and enters the address information of the rental property. As the user enters the information, the emotion engine analyzes the user's typing speed, facial expression, tone of voice, etc. to obtain emotional information. This allows the system to recognize how the user feels about rent negotiations.

[0673] 2. The server receives the address information and emotion information.

[0674] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[0675] 3. Calculating the market rent

[0676] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[0677] 4. Generating and providing evidence that takes emotional information into account

[0678] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[0679] 5. Supporting users in using the service and negotiating rent

[0680] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user then uses the generated evidence to negotiate the rent when it comes time to renew the rental contract. For example, the server may suggest to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence. The emotion engine may also suggest negotiating the rent on the user's behalf, depending on the user's emotional state. For example, if the server recognizes that the user is feeling very stressed, the server will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on the user's behalf. The server then notifies the owner or management company of the details of the negotiation along with the evidence.

[0681] Program processing

[0682] This program uses OpenCV to capture the user's face, convert it to grayscale, and then input it into a pre-trained emotion recognition model (pre-prepared pkl file) to analyze the user's emotional state. Once the emotion is recognized, an API request is made based on the emotion to obtain recommended content information.

[0683] Hardware and software used

[0684] Hardware: Smartphone or PC camera and microphone.

[0685] Software: Python, OpenCV, sklearn, requests.

[0686] Specific examples

[0687] For example, consider a specific user named Tanaka, who lives at an address in Tokyo and is about to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka wishes, the server will negotiate on his behalf. In this way, Tanaka can proceed with the rent negotiation with peace of mind.

[0688] Prompt Sentence Examples

[0689] "I want to laugh at movies, so please recommend some movies that will put me in a good mood."

[0690] "I want to relax, so please recommend some relaxation music."

[0691] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0692] Step 1:

[0693] This is a method for users to input address information. Users input the address information of rental properties into an input form on their smartphone or PC. At this time, the emotion engine analyzes the input speed, facial expression, and tone of voice. The input includes address information and biometric information (facial expression, voice, etc.), and emotional information is generated as the output.

[0694] Step 2:

[0695] The terminal sends the address information and emotion information to the server. The sent information is parsed (analyzed) on the server side and separated into address information and emotion information. The address information and emotion information are included as input, and the analyzed data is obtained as output.

[0696] Step 3:

[0697] The server uses a generative AI model to calculate the average rent based on the address information received, referencing rent data for similar properties in the area and past rent trends. The input includes the address information and data on surrounding properties, and the output is the average rent.

[0698] Step 4:

[0699] The server generates evidence for optimized rent negotiation support, taking into account the emotional information recognized by the emotion engine. The generated evidence includes market rent data and the underlying data. Market rent data and emotional information are included as inputs, and evidence is obtained as output.

[0700] Step 5:

[0701] The server sends the evidence back to the terminal. The terminal receives this evidence and displays it in a user interface. The user can view the evidence and download or print it as a PDF. The input contains the evidence, and the output is the displayed evidence.

[0702] Step 6:

[0703] The user uses the generated evidence to negotiate the rent, and if necessary, proposes to the management company to lower the current rent. The input includes the evidence, and the output is the negotiation result.

[0704] Step 7:

[0705] The emotion engine may also suggest proxy negotiation of the rent depending on the user's emotional state. For example, if the server recognizes that the user is feeling highly stressed, it will suggest a proxy negotiation option. If the user requests it, the server will negotiate the rent on their behalf. The input includes emotional information and evidence, and the output is the result of the proxy negotiation.

[0706] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0707] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0708] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0709] [Third embodiment]

[0710] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0711] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0712] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0713] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0714] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0715] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0716] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0717] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0718] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0719] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0720] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0721] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0722] This invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. To achieve this, the system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0723] Enter user address information

[0724] First, the user must enter their address information. The user starts the application using a device (PC or smartphone) and enters the address of the rental property (for example, 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the input form. This input information is sent to the server by pressing the "Submit" button.

[0725] The server receives address information and calculates the average rent

[0726] The server receives the address information sent by the user. Based on this address information, a generative AI model is used to calculate the real-time market rent. The generative AI model calculates an accurate market rent by taking into account rent data for similar properties in the area and past rent trends. In this calculation process, it is important that the collected data reflects the actual market price.

[0727] Generate and provide evidence of market rents

[0728] The server generates the calculated market rent data as evidence. The evidence includes the calculated market rent data and the underlying data (for example, rent data for surrounding properties and past rent trends). The evidence is generated in PDF or web format and sent from the server to the terminal.

[0729] The terminal receives the evidence sent from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary.

[0730] Rent negotiation assistance

[0731] Users can use the generated evidence to negotiate rent when renewing a rental contract. For example, a user can inform a management company that the current rent is 350,000 yen and negotiate to lower it to 300,000 yen based on the evidence. This evidence enables persuasive negotiations with the owner and management company.

[0732] Furthermore, if the user wishes, they can use a service in which the server handles rent negotiations on their behalf. In this case, the server uses evidence to negotiate rent on the user's behalf and contacts the owner or management company. This proxy negotiation significantly reduces the time and effort required for the user to negotiate rent.

[0733] Specific examples

[0734] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address. The server receives the address information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this data as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on that, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0735] In this way, this system will be a powerful tool for residents to ensure they receive fair rent when renewing their rental contracts.

[0736] The processing flow will be explained below.

[0737] Step 1:

[0738] The user starts the application using a terminal. The user enters the address information of the rental property into the application's input form. Specifically, the user enters an address such as "1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0739] Step 2:

[0740] When the user presses the "Send" button, the address information is sent from the device to the server via an HTTP request.

[0741] Step 3:

[0742] The server receives the address information sent from the device, parses the received data, and prepares it for passing to the generative AI model.

[0743] Step 4:

[0744] The server calculates the market rent using a generated AI model, which takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data.

[0745] Step 5:

[0746] The server generates evidence based on the calculated market rent. The evidence includes market rent data and the underlying data (such as rent data for surrounding properties and trend graphs).

[0747] Step 6:

[0748] The server returns the generated evidence to the terminal using an HTTP response.

[0749] Step 7:

[0750] The terminal receives the evidence returned from the server and displays it on the user interface for the user to review.

[0751] Step 8:

[0752] The user uses the evidence to negotiate the rent when renewing the rental contract. Specifically, the user proposes to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence.

[0753] Step 9:

[0754] If the user wishes, they can select the proxy negotiation option, which allows the server to negotiate the rent on their behalf without the user having to negotiate directly.

[0755] Step 10:

[0756] The server uses the evidence to negotiate rent with the management company or owner on behalf of the user, and conveys the evidence and the details of the negotiation via email or telephone.

[0757] Example 1

[0758] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0759] Previously, when residents negotiated rent at the time of lease contract renewal, it was difficult to grasp the appropriate market rent, making it difficult to negotiate persuasively with management companies and owners. In particular, the inability to obtain accurate market rent data based on real-time data meant there was a lack of evidence, which meant that residents could renew their contracts on unfavorable terms. Another problem was that rent negotiations themselves were complicated, requiring a lot of time and effort.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0761] In this invention, the server includes a means for a user to input address information, a means for receiving the address information, a means including a generative AI model that calculates average rent prices based on the address information, a means for generating the calculated average rent prices as evidence, a means for returning the evidence to a terminal, a means for generating the evidence in PDF or web format, a means for calculating average rent prices in real time using the generative AI model with data on surrounding properties and past rent trends, a means for displaying the evidence on a user interface, and a means for storing the address information sent from the terminal to the server in a database. This allows residents to understand the appropriate average rent prices when renewing their rental contracts and negotiate rent based on convincing evidence. Furthermore, using a server-based service to handle rent negotiations can reduce the residents' time and effort.

[0762] "User" refers to a resident of a rental property who uses the system to negotiate rent.

[0763] "Address information" is data indicating the location of a rental property, and specifically includes information such as prefecture, city, ward, town, street name, and house number.

[0764] The "server" is a computer system that receives the user's address information via the network and calculates the average rent using a generative AI model.

[0765] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to make predictions and analyses based on input data.

[0766] "Average rent" is data that shows the average and distribution of appropriate rents in a particular area or property type.

[0767] "Evidence" refers to documents and supporting evidence provided to support rent negotiations, including calculated market rent data and the underlying data.

[0768] A "terminal" is a computing device used by a user, specifically a PC or smartphone.

[0769] A "database" is a system for efficiently storing, managing, and searching structured data.

[0770] The "user interface" is the part that provides the screen and operation means for the user to interact with the system.

[0771] "Rent negotiation" refers to the process of reviewing current rental terms and adjusting them to an appropriate rent.

[0772] "PDF" is an abbreviation for Portable Document Format, a file format for electronically distributing and displaying documents while preserving their format and layout.

[0773] "Web format" refers to a format of digital content that can be viewed and manipulated through a web browser.

[0774] The present invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. This system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[0775] Hardware and software used

[0776] This system uses the following hardware and software:

[0777] Server: A central computer that processes data and runs AI models.

[0778] Terminal: A device used by a user, such as a PC or smartphone.

[0779] Generative AI models: Examples include natural language processing models such as OpenAI's GPT-3 and Google's BERT.

[0780] Database: A data management system for storing address information and rent data.

[0781] Application: Software that allows users to enter address information and verify evidence.

[0782] Explanation of program processing

[0783] First, the user launches the application using their own device (PC or smartphone) and enters address information. Specifically, the user enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the application's input form and presses the "Submit" button to send it to the server.

