system

Abstract

Provide a system. The method includes providing an interactive interface for a user to input trade area information and competitor information; A means for using a generative AI model to analyze trade area conditions and competitive information specified based on user input; A database search means for identifying the most suitable candidate site for opening a store based on the above analysis; a map data generating means for displaying the identified store candidate site on an online map; means for providing the map data to users online; A system including:

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] Selecting a location for a store typically requires a lot of time and money, and it is difficult to accurately grasp the market and competitive situation. Furthermore, existing methods often require manual collection and analysis of information, making it difficult to make quick and effective decisions. These problems are particularly pronounced for retailers and companies considering opening new stores, and there is a need for a system that can consistently and efficiently perform market analysis and store location selection. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. It employs a system that includes: means for providing an interactive interface for users to input trade area information and competitive information; means for using a generative AI model to analyze the trade area conditions and competitive information specified based on the user input; database search means for identifying optimal store location candidates based on the above analysis; map data generation means for displaying the identified store location candidates on an online map; and means for providing the map data to users online. This system enables users to easily, quickly, and accurately analyze the market and effectively select store locations.

[0006] "User" means an individual or corporation that uses the system.

[0007] "Trade area information" refers to information about the market characteristics of the area where a store is being considered, including population density, consumer purchasing power, and transportation access.

[0008] "Competitive information" refers to information about existing stores in the same industry in the area where you are considering opening a store, including their location, number, size, etc.

[0009] An "interactive interface" is a user interface in which a user can enter questions or commands in natural language and the system responds to them.

[0010] A "generative AI model" is an algorithm or software that uses natural language processing and machine learning to analyze user input and extract useful information.

[0011] The "database search means" is a mechanism for searching a database based on specified conditions and obtaining the required information.

[0012] The "map data generation means" is a means for mapping the identified potential store locations on an online map, and includes a geographic information system (GIS) and an API.

[0013] "Online Map" means a map service accessible via the Internet that displays geographic information in real time.

[0014] A "prospective store location" is a location identified by the system that is suitable for opening a new store. [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] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, and online map display means. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with specific examples.

[0037] System Operation Overview

[0038] 1. User input

[0039] The user uses a terminal to input desired business area conditions and competitive information into the chat interface. For example, they might input, "I'm looking for an area in Tokyo with a high population but few cafes."

[0040] 2. Data transmission by the terminal

[0041] The terminal sends the user's input data to the server, which is encrypted for security reasons.

[0042] 3. Data analysis by the server

[0043] The server analyzes the received data using a generative AI model. This model uses natural language processing algorithms to extract important keywords and conditions from the input text. Conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0044] 4. Database search by server

[0045] The server searches specified databases (e.g., geographic information databases, demographic data, competitor store data, etc.) based on the analyzed conditions. For example, it identifies areas in Tokyo with high population density and filters out areas with few cafes.

[0046] 5. Identification of potential store locations by the server

[0047] Based on the information obtained from the database, potential locations that meet the criteria are identified, such as specific areas in Shinjuku Ward or Shibuya Ward.

[0048] 6. Map data generation by the server

[0049] The server uses an online map service (e.g., Google® Maps API) to map the identified potential locations, adding pop-up information (e.g., population density, number of existing cafes) to each location.

[0050] 7. Sending map data to the device

[0051] The server sends the generated map data to the device, where it is provided in an interactive format.

[0052] 8. User confirmation of candidate sites

[0053] The device displays the received map data to the user, who can then click on the markers on the map to view detailed information about each candidate location.

[0054] Specific examples

[0055] scenario

[0056] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0057] 1. Enter information

[0058] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population and few cafes."

[0059] 2. Data Transmission

[0060] The terminal transmits the input data to the server.

[0061] 3. Data Analysis

[0062] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0063] 4. Database Search

[0064] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[0065] 5. Identifying potential sites

[0066] The server obtains location information for the specified area and performs further filtering, which may result in a specific location within Shinjuku Ward.

[0067] 6. Map data generation

[0068] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[0069] 7. Map data transmission

[0070] The server transmits the map data to the terminal.

[0071] 8. Confirmation of candidate sites

[0072] The device displays map data to the user, who can click on a marker to see more information.

[0073] In this way, users can intuitively and quickly find potential store locations, enabling them to efficiently proceed with the execution of store opening plans.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[0077] Step 2:

[0078] The terminal encrypts the information entered by the user and sends it to the server. This encryption ensures the security of the transmitted data.

[0079] Step 3:

[0080] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0081] Step 4:

[0082] The server then begins a database search based on the analysis results. First, it searches the geographic information database to obtain information about areas within Tokyo.

[0083] Step 5:

[0084] Next, the server searches a demographic database to obtain population density information for each area in Tokyo, and filters out areas with high population density.

[0085] Step 6:

[0086] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[0087] Step 7:

[0088] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0089] Step 8:

[0090] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0091] Step 9:

[0092] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0093] Step 10:

[0094] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] Conventional store opening support systems required users to analyze complex trade area conditions and competitive information to find the optimal store location, which required specialized knowledge and was time-consuming and labor-intensive.In addition, they lacked a visual interface for making decisions based on detailed information, resulting in an unsatisfactory user experience.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitive information, means for using a generative AI model to analyze the trade area conditions and competitive information specified based on user input, and map data generation means for displaying identified store candidate sites on an online map, allowing users to easily identify and visually confirm store candidate sites without requiring specialized knowledge.

[0100] A "user" is an individual or corporation that uses this system to input trade area information and competitor information to identify potential locations for opening a store.

[0101] "Trade area information" is data on market characteristics and customer trends in a specific region.

[0102] "Competitor information" is data regarding the number and types of competing stores in a particular area.

[0103] A "conversational interface" is an application such as a chat interface or form designed to allow users to enter trade area or competitor information in natural language.

[0104] A "generative AI model" is an artificial intelligence model that analyzes natural language text entered by a user and extracts important keywords and conditions.

[0105] The "database search means" is a system function for searching for trade area information and competitor information based on specified conditions.

[0106] The "map data generating means" is a system function for displaying the identified potential store locations on an online map.

[0107] "Online Map" means a digital map application accessible via the Internet.

[0108] "Encryption" is a technology that converts data using a specific algorithm to ensure information security.

[0109] "Demographic data" refers to data about the population composition and density of a particular area.

[0110] "Geographic information data" is data relating to the geographic characteristics of a particular area.

[0111] A "marker" is a visual icon used to indicate a specific location on an online map.

[0112] "Detailed information" is additional data about a particular potential store location (e.g., population density, number of existing stores, etc.).

[0113] The system of this invention executes a series of processes to identify potential locations for store openings by inputting trade area information and competitor information using a generative AI model and analyzing the information. To achieve this, the system includes the following main components:

[0114] System configuration

[0115] 1. User input: A user uses a device to access a conversational interface and input information about the market and competitors. Specifically, the user uses a web or mobile application. For example, the user might enter, "I'm looking for an area in Tokyo that has a high population but few cafes," into a chat interface.

[0116] 2. Data transmission by the terminal: The terminal converts the information entered by the user into an appropriate format, encrypts it using SSL / TLS for security reasons, and sends it to the server. The software used includes request libraries that use the HTTP protocol (e.g., fetch API or HTTP client library).

[0117] 3. Data analysis by the server: The server inputs the received data into a generative AI model (e.g., ChatGPT (registered trademark)) and analyzes the text. The generative AI model uses natural language processing algorithms to extract important keywords and conditions. Examples include "within Tokyo," "large population," and "few cafes."

[0118] 4. Database Search: The server searches the specified database (e.g., PostgreSQL, MongoDB) based on the parsed criteria. The search targets can be geographical databases, demographic databases, competitor store data, etc. Specific SQL or NoSQL queries are used to extract the data.

[0119] 5. Identifying potential locations for store openings: The server identifies potential locations for store openings that meet the criteria based on information obtained from the database. For example, it filters areas in Tokyo with high population density and few cafes, and identifies Shinjuku Ward and Shibuya Ward.

[0120] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on an online map. Pop-up information such as population density and the number of existing cafes is added to each candidate location to make it easier for users to understand visually.

[0121] 7. Sending map data to the device: The server sends the generated map data to the device. The map data is provided in an interactive format (e.g., GeoJSON format).

[0122] 8. User confirmation of candidate locations: The device displays the received map data and allows the user to interactively check the candidate locations. The user can click on the markers on the map to view detailed information about each candidate location.

[0123] Specific examples

[0124] Below are some specific scenarios and examples of input to the generative AI model.

[0125] scenario

[0126] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0127] 1. Information input: The user enters into the chat interface on their device, "I'm looking for an area in Tokyo that has a high population but few cafes."

[0128] 2. Data transmission: The terminal transmits the input data to the server.

[0129] 3. Data analysis: The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0130] 4. Database search: The server searches the geographical information database, demographic database, and competitor store data based on the conditions to identify matching areas. For example, specific areas in Shinjuku Ward or Shibuya Ward are found.

[0131] 5. Identifying candidate locations: The server obtains location information for the identified areas and performs further filtering.

[0132] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on a map.

[0133] 7. Send map data: The server sends the generated map data to the device.

[0134] 8. Confirm candidate locations: The device displays map data to the user, and the user can click on a marker to see more information.

[0135] Example input to a generative AI model

[0136] Examples of prompts:

[0137] "I'm looking for an area in Tokyo that has a large population but few cafes. Which area is that?"

[0138] In this way, the system of the present invention allows users to easily conduct trade area surveys and quickly find the most suitable candidate site for opening a store.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] Enter information

[0142] Users use a device to access a dialogue-style interface and input business area and competitor information in natural language. Specifically, they might type into the chat interface, "I'm looking for an area in Tokyo that has a high population but few cafes." This input data is saved in text format on the device.

[0143] Step 2:

[0144] Data transmission

[0145] The terminal encrypts the text data entered by the user and sends it securely to the server using SSL / TLS. The input is the trade area conditions and competitive information entered by the user, and the output is the encrypted text data sent to the server.

[0146] Step 3:

[0147] Data analysis

[0148] The server decrypts the received encrypted data and inputs it as analysis data into a generative AI model (for example, ChatGPT). This model uses a natural language processing algorithm to analyze the text and extract important keywords and conditions. Specifically, conditions such as "within Tokyo," "large population," and "few cafes" are extracted. The input is the user's text data, and the output is the extracted keywords and conditions.

[0149] Step 4:

[0150] Database search

[0151] The server searches multiple databases based on the analyzed conditions, including geographic information databases, demographic databases, and competitor store databases. Specifically, it uses SQL and NoSQL queries to extract areas with high population density and few cafes. The input is the extracted conditions, and the output is the retrieved data entries.

[0152] Step 5:

[0153] Identifying potential locations for stores

[0154] The server identifies the optimal candidate locations for opening a store based on the information obtained from the database. Specifically, it filters areas with a small number of cafes in Shinjuku Ward or Shibuya Ward, for example, and identifies detailed candidate locations. The input is the acquired data entry, and the output is a list of identified candidate locations.

[0155] Step 6:

[0156] Map data generation

[0157] The server uses the Google Maps API to map the identified candidate locations on a map. It adds pop-up information to each candidate location, including detailed information such as population density and the number of existing cafes. This process generates visually easy-to-read map data. The input is a list of candidate locations, and the output is the mapped map data.

[0158] Step 7:

[0159] Map data transmission

[0160] The server sends the generated map data to the device. This sent data is provided in GeoJSON format so that it can be used interactively. The input is the mapped map data, and the output is the interactive map data sent to the device.

[0161] Step 8:

[0162] Check the candidate site

[0163] The device displays the received map data to the user. The user can click on a marker on the map to view detailed information about each candidate location. The input is interactive map data, and the output is detailed information about the marker the user clicked.

[0164] (Application example 1)

[0165] 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."

[0166] In recent years, efficient location of logistics bases has become extremely important in the logistics industry in order to reduce logistics costs and speed up delivery. However, identifying the optimal location for a logistics center is extremely complex, as it requires consideration of a wide range of information, including existing facilities, traffic conditions, and local demographics. Traditional methods for addressing this issue have struggled to efficiently analyze the situation and present appropriate candidate sites.

[0167] 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.

[0168] In this invention, the server includes means for providing an interactive interface for a user to input facility location information and efficiency conditions, means for using a generative AI model to analyze the efficiency conditions and facility information specified based on the user input, and database search means for identifying optimal location candidate sites based on the above analysis, thereby enabling intuitive and rapid identification of efficient base locations in the logistics industry.

[0169] "Means for providing an interactive interface for users to input facility location information and efficiency criteria" means a system or software for providing an interactive interface designed to allow users to easily input criteria and requirements for the location of distribution centers and other facilities.

[0170] "Means using a generative AI model to analyze specified efficiency conditions and facility information based on user input" refers to systems or software that use a generative AI model to analyze efficiency conditions and facility information entered by a user. This generative AI model uses natural language processing technology to interpret the information and extract appropriate conditions and requirements.

[0171] The "database search means for identifying optimal candidate locations" refers to a system or software for searching and identifying suitable candidate locations from a related database based on the analyzed efficiency conditions and facility information.

[0172] "Map data generation means for displaying identified candidate placement locations on an online map" refers to a system or software that generates map data for visually displaying identified candidate placement locations and provides it through an online map service.

[0173] "Means for providing map data to users online" refers to a system or software that provides generated map data to users' devices via the Internet.

[0174] "Facility location information" refers to information about the locations and conditions of logistics centers and other facilities.

[0175] "Efficiency conditions" refer to the conditions and requirements for achieving desired efficiency in logistics and facility layout.

[0176] This invention relates to a system that supports optimal location of logistics centers and other facilities. The system of the present invention interactively collects facility location information and efficiency conditions entered by the user and analyzes them using a generative AI model. Based on the analysis results, the system then identifies optimal location candidates and displays them on an online map after a database search. The system of the present invention is implemented by the following steps:

[0177] 1. Collect user input:

[0178] Users use an interactive interface on devices such as smartphones or computers to input facility location information and efficiency conditions. This interface is designed to allow users to easily input conditions. For example, a user might input "a location in Tokyo with good transportation access and a reasonable distance from existing logistics centers."

[0179] 2. Data Transmission and Encryption:

[0180] The information entered by the user is sent from the terminal to the server, where it is encrypted for security reasons.

[0181] 3. Data Analysis:

[0182] The server analyzes the received data using a generative AI model. This generative AI model uses natural language processing algorithms to extract important keywords and conditions from the input text. The generative AI model uses, for example, the OpenAI (registered trademark) API.

[0183] 4. Database Search:

[0184] The server searches specified databases (e.g., geographical and related data) based on the analyzed criteria, thereby identifying optimal candidate locations.

[0185] 5. Map data generation and display:

[0186] The server uses online map generation tools such as Folium to map the identified candidate locations, and the generated map data is provided in an interactive format, allowing users to intuitively check detailed information.

[0187] 6. Providing interactive maps:

[0188] The server then sends the generated map data to the device, where users can view the map data on their smartphones or computers and obtain detailed information about the candidate locations.

[0189] Example prompt sentence:

[0190] Interpret the distribution center criteria entered by the user to identify key information. Input: A location in Tokyo with good transportation access and within a reasonable distance from existing distribution centers.

[0191] By implementing this invention, efficient location selection becomes possible in the logistics industry and facility location, leading to cost reductions and improved logistics efficiency. This system is characterized by its ability to perform real-time data analysis and identify candidate locations by utilizing existing databases and generative AI models.

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

[0193] Step 1:

[0194] User input of information

[0195] Users input facility location information and efficiency conditions into an interactive interface. This interface is provided on devices such as smartphones and computers. For example, let's say a user inputs "a location in Tokyo that has good transportation access and is within a reasonable distance from existing logistics centers."

[0196] Input: Facility location information, efficiency conditions

[0197] Output: User input data

[0198] Step 2:

[0199] Data transmission and encryption by the device

[0200] The data entered by the user is sent to the server by the terminal. At this time, the data is encrypted to ensure security. Encrypted data prevents data leakage during communication.