[0784] The server receives the address information sent by the user. This address information is stored in a specific database table. The server then uses a generative AI model to calculate the average rent based on the received address information, taking into account rent data for similar properties in the area and past rent trends.

[0785] Once the market rent is calculated, the server generates the results as evidence. The evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, past rent trends). The evidence is generated in PDF or web format and sent from the server to the user's device.

[0786] The user checks the received evidence on their device. The evidence is displayed on the application and can be downloaded or printed as needed. The user can use this evidence to negotiate the rent when renewing their rental contract. For example, if the current rent is 350,000 yen, the user can use the evidence to negotiate with the management company or owner to lower it to 300,000 yen.

[0787] Furthermore, if the user wishes, the server will negotiate the rent on their behalf. In this case, the server will use an automatic email sending function or API to contact the management company or owner on the user's behalf and negotiate. This reduces the user's time and effort.

[0788] Examples and prompts

[0789] For example, suppose a user named Tanaka lives in a rental property at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his lease contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address information. The server receives this information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on it, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[0790] Example prompt sentence:

[0791] "Please tell me the real-time average rent for properties around 1-2-3 XX-cho, Shibuya-ku, Tokyo."

[0792] "Please generate evidence to review my current rent of 350,000 yen to a fair price."

[0793] In this way, this system is a powerful tool that helps residents to obtain fair rent when renewing their rental contracts.

[0794] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] The user starts the application using a device (PC or smartphone), enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) in the address information input form, and presses the "Submit" button.

[0797] Input: Rental property address information

[0798] Output: Request with address information sent to server

[0799] What happens: A user opens the application, enters address information, and presses the submit button.

[0800] Step 2:

[0801] The server receives the address information submitted by the user, parses the HTTP request, and stores the address information in a specific database table.

[0802] Input: Address information submitted by the user

[0803] Output: Address information stored in a database

[0804] Specific operation: The server receives the HTTP request, analyzes it, and saves the extracted address information in a database.

[0805] Step 3:

[0806] The server uses a generative AI model based on the stored address information to calculate the average rent price. The generative AI model includes data on surrounding properties and past rent trends, and takes this data into account to derive the average rent price in real time.

[0807] Input: Address information stored in the database

[0808] Output: Calculated market rent data

[0809] Specific operation: The server inputs address information into a generative AI model, which then calculates the average rent.

[0810] Step 4:

[0811] The server generates evidence based on the generated market rent data. The evidence includes market rent data and its basis (e.g., data on surrounding properties, past rent trends). The evidence is generated in PDF format or web format.

[0812] Input: Calculated market rent data

[0813] Output: Generated evidence (PDF or web format)

[0814] What happens: The server formats the rent quote data and creates evidence using a PDF generation library.

[0815] Step 5:

[0816] The server sends the generated evidence to the user's device, and returns the evidence to the user as an HTTP response or provides a URL link.

[0817] Input: Generated evidence

[0818] Output: Evidence sent to the user's device

[0819] Specific operation: The server generates an evidence file and returns it in an HTTP response. In some cases, it generates a URL link and notifies the user.

[0820] Step 6:

[0821] The user checks the received evidence on the device. The evidence is displayed within the application, and the user can download or print it as needed.

[0822] Input: Evidence received from the server

[0823] Output: User interface with evidence displayed

[0824] Specific operations: The user opens the evidence confirmation screen within the application, checks the contents, and operates the download and print buttons.

[0825] Step 7:

[0826] The user can use the generated evidence to negotiate rent when renewing the rental contract. Specifically, the user submits the evidence to the management company or owner and negotiates to revise the current rent to a fair price.

[0827] Input:Evidence

[0828] Output: Rent negotiation result (e.g. rent reduction)

[0829] Specific actions: The user presents evidence in print or digital form and negotiates with the management company.

[0830] Step 8:

[0831] If the user wishes, the server will handle rent negotiations on their behalf. The server uses an automatic email sending function and API to contact the management company or owner and negotiate.

[0832] Input: User's request for negotiation

[0833] Output: Rent negotiation result (e.g. rent reduction)

[0834] Specific operation: The server receives a request for negotiation on behalf of the user and uses the automatic email sending function to send a negotiation email to the management company.

[0835] (Application example 1)

[0836] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] With conventional rent negotiation systems, it was difficult for residents to accurately grasp the market rent in real time, and the provision of evidence was limited, making it difficult to conduct rent negotiations effectively.In addition, support for viewing rental properties and rent negotiations using virtual reality technology was not widespread, so a more efficient and effective system was needed.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0839] In this invention, the server includes means for a user to input address information, means for receiving the address information, means including a generative AI model for calculating market rents based on the address information, means for generating the calculated market rents as evidence, means for returning the evidence to a terminal, means for viewing properties in a virtual reality environment, means for displaying the evidence in the virtual reality environment, and means for supporting rent negotiations in the virtual reality environment. This allows a user to check market rents in real time and engage in efficient and persuasive rent negotiations through the virtual reality environment.

[0840] The "means by which the user inputs address information" refers to an interface or device that allows the user to input address information for their own residence or rental property.

[0841] The "server that receives the address information" is a computer system that receives and processes the address information sent by the user.

[0842] A "server including a generative AI model that calculates average rent prices based on the address information" is a computer system that has an internal generative AI model for calculating average rent prices using address information.

[0843] "Means for generating evidence of calculated market rents" refers to the functions and processes for turning the market rents calculated by the generative AI model into evidence.

[0844] The "means for returning the evidence to the terminal" refers to a function or process for transmitting the market rent data generated as evidence to the terminal used by the user.

[0845] "Means for viewing properties in a virtual reality environment" refers to systems or technologies that allow users to view rental properties using virtual reality technology.

[0846] The "means for displaying the evidence within the virtual reality environment" refers to a system or technology for visually presenting evidence of market rent prices to a user within a virtual reality environment.

[0847] The "means for supporting rent negotiations within the virtual reality environment" refers to a system or function that supports a user when negotiating rent within the virtual reality environment.

[0848] This invention is a system that provides accurate market rent information when users negotiate rent for rental properties. It also makes it possible to more efficiently view properties and negotiate rent using a virtual reality environment.

[0849] System Configuration

[0850] 1. How users enter address information

[0851] Users use an interface to input address information using a smartphone or PC, which can be provided as an application or web form.

[0852] 2. Server that receives the address information

[0853] The server receives the address information entered by the user and stores it in a database. This reception process uses HTTP requests and REST APIs.

[0854] 3. A server containing a generative AI model that calculates market rents based on the address information.

[0855] The server uses a generative AI model to calculate average rent prices based on the address information entered by the user. This generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. The model learns from historical rent data and current market conditions to provide accurate rent prices in real time.

[0856] 4. A method for generating evidence of the calculated market rent

[0857] The server generates evidence of the calculated rent market price. This evidence is created in PDF or web page format and includes detailed data and rationale for the rent market price. Python's FPDF library is used to generate the evidence.

[0858] 5. Means for returning said evidence to the terminal

[0859] The server sends the generated evidence to the user's device using a REST API or email sending system. The user can then check the evidence on their smartphone or PC.

[0860] 6. A way to view properties in a virtual reality environment

[0861] Users can virtually view properties using a VR headset. The VR environment is built in conjunction with Unity and Unreal Engine to provide users with a 360-degree virtual experience.

[0862] 7. Means for displaying said evidence within said virtual reality environment

[0863] This is a system for displaying evidence of calculated market rents in a virtual reality environment, allowing users to check market rents in real time while viewing properties.

[0864] 8. Means for assisting in rent negotiations within said virtual reality environment

[0865] The chatbot function is used in virtual reality to support real-time rent negotiations. This chatbot uses natural language processing technology to converse with users. It can also negotiate on behalf of users, providing them with the ability to negotiate rent on their behalf.

[0866] Specific examples of processing

[0867] The user views a rental property in a virtual store and enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo." The server receives the address information and calculates the average rent using a generative AI model. The result is 300,000 yen, and evidence is displayed in the virtual space. The user then begins rent negotiations with the management company via a chatbot.

[0868] Prompt Sentence Examples

[0869] "Please calculate the average rent for the following address: 1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0870] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0871] Step 1:

[0872] The user enters address information. Using a smartphone or PC, the user enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo" through an application or web form. The entered address information is sent from the device to the server.

[0873] Step 2:

[0874] The server receives the address information, processes the HTTP request, and stores the address information in a database. This data is then used by the generative AI model to calculate market rents.

[0875] Step 3:

[0876] The server calculates the average rent. The server inputs the stored address information into a generative AI model to predict the average rent. This model is built using TensorFlow and PyTorch, and predicts the average rent in real time based on past data and market trends. The output is average rent data such as "300,000 yen."

[0877] Step 4:

[0878] The server generates evidence. Based on the calculated market rent data, the server creates evidence in PDF or web format. This evidence includes details of market rents and the underlying data. The PDF is generated using a library such as Python's FPDF library.

[0879] Step 5:

[0880] The server returns the evidence to the device. The generated evidence is sent back to the user's smartphone or PC via REST API or email. The user can then view this evidence on their device.

[0881] Step 6:

[0882] Users can view properties in a virtual reality environment. Users wear a VR headset and access the virtual reality environment. This environment is built using Unity and Unreal Engine, allowing users to inspect the property in detail with a 360-degree view.