[0201] Input: User-entered data

[0202] Output: Encrypted user-entered data

[0203] Step 3:

[0204] Data reception by the server

[0205] The server receives the encrypted user-entered data, which is then decrypted back into a format that can be parsed. The decrypted data is then used for parsing in the next step.

[0206] Input: Encrypted user-entered data

[0207] Output: Decoded user input data

[0208] Step 4:

[0209] Data analysis

[0210] The server then analyzes the decoded user input data using a generative AI model. This generative AI model uses natural language processing technology to extract important keywords and conditions from the user's input text. For example, conditions such as "within Tokyo," "good transportation access," and "reasonable distance from existing logistics centers" are extracted.

[0211] Input: Decrypted user-entered data

[0212] Output: Parsed keywords and conditions

[0213] Step 5:

[0214] Searching the database

[0215] The server searches the specified database (geographical information and related data) based on the analyzed keywords and conditions, such as data on areas with good transportation access or the locations of existing logistics centers, to identify the optimal candidate locations.

[0216] Input: Parsed keywords and conditions

[0217] Output: Identified candidate locations

[0218] Step 6:

[0219] Map data generation

[0220] The server uses a map generation tool such as Folium to map the identified candidate locations, and the map displays detailed information about each location (e.g., access to the site, distance from existing facilities) as a pop-up.

[0221] Input: Identified candidate locations

[0222] Output: Generated map data

[0223] Step 7:

[0224] Sending map data

[0225] The server then sends the generated map data to the terminal, which provides the map data in an interactive format, allowing users to intuitively check detailed information.

[0226] Input: Generated map data

[0227] Output: Map data received by the device

[0228] Step 8:

[0229] Providing interactive maps

[0230] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each candidate site. This supports efficient facility placement decision-making.

[0231] Input: Map data received by the device

[0232] Output: An interactive map screen that the user sees

[0233] 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.

[0234] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with concrete examples.

[0235] System Operation Overview

[0236] 1. User input

[0237] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[0238] 2. Data transmission by the terminal

[0239] The terminal encrypts the data entered by the user and sends it to the server. This data is encrypted for security reasons.

[0240] 3. Data analysis by the server

[0241] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0242] 4. Recognition of user emotions using an emotion engine

[0243] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting when a user is feeling stressed or has positive emotions.

[0244] 5. Database search by server

[0245] The server starts a database search based on the analysis results and the user's sentiment. It searches the specified database (e.g., geographic information database, demographic data, competitor store data, etc.).

[0246] 6. Adaptive Feedback by the Server

[0247] The server provides appropriate feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it provides additional reassuring information (e.g., successful store openings).

[0248] 7. Identification of potential store locations by the server

[0249] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0250] 8. Map data generation by the server

[0251] The server uses an online map service (e.g., Google Maps API) to map potential locations, and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0252] 9. Sending map data to the device

[0253] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0254] 10. User confirmation of candidate sites

[0255] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[0256] Specific examples

[0257] scenario

[0258] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0259] 1. Enter information

[0260] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0261] 2. Data Transmission

[0262] The terminal transmits the input data to the server.

[0263] 3. Data Analysis

[0264] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0265] 4. Emotion recognition

[0266] The server uses an emotion engine to recognize the user's emotions from the user's input sentences and interactions. For example, it detects emotions such as "worry" and "expectation" in the user's posts.

[0267] 5. Database Search

[0268] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[0269] 6. Adaptive Feedback

[0270] If the user's feelings are recognized as worrying, the server provides additional reassurance, such as past success stories and risk mitigation strategies.

[0271] 7. Identifying potential sites

[0272] The server obtains location information for the specified area and performs further filtering, allowing users to find specific locations within Shinjuku Ward or locations that meet specific criteria.

[0273] 8. Map data generation

[0274] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[0275] 9. Map data transmission

[0276] The server transmits the map data to the terminal.

[0277] 10. Confirmation of candidate sites

[0278] The device displays map data to the user, who can click on a marker to see more information.

[0279] This allows users to quickly find the best potential location for a store through an interactive format, and with the help of an emotion engine, they can make more satisfying decisions.

[0280] The processing flow will be explained below.

[0281] Step 1:

[0282] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0283] Step 2:

[0284] The terminal encrypts the input data and sends it to the server. Encryption ensures the security of the data.

[0285] Step 3:

[0286] The server analyzes the received data and uses a generative AI model to extract important keywords and conditions from the input text, such as "within Tokyo," "high population," and "few cafes."

[0287] Step 4:

[0288] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting whether the user is feeling "worried" or "expecting."

[0289] Step 5:

[0290] The server then begins a database search based on the analysis results and the recognized emotion. First, it searches a geographic information database to obtain information about areas within Tokyo.

[0291] Step 6:

[0292] The server searches a demographic database to obtain population density information for each area in Tokyo, extracts areas with high population density, and performs filtering.

[0293] Step 7:

[0294] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[0295] Step 8:

[0296] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0297] Step 9:

[0298] The server provides adaptive feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it will provide additional information such as successful store openings and risk mitigation measures.

[0299] Step 10:

[0300] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0301] Step 11:

[0302] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0303] Step 12:

[0304] The terminal displays the received map data to the user, who can click on markers on the map to view detailed information about each potential store location.

[0305] Step 13:

[0306] The user selects the optimal location for a store based on the feedback information provided by the emotion engine. During this process, the user can ask additional questions or change conditions, and the system will then suggest the optimal location again.

[0307] Example 2

[0308] 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."

[0309] Conventional systems require a great deal of time and effort to manually analyze trade area and competitor information, and they also have the problem of being unable to provide appropriate feedback because they do not take into account the user's emotional state. Furthermore, data encryption and adaptive feedback provision were insufficient, which meant that users' concerns could not be fully alleviated. Therefore, there was a need for efficient and satisfying information provision.

[0310] 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.

[0311] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitor information, means for using a generative AI model to analyze the trade area conditions and competitor information specified based on user input, database search means for identifying optimal store location candidates, map data generation means for displaying the identified store location candidates on an online map, means for providing the map data to users online, means for using an emotion engine that recognizes emotions by analyzing user input and interactions, and means for providing adaptive feedback based on the emotion recognition, thereby enabling efficient information provision that takes the user's emotional state into consideration and provides a high level of satisfaction.

[0312] "User" means an individual or corporation that uses this system.

[0313] "Trade area information" is information about market demand and consumer behavior in a specific area.

[0314] "Competitive information" refers to information on competing businesses and products within a trade area.

[0315] An "interactive interface" is a user interface that allows a user to interact with a system in a conversational manner.

[0316] A "generative AI model" is an algorithm that uses artificial intelligence to analyze user input information and extract trade area conditions and competitive information.

[0317] The "database search means" is a means for searching a database based on specific conditions and obtaining required information.

[0318] The "map data generating means" is a means for generating data for displaying the identified store candidate site on an online map.

[0319] An "emotion engine" is a technology that analyzes user input and interactions to identify emotions.

[0320] "Adaptive feedback" is feedback that provides optimal advice or information based on the user's emotional state.

[0321] "Encryption" is the process of transforming data so that it cannot be read by third parties.

[0322] MODE FOR CARRYING OUT THE INVENTION

[0323] System Configuration

[0324] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. The following describes embodiments of the present invention.

[0325] Hardware and software used

[0326] Server: Used for data analysis, emotion recognition, database search, and map data generation.

[0327] Terminal: The device (e.g., computer, smartphone) on which the user enters information and checks results.

[0328] Generative AI models: Used to analyze user input information (e.g., GPT-4 (registered trademark)).

[0329] Emotion engine: Used to recognize the user's emotions.

[0330] Databases: Geographical databases, demographic data, competitor data, etc.

[0331] Online map service APIs: Used to generate and display map data (e.g., Google Maps API).

[0332] System processing flow

[0333] First, the user enters information about the business area and competitors into the chat interface on the device. For example, the user might enter, "I'm looking for an area in Tokyo with a large population but few cafes."

[0334] The terminal then encrypts the input data and sends it to the server using the TLS (Transport Layer Security) protocol.

[0335] The server receives the encrypted data, decrypts it, and then analyzes the input text using a generative AI model, extracting conditions such as "within Tokyo," "high population," and "few cafes."

[0336] The server then uses an emotion engine to recognize emotions from the user's input and interactions. For example, it can detect emotions such as "worry" or "expectation" in the user's input.

[0337] Based on the analysis results and emotion recognition data, the server searches specified databases, including geographic information databases, demographic data, and competitor store databases.

[0338] Depending on the search results, the server provides adaptive feedback that matches the user's emotional state. For example, if the server detects that the user is anxious, it will present reassuring information such as past success stories and risk mitigation measures.

[0339] The server then lists specific potential locations and obtains the latitude and longitude of each area. The identified areas (such as Shinjuku Ward or Shibuya Ward) are then analyzed in more detail to obtain information about each location (e.g., population density, number of existing cafes).

[0340] The server uses an online map service API (e.g., Google Maps API) to map potential locations for store openings on a map, and adds appropriate information to each location as a pop-up display.

[0341] The generated map data is sent to the device, and the user can view detailed information about the candidate locations on an interactive map. For example, the user can click on a marker on the map to view detailed information about each candidate location.

[0342] Specific examples

[0343] Scenario: A user is thinking about opening a new cafe and wants to find areas in Tokyo that are densely populated but have few cafes.

[0344] 1. User input:

[0345] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0346] 2. Data transmission:

[0347] The terminal encrypts the input data via TLS and sends it to the server.

[0348] 3. Data Analysis:

[0349] The server decrypts the received data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0350] 4. Emotion recognition:

[0351] The server uses an emotion engine to detect emotions such as "worry" or "expectation" from the user's input text and behavior.

[0352] 5. Database Search:

[0353] The server searches a geographic database, demographic data, and competitor store data to identify areas that meet the criteria (for example, Shinjuku Ward or Shibuya Ward).

[0354] 6. Adaptive Feedback:

[0355] If the user expresses "worried," the server presents past success stories and risk mitigation measures.

[0356] 7. Site Identification:

[0357] The server extracts more detailed candidate locations from the identified area and obtains their latitude and longitude information.

[0358] 8. Map data generation:

[0359] The server uses the Google Maps API to display the identified candidate locations on a map and adds detailed information (e.g., population density, number of existing cafes) to each candidate location as a pop-up.

[0360] 9. Map data transmission:

[0361] The server sends the generated map data to the terminal.

[0362] 10. Site confirmation:

[0363] The device displays map data to the user, who can click on each marker for more information.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1:

[0366] User input of information

[0367] Users input trade area information and competitor information into the chat interface on their device.

[0368] Input: Enter the prompt text "I'm looking for an area in Tokyo with a high population and few cafes."

[0369] Output: The user's input data is obtained.

[0370] Step 2:

[0371] Data transmission by the terminal

[0372] The terminal encrypts the data entered by the user using TLS and sends it to the server.

[0373] Input: User input data is captured at the terminal.

[0374] Output: TLS encrypted data is generated and sent to the server.

[0375] Step 3:

[0376] Data reception and analysis by the server

[0377] The server receives and decrypts the encrypted data sent from the device, then uses a generative AI model (e.g., GPT-4) to analyze the received data and extract important keywords and conditions.

[0378] Input: TLS encrypted data is sent to the server.

[0379] Output: As a result of the analysis, conditions such as "within Tokyo," "large population," and "few cafes" are extracted.

[0380] Step 4:

[0381] Recognizing user emotions with an emotion engine

[0382] The server uses an emotion engine to recognize emotions based on user input and interactions, for example, detecting emotions such as "worry" or "anticipation."

[0383] Input: Analysis results and user input data.

[0384] Output: Recognition result of the user's emotional state.

[0385] Step 5:

[0386] Database search by server

[0387] Taking into account the output of the emotion engine, the server searches databases (e.g., geographic information databases, demographic data, competitor store data).

[0388] Input: Analysis results and emotion recognition results.

[0389] Output: Search results include a list of potential locations that match the criteria.

[0390] Step 6:

[0391] Adaptive feedback by the server

[0392] The server provides adaptive feedback based on the user's emotional state, for example, providing additional information such as success stories and risk mitigation strategies if the user is anxious.

[0393] Input: Emotion recognition results and search results.

[0394] Output: Adaptive feedback content.

[0395] Step 7:

[0396] Identification of potential store locations by the server

[0397] The server identifies the latitude and longitude information of specific candidate locations and then filters them to see if they match more specific criteria, such as Shinjuku Ward or Shibuya Ward.

[0398] Input: Search results.

[0399] Output: A detailed list of potential locations with their latitude and longitude coordinates.

[0400] Step 8:

[0401] Map data generation by the server

[0402] The server generates map data for the identified candidate locations using the Google Maps API, etc. Pop-up information such as population density and the number of existing cafes is added to each candidate location.

[0403] Input: A detailed list of potential store locations and their latitude and longitude information.

[0404] Output: The generated map data.

[0405] Step 9:

[0406] Sending map data to the device

[0407] The server sends the generated map data to the terminal.

[0408] Input: Generated map data.

[0409] Output: Interactive map data is sent to the device.

[0410] Step 10:

[0411] User review of candidate sites

[0412] The terminal displays the received map data to the user, who can click on markers on the map to check detailed information about each potential store location.

[0413] Input: Submitted map data.

[0414] Output: An interface where the user can view detailed information.

[0415] (Application example 2)

[0416] 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."

[0417] In today's business environment, selecting an appropriate location is extremely important, especially when opening a brick-and-mortar store. However, selecting a location requires a lot of time and effort, and the amount of commercial area and competitive information is complex and vast, making it difficult to efficiently analyze data and find the optimal candidate location. Furthermore, while there is a need to provide information that takes into account the psychological anxieties and expectations of prospective store owners, existing systems do not adequately address this need. Therefore, the present invention aims to provide a system that quickly and accurately identifies candidate locations for store openings while taking into account the user's emotions.

[0418] The identification process by the identification 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 providing an interactive interface for a user to input market information and competitive information, means for using a generative AI model to analyze market conditions and competitive information specified based on the user input, emotion analysis means for recognizing the user's emotion from the analyzed information, feedback provision means for providing adaptive feedback based on the user's emotion, database search means for identifying an optimal store candidate site, map data generation means for displaying the identified store candidate site on an online map, and means for providing the map data to the user online. This enables the user to quickly and accurately find an optimal store candidate site while reducing emotional anxiety.

[0419] "Market information" is data about commercial activity in a particular geographic area, such as market size, customer demographic characteristics, purchasing trends, and local economic trends.

[0420] "Competitive information" refers to information such as the number, location, size, type of business, and market share of competitors in a particular area.

[0421] An "interactive interface" is an input method that allows a user to communicate with a system using natural language, and is an interface that can take the form of a text box, chatbot, or similar.

[0422] A "generative AI model" is an artificial intelligence model that analyzes information entered by a user and extracts intent from that information, and uses natural language processing technology.

[0423] "Emotion analysis means" is a technology that recognizes a user's emotions from their input and interactions, and provides data based on those emotions.

[0424] A "feedback providing means" is a method for providing appropriate information or advice to a user, taking into consideration the user's feelings.

[0425] "Database search means" refers to a technique for searching and acquiring necessary information from related databases based on specified conditions.

[0426] The "map data generating means" is a method for generating data for displaying the specified information on a map and visually presenting it to the user.

[0427] "Online provision means" refers to the technology used to provide information and services to users via the Internet.

[0428] The system of the present invention supports the process of selecting a potential store location and includes the following means: It integrates various technologies to allow users to input market and competitive information and identify the most suitable potential store location.

[0429] System Configuration

[0430] The system consists of an interactive interface, a generative AI model, an emotion analysis means, a feedback provision means, a database search means, a map data generation means, and an online provision means.

[0431] Program processing flow

[0432] 1. User input

[0433] Users input market and competitive information using an interactive interface on their smartphones or PCs. A concrete example of a prompt might be, "Please tell me an area in Osaka City that has a lot of young people and few restaurants."

[0434] 2. Data analysis by the server

[0435] The user's input data is encrypted and securely transmitted to a server, where it is analyzed using a generative AI model (e.g., Hugging Face's "bert-base-multilingual-cased") to extract key terms.