[0883] Step 7:

[0884] The server displays evidence within the virtual reality environment. Rent market evidence is displayed within the user's field of vision. This display is done in real time, providing rent data and its rationale as an overlay in the virtual space.

[0885] Step 8:

[0886] Users will be provided with a means to assist in rent negotiations. Within the virtual reality environment, a chatbot will receive instructions from the user and assist in rent negotiations with the property management company in real time. The chatbot will use natural language processing technology to converse and convey the user's request for a rent reduction. If the user so desires, the chatbot can also negotiate with the property management company on their behalf.

[0887] As described above, the data input and output are clearly defined at each step, and data processing and calculations are performed based on this, allowing the system to enable users to efficiently negotiate rent in a virtual reality environment.

[0888] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0889] This invention combines a system that enables residents of rental housing to easily negotiate rent when renewing their rental contracts with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state and optimizes support for rent negotiations based on the results.

[0890] User address input and emotion recognition

[0891] First, the user launches the application using a device (PC or smartphone). The user enters the address information of the rental property into the application's input form (for example, "1-2-3 XX-cho, Shibuya-ku, Tokyo"). As the user enters the information, the emotion engine analyzes the user's input speed and facial expression, and recognizes the user's emotional state regarding the address information. This emotional information is also sent to the server.

[0892] The server receives the address information and emotion information.

[0893] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[0894] Calculating market rent

[0895] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[0896] Generating and providing evidence that takes emotional information into account

[0897] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[0898] Rent negotiation support and proxy proposals

[0899] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user can use the generated evidence to negotiate the rent when renewing the rental contract. For example, based on the evidence, the user can propose to the management company that the current rent of 350,000 yen be reduced to 300,000 yen.

[0900] The emotion engine may also suggest negotiating rent on behalf of the user depending on the user's emotional state. For example, if the server detects that the user is feeling highly stressed, it will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on their behalf. The server will then communicate the details of the negotiation along with the evidence to the owner or management company.

[0901] Specific examples

[0902] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and is due to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka requests it, the server will negotiate on his behalf.

[0903] In this way, this system supports rent negotiations while taking into account the user's emotional state, making it a powerful tool for residents to achieve a fair rent.

[0904] The processing flow will be explained below.

[0905] Step 1:

[0906] The user launches the application using their device. The user enters the address information of the rental property (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo") into the application's input form. As the user enters information, the emotion engine analyzes the user's input patterns and facial expression data in real time to recognize their emotional state (e.g., anxiety, stress).

[0907] Step 2:

[0908] The user presses the "Submit" button to send the address information and the detected emotion information to the server via an HTTP request.

[0909] Step 3:

[0910] The server receives the address information and emotion information sent from the device, parses the data, and passes the address information and emotion information to the appropriate processing module.

[0911] Step 4:

[0912] The server calculates the average rent using a generative AI model. The generative AI model calculates the real-time average rent (e.g., 300,000 yen) based on the address information by collecting and analyzing rent data for similar properties in the area and past rent trends.

[0913] Step 5:

[0914] The server generates evidence based on the calculated market rent. The evidence includes market rent data and related evidence (such as rent data for surrounding properties and trend graphs). Furthermore, based on the emotional information recognized by the emotion engine, negotiation support advice (e.g., "Please pay attention to these points to reduce your anxiety") is added to the user.

[0915] Step 6:

[0916] The server returns the generated evidence to the terminal using an HTTP response.

[0917] Step 7:

[0918] The terminal receives the evidence returned from the server. The terminal displays the evidence in the user interface so that the user can review it. The user can review the evidence and download or print it as a PDF.

[0919] Step 8:

[0920] Users negotiate rent based on evidence when renewing a rental contract. Based on evidence, users propose to the management company that the current rent (e.g., 350,000 yen) be lowered to a fair market price (e.g., 300,000 yen). Users can negotiate more effectively by following the advice provided by the emotion engine.

[0921] Step 9:

[0922] The emotion engine continuously monitors the user's emotional state, and if it detects that the user is experiencing high levels of stress or anxiety, it suggests proxy negotiation options, which are displayed in the user interface.

[0923] Step 10:

[0924] If the user selects the proxy negotiation option, the server will negotiate the rent on the user's behalf. The server will organize the evidence and negotiation details and contact the management company or owner. Specifically, it will send the evidence by email or phone and explain the negotiation points.

[0925] Through the above steps, the system can effectively support rent negotiations while taking into account the user's emotional state.

[0926] Example 2

[0927] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0928] Conventional rent negotiation systems have the problem that users negotiate rent without considering their own emotional state, making it difficult to negotiate effectively. In particular, emotions such as tension and anxiety often have a negative impact on the outcome of the negotiation, placing a heavy burden on users. Furthermore, many users have little experience in rent negotiations, making it difficult for them to collect appropriate evidence and implement effective approaches. Furthermore, if users feel strong stress during the negotiation process, they may be unable to achieve a fair rent.

[0929] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0930] In this invention, the server includes a means for a user to input address information and recognize the user's emotional state; a server that receives the address information and emotional information; a server that includes a generative AI model that calculates the average rent price based on the address information and emotional information; a means for generating the calculated average rent price as evidence and providing advice to the user based on the emotional information; and a means for returning the evidence and advice to the terminal. This allows the system to calculate an appropriate average rent price and provide effective evidence while taking the user's emotional state into consideration, allowing the user to negotiate the rent with peace of mind. Furthermore, by offering proxy negotiations as needed, the system can reduce the user's mental burden and help them achieve a more appropriate rent price.

[0931] "User address information" is geographical information that a user inputs to identify the location of a rental property.

[0932] "Emotional state" is information that represents the user's emotions and mood, and is analyzed from input speed, facial expressions, voice, etc.

[0933] A "server" is a computer device that receives address information and emotion information sent by a user and processes and analyzes them.

[0934] A "generative AI model" is a program that uses artificial intelligence algorithms to calculate market rent prices based on specific input data (address information and emotional information).

[0935] "Evidence" refers to documents or reports containing data or supporting information to support market rents.

[0936] "Advice" is advice or suggestions provided to users based on the results of generative AI models and emotion engines.

[0937] A "terminal" is a device (such as a personal computer or smartphone) that a user uses to input information and receive evidence and advice sent from a server.

[0938] An "emotion engine" is software or a system for analyzing a user's emotional state, analyzing data such as the user's input speed, facial expressions, and voice.

[0939] "Market rent" refers to the market price of rent in a specific area or property, and is calculated using a generative AI model.

[0940] This invention is a system that allows residents of rental housing to easily negotiate rent. The system uses an emotion engine and generative AI model to recognize the user's emotional state and assist with rent negotiations based on this.

[0941] First, the user launches the application using a device (such as a PC or smartphone). The user enters the address information of the rental property into the application's input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo"). At this time, an emotion engine (such as Microsoft Azure Cognitive Services Emotion API) analyzes the user's input speed, facial expressions, and voice to recognize their emotional state. The device then sends the address information and emotion information to the server.

[0942] The server receives the address and emotion information sent by the user. The received information is parsed and passed to a generative AI model (e.g., OpenAI GPT-4). The server sends the following prompt to the generative AI model:

[0943] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0944] User Sentiment: "Mild Anxiety"

[0945] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0946] Goal: "Calculate the fair market rent price"

[0947] The generative AI model calculates an appropriate market rent based on the prompt sentence, taking into account rent data for similar properties in the area and past rent trends. The server receives the market rent data calculated by the generative AI model.

[0948] Next, the server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, trend graphs, etc.). Furthermore, appropriate rent negotiation support advice is provided to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, advice to reassure them is added.

[0949] Once the evidence and advice are ready, the server generates them in PDF or web format and sends them back to the device, where the user can review the evidence and advice and download the PDF or print it as needed.

[0950] As a concrete example, consider the case where Mr. Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal. Mr. Tanaka accesses the system from his smartphone and enters his address information. At this time, the emotion engine analyzes Mr. Tanaka's facial expressions and recognizes that he is feeling anxious. The server receives the entered address information and emotion information and calculates the average rent to be 300,000 yen based on the generative AI model. The server then generates evidence based on this data and adds emotion-based advice. Mr. Tanaka uses the evidence to negotiate a reduction in his current rent of 350,000 yen to 300,000 yen.

[0951] Furthermore, if the system recognizes that Tanaka felt a great deal of stress during the negotiations, it will suggest the option of negotiating on his behalf, and if Tanaka agrees, the server will negotiate on his behalf, thereby reducing Tanaka's mental burden and helping to achieve a fair rent.

[0952] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0953] System program processing flow

[0954] 1. Divide into processing steps

[0955] 1. User address input and emotion recognition

[0956] 2. The server receives the address information and emotion information.

[0957] 3. Calculating the market rent

[0958] 4. Generating and providing evidence that takes emotional information into account

[0959] 5. Rent negotiation support and proxy proposals

[0960] 2. Explain each processing step in detail

[0961] Step 1:

[0962] The user launches the application using a device (PC or smartphone).

[0963] The user enters the address information of the rental property into the input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo").

[0964] Input: Address information

[0965] Processing: The emotion engine analyzes the user's input speed, facial expressions, and voice to recognize their emotional state.

[0966] Output: Recognized emotion information

[0967] How it works: The emotion engine (e.g., Microsoft Azure Cognitive Services Emotion API) collects data from the user's camera and microphone and analyzes their emotions in real time. Address information and emotion information are sent from the device to the server.