[0436] 3. Emotion Analysis and Adaptive Feedback

[0437] The server uses emotion analysis to recognize emotions from the user's input. Based on the analysis results, if the user is feeling anxious or hopeful, it provides appropriate feedback accordingly. For example, providing additional information such as past success stories and risk mitigation measures can reassure the user.

[0438] 4. Criteria-based database search

[0439] Based on the criteria extracted by the generative AI model, a database search tool searches relevant databases such as market data, competitive information, and demographic data, thereby identifying areas that meet the criteria.

[0440] 5. Map data generation and online provision

[0441] Based on the latitude and longitude information of the identified candidate locations for store openings, the map data generation means generates a map using an online map service (e.g., Google Maps API). Pop-up information including detailed information such as population density and competitor information is also added to this map. The generated map data is provided to users online, allowing them to interactively check each candidate location.

[0442] Specific examples

[0443] For example, if a user inputs "Please tell me an area in Osaka City that has a lot of young people and few restaurants," the server analyzes this information using a generative AI model and extracts conditions such as "Osaka City," "Many young people," and "Few restaurants." At the same time, the emotion analysis means recognizes the user's emotions, such as expectations and anxieties, and provides feedback based on those. The database search means then searches for areas that meet the conditions, and the map data generation means plots candidate locations using the Google Maps API. As a result, the user can interactively check the map and obtain detailed information about each candidate location.

[0444] In this way, by using the system of the present invention, the user can quickly and accurately select the most suitable candidate site for opening a store while reducing emotional anxiety.

[0445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0446] Step 1:

[0447] Users input market and competitive information using an interactive interface on their smartphone or PC. Specifically, they input a prompt such as, "Please tell me an area in Osaka City that has a lot of young people and few restaurants." This clarifies the conditions the user is looking for, and the subsequent processing begins.

[0448] Step 2:

[0449] The terminal encrypts the input data and sends it securely to the server. The terminal properly formats the user's input information and sends it securely using an encryption algorithm (e.g., AES). This protects the user's privacy.

[0450] Step 3:

[0451] The server decrypts the received encrypted data and analyzes the user's input using a generative AI model. Specifically, an AI model (e.g., bert-base-multilingual-cased) is used to extract conditions such as "Osaka city," "lots of young people," and "few restaurants" from the text data. This analysis clarifies the user's intent and specifies the conditions.

[0452] Step 4:

[0453] The server uses emotion analysis to recognize the user's emotions from the analyzed information. Specifically, it uses an emotion analysis model to identify emotions such as "anxiety" or "expectation" that the user is feeling. The results of emotion recognition enable it to provide adaptive feedback.

[0454] Step 5:

[0455] The server provides adaptive feedback based on the results of sentiment analysis. For example, if the user feels anxious, it provides additional information about past success stories and risk mitigation measures. This reduces the user's anxiety and provides a sense of security.

[0456] Step 6:

[0457] The server searches for relevant data from the specified database based on the conditions extracted by the generative AI model. Specifically, it searches demographic data, geographic information data, competing store data, etc. to identify areas that meet the conditions. The search results provide useful information to the user.

[0458] Step 7:

[0459] The server acquires the latitude and longitude information of the identified potential store locations and generates an online map using a map data generation method. Specifically, it uses the Google Maps API to map the potential locations. This map also includes detailed information such as the population density of each area and competitor information.

[0460] Step 8:

[0461] The server sends the generated map data to the user's device, allowing the user to interactively check the map data. By clicking on a marker on the map, the user can check detailed information about each candidate site and select the optimal store location. This step allows the user to quickly and accurately find the optimal store location.

[0462] 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.

[0463] 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 (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0464] 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.

[0465] [Second embodiment]

[0466] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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).

[0472] 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. 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.

[0473] 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.

[0474] 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.

[0475] 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.

[0476] In the smart glasses 214, 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.

[0477] 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."

[0478] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, and online map display means. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with specific examples.

[0479] System Operation Overview

[0480] 1. User input

[0481] The user uses a terminal to input desired business area conditions and competitive information into the chat interface. For example, they might input, "I'm looking for an area in Tokyo with a high population but few cafes."

[0482] 2. Data transmission by the terminal

[0483] The terminal sends the user's input data to the server, which is encrypted for security reasons.

[0484] 3. Data analysis by the server

[0485] The server analyzes the received data using a generative AI model. This model uses natural language processing algorithms to extract important keywords and conditions from the input text. Conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0486] 4. Database search by server

[0487] The server searches specified databases (e.g., geographic information databases, demographic data, competitor store data, etc.) based on the analyzed conditions. For example, it identifies areas in Tokyo with high population density and filters out areas with few cafes.

[0488] 5. Identification of potential store locations by the server

[0489] Based on the information obtained from the database, potential locations that meet the criteria are identified, such as specific areas in Shinjuku Ward or Shibuya Ward.

[0490] 6. Map data generation by the server

[0491] The server uses an online map service (e.g., Google Maps API) to map the identified potential locations, adding pop-up information (e.g., population density, number of existing cafes) to each location.

[0492] 7. Sending map data to the device

[0493] The server sends the generated map data to the device, where it is provided in an interactive format.

[0494] 8. User confirmation of candidate sites

[0495] The device displays the received map data to the user, who can then click on the markers on the map to view detailed information about each candidate location.

[0496] Specific examples

[0497] scenario

[0498] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0499] 1. Enter information

[0500] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population and few cafes."

[0501] 2. Data Transmission

[0502] The terminal transmits the input data to the server.

[0503] 3. Data Analysis

[0504] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0505] 4. Database Search

[0506] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[0507] 5. Identifying potential sites

[0508] The server obtains location information for the specified area and performs further filtering, which may result in a specific location within Shinjuku Ward.

[0509] 6. Map data generation

[0510] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[0511] 7. Map data transmission

[0512] The server transmits the map data to the terminal.

[0513] 8. Confirmation of candidate sites

[0514] The device displays map data to the user, who can click on a marker to see more information.

[0515] In this way, users can intuitively and quickly find potential store locations, enabling them to efficiently proceed with the execution of store opening plans.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[0519] Step 2:

[0520] The terminal encrypts the information entered by the user and sends it to the server. This encryption ensures the security of the transmitted data.

[0521] Step 3:

[0522] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0523] Step 4:

[0524] The server then begins a database search based on the analysis results. First, it searches the geographic information database to obtain information about areas within Tokyo.

[0525] Step 5:

[0526] Next, the server searches a demographic database to obtain population density information for each area in Tokyo, and filters out areas with high population density.

[0527] Step 6:

[0528] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[0529] Step 7:

[0530] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0531] Step 8:

[0532] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0533] Step 9:

[0534] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0535] Step 10:

[0536] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[0537] Example 1

[0538] 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."

[0539] Conventional store opening support systems required users to analyze complex trade area conditions and competitive information to find the optimal store location, which required specialized knowledge and was time-consuming and labor-intensive.In addition, they lacked a visual interface for making decisions based on detailed information, resulting in an unsatisfactory user experience.

[0540] 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.

[0541] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitive information, means for using a generative AI model to analyze the trade area conditions and competitive information specified based on user input, and map data generation means for displaying identified store candidate sites on an online map, allowing users to easily identify and visually confirm store candidate sites without requiring specialized knowledge.

[0542] A "user" is an individual or corporation that uses this system to input trade area information and competitor information to identify potential locations for opening a store.

[0543] "Trade area information" is data on market characteristics and customer trends in a specific region.

[0544] "Competitor information" is data regarding the number and types of competing stores in a particular area.

[0545] A "conversational interface" is an application such as a chat interface or form designed to allow users to enter trade area or competitor information in natural language.

[0546] A "generative AI model" is an artificial intelligence model that analyzes natural language text entered by a user and extracts important keywords and conditions.

[0547] The "database search means" is a system function for searching for trade area information and competitor information based on specified conditions.

[0548] The "map data generating means" is a system function for displaying the identified potential store locations on an online map.

[0549] "Online Map" means a digital map application accessible via the Internet.

[0550] "Encryption" is a technology that converts data using a specific algorithm to ensure information security.

[0551] "Demographic data" refers to data about the population composition and density of a particular area.

[0552] "Geographic information data" is data relating to the geographic characteristics of a particular area.

[0553] A "marker" is a visual icon used to indicate a specific location on an online map.

[0554] "Detailed information" is additional data about a particular potential store location (e.g., population density, number of existing stores, etc.).

[0555] The system of this invention executes a series of processes to identify potential locations for store openings by inputting trade area information and competitor information using a generative AI model and analyzing the information. To achieve this, the system includes the following main components:

[0556] System configuration

[0557] 1. User input: A user uses a device to access a conversational interface and input information about the market and competitors. Specifically, the user uses a web or mobile application. For example, the user might enter, "I'm looking for an area in Tokyo that has a high population but few cafes," into a chat interface.

[0558] 2. Data transmission by the terminal: The terminal converts the information entered by the user into an appropriate format, encrypts it using SSL / TLS for security reasons, and sends it to the server. The software used includes request libraries that use the HTTP protocol (e.g., fetch API or HTTP client library).

[0559] 3. Data analysis by the server: The server inputs the received data into a generative AI model (e.g., ChatGPT) and analyzes the text. The generative AI model uses natural language processing algorithms to extract important keywords and conditions. Examples include "within Tokyo," "large population," and "few cafes."

[0560] 4. Database Search: The server searches the specified database (e.g., PostgreSQL, MongoDB) based on the parsed criteria. The search targets can be geographical databases, demographic databases, competitor store data, etc. Specific SQL or NoSQL queries are used to extract the data.

[0561] 5. Identifying potential locations for store openings: The server identifies potential locations for store openings that meet the criteria based on information obtained from the database. For example, it filters areas in Tokyo with high population density and few cafes, and identifies Shinjuku Ward and Shibuya Ward.

[0562] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on an online map. Pop-up information such as population density and the number of existing cafes is added to each candidate location to make it easier for users to understand visually.

[0563] 7. Sending map data to the device: The server sends the generated map data to the device. The map data is provided in an interactive format (e.g., GeoJSON format).

[0564] 8. User confirmation of candidate locations: The device displays the received map data and allows the user to interactively check the candidate locations. The user can click on the markers on the map to view detailed information about each candidate location.

[0565] Specific examples

[0566] Below are some specific scenarios and examples of input to the generative AI model.

[0567] scenario

[0568] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0569] 1. Information input: The user enters into the chat interface on their device, "I'm looking for an area in Tokyo that has a high population but few cafes."

[0570] 2. Data transmission: The terminal transmits the input data to the server.

[0571] 3. Data analysis: The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0572] 4. Database search: The server searches the geographical information database, demographic database, and competitor store data based on the conditions to identify matching areas. For example, specific areas in Shinjuku Ward or Shibuya Ward are found.

[0573] 5. Identifying candidate locations: The server obtains location information for the identified areas and performs further filtering.

[0574] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on a map.

[0575] 7. Send map data: The server sends the generated map data to the device.

[0576] 8. Confirm candidate locations: The device displays map data to the user, and the user can click on a marker to see more information.

[0577] Example input to a generative AI model

[0578] Examples of prompts:

[0579] "I'm looking for an area in Tokyo that has a large population but few cafes. Which area is that?"

[0580] In this way, the system of the present invention allows users to easily conduct trade area surveys and quickly find the most suitable candidate site for opening a store.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1:

[0583] Enter information

[0584] Users use a device to access a dialogue-style interface and input business area and competitor information in natural language. Specifically, they might type into the chat interface, "I'm looking for an area in Tokyo that has a high population but few cafes." This input data is saved in text format on the device.

[0585] Step 2:

[0586] Data transmission

[0587] The terminal encrypts the text data entered by the user and sends it securely to the server using SSL / TLS. The input is the trade area conditions and competitive information entered by the user, and the output is the encrypted text data sent to the server.

[0588] Step 3:

[0589] Data analysis

[0590] The server decrypts the received encrypted data and inputs it as analysis data into a generative AI model (for example, ChatGPT). This model uses a natural language processing algorithm to analyze the text and extract important keywords and conditions. Specifically, conditions such as "within Tokyo," "large population," and "few cafes" are extracted. The input is the user's text data, and the output is the extracted keywords and conditions.

[0591] Step 4:

[0592] Database search

[0593] The server searches multiple databases based on the analyzed conditions, including geographic information databases, demographic databases, and competitor store databases. Specifically, it uses SQL and NoSQL queries to extract areas with high population density and few cafes. The input is the extracted conditions, and the output is the retrieved data entries.

[0594] Step 5:

[0595] Identifying potential locations for stores

[0596] The server identifies the optimal candidate locations for opening a store based on the information obtained from the database. Specifically, it filters areas with a small number of cafes in Shinjuku Ward or Shibuya Ward, for example, and identifies detailed candidate locations. The input is the acquired data entry, and the output is a list of identified candidate locations.

[0597] Step 6:

[0598] Map data generation

[0599] The server uses the Google Maps API to map the identified candidate locations on a map. It adds pop-up information to each candidate location, including detailed information such as population density and the number of existing cafes. This process generates visually easy-to-read map data. The input is a list of candidate locations, and the output is the mapped map data.

[0600] Step 7:

[0601] Map data transmission

[0602] The server sends the generated map data to the device. This sent data is provided in GeoJSON format so that it can be used interactively. The input is the mapped map data, and the output is the interactive map data sent to the device.

[0603] Step 8:

[0604] Check the candidate site

[0605] The device displays the received map data to the user. The user can click on a marker on the map to view detailed information about each candidate location. The input is interactive map data, and the output is detailed information about the marker the user clicked.

[0606] (Application example 1)

[0607] 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."

[0608] In recent years, efficient location of logistics bases has become extremely important in the logistics industry in order to reduce logistics costs and speed up delivery. However, identifying the optimal location for a logistics center is extremely complex, as it requires consideration of a wide range of information, including existing facilities, traffic conditions, and local demographics. Traditional methods for addressing this issue have struggled to efficiently analyze the situation and present appropriate candidate sites.

[0609] 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.

[0610] In this invention, the server includes means for providing an interactive interface for a user to input facility location information and efficiency conditions, means for using a generative AI model to analyze the efficiency conditions and facility information specified based on the user input, and database search means for identifying optimal location candidate sites based on the above analysis, thereby enabling intuitive and rapid identification of efficient base locations in the logistics industry.

[0611] "Means for providing an interactive interface for users to input facility location information and efficiency criteria" means a system or software for providing an interactive interface designed to allow users to easily input criteria and requirements for the location of distribution centers and other facilities.

[0612] "Means using a generative AI model to analyze specified efficiency conditions and facility information based on user input" refers to systems or software that use a generative AI model to analyze efficiency conditions and facility information entered by a user. This generative AI model uses natural language processing technology to interpret the information and extract appropriate conditions and requirements.

[0613] The "database search means for identifying optimal candidate locations" refers to a system or software for searching and identifying suitable candidate locations from a related database based on the analyzed efficiency conditions and facility information.

[0614] "Map data generation means for displaying identified candidate placement locations on an online map" refers to a system or software that generates map data for visually displaying identified candidate placement locations and provides it through an online map service.

[0615] "Means for providing map data to users online" refers to a system or software that provides generated map data to users' devices via the Internet.

[0616] "Facility location information" refers to information about the locations and conditions of logistics centers and other facilities.

[0617] "Efficiency conditions" refer to the conditions and requirements for achieving desired efficiency in logistics and facility layout.

[0618] This invention relates to a system that supports optimal location of logistics centers and other facilities. The system of the present invention interactively collects facility location information and efficiency conditions entered by the user and analyzes them using a generative AI model. Based on the analysis results, the system then identifies optimal location candidates and displays them on an online map after a database search. The system of the present invention is implemented by the following steps:

[0619] 1. Collect user input:

[0620] Users use an interactive interface on devices such as smartphones or computers to input facility location information and efficiency conditions. This interface is designed to allow users to easily input conditions. For example, a user might input "a location in Tokyo with good transportation access and a reasonable distance from existing logistics centers."

[0621] 2. Data Transmission and Encryption:

[0622] The information entered by the user is sent from the terminal to the server, where it is encrypted for security reasons.

[0623] 3. Data Analysis:

[0624] The server analyzes the received data using a generative AI model, which uses natural language processing algorithms to extract important keywords and conditions from the input text. The generative AI model uses, for example, OpenAI's API.

[0625] 4. Database Search:

[0626] The server searches specified databases (e.g., geographical and related data) based on the analyzed criteria, thereby identifying optimal candidate locations.

[0627] 5. Map data generation and display:

[0628] The server uses online map generation tools such as Folium to map the identified candidate locations, and the generated map data is provided in an interactive format, allowing users to intuitively check detailed information.

[0629] 6. Providing interactive maps:

[0630] The server then sends the generated map data to the device, where users can view the map data on their smartphones or computers and obtain detailed information about the candidate locations.

[0631] Example prompt sentence:

[0632] Interpret the distribution center criteria entered by the user to identify key information. Input: A location in Tokyo with good transportation access and within a reasonable distance from existing distribution centers.

[0633] By implementing this invention, efficient location selection becomes possible in the logistics industry and facility location, leading to cost reductions and improved logistics efficiency. This system is characterized by its ability to perform real-time data analysis and identify candidate locations by utilizing existing databases and generative AI models.

[0634] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0635] Step 1:

[0636] User input of information

[0637] Users input facility location information and efficiency conditions into an interactive interface. This interface is provided on devices such as smartphones and computers. For example, let's say a user inputs "a location in Tokyo that has good transportation access and is within a reasonable distance from existing logistics centers."

[0638] Input: Facility location information, efficiency conditions

[0639] Output: User input data

[0640] Step 2:

[0641] Data transmission and encryption by the device

[0642] The data entered by the user is sent to the server by the terminal. At this time, the data is encrypted to ensure security. Encrypted data prevents data leakage during communication.

[0643] Input: User-entered data

[0644] Output: Encrypted user-entered data

[0645] Step 3:

[0646] Data reception by the server

[0647] The server receives the encrypted user-entered data, which is then decrypted back into a format that can be parsed. The decrypted data is then used for parsing in the next step.

[0648] Input: Encrypted user-entered data

[0649] Output: Decoded user input data

[0650] Step 4:

[0651] Data analysis

[0652] The server then analyzes the decoded user input data using a generative AI model. This generative AI model uses natural language processing technology to extract important keywords and conditions from the user's input text. For example, conditions such as "within Tokyo," "good transportation access," and "reasonable distance from existing logistics centers" are extracted.

[0653] Input: Decrypted user-entered data

[0654] Output: Parsed keywords and conditions

[0655] Step 5:

[0656] Searching the database

[0657] The server searches the specified database (geographical information and related data) based on the analyzed keywords and conditions, such as data on areas with good transportation access or the locations of existing logistics centers, to identify the optimal candidate locations.

[0658] Input: Parsed keywords and conditions

[0659] Output: Identified candidate locations

[0660] Step 6:

[0661] Map data generation

[0662] The server uses a map generation tool such as Folium to map the identified candidate locations, and the map displays detailed information about each location (e.g., access to the site, distance from existing facilities) as a pop-up.

[0663] Input: Identified candidate locations

[0664] Output: Generated map data

[0665] Step 7:

[0666] Sending map data

[0667] The server then sends the generated map data to the terminal, which provides the map data in an interactive format, allowing users to intuitively check detailed information.

[0668] Input: Generated map data

[0669] Output: Map data received by the device

[0670] Step 8:

[0671] Providing interactive maps

[0672] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each candidate site. This supports efficient facility placement decision-making.

[0673] Input: Map data received by the device

[0674] Output: An interactive map screen that the user sees

[0675] 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.

[0676] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with concrete examples.

[0677] System Operation Overview

[0678] 1. User input

[0679] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[0680] 2. Data transmission by the terminal

[0681] The terminal encrypts the data entered by the user and sends it to the server. This data is encrypted for security reasons.

[0682] 3. Data analysis by the server

[0683] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0684] 4. Recognition of user emotions using an emotion engine

[0685] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting when a user is feeling stressed or has positive emotions.

[0686] 5. Database search by server

[0687] The server starts a database search based on the analysis results and the user's sentiment. It searches the specified database (e.g., geographic information database, demographic data, competitor store data, etc.).

[0688] 6. Adaptive Feedback by the Server

[0689] The server provides appropriate feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it provides additional reassuring information (e.g., successful store openings).

[0690] 7. Identification of potential store locations by the server

[0691] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0692] 8. Map data generation by the server

[0693] The server uses an online map service (e.g., Google Maps API) to map potential locations, and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0694] 9. Sending map data to the device

[0695] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0696] 10. User confirmation of candidate sites

[0697] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[0698] Specific examples

[0699] scenario

[0700] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0701] 1. Enter information

[0702] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0703] 2. Data Transmission

[0704] The terminal transmits the input data to the server.

[0705] 3. Data Analysis

[0706] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0707] 4. Emotion recognition

[0708] The server uses an emotion engine to recognize the user's emotions from the user's input sentences and interactions. For example, it detects emotions such as "worry" and "expectation" in the user's posts.

[0709] 5. Database Search

[0710] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[0711] 6. Adaptive Feedback

[0712] If the user's feelings are recognized as worrying, the server provides additional reassurance, such as past success stories and risk mitigation strategies.

[0713] 7. Identifying potential sites

[0714] The server obtains location information for the specified area and performs further filtering, allowing users to find specific locations within Shinjuku Ward or locations that meet specific criteria.

[0715] 8. Map data generation

[0716] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[0717] 9. Map data transmission

[0718] The server transmits the map data to the terminal.

[0719] 10. Confirmation of candidate sites

[0720] The device displays map data to the user, who can click on a marker to see more information.

[0721] This allows users to quickly find the best potential location for a store through an interactive format, and with the help of an emotion engine, they can make more satisfying decisions.

[0722] The processing flow will be explained below.

[0723] Step 1:

[0724] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0725] Step 2:

[0726] The terminal encrypts the input data and sends it to the server. Encryption ensures the security of the data.

[0727] Step 3:

[0728] The server analyzes the received data and uses a generative AI model to extract important keywords and conditions from the input text, such as "within Tokyo," "high population," and "few cafes."

[0729] Step 4:

[0730] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting whether the user is feeling "worried" or "expecting."

[0731] Step 5:

[0732] The server then begins a database search based on the analysis results and the recognized emotion. First, it searches a geographic information database to obtain information about areas within Tokyo.

[0733] Step 6:

[0734] The server searches a demographic database to obtain population density information for each area in Tokyo, extracts areas with high population density, and performs filtering.

[0735] Step 7:

[0736] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[0737] Step 8:

[0738] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0739] Step 9:

[0740] The server provides adaptive feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it will provide additional information such as successful store openings and risk mitigation measures.

[0741] Step 10:

[0742] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0743] Step 11:

[0744] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0745] Step 12:

[0746] The terminal displays the received map data to the user, who can click on markers on the map to view detailed information about each potential store location.

[0747] Step 13:

[0748] The user selects the optimal location for a store based on the feedback information provided by the emotion engine. During this process, the user can ask additional questions or change conditions, and the system will then suggest the optimal location again.

[0749] Example 2

[0750] 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."

[0751] Conventional systems require a great deal of time and effort to manually analyze trade area and competitor information, and they also have the problem of being unable to provide appropriate feedback because they do not take into account the user's emotional state. Furthermore, data encryption and adaptive feedback provision were insufficient, which meant that users' concerns could not be fully alleviated. Therefore, there was a need for efficient and satisfying information provision.

[0752] 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.

[0753] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitor information, means for using a generative AI model to analyze the trade area conditions and competitor information specified based on user input, database search means for identifying optimal store location candidates, map data generation means for displaying the identified store location candidates on an online map, means for providing the map data to users online, means for using an emotion engine that recognizes emotions by analyzing user input and interactions, and means for providing adaptive feedback based on the emotion recognition, thereby enabling efficient information provision that takes the user's emotional state into consideration and provides a high level of satisfaction.

[0754] "User" means an individual or corporation that uses this system.

[0755] "Trade area information" is information about market demand and consumer behavior in a specific area.

[0756] "Competitive information" refers to information on competing businesses and products within a trade area.

[0757] An "interactive interface" is a user interface that allows a user to interact with a system in a conversational manner.

[0758] A "generative AI model" is an algorithm that uses artificial intelligence to analyze user input information and extract trade area conditions and competitive information.

[0759] The "database search means" is a means for searching a database based on specific conditions and obtaining required information.

[0760] The "map data generating means" is a means for generating data for displaying the identified store candidate site on an online map.

[0761] An "emotion engine" is a technology that analyzes user input and interactions to identify emotions.

[0762] "Adaptive feedback" is feedback that provides optimal advice or information based on the user's emotional state.

[0763] "Encryption" is the process of transforming data so that it cannot be read by third parties.

[0764] MODE FOR CARRYING OUT THE INVENTION

[0765] System Configuration

[0766] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. The following describes embodiments of the present invention.

[0767] Hardware and software used

[0768] Server: Used for data analysis, emotion recognition, database search, and map data generation.

[0769] Terminal: The device (e.g., computer, smartphone) on which the user enters information and checks results.

[0770] Generative AI models: Used to analyze user input (e.g., GPT-4).

[0771] Emotion engine: Used to recognize the user's emotions.

[0772] Databases: Geographical databases, demographic data, competitor data, etc.

[0773] Online map service APIs: Used to generate and display map data (e.g., Google Maps API).

[0774] System processing flow

[0775] First, the user enters information about the business area and competitors into the chat interface on the device. For example, the user might enter, "I'm looking for an area in Tokyo with a large population but few cafes."

[0776] The terminal then encrypts the input data and sends it to the server using the TLS (Transport Layer Security) protocol.

[0777] The server receives the encrypted data, decrypts it, and then analyzes the input text using a generative AI model, extracting conditions such as "within Tokyo," "high population," and "few cafes."

[0778] The server then uses an emotion engine to recognize emotions from the user's input and interactions. For example, it can detect emotions such as "worry" or "expectation" in the user's input.

[0779] Based on the analysis results and emotion recognition data, the server searches specified databases, including geographic information databases, demographic data, and competitor store databases.

[0780] Depending on the search results, the server provides adaptive feedback that matches the user's emotional state. For example, if the server detects that the user is anxious, it will present reassuring information such as past success stories and risk mitigation measures.

[0781] The server then lists specific potential locations and obtains the latitude and longitude of each area. The identified areas (such as Shinjuku Ward or Shibuya Ward) are then analyzed in more detail to obtain information about each location (e.g., population density, number of existing cafes).

[0782] The server uses an online map service API (e.g., Google Maps API) to map potential locations for store openings on a map, and adds appropriate information to each location as a pop-up display.

[0783] The generated map data is sent to the device, and the user can view detailed information about the candidate locations on an interactive map. For example, the user can click on a marker on the map to view detailed information about each candidate location.

[0784] Specific examples

[0785] Scenario: A user is thinking about opening a new cafe and wants to find areas in Tokyo that are densely populated but have few cafes.

[0786] 1. User input:

[0787] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[0788] 2. Data transmission:

[0789] The terminal encrypts the input data via TLS and sends it to the server.

[0790] 3. Data Analysis:

[0791] The server decrypts the received data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0792] 4. Emotion recognition:

[0793] The server uses an emotion engine to detect emotions such as "worry" or "expectation" from the user's input text and behavior.

[0794] 5. Database Search:

[0795] The server searches a geographic database, demographic data, and competitor store data to identify areas that meet the criteria (for example, Shinjuku Ward or Shibuya Ward).

[0796] 6. Adaptive Feedback:

[0797] If the user expresses "worried," the server presents past success stories and risk mitigation measures.

[0798] 7. Site Identification:

[0799] The server extracts more detailed candidate locations from the identified area and obtains their latitude and longitude information.

[0800] 8. Map data generation:

[0801] The server uses the Google Maps API to display the identified candidate locations on a map and adds detailed information (e.g., population density, number of existing cafes) to each candidate location as a pop-up.

[0802] 9. Map data transmission:

[0803] The server sends the generated map data to the terminal.

[0804] 10. Site confirmation:

[0805] The device displays map data to the user, who can click on each marker for more information.

[0806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0807] Step 1:

[0808] User input of information

[0809] Users input trade area information and competitor information into the chat interface on their device.

[0810] Input: Enter the prompt text "I'm looking for an area in Tokyo with a high population and few cafes."

[0811] Output: The user's input data is obtained.

[0812] Step 2:

[0813] Data transmission by the terminal

[0814] The terminal encrypts the data entered by the user using TLS and sends it to the server.

[0815] Input: User input data is captured at the terminal.

[0816] Output: TLS encrypted data is generated and sent to the server.

[0817] Step 3:

[0818] Data reception and analysis by the server

[0819] The server receives and decrypts the encrypted data sent from the device, then uses a generative AI model (e.g., GPT-4) to analyze the received data and extract important keywords and conditions.

[0820] Input: TLS encrypted data is sent to the server.

[0821] Output: As a result of the analysis, conditions such as "within Tokyo," "large population," and "few cafes" are extracted.

[0822] Step 4:

[0823] Recognizing user emotions with an emotion engine

[0824] The server uses an emotion engine to recognize emotions based on user input and interactions, for example, detecting emotions such as "worry" or "anticipation."

[0825] Input: Analysis results and user input data.

[0826] Output: Recognition result of the user's emotional state.

[0827] Step 5:

[0828] Database search by server

[0829] Taking into account the output of the emotion engine, the server searches databases (e.g., geographic information databases, demographic data, competitor store data).

[0830] Input: Analysis results and emotion recognition results.

[0831] Output: Search results include a list of potential locations that match the criteria.

[0832] Step 6:

[0833] Adaptive feedback by the server

[0834] The server provides adaptive feedback based on the user's emotional state, for example, providing additional information such as success stories and risk mitigation strategies if the user is anxious.

[0835] Input: Emotion recognition results and search results.

[0836] Output: Adaptive feedback content.

[0837] Step 7:

[0838] Identification of potential store locations by the server

[0839] The server identifies the latitude and longitude information of specific candidate locations and then filters them to see if they match more specific criteria, such as Shinjuku Ward or Shibuya Ward.

[0840] Input: Search results.

[0841] Output: A detailed list of potential locations with their latitude and longitude coordinates.

[0842] Step 8:

[0843] Map data generation by the server

[0844] The server generates map data for the identified candidate locations using the Google Maps API, etc. Pop-up information such as population density and the number of existing cafes is added to each candidate location.

[0845] Input: A detailed list of potential store locations and their latitude and longitude information.

[0846] Output: The generated map data.

[0847] Step 9:

[0848] Sending map data to the device

[0849] The server sends the generated map data to the terminal.

[0850] Input: Generated map data.

[0851] Output: Interactive map data is sent to the device.

[0852] Step 10:

[0853] User review of candidate sites

[0854] The terminal displays the received map data to the user, who can click on markers on the map to check detailed information about each potential store location.

[0855] Input: Submitted map data.

[0856] Output: An interface where the user can view detailed information.

[0857] (Application example 2)

[0858] 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."

[0859] In today's business environment, selecting an appropriate location is extremely important, especially when opening a brick-and-mortar store. However, selecting a location requires a lot of time and effort, and the amount of commercial area and competitive information is complex and vast, making it difficult to efficiently analyze data and find the optimal candidate location. Furthermore, while there is a need to provide information that takes into account the psychological anxieties and expectations of prospective store owners, existing systems do not adequately address this need. Therefore, the present invention aims to provide a system that quickly and accurately identifies candidate locations for store openings while taking into account the user's emotions.

[0860] The identification process by the identification 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 providing an interactive interface for a user to input market information and competitive information, means for using a generative AI model to analyze market conditions and competitive information specified based on the user input, emotion analysis means for recognizing the user's emotion from the analyzed information, feedback provision means for providing adaptive feedback based on the user's emotion, database search means for identifying an optimal store candidate site, map data generation means for displaying the identified store candidate site on an online map, and means for providing the map data to the user online. This enables the user to quickly and accurately find an optimal store candidate site while reducing emotional anxiety.

[0861] "Market information" is data about commercial activity in a particular geographic area, such as market size, customer demographic characteristics, purchasing trends, and local economic trends.