[0968] Step 2:

[0969] The server receives the address information and emotion information sent by the user.

[0970] Input: Address information and emotion information

[0971] Processing: Parses the received information and prepares it for passing to the generative AI model.

[0972] Output: Parsed address information and sentiment information

[0973] What it does: The server checks the data it receives and formats it as needed, standardizing addresses and sentiment information for consistency.

[0974] Step 3:

[0975] The server runs the generative AI model.

[0976] Input: Analyzed address information and sentiment information, historical data (rent trend data for the same area over the past year, average rent data for surrounding properties)

[0977] Processing: Send a prompt to the generative AI model to calculate the appropriate market rent.

[0978] Output: Calculated market rent data

[0979] Specific operation: The server sends the following prompt to the generative AI model:

[0980] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[0981] User Sentiment: "Mild Anxiety"

[0982] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[0983] Goal: "Calculate the fair market rent price"

[0984] A generative AI model (e.g., OpenAI GPT-4) performs calculations based on this information and outputs an appropriate market rent.

[0985] Step 4:

[0986] The server generates evidence based on the calculated market rent and provides emotion-based advice.

[0987] Input: Calculated market rent data, sentiment information

[0988] Processing: Document market rents as evidence and add emotionally informed advice.

[0989] Output: Generated evidence and advice

[0990] Specific operation: The server compiles the calculated rent market price into a PDF or web report. Taking into account emotional information, if the user is feeling anxious, it adds reassuring advice and specific negotiation steps.

[0991] Step 5:

[0992] The server returns evidence and advice to the terminal.

[0993] Input: Generated evidence and advice

[0994] Processing: Send evidence and advice to the terminal.

[0995] Output: Evidence and advice displayed on the terminal

[0996] Specific operation: The evidence and advice returned from the server arrives at the terminal and is displayed on the user interface. The user can review it and download or print the PDF as needed.

[0997] It includes specific actions at each step and provides a detailed explanation of how the system works.

[0998] (Application example 2)

[0999] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1000] The present invention solves the problem that the information and support provided by conventional rent negotiation support systems does not take into account the emotional state of the user, making it difficult for users to negotiate rent with confidence. Another problem is that there is a lack of personalized recommended content that corresponds to the emotional state of the user.

[1001] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's address information, means for receiving the address information, means including a generative AI model that calculates a rent market price based on the address information, means including an emotion engine that analyzes the user's emotional state, means for providing rent negotiation support optimized based on the analyzed emotional state, means for generating personalized recommended content based on the emotional state of the viewing content, means for transmitting emotion information to the server, means for generating the calculated rent market price as evidence, and means for returning the evidence to the terminal. This allows the user to receive optimal rent negotiation support that takes their emotional state into consideration, and further enables them to enjoy personalized recommended content based on their emotional state in viewing content as well.

[1002] "User" refers to the end user who uses the system to negotiate rent and view content.

[1003] "Address information" refers to data containing detailed information about the location of the property where the user lives.

[1004] "Server" refers to the computer system that receives, analyzes, and processes address information and emotion information sent by users.

[1005] A "generative AI model" refers to an artificial intelligence algorithm that calculates average rent prices based on given data.

[1006] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions, voice, etc.

[1007] "Optimized rent negotiation support" refers to advice and tools provided to facilitate rent negotiations, taking into account the user's emotional state.

[1008] "Personalized recommended content" refers to viewing content that is individually suggested based on the user's emotional state.

[1009] "Emotion information" refers to data that indicates the user's current emotional state as analyzed by the emotion engine.

[1010] "Evidence" refers to empirical materials including market rent prices and the underlying data, which users use when negotiating rent.

[1011] "Terminal" refers to a device such as a smartphone, PC, or tablet that allows a user to access the system via the Internet.

[1012] To implement this invention, a user utilizes a system that analyzes their emotional state and appropriately negotiates rent. This system consists of an application and a server that users can access via devices such as smartphones and PCs.

[1013] System Configuration

[1014] 1. User address input and emotion recognition

[1015] The user launches the application using a device such as a smartphone and enters the address information of the rental property. As the user enters the information, the emotion engine analyzes the user's typing speed, facial expression, tone of voice, etc. to obtain emotional information. This allows the system to recognize how the user feels about rent negotiations.

[1016] 2. The server receives the address information and emotion information.

[1017] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[1018] 3. Calculating the market rent

[1019] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[1020] 4. Generating and providing evidence that takes emotional information into account

[1021] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[1022] 5. Supporting users in using the service and negotiating rent

[1023] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user then uses the generated evidence to negotiate the rent when it comes time to renew the rental contract. For example, the server may suggest to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence. The emotion engine may also suggest negotiating the rent on the user's behalf, depending on the user's emotional state. For example, if the server recognizes that the user is feeling very stressed, the server will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on the user's behalf. The server then notifies the owner or management company of the details of the negotiation along with the evidence.

[1024] Program processing

[1025] This program uses OpenCV to capture the user's face, convert it to grayscale, and then input it into a pre-trained emotion recognition model (pre-prepared pkl file) to analyze the user's emotional state. Once the emotion is recognized, an API request is made based on the emotion to obtain recommended content information.

[1026] Hardware and software used

[1027] Hardware: Smartphone or PC camera and microphone.

[1028] Software: Python, OpenCV, sklearn, requests.

[1029] Specific examples

[1030] For example, consider a specific user named Tanaka, who lives at an address in Tokyo and is about to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka wishes, the server will negotiate on his behalf. In this way, Tanaka can proceed with the rent negotiation with peace of mind.

[1031] Prompt Sentence Examples

[1032] "I want to laugh at movies, so please recommend some movies that will put me in a good mood."

[1033] "I want to relax, so please recommend some relaxation music."

[1034] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1035] Step 1:

[1036] This is a method for users to input address information. Users input the address information of rental properties into an input form on their smartphone or PC. At this time, the emotion engine analyzes the input speed, facial expression, and tone of voice. The input includes address information and biometric information (facial expression, voice, etc.), and emotional information is generated as the output.

[1037] Step 2:

[1038] The terminal sends the address information and emotion information to the server. The sent information is parsed (analyzed) on the server side and separated into address information and emotion information. The address information and emotion information are included as input, and the analyzed data is obtained as output.

[1039] Step 3:

[1040] The server uses a generative AI model to calculate the average rent based on the address information received, referencing rent data for similar properties in the area and past rent trends. The input includes the address information and data on surrounding properties, and the output is the average rent.

[1041] Step 4:

[1042] The server generates evidence for optimized rent negotiation support, taking into account the emotional information recognized by the emotion engine. The generated evidence includes market rent data and the underlying data. Market rent data and emotional information are included as inputs, and evidence is obtained as output.

[1043] Step 5:

[1044] The server sends the evidence back to the terminal. The terminal receives this evidence and displays it in a user interface. The user can view the evidence and download or print it as a PDF. The input contains the evidence, and the output is the displayed evidence.

[1045] Step 6:

[1046] The user uses the generated evidence to negotiate the rent, and if necessary, proposes to the management company to lower the current rent. The input includes the evidence, and the output is the negotiation result.

[1047] Step 7:

[1048] The emotion engine may also suggest proxy negotiation of the rent depending on the user's emotional state. For example, if the server recognizes that the user is feeling highly stressed, it will suggest a proxy negotiation option. If the user requests it, the server will negotiate the rent on their behalf. The input includes emotional information and evidence, and the output is the result of the proxy negotiation.

[1049] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1050] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1051] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1052] [Fourth embodiment]

[1053] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1054] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1055] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1056] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1057] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1058] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1059] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1060] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1061] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1062] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1063] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1064] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1065] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1066] This invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. To achieve this, the system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[1067] Enter user address information

[1068] First, the user must enter their address information. The user starts the application using a device (PC or smartphone) and enters the address of the rental property (for example, 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the input form. This input information is sent to the server by pressing the "Submit" button.

[1069] The server receives address information and calculates the average rent

[1070] The server receives the address information sent by the user. Based on this address information, a generative AI model is used to calculate the real-time market rent. The generative AI model calculates an accurate market rent by taking into account rent data for similar properties in the area and past rent trends. In this calculation process, it is important that the collected data reflects the actual market price.

[1071] Generate and provide evidence of market rents

[1072] The server generates the calculated market rent data as evidence. The evidence includes the calculated market rent data and the underlying data (for example, rent data for surrounding properties and past rent trends). The evidence is generated in PDF or web format and sent from the server to the terminal.

[1073] The terminal receives the evidence sent from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary.

[1074] Rent negotiation assistance

[1075] Users can use the generated evidence to negotiate rent when renewing a rental contract. For example, a user can inform a management company that the current rent is 350,000 yen and negotiate to lower it to 300,000 yen based on the evidence. This evidence enables persuasive negotiations with the owner and management company.

[1076] Furthermore, if the user wishes, they can use a service in which the server handles rent negotiations on their behalf. In this case, the server uses evidence to negotiate rent on the user's behalf and contacts the owner or management company. This proxy negotiation significantly reduces the time and effort required for the user to negotiate rent.

[1077] Specific examples

[1078] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address. The server receives the address information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this data as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on that, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[1079] In this way, this system will be a powerful tool for residents to ensure they receive fair rent when renewing their rental contracts.

[1080] The processing flow will be explained below.