[0862] "Competitive information" refers to information such as the number, location, size, type of business, and market share of competitors in a particular area.

[0863] An "interactive interface" is an input method that allows a user to communicate with a system using natural language, and is an interface that can take the form of a text box, chatbot, or similar.

[0864] A "generative AI model" is an artificial intelligence model that analyzes information entered by a user and extracts intent from that information, and uses natural language processing technology.

[0865] "Emotion analysis means" is a technology that recognizes a user's emotions from their input and interactions, and provides data based on those emotions.

[0866] A "feedback providing means" is a method for providing appropriate information or advice to a user, taking into consideration the user's feelings.

[0867] "Database search means" refers to a technique for searching and acquiring necessary information from related databases based on specified conditions.

[0868] The "map data generating means" is a method for generating data for displaying the specified information on a map and visually presenting it to the user.

[0869] "Online provision means" refers to the technology used to provide information and services to users via the Internet.

[0870] The system of the present invention supports the process of selecting a potential store location and includes the following means: It integrates various technologies to allow users to input market and competitive information and identify the most suitable potential store location.

[0871] System Configuration

[0872] The system consists of an interactive interface, a generative AI model, an emotion analysis means, a feedback provision means, a database search means, a map data generation means, and an online provision means.

[0873] Program processing flow

[0874] 1. User input

[0875] Users input market and competitive information using an interactive interface on their smartphones or PCs. A concrete example of a prompt might be, "Please tell me an area in Osaka City that has a lot of young people and few restaurants."

[0876] 2. Data analysis by the server

[0877] The user's input data is encrypted and securely transmitted to a server, where it is analyzed using a generative AI model (e.g., Hugging Face's "bert-base-multilingual-cased") to extract key terms.

[0878] 3. Emotion Analysis and Adaptive Feedback

[0879] The server uses emotion analysis to recognize emotions from the user's input. Based on the analysis results, if the user is feeling anxious or hopeful, it provides appropriate feedback accordingly. For example, providing additional information such as past success stories and risk mitigation measures can reassure the user.

[0880] 4. Criteria-based database search

[0881] Based on the criteria extracted by the generative AI model, a database search tool searches relevant databases such as market data, competitive information, and demographic data, thereby identifying areas that meet the criteria.

[0882] 5. Map data generation and online provision

[0883] Based on the latitude and longitude information of the identified candidate locations for store openings, the map data generation means generates a map using an online map service (e.g., Google Maps API). Pop-up information including detailed information such as population density and competitor information is also added to this map. The generated map data is provided to users online, allowing them to interactively check each candidate location.

[0884] Specific examples

[0885] For example, if a user inputs "Please tell me an area in Osaka City that has a lot of young people and few restaurants," the server analyzes this information using a generative AI model and extracts conditions such as "Osaka City," "Many young people," and "Few restaurants." At the same time, the emotion analysis means recognizes the user's emotions, such as expectations and anxieties, and provides feedback based on those. The database search means then searches for areas that meet the conditions, and the map data generation means plots candidate locations using the Google Maps API. As a result, the user can interactively check the map and obtain detailed information about each candidate location.

[0886] In this way, by using the system of the present invention, the user can quickly and accurately select the most suitable candidate site for opening a store while reducing emotional anxiety.

[0887] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0888] Step 1:

[0889] Users input market and competitive information using an interactive interface on their smartphone or PC. Specifically, they input a prompt such as, "Please tell me an area in Osaka City that has a lot of young people and few restaurants." This clarifies the conditions the user is looking for, and the subsequent processing begins.

[0890] Step 2:

[0891] The terminal encrypts the input data and sends it securely to the server. The terminal properly formats the user's input information and sends it securely using an encryption algorithm (e.g., AES). This protects the user's privacy.

[0892] Step 3:

[0893] The server decrypts the received encrypted data and analyzes the user's input using a generative AI model. Specifically, an AI model (e.g., bert-base-multilingual-cased) is used to extract conditions such as "Osaka city," "lots of young people," and "few restaurants" from the text data. This analysis clarifies the user's intent and specifies the conditions.

[0894] Step 4:

[0895] The server uses emotion analysis to recognize the user's emotions from the analyzed information. Specifically, it uses an emotion analysis model to identify emotions such as "anxiety" or "expectation" that the user is feeling. The results of emotion recognition enable it to provide adaptive feedback.

[0896] Step 5:

[0897] The server provides adaptive feedback based on the results of sentiment analysis. For example, if the user feels anxious, it provides additional information about past success stories and risk mitigation measures. This reduces the user's anxiety and provides a sense of security.

[0898] Step 6:

[0899] The server searches for relevant data from the specified database based on the conditions extracted by the generative AI model. Specifically, it searches demographic data, geographic information data, competing store data, etc. to identify areas that meet the conditions. The search results provide useful information to the user.

[0900] Step 7:

[0901] The server acquires the latitude and longitude information of the identified potential store locations and generates an online map using a map data generation method. Specifically, it uses the Google Maps API to map the potential locations. This map also includes detailed information such as the population density of each area and competitor information.

[0902] Step 8:

[0903] The server sends the generated map data to the user's device, allowing the user to interactively check the map data. By clicking on a marker on the map, the user can check detailed information about each candidate site and select the optimal store location. This step allows the user to quickly and accurately find the optimal store location.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] [Third embodiment]

[0908] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0909] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0910] 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).

[0911] 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.

[0912] 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.

[0913] 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).

[0914] 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. 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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."

[0920] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, and online map display means. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with specific examples.

[0921] System Operation Overview

[0922] 1. User input

[0923] The user uses a terminal to input desired business area conditions and competitive information into the chat interface. For example, they might input, "I'm looking for an area in Tokyo with a high population but few cafes."

[0924] 2. Data transmission by the terminal

[0925] The terminal sends the user's input data to the server, which is encrypted for security reasons.

[0926] 3. Data analysis by the server

[0927] The server analyzes the received data using a generative AI model. This model uses natural language processing algorithms to extract important keywords and conditions from the input text. Conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0928] 4. Database search by server

[0929] The server searches specified databases (e.g., geographic information databases, demographic data, competitor store data, etc.) based on the analyzed conditions. For example, it identifies areas in Tokyo with high population density and filters out areas with few cafes.

[0930] 5. Identification of potential store locations by the server

[0931] Based on the information obtained from the database, potential locations that meet the criteria are identified, such as specific areas in Shinjuku Ward or Shibuya Ward.

[0932] 6. Map data generation by the server

[0933] The server uses an online map service (e.g., Google Maps API) to map the identified potential locations, adding pop-up information (e.g., population density, number of existing cafes) to each location.

[0934] 7. Sending map data to the device

[0935] The server sends the generated map data to the device, where it is provided in an interactive format.

[0936] 8. User confirmation of candidate sites

[0937] The device displays the received map data to the user, who can then click on the markers on the map to view detailed information about each candidate location.

[0938] Specific examples

[0939] scenario

[0940] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[0941] 1. Enter information

[0942] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population and few cafes."

[0943] 2. Data Transmission

[0944] The terminal transmits the input data to the server.

[0945] 3. Data Analysis

[0946] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[0947] 4. Database Search

[0948] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[0949] 5. Identifying potential sites

[0950] The server obtains location information for the specified area and performs further filtering, which may result in a specific location within Shinjuku Ward.

[0951] 6. Map data generation

[0952] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[0953] 7. Map data transmission

[0954] The server transmits the map data to the terminal.

[0955] 8. Confirmation of candidate sites

[0956] The device displays map data to the user, who can click on a marker to see more information.

[0957] In this way, users can intuitively and quickly find potential store locations, enabling them to efficiently proceed with the execution of store opening plans.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[0961] Step 2:

[0962] The terminal encrypts the information entered by the user and sends it to the server. This encryption ensures the security of the transmitted data.

[0963] Step 3:

[0964] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[0965] Step 4:

[0966] The server then begins a database search based on the analysis results. First, it searches the geographic information database to obtain information about areas within Tokyo.

[0967] Step 5:

[0968] Next, the server searches a demographic database to obtain population density information for each area in Tokyo, and filters out areas with high population density.

[0969] Step 6:

[0970] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[0971] Step 7:

[0972] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[0973] Step 8:

[0974] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[0975] Step 9:

[0976] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[0977] Step 10:

[0978] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[0979] Example 1

[0980] 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."

[0981] Conventional store opening support systems required users to analyze complex trade area conditions and competitive information to find the optimal store location, which required specialized knowledge and was time-consuming and labor-intensive.In addition, they lacked a visual interface for making decisions based on detailed information, resulting in an unsatisfactory user experience.

[0982] 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.

[0983] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitive information, means for using a generative AI model to analyze the trade area conditions and competitive information specified based on user input, and map data generation means for displaying identified store candidate sites on an online map, allowing users to easily identify and visually confirm store candidate sites without requiring specialized knowledge.

[0984] A "user" is an individual or corporation that uses this system to input trade area information and competitor information to identify potential locations for opening a store.

[0985] "Trade area information" is data on market characteristics and customer trends in a specific region.

[0986] "Competitor information" is data regarding the number and types of competing stores in a particular area.

[0987] A "conversational interface" is an application such as a chat interface or form designed to allow users to enter trade area or competitor information in natural language.

[0988] A "generative AI model" is an artificial intelligence model that analyzes natural language text entered by a user and extracts important keywords and conditions.

[0989] The "database search means" is a system function for searching for trade area information and competitor information based on specified conditions.

[0990] The "map data generating means" is a system function for displaying the identified potential store locations on an online map.

[0991] "Online Map" means a digital map application accessible via the Internet.

[0992] "Encryption" is a technology that converts data using a specific algorithm to ensure information security.

[0993] "Demographic data" refers to data about the population composition and density of a particular area.

[0994] "Geographic information data" is data relating to the geographic characteristics of a particular area.

[0995] A "marker" is a visual icon used to indicate a specific location on an online map.

[0996] "Detailed information" is additional data about a particular potential store location (e.g., population density, number of existing stores, etc.).

[0997] The system of this invention executes a series of processes to identify potential locations for store openings by inputting trade area information and competitor information using a generative AI model and analyzing the information. To achieve this, the system includes the following main components:

[0998] System configuration

[0999] 1. User input: A user uses a device to access a conversational interface and input information about the market and competitors. Specifically, the user uses a web or mobile application. For example, the user might enter, "I'm looking for an area in Tokyo that has a high population but few cafes," into a chat interface.

[1000] 2. Data transmission by the terminal: The terminal converts the information entered by the user into an appropriate format, encrypts it using SSL / TLS for security reasons, and sends it to the server. The software used includes request libraries that use the HTTP protocol (e.g., fetch API or HTTP client library).

[1001] 3. Data analysis by the server: The server inputs the received data into a generative AI model (e.g., ChatGPT) and analyzes the text. The generative AI model uses natural language processing algorithms to extract important keywords and conditions. Examples include "within Tokyo," "large population," and "few cafes."

[1002] 4. Database Search: The server searches the specified database (e.g., PostgreSQL, MongoDB) based on the parsed criteria. The search targets can be geographical databases, demographic databases, competitor store data, etc. Specific SQL or NoSQL queries are used to extract the data.

[1003] 5. Identifying potential locations for store openings: The server identifies potential locations for store openings that meet the criteria based on information obtained from the database. For example, it filters areas in Tokyo with high population density and few cafes, and identifies Shinjuku Ward and Shibuya Ward.

[1004] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on an online map. Pop-up information such as population density and the number of existing cafes is added to each candidate location to make it easier for users to understand visually.

[1005] 7. Sending map data to the device: The server sends the generated map data to the device. The map data is provided in an interactive format (e.g., GeoJSON format).

[1006] 8. User confirmation of candidate locations: The device displays the received map data and allows the user to interactively check the candidate locations. The user can click on the markers on the map to view detailed information about each candidate location.

[1007] Specific examples

[1008] Below are some specific scenarios and examples of input to the generative AI model.

[1009] scenario

[1010] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[1011] 1. Information input: The user enters into the chat interface on their device, "I'm looking for an area in Tokyo that has a high population but few cafes."

[1012] 2. Data transmission: The terminal transmits the input data to the server.

[1013] 3. Data analysis: The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1014] 4. Database search: The server searches the geographical information database, demographic database, and competitor store data based on the conditions to identify matching areas. For example, specific areas in Shinjuku Ward or Shibuya Ward are found.

[1015] 5. Identifying candidate locations: The server obtains location information for the identified areas and performs further filtering.

[1016] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on a map.

[1017] 7. Send map data: The server sends the generated map data to the device.

[1018] 8. Confirm candidate locations: The device displays map data to the user, and the user can click on a marker to see more information.

[1019] Example input to a generative AI model

[1020] Examples of prompts:

[1021] "I'm looking for an area in Tokyo that has a large population but few cafes. Which area is that?"

[1022] In this way, the system of the present invention allows users to easily conduct trade area surveys and quickly find the most suitable candidate site for opening a store.

[1023] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] Enter information

[1026] Users use a device to access a dialogue-style interface and input business area and competitor information in natural language. Specifically, they might type into the chat interface, "I'm looking for an area in Tokyo that has a high population but few cafes." This input data is saved in text format on the device.

[1027] Step 2:

[1028] Data transmission

[1029] The terminal encrypts the text data entered by the user and sends it securely to the server using SSL / TLS. The input is the trade area conditions and competitive information entered by the user, and the output is the encrypted text data sent to the server.

[1030] Step 3:

[1031] Data analysis

[1032] The server decrypts the received encrypted data and inputs it as analysis data into a generative AI model (for example, ChatGPT). This model uses a natural language processing algorithm to analyze the text and extract important keywords and conditions. Specifically, conditions such as "within Tokyo," "large population," and "few cafes" are extracted. The input is the user's text data, and the output is the extracted keywords and conditions.

[1033] Step 4:

[1034] Database search

[1035] The server searches multiple databases based on the analyzed conditions, including geographic information databases, demographic databases, and competitor store databases. Specifically, it uses SQL and NoSQL queries to extract areas with high population density and few cafes. The input is the extracted conditions, and the output is the retrieved data entries.

[1036] Step 5:

[1037] Identifying potential locations for stores

[1038] The server identifies the optimal candidate locations for opening a store based on the information obtained from the database. Specifically, it filters areas with a small number of cafes in Shinjuku Ward or Shibuya Ward, for example, and identifies detailed candidate locations. The input is the acquired data entry, and the output is a list of identified candidate locations.

[1039] Step 6:

[1040] Map data generation

[1041] The server uses the Google Maps API to map the identified candidate locations on a map. It adds pop-up information to each candidate location, including detailed information such as population density and the number of existing cafes. This process generates visually easy-to-read map data. The input is a list of candidate locations, and the output is the mapped map data.

[1042] Step 7:

[1043] Map data transmission

[1044] The server sends the generated map data to the device. This sent data is provided in GeoJSON format so that it can be used interactively. The input is the mapped map data, and the output is the interactive map data sent to the device.

[1045] Step 8:

[1046] Check the candidate site

[1047] The device displays the received map data to the user. The user can click on a marker on the map to view detailed information about each candidate location. The input is interactive map data, and the output is detailed information about the marker the user clicked.

[1048] (Application example 1)

[1049] 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."

[1050] In recent years, efficient location of logistics bases has become extremely important in the logistics industry in order to reduce logistics costs and speed up delivery. However, identifying the optimal location for a logistics center is extremely complex, as it requires consideration of a wide range of information, including existing facilities, traffic conditions, and local demographics. Traditional methods for addressing this issue have struggled to efficiently analyze the situation and present appropriate candidate sites.

[1051] 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.

[1052] In this invention, the server includes means for providing an interactive interface for a user to input facility location information and efficiency conditions, means for using a generative AI model to analyze the efficiency conditions and facility information specified based on the user input, and database search means for identifying optimal location candidate sites based on the above analysis, thereby enabling intuitive and rapid identification of efficient base locations in the logistics industry.

[1053] "Means for providing an interactive interface for users to input facility location information and efficiency criteria" means a system or software for providing an interactive interface designed to allow users to easily input criteria and requirements for the location of distribution centers and other facilities.

[1054] "Means using a generative AI model to analyze specified efficiency conditions and facility information based on user input" refers to systems or software that use a generative AI model to analyze efficiency conditions and facility information entered by a user. This generative AI model uses natural language processing technology to interpret the information and extract appropriate conditions and requirements.

[1055] The "database search means for identifying optimal candidate locations" refers to a system or software for searching and identifying suitable candidate locations from a related database based on the analyzed efficiency conditions and facility information.

[1056] "Map data generation means for displaying identified candidate placement locations on an online map" refers to a system or software that generates map data for visually displaying identified candidate placement locations and provides it through an online map service.

[1057] "Means for providing map data to users online" refers to a system or software that provides generated map data to users' devices via the Internet.

[1058] "Facility location information" refers to information about the locations and conditions of logistics centers and other facilities.

[1059] "Efficiency conditions" refer to the conditions and requirements for achieving desired efficiency in logistics and facility layout.

[1060] This invention relates to a system that supports optimal location of logistics centers and other facilities. The system of the present invention interactively collects facility location information and efficiency conditions entered by the user and analyzes them using a generative AI model. Based on the analysis results, the system then identifies optimal location candidates and displays them on an online map after a database search. The system of the present invention is implemented by the following steps:

[1061] 1. Collect user input:

[1062] Users use an interactive interface on devices such as smartphones or computers to input facility location information and efficiency conditions. This interface is designed to allow users to easily input conditions. For example, a user might input "a location in Tokyo with good transportation access and a reasonable distance from existing logistics centers."

[1063] 2. Data Transmission and Encryption:

[1064] The information entered by the user is sent from the terminal to the server, where it is encrypted for security reasons.

[1065] 3. Data Analysis:

[1066] The server analyzes the received data using a generative AI model, which uses natural language processing algorithms to extract important keywords and conditions from the input text. The generative AI model uses, for example, OpenAI's API.

[1067] 4. Database Search:

[1068] The server searches specified databases (e.g., geographical and related data) based on the analyzed criteria, thereby identifying optimal candidate locations.

[1069] 5. Map data generation and display:

[1070] The server uses online map generation tools such as Folium to map the identified candidate locations, and the generated map data is provided in an interactive format, allowing users to intuitively check detailed information.

[1071] 6. Providing interactive maps:

[1072] The server then sends the generated map data to the device, where users can view the map data on their smartphones or computers and obtain detailed information about the candidate locations.

[1073] Example prompt sentence:

[1074] Interpret the distribution center criteria entered by the user to identify key information. Input: A location in Tokyo with good transportation access and within a reasonable distance from existing distribution centers.

[1075] By implementing this invention, efficient location selection becomes possible in the logistics industry and facility location, leading to cost reductions and improved logistics efficiency. This system is characterized by its ability to perform real-time data analysis and identify candidate locations by utilizing existing databases and generative AI models.

[1076] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1077] Step 1:

[1078] User input of information

[1079] Users input facility location information and efficiency conditions into an interactive interface. This interface is provided on devices such as smartphones and computers. For example, let's say a user inputs "a location in Tokyo that has good transportation access and is within a reasonable distance from existing logistics centers."

[1080] Input: Facility location information, efficiency conditions

[1081] Output: User input data

[1082] Step 2:

[1083] Data transmission and encryption by the device

[1084] The data entered by the user is sent to the server by the terminal. At this time, the data is encrypted to ensure security. Encrypted data prevents data leakage during communication.

[1085] Input: User-entered data

[1086] Output: Encrypted user-entered data

[1087] Step 3:

[1088] Data reception by the server

[1089] The server receives the encrypted user-entered data, which is then decrypted back into a format that can be parsed. The decrypted data is then used for parsing in the next step.

[1090] Input: Encrypted user-entered data

[1091] Output: Decoded user input data

[1092] Step 4:

[1093] Data analysis

[1094] The server then analyzes the decoded user input data using a generative AI model. This generative AI model uses natural language processing technology to extract important keywords and conditions from the user's input text. For example, conditions such as "within Tokyo," "good transportation access," and "reasonable distance from existing logistics centers" are extracted.

[1095] Input: Decrypted user-entered data

[1096] Output: Parsed keywords and conditions

[1097] Step 5:

[1098] Searching the database

[1099] The server searches the specified database (geographical information and related data) based on the analyzed keywords and conditions, such as data on areas with good transportation access or the locations of existing logistics centers, to identify the optimal candidate locations.

[1100] Input: Parsed keywords and conditions

[1101] Output: Identified candidate locations

[1102] Step 6:

[1103] Map data generation

[1104] The server uses a map generation tool such as Folium to map the identified candidate locations, and the map displays detailed information about each location (e.g., access to the site, distance from existing facilities) as a pop-up.

[1105] Input: Identified candidate locations

[1106] Output: Generated map data

[1107] Step 7:

[1108] Sending map data

[1109] The server then sends the generated map data to the terminal, which provides the map data in an interactive format, allowing users to intuitively check detailed information.

[1110] Input: Generated map data

[1111] Output: Map data received by the device

[1112] Step 8:

[1113] Providing interactive maps

[1114] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each candidate site. This supports efficient facility placement decision-making.

[1115] Input: Map data received by the device

[1116] Output: An interactive map screen that the user sees

[1117] 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.

[1118] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with concrete examples.

[1119] System Operation Overview

[1120] 1. User input

[1121] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[1122] 2. Data transmission by the terminal

[1123] The terminal encrypts the data entered by the user and sends it to the server. This data is encrypted for security reasons.

[1124] 3. Data analysis by the server

[1125] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[1126] 4. Recognition of user emotions using an emotion engine

[1127] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting when a user is feeling stressed or has positive emotions.

[1128] 5. Database search by server

[1129] The server starts a database search based on the analysis results and the user's sentiment. It searches the specified database (e.g., geographic information database, demographic data, competitor store data, etc.).

[1130] 6. Adaptive Feedback by the Server

[1131] The server provides appropriate feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it provides additional reassuring information (e.g., successful store openings).

[1132] 7. Identification of potential store locations by the server

[1133] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[1134] 8. Map data generation by the server

[1135] The server uses an online map service (e.g., Google Maps API) to map potential locations, and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[1136] 9. Sending map data to the device

[1137] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[1138] 10. User confirmation of candidate sites

[1139] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[1140] Specific examples

[1141] scenario

[1142] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[1143] 1. Enter information

[1144] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1145] 2. Data Transmission

[1146] The terminal transmits the input data to the server.

[1147] 3. Data Analysis

[1148] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1149] 4. Emotion recognition

[1150] The server uses an emotion engine to recognize the user's emotions from the user's input sentences and interactions. For example, it detects emotions such as "worry" and "expectation" in the user's posts.

[1151] 5. Database Search

[1152] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[1153] 6. Adaptive Feedback

[1154] If the user's feelings are recognized as worrying, the server provides additional reassurance, such as past success stories and risk mitigation strategies.

[1155] 7. Identifying potential sites

[1156] The server obtains location information for the specified area and performs further filtering, allowing users to find specific locations within Shinjuku Ward or locations that meet specific criteria.

[1157] 8. Map data generation

[1158] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[1159] 9. Map data transmission

[1160] The server transmits the map data to the terminal.

[1161] 10. Confirmation of candidate sites

[1162] The device displays map data to the user, who can click on a marker to see more information.

[1163] This allows users to quickly find the best potential location for a store through an interactive format, and with the help of an emotion engine, they can make more satisfying decisions.

[1164] The processing flow will be explained below.

[1165] Step 1:

[1166] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1167] Step 2:

[1168] The terminal encrypts the input data and sends it to the server. Encryption ensures the security of the data.

[1169] Step 3:

[1170] The server analyzes the received data and uses a generative AI model to extract important keywords and conditions from the input text, such as "within Tokyo," "high population," and "few cafes."

[1171] Step 4:

[1172] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting whether the user is feeling "worried" or "expecting."

[1173] Step 5:

[1174] The server then begins a database search based on the analysis results and the recognized emotion. First, it searches a geographic information database to obtain information about areas within Tokyo.

[1175] Step 6:

[1176] The server searches a demographic database to obtain population density information for each area in Tokyo, extracts areas with high population density, and performs filtering.

[1177] Step 7:

[1178] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[1179] Step 8:

[1180] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[1181] Step 9:

[1182] The server provides adaptive feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it will provide additional information such as successful store openings and risk mitigation measures.

[1183] Step 10:

[1184] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[1185] Step 11:

[1186] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[1187] Step 12:

[1188] The terminal displays the received map data to the user, who can click on markers on the map to view detailed information about each potential store location.

[1189] Step 13:

[1190] The user selects the optimal location for a store based on the feedback information provided by the emotion engine. During this process, the user can ask additional questions or change conditions, and the system will then suggest the optimal location again.

[1191] Example 2

[1192] 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."

[1193] Conventional systems require a great deal of time and effort to manually analyze trade area and competitor information, and they also have the problem of being unable to provide appropriate feedback because they do not take into account the user's emotional state. Furthermore, data encryption and adaptive feedback provision were insufficient, which meant that users' concerns could not be fully alleviated. Therefore, there was a need for efficient and satisfying information provision.

[1194] 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.

[1195] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitor information, means for using a generative AI model to analyze the trade area conditions and competitor information specified based on user input, database search means for identifying optimal store location candidates, map data generation means for displaying the identified store location candidates on an online map, means for providing the map data to users online, means for using an emotion engine that recognizes emotions by analyzing user input and interactions, and means for providing adaptive feedback based on the emotion recognition, thereby enabling efficient information provision that takes the user's emotional state into consideration and provides a high level of satisfaction.

[1196] "User" means an individual or corporation that uses this system.

[1197] "Trade area information" is information about market demand and consumer behavior in a specific area.

[1198] "Competitive information" refers to information on competing businesses and products within a trade area.

[1199] An "interactive interface" is a user interface that allows a user to interact with a system in a conversational manner.

[1200] A "generative AI model" is an algorithm that uses artificial intelligence to analyze user input information and extract trade area conditions and competitive information.

[1201] The "database search means" is a means for searching a database based on specific conditions and obtaining required information.

[1202] The "map data generating means" is a means for generating data for displaying the identified store candidate site on an online map.

[1203] An "emotion engine" is a technology that analyzes user input and interactions to identify emotions.

[1204] "Adaptive feedback" is feedback that provides optimal advice or information based on the user's emotional state.

[1205] "Encryption" is the process of transforming data so that it cannot be read by third parties.

[1206] MODE FOR CARRYING OUT THE INVENTION

[1207] System Configuration

[1208] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. The following describes embodiments of the present invention.

[1209] Hardware and software used

[1210] Server: Used for data analysis, emotion recognition, database search, and map data generation.

[1211] Terminal: The device (e.g., computer, smartphone) on which the user enters information and checks results.

[1212] Generative AI models: Used to analyze user input (e.g., GPT-4).

[1213] Emotion engine: Used to recognize the user's emotions.

[1214] Databases: Geographical databases, demographic data, competitor data, etc.

[1215] Online map service APIs: Used to generate and display map data (e.g., Google Maps API).

[1216] System processing flow

[1217] First, the user enters information about the business area and competitors into the chat interface on the device. For example, the user might enter, "I'm looking for an area in Tokyo with a large population but few cafes."

[1218] The terminal then encrypts the input data and sends it to the server using the TLS (Transport Layer Security) protocol.

[1219] The server receives the encrypted data, decrypts it, and then analyzes the input text using a generative AI model, extracting conditions such as "within Tokyo," "high population," and "few cafes."

[1220] The server then uses an emotion engine to recognize emotions from the user's input and interactions. For example, it can detect emotions such as "worry" or "expectation" in the user's input.

[1221] Based on the analysis results and emotion recognition data, the server searches specified databases, including geographic information databases, demographic data, and competitor store databases.

[1222] Depending on the search results, the server provides adaptive feedback that matches the user's emotional state. For example, if the server detects that the user is anxious, it will present reassuring information such as past success stories and risk mitigation measures.

[1223] The server then lists specific potential locations and obtains the latitude and longitude of each area. The identified areas (such as Shinjuku Ward or Shibuya Ward) are then analyzed in more detail to obtain information about each location (e.g., population density, number of existing cafes).

[1224] The server uses an online map service API (e.g., Google Maps API) to map potential locations for store openings on a map, and adds appropriate information to each location as a pop-up display.

[1225] The generated map data is sent to the device, and the user can view detailed information about the candidate locations on an interactive map. For example, the user can click on a marker on the map to view detailed information about each candidate location.

[1226] Specific examples

[1227] Scenario: A user is thinking about opening a new cafe and wants to find areas in Tokyo that are densely populated but have few cafes.

[1228] 1. User input:

[1229] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1230] 2. Data transmission:

[1231] The terminal encrypts the input data via TLS and sends it to the server.

[1232] 3. Data Analysis:

[1233] The server decrypts the received data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1234] 4. Emotion recognition:

[1235] The server uses an emotion engine to detect emotions such as "worry" or "expectation" from the user's input text and behavior.

[1236] 5. Database Search:

[1237] The server searches a geographic database, demographic data, and competitor store data to identify areas that meet the criteria (for example, Shinjuku Ward or Shibuya Ward).

[1238] 6. Adaptive Feedback:

[1239] If the user expresses "worried," the server presents past success stories and risk mitigation measures.

[1240] 7. Site Identification:

[1241] The server extracts more detailed candidate locations from the identified area and obtains their latitude and longitude information.

[1242] 8. Map data generation:

[1243] The server uses the Google Maps API to display the identified candidate locations on a map and adds detailed information (e.g., population density, number of existing cafes) to each candidate location as a pop-up.

[1244] 9. Map data transmission:

[1245] The server sends the generated map data to the terminal.

[1246] 10. Site confirmation:

[1247] The device displays map data to the user, who can click on each marker for more information.

[1248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1249] Step 1:

[1250] User input of information

[1251] Users input trade area information and competitor information into the chat interface on their device.

[1252] Input: Enter the prompt text "I'm looking for an area in Tokyo with a high population and few cafes."

[1253] Output: The user's input data is obtained.

[1254] Step 2:

[1255] Data transmission by the terminal

[1256] The terminal encrypts the data entered by the user using TLS and sends it to the server.

[1257] Input: User input data is captured at the terminal.

[1258] Output: TLS encrypted data is generated and sent to the server.

[1259] Step 3:

[1260] Data reception and analysis by the server

[1261] The server receives and decrypts the encrypted data sent from the device, then uses a generative AI model (e.g., GPT-4) to analyze the received data and extract important keywords and conditions.

[1262] Input: TLS encrypted data is sent to the server.

[1263] Output: As a result of the analysis, conditions such as "within Tokyo," "large population," and "few cafes" are extracted.

[1264] Step 4:

[1265] Recognizing user emotions with an emotion engine

[1266] The server uses an emotion engine to recognize emotions based on user input and interactions, for example, detecting emotions such as "worry" or "anticipation."

[1267] Input: Analysis results and user input data.

[1268] Output: Recognition result of the user's emotional state.

[1269] Step 5:

[1270] Database search by server

[1271] Taking into account the output of the emotion engine, the server searches databases (e.g., geographic information databases, demographic data, competitor store data).

[1272] Input: Analysis results and emotion recognition results.

[1273] Output: Search results include a list of potential locations that match the criteria.

[1274] Step 6:

[1275] Adaptive feedback by the server

[1276] The server provides adaptive feedback based on the user's emotional state, for example, providing additional information such as success stories and risk mitigation strategies if the user is anxious.

[1277] Input: Emotion recognition results and search results.

[1278] Output: Adaptive feedback content.

[1279] Step 7:

[1280] Identification of potential store locations by the server

[1281] The server identifies the latitude and longitude information of specific candidate locations and then filters them to see if they match more specific criteria, such as Shinjuku Ward or Shibuya Ward.

[1282] Input: Search results.

[1283] Output: A detailed list of potential locations with their latitude and longitude coordinates.

[1284] Step 8:

[1285] Map data generation by the server

[1286] The server generates map data for the identified candidate locations using the Google Maps API, etc. Pop-up information such as population density and the number of existing cafes is added to each candidate location.