[1081] Step 1:

[1082] The user starts the application using a terminal. The user enters the address information of the rental property into the application's input form. Specifically, the user enters an address such as "1-2-3 XX-cho, Shibuya-ku, Tokyo."

[1083] Step 2:

[1084] When the user presses the "Send" button, the address information is sent from the device to the server via an HTTP request.

[1085] Step 3:

[1086] The server receives the address information sent from the device, parses the received data, and prepares it for passing to the generative AI model.

[1087] Step 4:

[1088] The server calculates the market rent using a generated AI model, which takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data.

[1089] Step 5:

[1090] The server generates evidence based on the calculated market rent. The evidence includes market rent data and the underlying data (such as rent data for surrounding properties and trend graphs).

[1091] Step 6:

[1092] The server returns the generated evidence to the terminal using an HTTP response.

[1093] Step 7:

[1094] The terminal receives the evidence returned from the server and displays it on the user interface for the user to review.

[1095] Step 8:

[1096] The user uses the evidence to negotiate the rent when renewing the rental contract. Specifically, the user proposes to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence.

[1097] Step 9:

[1098] If the user wishes, they can select the proxy negotiation option, which allows the server to negotiate the rent on their behalf without the user having to negotiate directly.

[1099] Step 10:

[1100] The server uses the evidence to negotiate rent with the management company or owner on behalf of the user, and conveys the evidence and the details of the negotiation via email or telephone.

[1101] Example 1

[1102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1103] Previously, when residents negotiated rent at the time of lease contract renewal, it was difficult to grasp the appropriate market rent, making it difficult to negotiate persuasively with management companies and owners. In particular, the inability to obtain accurate market rent data based on real-time data meant there was a lack of evidence, which meant that residents could renew their contracts on unfavorable terms. Another problem was that rent negotiations themselves were complicated, requiring a lot of time and effort.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1105] In this invention, the server includes a means for a user to input address information, a means for receiving the address information, a means including a generative AI model that calculates average rent prices based on the address information, a means for generating the calculated average rent prices as evidence, a means for returning the evidence to a terminal, a means for generating the evidence in PDF or web format, a means for calculating average rent prices in real time using the generative AI model with data on surrounding properties and past rent trends, a means for displaying the evidence on a user interface, and a means for storing the address information sent from the terminal to the server in a database. This allows residents to understand the appropriate average rent prices when renewing their rental contracts and negotiate rent based on convincing evidence. Furthermore, using a server-based service to handle rent negotiations can reduce the residents' time and effort.

[1106] "User" refers to a resident of a rental property who uses the system to negotiate rent.

[1107] "Address information" is data indicating the location of a rental property, and specifically includes information such as prefecture, city, ward, town, street name, and house number.

[1108] The "server" is a computer system that receives the user's address information via the network and calculates the average rent using a generative AI model.

[1109] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to make predictions and analyses based on input data.

[1110] "Average rent" is data that shows the average and distribution of appropriate rents in a particular area or property type.

[1111] "Evidence" refers to documents and supporting evidence provided to support rent negotiations, including calculated market rent data and the underlying data.

[1112] A "terminal" is a computing device used by a user, specifically a PC or smartphone.

[1113] A "database" is a system for efficiently storing, managing, and searching structured data.

[1114] The "user interface" is the part that provides the screen and operation means for the user to interact with the system.

[1115] "Rent negotiation" refers to the process of reviewing current rental terms and adjusting them to an appropriate rent.

[1116] "PDF" is an abbreviation for Portable Document Format, a file format for electronically distributing and displaying documents while preserving their format and layout.

[1117] "Web format" refers to a format of digital content that can be viewed and manipulated through a web browser.

[1118] The present invention relates to a system that allows residents of rental housing to easily negotiate rent when renewing their rental contracts. This system uses a generative AI model to accurately calculate market rents based on real-time data and provides this as evidence. A specific embodiment of this system is described in detail below.

[1119] Hardware and software used

[1120] This system uses the following hardware and software:

[1121] Server: A central computer that processes data and runs AI models.

[1122] Terminal: A device used by a user, such as a PC or smartphone.

[1123] Generative AI models: Examples include natural language processing models such as OpenAI's GPT-3 and Google's BERT.

[1124] Database: A data management system for storing address information and rent data.

[1125] Application: Software that allows users to enter address information and verify evidence.

[1126] Explanation of program processing

[1127] First, the user launches the application using their own device (PC or smartphone) and enters address information. Specifically, the user enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) into the application's input form and presses the "Submit" button to send it to the server.

[1128] The server receives the address information sent by the user. This address information is stored in a specific database table. The server then uses a generative AI model to calculate the average rent based on the received address information, taking into account rent data for similar properties in the area and past rent trends.

[1129] Once the market rent is calculated, the server generates the results as evidence. The evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, past rent trends). The evidence is generated in PDF or web format and sent from the server to the user's device.

[1130] The user checks the received evidence on their device. The evidence is displayed on the application and can be downloaded or printed as needed. The user can use this evidence to negotiate the rent when renewing their rental contract. For example, if the current rent is 350,000 yen, the user can use the evidence to negotiate with the management company or owner to lower it to 300,000 yen.

[1131] Furthermore, if the user wishes, the server will negotiate the rent on their behalf. In this case, the server will use an automatic email sending function or API to contact the management company or owner on the user's behalf and negotiate. This reduces the user's time and effort.

[1132] Examples and prompts

[1133] For example, suppose a user named Tanaka lives in a rental property at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his lease contract is up for renewal in two years. Tanaka accesses the system from his smartphone and enters his address information. The server receives this information and uses a generative AI model to calculate the average rent as 300,000 yen. The server generates this as evidence and sends it to Tanaka's smartphone. Tanaka can check the evidence and, based on it, negotiate to lower the current rent of 350,000 yen to 300,000 yen. If Tanaka wishes, the server can also negotiate the rent on his behalf.

[1134] Example prompt sentence:

[1135] "Please tell me the real-time average rent for properties around 1-2-3 XX-cho, Shibuya-ku, Tokyo."

[1136] "Please generate evidence to review my current rent of 350,000 yen to a fair price."

[1137] In this way, this system is a powerful tool that helps residents to obtain fair rent when renewing their rental contracts.

[1138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1139] Step 1:

[1140] The user starts the application using a device (PC or smartphone), enters the address of the rental property (e.g., 1-2-3 XX-cho, Shibuya-ku, Tokyo) in the address information input form, and presses the "Submit" button.

[1141] Input: Rental property address information

[1142] Output: Request with address information sent to server

[1143] What happens: A user opens the application, enters address information, and presses the submit button.

[1144] Step 2:

[1145] The server receives the address information submitted by the user, parses the HTTP request, and stores the address information in a specific database table.

[1146] Input: Address information submitted by the user

[1147] Output: Address information stored in a database

[1148] Specific operation: The server receives the HTTP request, analyzes it, and saves the extracted address information in a database.

[1149] Step 3:

[1150] The server uses a generative AI model based on the stored address information to calculate the average rent price. The generative AI model includes data on surrounding properties and past rent trends, and takes this data into account to derive the average rent price in real time.

[1151] Input: Address information stored in the database

[1152] Output: Calculated market rent data

[1153] Specific operation: The server inputs address information into a generative AI model, which then calculates the average rent.

[1154] Step 4:

[1155] The server generates evidence based on the generated market rent data. The evidence includes market rent data and its basis (e.g., data on surrounding properties, past rent trends). The evidence is generated in PDF format or web format.

[1156] Input: Calculated market rent data

[1157] Output: Generated evidence (PDF or web format)

[1158] What happens: The server formats the rent quote data and creates evidence using a PDF generation library.

[1159] Step 5:

[1160] The server sends the generated evidence to the user's device, and returns the evidence to the user as an HTTP response or provides a URL link.

[1161] Input: Generated evidence

[1162] Output: Evidence sent to the user's device

[1163] Specific operation: The server generates an evidence file and returns it in an HTTP response. In some cases, it generates a URL link and notifies the user.

[1164] Step 6:

[1165] The user checks the received evidence on the device. The evidence is displayed within the application, and the user can download or print it as needed.

[1166] Input: Evidence received from the server

[1167] Output: User interface with evidence displayed

[1168] Specific operations: The user opens the evidence confirmation screen within the application, checks the contents, and operates the download and print buttons.

[1169] Step 7:

[1170] The user can use the generated evidence to negotiate rent when renewing the rental contract. Specifically, the user submits the evidence to the management company or owner and negotiates to revise the current rent to a fair price.

[1171] Input:Evidence

[1172] Output: Rent negotiation result (e.g. rent reduction)

[1173] Specific actions: The user presents evidence in print or digital form and negotiates with the management company.

[1174] Step 8:

[1175] If the user wishes, the server will handle rent negotiations on their behalf. The server uses an automatic email sending function and API to contact the management company or owner and negotiate.

[1176] Input: User's request for negotiation

[1177] Output: Rent negotiation result (e.g. rent reduction)

[1178] Specific operation: The server receives a request for negotiation on behalf of the user and uses the automatic email sending function to send a negotiation email to the management company.

[1179] (Application example 1)

[1180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1181] With conventional rent negotiation systems, it was difficult for residents to accurately grasp the market rent in real time, and the provision of evidence was limited, making it difficult to conduct rent negotiations effectively.In addition, support for viewing rental properties and rent negotiations using virtual reality technology was not widespread, so a more efficient and effective system was needed.