[1287] Input: A detailed list of potential store locations and their latitude and longitude information.

[1288] Output: The generated map data.

[1289] Step 9:

[1290] Sending map data to the device

[1291] The server sends the generated map data to the terminal.

[1292] Input: Generated map data.

[1293] Output: Interactive map data is sent to the device.

[1294] Step 10:

[1295] User review of candidate sites

[1296] The terminal displays the received map data to the user, who can click on markers on the map to check detailed information about each potential store location.

[1297] Input: Submitted map data.

[1298] Output: An interface where the user can view detailed information.

[1299] (Application example 2)

[1300] 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."

[1301] In today's business environment, selecting an appropriate location is extremely important, especially when opening a brick-and-mortar store. However, selecting a location requires a lot of time and effort, and the amount of commercial area and competitive information is complex and vast, making it difficult to efficiently analyze data and find the optimal candidate location. Furthermore, while there is a need to provide information that takes into account the psychological anxieties and expectations of prospective store owners, existing systems do not adequately address this need. Therefore, the present invention aims to provide a system that quickly and accurately identifies candidate locations for store openings while taking into account the user's emotions.

[1302] The identification process by the identification 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 providing an interactive interface for a user to input market information and competitive information, means for using a generative AI model to analyze market conditions and competitive information specified based on the user input, emotion analysis means for recognizing the user's emotion from the analyzed information, feedback provision means for providing adaptive feedback based on the user's emotion, database search means for identifying an optimal store candidate site, map data generation means for displaying the identified store candidate site on an online map, and means for providing the map data to the user online. This enables the user to quickly and accurately find an optimal store candidate site while reducing emotional anxiety.

[1303] "Market information" is data about commercial activity in a particular geographic area, such as market size, customer demographic characteristics, purchasing trends, and local economic trends.

[1304] "Competitive information" refers to information such as the number, location, size, type of business, and market share of competitors in a particular area.

[1305] An "interactive interface" is an input method that allows a user to communicate with a system using natural language, and is an interface that can take the form of a text box, chatbot, or similar.

[1306] A "generative AI model" is an artificial intelligence model that analyzes information entered by a user and extracts intent from that information, and uses natural language processing technology.

[1307] "Emotion analysis means" is a technology that recognizes a user's emotions from their input and interactions, and provides data based on those emotions.

[1308] A "feedback providing means" is a method for providing appropriate information or advice to a user, taking into consideration the user's feelings.

[1309] "Database search means" refers to a technique for searching and acquiring necessary information from related databases based on specified conditions.

[1310] The "map data generating means" is a method for generating data for displaying the specified information on a map and visually presenting it to the user.

[1311] "Online provision means" refers to the technology used to provide information and services to users via the Internet.

[1312] The system of the present invention supports the process of selecting a potential store location and includes the following means: It integrates various technologies to allow users to input market and competitive information and identify the most suitable potential store location.

[1313] System Configuration

[1314] The system consists of an interactive interface, a generative AI model, an emotion analysis means, a feedback provision means, a database search means, a map data generation means, and an online provision means.

[1315] Program processing flow

[1316] 1. User input

[1317] Users input market and competitive information using an interactive interface on their smartphones or PCs. A concrete example of a prompt might be, "Please tell me an area in Osaka City that has a lot of young people and few restaurants."

[1318] 2. Data analysis by the server

[1319] The user's input data is encrypted and securely transmitted to a server, where it is analyzed using a generative AI model (e.g., Hugging Face's "bert-base-multilingual-cased") to extract key terms.

[1320] 3. Emotion Analysis and Adaptive Feedback

[1321] The server uses emotion analysis to recognize emotions from the user's input. Based on the analysis results, if the user is feeling anxious or hopeful, it provides appropriate feedback accordingly. For example, providing additional information such as past success stories and risk mitigation measures can reassure the user.

[1322] 4. Criteria-based database search

[1323] Based on the criteria extracted by the generative AI model, a database search tool searches relevant databases such as market data, competitive information, and demographic data, thereby identifying areas that meet the criteria.

[1324] 5. Map data generation and online provision

[1325] Based on the latitude and longitude information of the identified candidate locations for store openings, the map data generation means generates a map using an online map service (e.g., Google Maps API). Pop-up information including detailed information such as population density and competitor information is also added to this map. The generated map data is provided to users online, allowing them to interactively check each candidate location.

[1326] Specific examples

[1327] For example, if a user inputs "Please tell me an area in Osaka City that has a lot of young people and few restaurants," the server analyzes this information using a generative AI model and extracts conditions such as "Osaka City," "Many young people," and "Few restaurants." At the same time, the emotion analysis means recognizes the user's emotions, such as expectations and anxieties, and provides feedback based on those. The database search means then searches for areas that meet the conditions, and the map data generation means plots candidate locations using the Google Maps API. As a result, the user can interactively check the map and obtain detailed information about each candidate location.

[1328] In this way, by using the system of the present invention, the user can quickly and accurately select the most suitable candidate site for opening a store while reducing emotional anxiety.

[1329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1330] Step 1:

[1331] Users input market and competitive information using an interactive interface on their smartphone or PC. Specifically, they input a prompt such as, "Please tell me an area in Osaka City that has a lot of young people and few restaurants." This clarifies the conditions the user is looking for, and the subsequent processing begins.

[1332] Step 2:

[1333] The terminal encrypts the input data and sends it securely to the server. The terminal properly formats the user's input information and sends it securely using an encryption algorithm (e.g., AES). This protects the user's privacy.

[1334] Step 3:

[1335] The server decrypts the received encrypted data and analyzes the user's input using a generative AI model. Specifically, an AI model (e.g., bert-base-multilingual-cased) is used to extract conditions such as "Osaka city," "lots of young people," and "few restaurants" from the text data. This analysis clarifies the user's intent and specifies the conditions.

[1336] Step 4:

[1337] The server uses emotion analysis to recognize the user's emotions from the analyzed information. Specifically, it uses an emotion analysis model to identify emotions such as "anxiety" or "expectation" that the user is feeling. The results of emotion recognition enable it to provide adaptive feedback.

[1338] Step 5:

[1339] The server provides adaptive feedback based on the results of sentiment analysis. For example, if the user feels anxious, it provides additional information about past success stories and risk mitigation measures. This reduces the user's anxiety and provides a sense of security.

[1340] Step 6:

[1341] The server searches for relevant data from the specified database based on the conditions extracted by the generative AI model. Specifically, it searches demographic data, geographic information data, competing store data, etc. to identify areas that meet the conditions. The search results provide useful information to the user.

[1342] Step 7:

[1343] The server acquires the latitude and longitude information of the identified potential store locations and generates an online map using a map data generation method. Specifically, it uses the Google Maps API to map the potential locations. This map also includes detailed information such as the population density of each area and competitor information.

[1344] Step 8:

[1345] The server sends the generated map data to the user's device, allowing the user to interactively check the map data. By clicking on a marker on the map, the user can check detailed information about each candidate site and select the optimal store location. This step allows the user to quickly and accurately find the optimal store location.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] [Fourth embodiment]

[1350] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1351] 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.

[1352] 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).

[1353] 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.

[1354] 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.

[1355] 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).

[1356] 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. 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] 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."

[1363] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, and online map display means. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with specific examples.

[1364] System Operation Overview

[1365] 1. User input

[1366] The user uses a terminal to input desired business area conditions and competitive information into the chat interface. For example, they might input, "I'm looking for an area in Tokyo with a high population but few cafes."

[1367] 2. Data transmission by the terminal

[1368] The terminal sends the user's input data to the server, which is encrypted for security reasons.

[1369] 3. Data analysis by the server

[1370] The server analyzes the received data using a generative AI model. This model uses natural language processing algorithms to extract important keywords and conditions from the input text. Conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[1371] 4. Database search by server

[1372] The server searches specified databases (e.g., geographic information databases, demographic data, competitor store data, etc.) based on the analyzed conditions. For example, it identifies areas in Tokyo with high population density and filters out areas with few cafes.

[1373] 5. Identification of potential store locations by the server

[1374] Based on the information obtained from the database, potential locations that meet the criteria are identified, such as specific areas in Shinjuku Ward or Shibuya Ward.

[1375] 6. Map data generation by the server

[1376] The server uses an online map service (e.g., Google Maps API) to map the identified potential locations, adding pop-up information (e.g., population density, number of existing cafes) to each location.

[1377] 7. Sending map data to the device

[1378] The server sends the generated map data to the device, where it is provided in an interactive format.

[1379] 8. User confirmation of candidate sites

[1380] The device displays the received map data to the user, who can then click on the markers on the map to view detailed information about each candidate location.

[1381] Specific examples

[1382] scenario

[1383] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[1384] 1. Enter information

[1385] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population and few cafes."

[1386] 2. Data Transmission

[1387] The terminal transmits the input data to the server.

[1388] 3. Data Analysis

[1389] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1390] 4. Database Search

[1391] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[1392] 5. Identifying potential sites

[1393] The server obtains location information for the specified area and performs further filtering, which may result in a specific location within Shinjuku Ward.

[1394] 6. Map data generation

[1395] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[1396] 7. Map data transmission

[1397] The server transmits the map data to the terminal.

[1398] 8. Confirmation of candidate sites

[1399] The device displays map data to the user, who can click on a marker to see more information.

[1400] In this way, users can intuitively and quickly find potential store locations, enabling them to efficiently proceed with the execution of store opening plans.

[1401] The processing flow will be explained below.

[1402] Step 1:

[1403] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[1404] Step 2:

[1405] The terminal encrypts the information entered by the user and sends it to the server. This encryption ensures the security of the transmitted data.

[1406] Step 3:

[1407] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[1408] Step 4:

[1409] The server then begins a database search based on the analysis results. First, it searches the geographic information database to obtain information about areas within Tokyo.

[1410] Step 5:

[1411] Next, the server searches a demographic database to obtain population density information for each area in Tokyo, and filters out areas with high population density.

[1412] Step 6:

[1413] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[1414] Step 7:

[1415] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[1416] Step 8:

[1417] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[1418] Step 9:

[1419] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[1420] Step 10:

[1421] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[1422] Example 1

[1423] 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."

[1424] Conventional store opening support systems required users to analyze complex trade area conditions and competitive information to find the optimal store location, which required specialized knowledge and was time-consuming and labor-intensive.In addition, they lacked a visual interface for making decisions based on detailed information, resulting in an unsatisfactory user experience.

[1425] 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.

[1426] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitive information, means for using a generative AI model to analyze the trade area conditions and competitive information specified based on user input, and map data generation means for displaying identified store candidate sites on an online map, allowing users to easily identify and visually confirm store candidate sites without requiring specialized knowledge.

[1427] A "user" is an individual or corporation that uses this system to input trade area information and competitor information to identify potential locations for opening a store.

[1428] "Trade area information" is data on market characteristics and customer trends in a specific region.

[1429] "Competitor information" is data regarding the number and types of competing stores in a particular area.

[1430] A "conversational interface" is an application such as a chat interface or form designed to allow users to enter trade area or competitor information in natural language.

[1431] A "generative AI model" is an artificial intelligence model that analyzes natural language text entered by a user and extracts important keywords and conditions.

[1432] The "database search means" is a system function for searching for trade area information and competitor information based on specified conditions.

[1433] The "map data generating means" is a system function for displaying the identified potential store locations on an online map.

[1434] "Online Map" means a digital map application accessible via the Internet.

[1435] "Encryption" is a technology that converts data using a specific algorithm to ensure information security.

[1436] "Demographic data" refers to data about the population composition and density of a particular area.

[1437] "Geographic information data" is data relating to the geographic characteristics of a particular area.

[1438] A "marker" is a visual icon used to indicate a specific location on an online map.

[1439] "Detailed information" is additional data about a particular potential store location (e.g., population density, number of existing stores, etc.).

[1440] The system of this invention executes a series of processes to identify potential locations for store openings by inputting trade area information and competitor information using a generative AI model and analyzing the information. To achieve this, the system includes the following main components:

[1441] System configuration

[1442] 1. User input: A user uses a device to access a conversational interface and input information about the market and competitors. Specifically, the user uses a web or mobile application. For example, the user might enter, "I'm looking for an area in Tokyo that has a high population but few cafes," into a chat interface.

[1443] 2. Data transmission by the terminal: The terminal converts the information entered by the user into an appropriate format, encrypts it using SSL / TLS for security reasons, and sends it to the server. The software used includes request libraries that use the HTTP protocol (e.g., fetch API or HTTP client library).

[1444] 3. Data analysis by the server: The server inputs the received data into a generative AI model (e.g., ChatGPT) and analyzes the text. The generative AI model uses natural language processing algorithms to extract important keywords and conditions. Examples include "within Tokyo," "large population," and "few cafes."

[1445] 4. Database Search: The server searches the specified database (e.g., PostgreSQL, MongoDB) based on the parsed criteria. The search targets can be geographical databases, demographic databases, competitor store data, etc. Specific SQL or NoSQL queries are used to extract the data.

[1446] 5. Identifying potential locations for store openings: The server identifies potential locations for store openings that meet the criteria based on information obtained from the database. For example, it filters areas in Tokyo with high population density and few cafes, and identifies Shinjuku Ward and Shibuya Ward.

[1447] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on an online map. Pop-up information such as population density and the number of existing cafes is added to each candidate location to make it easier for users to understand visually.

[1448] 7. Sending map data to the device: The server sends the generated map data to the device. The map data is provided in an interactive format (e.g., GeoJSON format).

[1449] 8. User confirmation of candidate locations: The device displays the received map data and allows the user to interactively check the candidate locations. The user can click on the markers on the map to view detailed information about each candidate location.

[1450] Specific examples

[1451] Below are some specific scenarios and examples of input to the generative AI model.

[1452] scenario

[1453] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[1454] 1. Information input: The user enters into the chat interface on their device, "I'm looking for an area in Tokyo that has a high population but few cafes."

[1455] 2. Data transmission: The terminal transmits the input data to the server.

[1456] 3. Data analysis: The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1457] 4. Database search: The server searches the geographical information database, demographic database, and competitor store data based on the conditions to identify matching areas. For example, specific areas in Shinjuku Ward or Shibuya Ward are found.

[1458] 5. Identifying candidate locations: The server obtains location information for the identified areas and performs further filtering.

[1459] 6. Map data generation: The server uses the Google Maps API to map the identified candidate locations on a map.

[1460] 7. Send map data: The server sends the generated map data to the device.

[1461] 8. Confirm candidate locations: The device displays map data to the user, and the user can click on a marker to see more information.

[1462] Example input to a generative AI model

[1463] Examples of prompts:

[1464] "I'm looking for an area in Tokyo that has a large population but few cafes. Which area is that?"

[1465] In this way, the system of the present invention allows users to easily conduct trade area surveys and quickly find the most suitable candidate site for opening a store.

[1466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1467] Step 1:

[1468] Enter information

[1469] Users use a device to access a dialogue-style interface and input business area and competitor information in natural language. Specifically, they might type into the chat interface, "I'm looking for an area in Tokyo that has a high population but few cafes." This input data is saved in text format on the device.

[1470] Step 2:

[1471] Data transmission

[1472] The terminal encrypts the text data entered by the user and sends it securely to the server using SSL / TLS. The input is the trade area conditions and competitive information entered by the user, and the output is the encrypted text data sent to the server.

[1473] Step 3:

[1474] Data analysis

[1475] The server decrypts the received encrypted data and inputs it as analysis data into a generative AI model (for example, ChatGPT). This model uses a natural language processing algorithm to analyze the text and extract important keywords and conditions. Specifically, conditions such as "within Tokyo," "large population," and "few cafes" are extracted. The input is the user's text data, and the output is the extracted keywords and conditions.

[1476] Step 4:

[1477] Database search

[1478] The server searches multiple databases based on the analyzed conditions, including geographic information databases, demographic databases, and competitor store databases. Specifically, it uses SQL and NoSQL queries to extract areas with high population density and few cafes. The input is the extracted conditions, and the output is the retrieved data entries.