[1182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1183] In this invention, the server includes means for a user to input address information, means for receiving the address information, means including a generative AI model for calculating market rents based on the address information, means for generating the calculated market rents as evidence, means for returning the evidence to a terminal, means for viewing properties in a virtual reality environment, means for displaying the evidence in the virtual reality environment, and means for supporting rent negotiations in the virtual reality environment. This allows a user to check market rents in real time and engage in efficient and persuasive rent negotiations through the virtual reality environment.

[1184] The "means by which the user inputs address information" refers to an interface or device that allows the user to input address information for their own residence or rental property.

[1185] The "server that receives the address information" is a computer system that receives and processes the address information sent by the user.

[1186] A "server including a generative AI model that calculates average rent prices based on the address information" is a computer system that has an internal generative AI model for calculating average rent prices using address information.

[1187] "Means for generating evidence of calculated market rents" refers to the functions and processes for turning the market rents calculated by the generative AI model into evidence.

[1188] The "means for returning the evidence to the terminal" refers to a function or process for transmitting the market rent data generated as evidence to the terminal used by the user.

[1189] "Means for viewing properties in a virtual reality environment" refers to systems or technologies that allow users to view rental properties using virtual reality technology.

[1190] The "means for displaying the evidence within the virtual reality environment" refers to a system or technology for visually presenting evidence of market rent prices to a user within a virtual reality environment.

[1191] The "means for supporting rent negotiations within the virtual reality environment" refers to a system or function that supports a user when negotiating rent within the virtual reality environment.

[1192] This invention is a system that provides accurate market rent information when users negotiate rent for rental properties. It also makes it possible to more efficiently view properties and negotiate rent using a virtual reality environment.

[1193] System Configuration

[1194] 1. How users enter address information

[1195] Users use an interface to input address information using a smartphone or PC, which can be provided as an application or web form.

[1196] 2. Server that receives the address information

[1197] The server receives the address information entered by the user and stores it in a database. This reception process uses HTTP requests and REST APIs.

[1198] 3. A server containing a generative AI model that calculates market rents based on the address information.

[1199] The server uses a generative AI model to calculate average rent prices based on the address information entered by the user. This generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. The model learns from historical rent data and current market conditions to provide accurate rent prices in real time.

[1200] 4. A method for generating evidence of the calculated market rent

[1201] The server generates evidence of the calculated rent market price. This evidence is created in PDF or web page format and includes detailed data and rationale for the rent market price. Python's FPDF library is used to generate the evidence.

[1202] 5. Means for returning said evidence to the terminal

[1203] The server sends the generated evidence to the user's device using a REST API or email sending system. The user can then check the evidence on their smartphone or PC.

[1204] 6. A way to view properties in a virtual reality environment

[1205] Users can virtually view properties using a VR headset. The VR environment is built in conjunction with Unity and Unreal Engine to provide users with a 360-degree virtual experience.

[1206] 7. Means for displaying said evidence within said virtual reality environment

[1207] This is a system for displaying evidence of calculated market rents in a virtual reality environment, allowing users to check market rents in real time while viewing properties.

[1208] 8. Means for assisting in rent negotiations within said virtual reality environment

[1209] The chatbot function is used in virtual reality to support real-time rent negotiations. This chatbot uses natural language processing technology to converse with users. It can also negotiate on behalf of users, providing them with the ability to negotiate rent on their behalf.

[1210] Specific examples of processing

[1211] The user views a rental property in a virtual store and enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo." The server receives the address information and calculates the average rent using a generative AI model. The result is 300,000 yen, and evidence is displayed in the virtual space. The user then begins rent negotiations with the management company via a chatbot.

[1212] Prompt Sentence Examples

[1213] "Please calculate the average rent for the following address: 1-2-3 XX-cho, Shibuya-ku, Tokyo"

[1214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1215] Step 1:

[1216] The user enters address information. Using a smartphone or PC, the user enters the address "1-2-3 XX-cho, Shibuya-ku, Tokyo" through an application or web form. The entered address information is sent from the device to the server.

[1217] Step 2:

[1218] The server receives the address information, processes the HTTP request, and stores the address information in a database. This data is then used by the generative AI model to calculate market rents.

[1219] Step 3:

[1220] The server calculates the average rent. The server inputs the stored address information into a generative AI model to predict the average rent. This model is built using TensorFlow and PyTorch, and predicts the average rent in real time based on past data and market trends. The output is average rent data such as "300,000 yen."

[1221] Step 4:

[1222] The server generates evidence. Based on the calculated market rent data, the server creates evidence in PDF or web format. This evidence includes details of market rents and the underlying data. The PDF is generated using a library such as Python's FPDF library.

[1223] Step 5:

[1224] The server returns the evidence to the device. The generated evidence is sent back to the user's smartphone or PC via REST API or email. The user can then view this evidence on their device.

[1225] Step 6:

[1226] Users can view properties in a virtual reality environment. Users wear a VR headset and access the virtual reality environment. This environment is built using Unity and Unreal Engine, allowing users to inspect the property in detail with a 360-degree view.

[1227] Step 7:

[1228] The server displays evidence within the virtual reality environment. Rent market evidence is displayed within the user's field of vision. This display is done in real time, providing rent data and its rationale as an overlay in the virtual space.

[1229] Step 8:

[1230] Users will be provided with a means to assist in rent negotiations. Within the virtual reality environment, a chatbot will receive instructions from the user and assist in rent negotiations with the property management company in real time. The chatbot will use natural language processing technology to converse and convey the user's request for a rent reduction. If the user so desires, the chatbot can also negotiate with the property management company on their behalf.

[1231] As described above, the data input and output are clearly defined at each step, and data processing and calculations are performed based on this, allowing the system to enable users to efficiently negotiate rent in a virtual reality environment.

[1232] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1233] This invention combines a system that enables residents of rental housing to easily negotiate rent when renewing their rental contracts with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state and optimizes support for rent negotiations based on the results.

[1234] User address input and emotion recognition

[1235] First, the user launches the application using a device (PC or smartphone). The user enters the address information of the rental property into the application's input form (for example, "1-2-3 XX-cho, Shibuya-ku, Tokyo"). As the user enters the information, the emotion engine analyzes the user's input speed and facial expression, and recognizes the user's emotional state regarding the address information. This emotional information is also sent to the server.

[1236] The server receives the address information and emotion information.

[1237] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[1238] Calculating market rent

[1239] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[1240] Generating and providing evidence that takes emotional information into account

[1241] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[1242] Rent negotiation support and proxy proposals

[1243] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user can use the generated evidence to negotiate the rent when renewing the rental contract. For example, based on the evidence, the user can propose to the management company that the current rent of 350,000 yen be reduced to 300,000 yen.

[1244] The emotion engine may also suggest negotiating rent on behalf of the user depending on the user's emotional state. For example, if the server detects that the user is feeling highly stressed, it will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on their behalf. The server will then communicate the details of the negotiation along with the evidence to the owner or management company.

[1245] Specific examples

[1246] For example, suppose a user named Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and is due to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka requests it, the server will negotiate on his behalf.

[1247] In this way, this system supports rent negotiations while taking into account the user's emotional state, making it a powerful tool for residents to achieve a fair rent.

[1248] The processing flow will be explained below.

[1249] Step 1:

[1250] The user launches the application using their device. The user enters the address information of the rental property (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo") into the application's input form. As the user enters information, the emotion engine analyzes the user's input patterns and facial expression data in real time to recognize their emotional state (e.g., anxiety, stress).

[1251] Step 2:

[1252] The user presses the "Submit" button to send the address information and the detected emotion information to the server via an HTTP request.

[1253] Step 3:

[1254] The server receives the address information and emotion information sent from the device, parses the data, and passes the address information and emotion information to the appropriate processing module.

[1255] Step 4:

[1256] The server calculates the average rent using a generative AI model. The generative AI model calculates the real-time average rent (e.g., 300,000 yen) based on the address information by collecting and analyzing rent data for similar properties in the area and past rent trends.

[1257] Step 5:

[1258] The server generates evidence based on the calculated market rent. The evidence includes market rent data and related evidence (such as rent data for surrounding properties and trend graphs). Furthermore, based on the emotional information recognized by the emotion engine, negotiation support advice (e.g., "Please pay attention to these points to reduce your anxiety") is added to the user.

[1259] Step 6:

[1260] The server returns the generated evidence to the terminal using an HTTP response.

[1261] Step 7:

[1262] The terminal receives the evidence returned from the server. The terminal displays the evidence in the user interface so that the user can review it. The user can review the evidence and download or print it as a PDF.

[1263] Step 8:

[1264] Users negotiate rent based on evidence when renewing a rental contract. Based on evidence, users propose to the management company that the current rent (e.g., 350,000 yen) be lowered to a fair market price (e.g., 300,000 yen). Users can negotiate more effectively by following the advice provided by the emotion engine.

[1265] Step 9:

[1266] The emotion engine continuously monitors the user's emotional state, and if it detects that the user is experiencing high levels of stress or anxiety, it suggests proxy negotiation options, which are displayed in the user interface.

[1267] Step 10:

[1268] If the user selects the proxy negotiation option, the server will negotiate the rent on the user's behalf. The server will organize the evidence and negotiation details and contact the management company or owner. Specifically, it will send the evidence by email or phone and explain the negotiation points.

[1269] Through the above steps, the system can effectively support rent negotiations while taking into account the user's emotional state.

[1270] Example 2

[1271] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1272] Conventional rent negotiation systems have the problem that users negotiate rent without considering their own emotional state, making it difficult to negotiate effectively. In particular, emotions such as tension and anxiety often have a negative impact on the outcome of the negotiation, placing a heavy burden on users. Furthermore, many users have little experience in rent negotiations, making it difficult for them to collect appropriate evidence and implement effective approaches. Furthermore, if users feel strong stress during the negotiation process, they may be unable to achieve a fair rent.

[1273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1274] In this invention, the server includes a means for a user to input address information and recognize the user's emotional state; a server that receives the address information and emotional information; a server that includes a generative AI model that calculates the average rent price based on the address information and emotional information; a means for generating the calculated average rent price as evidence and providing advice to the user based on the emotional information; and a means for returning the evidence and advice to the terminal. This allows the system to calculate an appropriate average rent price and provide effective evidence while taking the user's emotional state into consideration, allowing the user to negotiate the rent with peace of mind. Furthermore, by offering proxy negotiations as needed, the system can reduce the user's mental burden and help them achieve a more appropriate rent price.

[1275] "User address information" is geographical information that a user inputs to identify the location of a rental property.

[1276] "Emotional state" is information that represents the user's emotions and mood, and is analyzed from input speed, facial expressions, voice, etc.

[1277] A "server" is a computer device that receives address information and emotion information sent by a user and processes and analyzes them.

[1278] A "generative AI model" is a program that uses artificial intelligence algorithms to calculate market rent prices based on specific input data (address information and emotional information).

[1279] "Evidence" refers to documents or reports containing data or supporting information to support market rents.

[1280] "Advice" is advice or suggestions provided to users based on the results of generative AI models and emotion engines.

[1281] A "terminal" is a device (such as a personal computer or smartphone) that a user uses to input information and receive evidence and advice sent from a server.

[1282] An "emotion engine" is software or a system for analyzing a user's emotional state, analyzing data such as the user's input speed, facial expressions, and voice.

[1283] "Market rent" refers to the market price of rent in a specific area or property, and is calculated using a generative AI model.

[1284] This invention is a system that allows residents of rental housing to easily negotiate rent. The system uses an emotion engine and generative AI model to recognize the user's emotional state and assist with rent negotiations based on this.

[1285] First, the user launches the application using a device (such as a PC or smartphone). The user enters the address information of the rental property into the application's input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo"). At this time, an emotion engine (such as Microsoft Azure Cognitive Services Emotion API) analyzes the user's input speed, facial expressions, and voice to recognize their emotional state. The device then sends the address information and emotion information to the server.

[1286] The server receives the address and emotion information sent by the user. The received information is parsed and passed to a generative AI model (e.g., OpenAI GPT-4). The server sends the following prompt to the generative AI model:

[1287] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[1288] User Sentiment: "Mild Anxiety"

[1289] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[1290] Goal: "Calculate the fair market rent price"

[1291] The generative AI model calculates an appropriate market rent based on the prompt sentence, taking into account rent data for similar properties in the area and past rent trends. The server receives the market rent data calculated by the generative AI model.

[1292] Next, the server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (e.g., rent data for surrounding properties, trend graphs, etc.). Furthermore, appropriate rent negotiation support advice is provided to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, advice to reassure them is added.

[1293] Once the evidence and advice are ready, the server generates them in PDF or web format and sends them back to the device, where the user can review the evidence and advice and download the PDF or print it as needed.

[1294] As a concrete example, consider the case where Mr. Tanaka lives at 1-2-3 XX-cho, Shibuya-ku, Tokyo, and his rental contract is up for renewal. Mr. Tanaka accesses the system from his smartphone and enters his address information. At this time, the emotion engine analyzes Mr. Tanaka's facial expressions and recognizes that he is feeling anxious. The server receives the entered address information and emotion information and calculates the average rent to be 300,000 yen based on the generative AI model. The server then generates evidence based on this data and adds emotion-based advice. Mr. Tanaka uses the evidence to negotiate a reduction in his current rent of 350,000 yen to 300,000 yen.

[1295] Furthermore, if the system recognizes that Tanaka felt a great deal of stress during the negotiations, it will suggest the option of negotiating on his behalf, and if Tanaka agrees, the server will negotiate on his behalf, thereby reducing Tanaka's mental burden and helping to achieve a fair rent.

[1296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1297] System program processing flow

[1298] 1. Divide into processing steps

[1299] 1. User address input and emotion recognition

[1300] 2. The server receives the address information and emotion information.

[1301] 3. Calculating the market rent

[1302] 4. Generating and providing evidence that takes emotional information into account

[1303] 5. Rent negotiation support and proxy proposals

[1304] 2. Explain each processing step in detail

[1305] Step 1:

[1306] The user launches the application using a device (PC or smartphone).

[1307] The user enters the address information of the rental property into the input form (e.g., "1-2-3 XX-cho, Shibuya-ku, Tokyo").

[1308] Input: Address information

[1309] Processing: The emotion engine analyzes the user's input speed, facial expressions, and voice to recognize their emotional state.

[1310] Output: Recognized emotion information

[1311] How it works: The emotion engine (e.g., Microsoft Azure Cognitive Services Emotion API) collects data from the user's camera and microphone and analyzes their emotions in real time. Address information and emotion information are sent from the device to the server.

[1312] Step 2:

[1313] The server receives the address information and emotion information sent by the user.

[1314] Input: Address information and emotion information

[1315] Processing: Parses the received information and prepares it for passing to the generative AI model.

[1316] Output: Parsed address information and sentiment information

[1317] What it does: The server checks the data it receives and formats it as needed, standardizing addresses and sentiment information for consistency.

[1318] Step 3:

[1319] The server runs the generative AI model.

[1320] Input: Analyzed address information and sentiment information, historical data (rent trend data for the same area over the past year, average rent data for surrounding properties)

[1321] Processing: Send a prompt to the generative AI model to calculate the appropriate market rent.

[1322] Output: Calculated market rent data

[1323] Specific operation: The server sends the following prompt to the generative AI model:

[1324] User Address: "1-2-3 XX-cho, Shibuya-ku, Tokyo"

[1325] User Sentiment: "Mild Anxiety"

[1326] Historical data: "Rent trend data for the same area for the past year, average rent data for surrounding properties"

[1327] Goal: "Calculate the fair market rent price"

[1328] A generative AI model (e.g., OpenAI GPT-4) performs calculations based on this information and outputs an appropriate market rent.

[1329] Step 4:

[1330] The server generates evidence based on the calculated market rent and provides emotion-based advice.

[1331] Input: Calculated market rent data, sentiment information

[1332] Processing: Document market rents as evidence and add emotionally informed advice.

[1333] Output: Generated evidence and advice

[1334] Specific operation: The server compiles the calculated rent market price into a PDF or web report. Taking into account emotional information, if the user is feeling anxious, it adds reassuring advice and specific negotiation steps.

[1335] Step 5:

[1336] The server returns evidence and advice to the terminal.

[1337] Input: Generated evidence and advice

[1338] Processing: Send evidence and advice to the terminal.

[1339] Output: Evidence and advice displayed on the terminal

[1340] Specific operation: The evidence and advice returned from the server arrives at the terminal and is displayed on the user interface. The user can review it and download or print the PDF as needed.

[1341] It includes specific actions at each step and provides a detailed explanation of how the system works.

[1342] (Application example 2)

[1343] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1344] The present invention solves the problem that the information and support provided by conventional rent negotiation support systems does not take into account the emotional state of the user, making it difficult for users to negotiate rent with confidence. Another problem is that there is a lack of personalized recommended content that corresponds to the emotional state of the user.

[1345] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's address information, means for receiving the address information, means including a generative AI model that calculates a rent market price based on the address information, means including an emotion engine that analyzes the user's emotional state, means for providing rent negotiation support optimized based on the analyzed emotional state, means for generating personalized recommended content based on the emotional state of the viewing content, means for transmitting emotion information to the server, means for generating the calculated rent market price as evidence, and means for returning the evidence to the terminal. This allows the user to receive optimal rent negotiation support that takes their emotional state into consideration, and further enables them to enjoy personalized recommended content based on their emotional state in viewing content as well.

[1346] "User" refers to the end user who uses the system to negotiate rent and view content.

[1347] "Address information" refers to data containing detailed information about the location of the property where the user lives.

[1348] "Server" refers to the computer system that receives, analyzes, and processes address information and emotion information sent by users.

[1349] A "generative AI model" refers to an artificial intelligence algorithm that calculates average rent prices based on given data.

[1350] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions, voice, etc.

[1351] "Optimized rent negotiation support" refers to advice and tools provided to facilitate rent negotiations, taking into account the user's emotional state.

[1352] "Personalized recommended content" refers to viewing content that is individually suggested based on the user's emotional state.

[1353] "Emotion information" refers to data that indicates the user's current emotional state as analyzed by the emotion engine.

[1354] "Evidence" refers to empirical materials including market rent prices and the underlying data, which users use when negotiating rent.

[1355] "Terminal" refers to a device such as a smartphone, PC, or tablet that allows a user to access the system via the Internet.

[1356] To implement this invention, a user utilizes a system that analyzes their emotional state and appropriately negotiates rent. This system consists of an application and a server that users can access via devices such as smartphones and PCs.

[1357] System Configuration

[1358] 1. User address input and emotion recognition

[1359] The user launches the application using a device such as a smartphone and enters the address information of the rental property. As the user enters the information, the emotion engine analyzes the user's typing speed, facial expression, tone of voice, etc. to obtain emotional information. This allows the system to recognize how the user feels about rent negotiations.

[1360] 2. The server receives the address information and emotion information.

[1361] The server receives the address information and emotion information sent by the user. The received information is parsed and passed to the generative AI model. The emotion information recognized by the emotion engine is also processed at the same time.

[1362] 3. Calculating the market rent

[1363] The server calculates the market rent using a generative AI model. The generative AI model takes into account rent data for similar properties in the area and past rent trends, and calculates an appropriate market rent based on real-time data. The accuracy of the collected data is important in this process.

[1364] 4. Generating and providing evidence that takes emotional information into account

[1365] The server generates evidence based on the calculated market rent. The generated evidence includes market rent data and the underlying data (for example, rent data for surrounding properties and trend graphs). In addition, appropriate rent negotiation support advice is added to the user based on the emotional information recognized by the emotion engine. For example, if the user is feeling anxious, the system will provide advice and procedures that will reassure them. The evidence is generated in PDF or web format and sent from the server to the terminal.

[1366] 5. Supporting users in using the service and negotiating rent

[1367] The terminal receives the evidence returned from the server and displays it on the user interface. The user can check the evidence and download or print it as a PDF if necessary. The user then uses the generated evidence to negotiate the rent when it comes time to renew the rental contract. For example, the server may suggest to the management company that the current rent of 350,000 yen be reduced to 300,000 yen based on the evidence. The emotion engine may also suggest negotiating the rent on the user's behalf, depending on the user's emotional state. For example, if the server recognizes that the user is feeling very stressed, the server will suggest a proxy negotiation option, and if the user wishes, the server will use the evidence to negotiate the rent on the user's behalf. The server then notifies the owner or management company of the details of the negotiation along with the evidence.

[1368] Program processing

[1369] This program uses OpenCV to capture the user's face, convert it to grayscale, and then input it into a pre-trained emotion recognition model (pre-prepared pkl file) to analyze the user's emotional state. Once the emotion is recognized, an API request is made based on the emotion to obtain recommended content information.

[1370] Hardware and software used

[1371] Hardware: Smartphone or PC camera and microphone.

[1372] Software: Python, OpenCV, sklearn, requests.

[1373] Specific examples

[1374] For example, consider a specific user named Tanaka, who lives at an address in Tokyo and is about to renew his rental contract. Tanaka accesses the system from his smartphone and enters his address information. As he enters the information, the emotion engine analyzes his facial expressions and recognizes that he is feeling mild anxiety. The server receives the address information and emotion information, and uses a generative AI model to calculate the average rent as 300,000 yen. The server then generates evidence based on this data and adds emotion-based advice. Tanaka reviews the evidence and negotiates to lower his current rent of 350,000 yen to 300,000 yen. If Tanaka is feeling stressed, the system will suggest a proxy negotiation option, and if Tanaka wishes, the server will negotiate on his behalf. In this way, Tanaka can proceed with the rent negotiation with peace of mind.

[1375] Prompt Sentence Examples

[1376] "I want to laugh at movies, so please recommend some movies that will put me in a good mood."

[1377] "I want to relax, so please recommend some relaxation music."

[1378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1379] Step 1:

[1380] This is a method for users to input address information. Users input the address information of rental properties into an input form on their smartphone or PC. At this time, the emotion engine analyzes the input speed, facial expression, and tone of voice. The input includes address information and biometric information (facial expression, voice, etc.), and emotional information is generated as the output.

[1381] Step 2:

[1382] The terminal sends the address information and emotion information to the server. The sent information is parsed (analyzed) on the server side and separated into address information and emotion information. The address information and emotion information are included as input, and the analyzed data is obtained as output.

[1383] Step 3:

[1384] The server uses a generative AI model to calculate the average rent based on the address information received, referencing rent data for similar properties in the area and past rent trends. The input includes the address information and data on surrounding properties, and the output is the average rent.

[1385] Step 4:

[1386] The server generates evidence for optimized rent negotiation support, taking into account the emotional information recognized by the emotion engine. The generated evidence includes market rent data and the underlying data. Market rent data and emotional information are included as inputs, and evidence is obtained as output.

[1387] Step 5:

[1388] The server sends the evidence back to the terminal. The terminal receives this evidence and displays it in a user interface. The user can view the evidence and download or print it as a PDF. The input contains the evidence, and the output is the displayed evidence.

[1389] Step 6:

[1390] The user uses the generated evidence to negotiate the rent, and if necessary, proposes to the management company to lower the current rent. The input includes the evidence, and the output is the negotiation result.

[1391] Step 7:

[1392] The emotion engine may also suggest proxy negotiation of the rent depending on the user's emotional state. For example, if the server recognizes that the user is feeling highly stressed, it will suggest a proxy negotiation option. If the user requests it, the server will negotiate the rent on their behalf. The input includes emotional information and evidence, and the output is the result of the proxy negotiation.

[1393] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1394] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1395] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1396] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1397] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1398] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1399] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1400] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1401] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1402] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1403] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1404] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1405] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1406] 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.

[1407] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1408] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1409] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1410] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1411] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1412] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1413] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1414] The following is further disclosed regarding the above embodiment.

[1415] (Claim 1)

[1416] a means for a user to input address information;

[1417] a server that receives the address information;

[1418] A server including a generation AI model that calculates market rent prices based on the address information;

[1419] A means for generating evidence of the calculated market rent;

[1420] The system includes means for returning the evidence to the terminal.

[1421] (Claim 2)

[1422] The system of claim 1 , further comprising means for a user to negotiate rent using the evidence.

[1423] (Claim 3)

[1424] The system of claim 1 , further comprising means for using the evidence to negotiate rent on behalf of a user.

[1425] "Example 1"

[1426] (Claim 1)

[1427] a means for a user to input address information;

[1428] a server that receives the address information;

[1429] A server including a generation AI model that calculates market rent prices based on the address information;

[1430] A means for generating evidence of the calculated market rent;

[1431] means for returning said evidence to a terminal;

[1432] means for generating said evidence in PDF or web format;

[1433] A means for calculating market rent prices in real time using data on surrounding properties and past rent trends in the generating AI model;

[1434] a means for displaying the evidence in a user interface;

[1435] The system includes a means for storing address information transmitted from the terminal to the server in a database.

[1436] (Claim 2)

[1437] The system of claim 1 , further comprising means for a user to negotiate rent using the evidence.

[1438] (Claim 3)

[1439] The system of claim 1 , further comprising means for using the evidence to negotiate rent on behalf of a user.

[1440] "Application Example 1"

[1441] (Claim 1)

[1442] a means for a user to input address information;

[1443] a server that receives the address information;

[1444] A server including a generation AI model that calculates market rent prices based on the address information;

[1445] A means for generating evidence of the calculated market rent;

[1446] means for returning said evidence to a terminal;

[1447] A means to view properties in a virtual reality environment;

[1448] means for displaying the evidence within the virtual reality environment;

[1449] means for facilitating rent negotiation within said virtual reality environment;

[1450] A system including:

[1451] (Claim 2)

[1452] The system of claim 1 , further comprising means for a user to negotiate rent using the evidence.

[1453] (Claim 3)

[1454] The system of claim 1 , further comprising means for using the evidence to negotiate rent on behalf of a user.

[1455] "Example 2: Combining Emotion Engines"

[1456] (Claim 1)

[1457] means for a user to input address information and recognize emotional states;

[1458] a server that receives the address information and emotion information;

[1459] a server including a generation AI model that calculates market rent prices based on the address information and emotion information;

[1460] A means for generating the calculated market rent as evidence and providing advice to the user based on emotional information;

[1461] The system includes means for transmitting said evidence and advice back to the terminal.

[1462] (Claim 2)

[1463] The system of claim 1 , further comprising means for a user to negotiate rent using the evidence and advice.

[1464] (Claim 3)

[1465] The system of claim 1 , further comprising means for using the evidence and advice to negotiate rent on behalf of a user.

[1466] "Application example 2 when combining emotion engines"

[1467] (Claim 1)

[1468] a means for a user to input address information;

[1469] a server that receives the address information;

[1470] A server including a generation AI model that calculates market rent prices based on the address information;

[1471] means including an emotion engine for analyzing an emotional state of a user;

[1472] a means for providing optimized rent negotiation assistance based on the analyzed emotional state;

[1473] means for generating personalized recommended content based on the emotional state of the viewed content;

[1474] means for transmitting the recognized emotion information of the non-life insurance to a server;

[1475] A means for generating evidence of the calculated market rent;

[1476] The system includes means for returning the evidence to the terminal.

[1477] (Claim 2)

[1478] The system of claim 1 , further comprising means for a user to negotiate rent using the evidence.

[1479] (Claim 3)

[1480] The system of claim 1 , further comprising means for using the evidence to negotiate rent on behalf of a user. [Explanation of symbols]

[1481] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input address information; a server that receives the address information; A server including a generation AI model that calculates market rent prices based on the address information; A means for generating evidence of the calculated market rent; The system includes means for returning the evidence to the terminal.

2. The system of claim 1 , further comprising means for a user to negotiate rent using the evidence.

3. The system of claim 1 , further comprising means for using the evidence to negotiate rent on behalf of a user.

Images