[1479] Step 5:

[1480] Identifying potential locations for stores

[1481] The server identifies the optimal candidate locations for opening a store based on the information obtained from the database. Specifically, it filters areas with a small number of cafes in Shinjuku Ward or Shibuya Ward, for example, and identifies detailed candidate locations. The input is the acquired data entry, and the output is a list of identified candidate locations.

[1482] Step 6:

[1483] Map data generation

[1484] The server uses the Google Maps API to map the identified candidate locations on a map. It adds pop-up information to each candidate location, including detailed information such as population density and the number of existing cafes. This process generates visually easy-to-read map data. The input is a list of candidate locations, and the output is the mapped map data.

[1485] Step 7:

[1486] Map data transmission

[1487] The server sends the generated map data to the device. This sent data is provided in GeoJSON format so that it can be used interactively. The input is the mapped map data, and the output is the interactive map data sent to the device.

[1488] Step 8:

[1489] Check the candidate site

[1490] The device displays the received map data to the user. The user can click on a marker on the map to view detailed information about each candidate location. The input is interactive map data, and the output is detailed information about the marker the user clicked.

[1491] (Application example 1)

[1492] 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."

[1493] In recent years, efficient location of logistics bases has become extremely important in the logistics industry in order to reduce logistics costs and speed up delivery. However, identifying the optimal location for a logistics center is extremely complex, as it requires consideration of a wide range of information, including existing facilities, traffic conditions, and local demographics. Traditional methods for addressing this issue have struggled to efficiently analyze the situation and present appropriate candidate sites.

[1494] 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.

[1495] In this invention, the server includes means for providing an interactive interface for a user to input facility location information and efficiency conditions, means for using a generative AI model to analyze the efficiency conditions and facility information specified based on the user input, and database search means for identifying optimal location candidate sites based on the above analysis, thereby enabling intuitive and rapid identification of efficient base locations in the logistics industry.

[1496] "Means for providing an interactive interface for users to input facility location information and efficiency criteria" means a system or software for providing an interactive interface designed to allow users to easily input criteria and requirements for the location of distribution centers and other facilities.

[1497] "Means using a generative AI model to analyze specified efficiency conditions and facility information based on user input" refers to systems or software that use a generative AI model to analyze efficiency conditions and facility information entered by a user. This generative AI model uses natural language processing technology to interpret the information and extract appropriate conditions and requirements.

[1498] The "database search means for identifying optimal candidate locations" refers to a system or software for searching and identifying suitable candidate locations from a related database based on the analyzed efficiency conditions and facility information.

[1499] "Map data generation means for displaying identified candidate placement locations on an online map" refers to a system or software that generates map data for visually displaying identified candidate placement locations and provides it through an online map service.

[1500] "Means for providing map data to users online" refers to a system or software that provides generated map data to users' devices via the Internet.

[1501] "Facility location information" refers to information about the locations and conditions of logistics centers and other facilities.

[1502] "Efficiency conditions" refer to the conditions and requirements for achieving desired efficiency in logistics and facility layout.

[1503] This invention relates to a system that supports optimal location of logistics centers and other facilities. The system of the present invention interactively collects facility location information and efficiency conditions entered by the user and analyzes them using a generative AI model. Based on the analysis results, the system then identifies optimal location candidates and displays them on an online map after a database search. The system of the present invention is implemented by the following steps:

[1504] 1. Collect user input:

[1505] Users use an interactive interface on devices such as smartphones or computers to input facility location information and efficiency conditions. This interface is designed to allow users to easily input conditions. For example, a user might input "a location in Tokyo with good transportation access and a reasonable distance from existing logistics centers."

[1506] 2. Data Transmission and Encryption:

[1507] The information entered by the user is sent from the terminal to the server, where it is encrypted for security reasons.

[1508] 3. Data Analysis:

[1509] The server analyzes the received data using a generative AI model, which uses natural language processing algorithms to extract important keywords and conditions from the input text. The generative AI model uses, for example, OpenAI's API.

[1510] 4. Database Search:

[1511] The server searches specified databases (e.g., geographical and related data) based on the analyzed criteria, thereby identifying optimal candidate locations.

[1512] 5. Map data generation and display:

[1513] The server uses online map generation tools such as Folium to map the identified candidate locations, and the generated map data is provided in an interactive format, allowing users to intuitively check detailed information.

[1514] 6. Providing interactive maps:

[1515] The server then sends the generated map data to the device, where users can view the map data on their smartphones or computers and obtain detailed information about the candidate locations.

[1516] Example prompt sentence:

[1517] Interpret the distribution center criteria entered by the user to identify key information. Input: A location in Tokyo with good transportation access and within a reasonable distance from existing distribution centers.

[1518] By implementing this invention, efficient location selection becomes possible in the logistics industry and facility location, leading to cost reductions and improved logistics efficiency. This system is characterized by its ability to perform real-time data analysis and identify candidate locations by utilizing existing databases and generative AI models.

[1519] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1520] Step 1:

[1521] User input of information

[1522] Users input facility location information and efficiency conditions into an interactive interface. This interface is provided on devices such as smartphones and computers. For example, let's say a user inputs "a location in Tokyo that has good transportation access and is within a reasonable distance from existing logistics centers."

[1523] Input: Facility location information, efficiency conditions

[1524] Output: User input data

[1525] Step 2:

[1526] Data transmission and encryption by the device

[1527] The data entered by the user is sent to the server by the terminal. At this time, the data is encrypted to ensure security. Encrypted data prevents data leakage during communication.

[1528] Input: User-entered data

[1529] Output: Encrypted user-entered data

[1530] Step 3:

[1531] Data reception by the server

[1532] The server receives the encrypted user-entered data, which is then decrypted back into a format that can be parsed. The decrypted data is then used for parsing in the next step.

[1533] Input: Encrypted user-entered data

[1534] Output: Decoded user input data

[1535] Step 4:

[1536] Data analysis

[1537] The server then analyzes the decoded user input data using a generative AI model. This generative AI model uses natural language processing technology to extract important keywords and conditions from the user's input text. For example, conditions such as "within Tokyo," "good transportation access," and "reasonable distance from existing logistics centers" are extracted.

[1538] Input: Decrypted user-entered data

[1539] Output: Parsed keywords and conditions

[1540] Step 5:

[1541] Searching the database

[1542] The server searches the specified database (geographical information and related data) based on the analyzed keywords and conditions, such as data on areas with good transportation access or the locations of existing logistics centers, to identify the optimal candidate locations.

[1543] Input: Parsed keywords and conditions

[1544] Output: Identified candidate locations

[1545] Step 6:

[1546] Map data generation

[1547] The server uses a map generation tool such as Folium to map the identified candidate locations, and the map displays detailed information about each location (e.g., access to the site, distance from existing facilities) as a pop-up.

[1548] Input: Identified candidate locations

[1549] Output: Generated map data

[1550] Step 7:

[1551] Sending map data

[1552] The server then sends the generated map data to the terminal, which provides the map data in an interactive format, allowing users to intuitively check detailed information.

[1553] Input: Generated map data

[1554] Output: Map data received by the device

[1555] Step 8:

[1556] Providing interactive maps

[1557] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each candidate site. This supports efficient facility placement decision-making.

[1558] Input: Map data received by the device

[1559] Output: An interactive map screen that the user sees

[1560] 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.

[1561] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. Below, the program processing of this system is explained in natural language, and a form for implementing the invention is shown with concrete examples.

[1562] System Operation Overview

[1563] 1. User input

[1564] Users input business area and competitor information into the chat interface on their device. For example, they might enter, "I'm looking for an area in Tokyo with a high population but few cafes."

[1565] 2. Data transmission by the terminal

[1566] The terminal encrypts the data entered by the user and sends it to the server. This data is encrypted for security reasons.

[1567] 3. Data analysis by the server

[1568] The server analyzes the received user input and uses a generative AI model to extract important keywords and conditions from the input text. In this case, conditions such as "within Tokyo," "high population," and "few cafes" are extracted.

[1569] 4. Recognition of user emotions using an emotion engine

[1570] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting when a user is feeling stressed or has positive emotions.

[1571] 5. Database search by server

[1572] The server starts a database search based on the analysis results and the user's sentiment. It searches the specified database (e.g., geographic information database, demographic data, competitor store data, etc.).

[1573] 6. Adaptive Feedback by the Server

[1574] The server provides appropriate feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it provides additional reassuring information (e.g., successful store openings).

[1575] 7. Identification of potential store locations by the server

[1576] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[1577] 8. Map data generation by the server

[1578] The server uses an online map service (e.g., Google Maps API) to map potential locations, and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[1579] 9. Sending map data to the device

[1580] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[1581] 10. User confirmation of candidate sites

[1582] The terminal displays the received map data to the user, who can then click on a marker on the map to view detailed information about each potential store location.

[1583] Specific examples

[1584] scenario

[1585] Let's say a user is thinking about opening a new cafe and wants to find an area in Tokyo that is densely populated but has few cafes.

[1586] 1. Enter information

[1587] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1588] 2. Data Transmission

[1589] The terminal transmits the input data to the server.

[1590] 3. Data Analysis

[1591] The server receives the data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1592] 4. Emotion recognition

[1593] The server uses an emotion engine to recognize the user's emotions from the user's input sentences and interactions. For example, it detects emotions such as "worry" and "expectation" in the user's posts.

[1594] 5. Database Search

[1595] The server searches the geographic database, demographic data, and competitor store data based on the conditions, and identifies matching areas. For example, it finds specific areas in Shinjuku Ward or Shibuya Ward.

[1596] 6. Adaptive Feedback

[1597] If the user's feelings are recognized as worrying, the server provides additional reassurance, such as past success stories and risk mitigation strategies.

[1598] 7. Identifying potential sites

[1599] The server obtains location information for the specified area and performs further filtering, allowing users to find specific locations within Shinjuku Ward or locations that meet specific criteria.

[1600] 8. Map data generation

[1601] The server uses the Google Maps API to map the identified potential locations, adding pop-up information for each location, such as population density and the number of existing cafes.

[1602] 9. Map data transmission

[1603] The server transmits the map data to the terminal.

[1604] 10. Confirmation of candidate sites

[1605] The device displays map data to the user, who can click on a marker to see more information.

[1606] This allows users to quickly find the best potential location for a store through an interactive format, and with the help of an emotion engine, they can make more satisfying decisions.

[1607] The processing flow will be explained below.

[1608] Step 1:

[1609] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1610] Step 2:

[1611] The terminal encrypts the input data and sends it to the server. Encryption ensures the security of the data.

[1612] Step 3:

[1613] The server analyzes the received data and uses a generative AI model to extract important keywords and conditions from the input text, such as "within Tokyo," "high population," and "few cafes."

[1614] Step 4:

[1615] The server uses an emotion engine to recognize emotions from user input and interactions, for example, detecting whether the user is feeling "worried" or "expecting."

[1616] Step 5:

[1617] The server then begins a database search based on the analysis results and the recognized emotion. First, it searches a geographic information database to obtain information about areas within Tokyo.

[1618] Step 6:

[1619] The server searches a demographic database to obtain population density information for each area in Tokyo, extracts areas with high population density, and performs filtering.

[1620] Step 7:

[1621] The server searches a database of competing cafes to identify areas with few cafes, thereby narrowing down the list of potential locations.

[1622] Step 8:

[1623] The server creates a list of potential locations that meet the criteria and obtains the latitude and longitude information for each location. For example, specific areas in Shinjuku Ward or Shibuya Ward are listed.

[1624] Step 9:

[1625] The server provides adaptive feedback based on the user's emotions. For example, if the emotion engine detects the user's anxiety, it will provide additional information such as successful store openings and risk mitigation measures.

[1626] Step 10:

[1627] The server uses an online map service (e.g., Google Maps API) to map potential locations and adds pop-up information (e.g., population density, number of existing cafes) to each location.

[1628] Step 11:

[1629] The server then sends the generated map data to the device, which includes interactive elements and is configured to allow the user to view detailed information.

[1630] Step 12:

[1631] The terminal displays the received map data to the user, who can click on markers on the map to view detailed information about each potential store location.

[1632] Step 13:

[1633] The user selects the optimal location for a store based on the feedback information provided by the emotion engine. During this process, the user can ask additional questions or change conditions, and the system will then suggest the optimal location again.

[1634] Example 2

[1635] 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."

[1636] Conventional systems require a great deal of time and effort to manually analyze trade area and competitor information, and they also have the problem of being unable to provide appropriate feedback because they do not take into account the user's emotional state. Furthermore, data encryption and adaptive feedback provision were insufficient, which meant that users' concerns could not be fully alleviated. Therefore, there was a need for efficient and satisfying information provision.

[1637] 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.

[1638] In this invention, the server includes means for providing an interactive interface for users to input trade area information and competitor information, means for using a generative AI model to analyze the trade area conditions and competitor information specified based on user input, database search means for identifying optimal store location candidates, map data generation means for displaying the identified store location candidates on an online map, means for providing the map data to users online, means for using an emotion engine that recognizes emotions by analyzing user input and interactions, and means for providing adaptive feedback based on the emotion recognition, thereby enabling efficient information provision that takes the user's emotional state into consideration and provides a high level of satisfaction.

[1639] "User" means an individual or corporation that uses this system.

[1640] "Trade area information" is information about market demand and consumer behavior in a specific area.

[1641] "Competitive information" refers to information on competing businesses and products within a trade area.

[1642] An "interactive interface" is a user interface that allows a user to interact with a system in a conversational manner.

[1643] A "generative AI model" is an algorithm that uses artificial intelligence to analyze user input information and extract trade area conditions and competitive information.

[1644] The "database search means" is a means for searching a database based on specific conditions and obtaining required information.

[1645] The "map data generating means" is a means for generating data for displaying the identified store candidate site on an online map.

[1646] An "emotion engine" is a technology that analyzes user input and interactions to identify emotions.

[1647] "Adaptive feedback" is feedback that provides optimal advice or information based on the user's emotional state.

[1648] "Encryption" is the process of transforming data so that it cannot be read by third parties.

[1649] MODE FOR CARRYING OUT THE INVENTION

[1650] System Configuration

[1651] The system of the present invention includes an interactive interface for users to input trade area information and competitor information, analysis of the input information using a generative AI model, database search means, map data generation means, online map display means, and an emotion engine that recognizes user emotions. The following describes embodiments of the present invention.

[1652] Hardware and software used

[1653] Server: Used for data analysis, emotion recognition, database search, and map data generation.

[1654] Terminal: The device (e.g., computer, smartphone) on which the user enters information and checks results.

[1655] Generative AI models: Used to analyze user input (e.g., GPT-4).

[1656] Emotion engine: Used to recognize the user's emotions.

[1657] Databases: Geographical databases, demographic data, competitor data, etc.

[1658] Online map service APIs: Used to generate and display map data (e.g., Google Maps API).

[1659] System processing flow

[1660] First, the user enters information about the business area and competitors into the chat interface on the device. For example, the user might enter, "I'm looking for an area in Tokyo with a large population but few cafes."

[1661] The terminal then encrypts the input data and sends it to the server using the TLS (Transport Layer Security) protocol.

[1662] The server receives the encrypted data, decrypts it, and then analyzes the input text using a generative AI model, extracting conditions such as "within Tokyo," "high population," and "few cafes."

[1663] The server then uses an emotion engine to recognize emotions from the user's input and interactions. For example, it can detect emotions such as "worry" or "expectation" in the user's input.

[1664] Based on the analysis results and emotion recognition data, the server searches specified databases, including geographic information databases, demographic data, and competitor store databases.

[1665] Depending on the search results, the server provides adaptive feedback that matches the user's emotional state. For example, if the server detects that the user is anxious, it will present reassuring information such as past success stories and risk mitigation measures.

[1666] The server then lists specific potential locations and obtains the latitude and longitude of each area. The identified areas (such as Shinjuku Ward or Shibuya Ward) are then analyzed in more detail to obtain information about each location (e.g., population density, number of existing cafes).

[1667] The server uses an online map service API (e.g., Google Maps API) to map potential locations for store openings on a map, and adds appropriate information to each location as a pop-up display.

[1668] The generated map data is sent to the device, and the user can view detailed information about the candidate locations on an interactive map. For example, the user can click on a marker on the map to view detailed information about each candidate location.

[1669] Specific examples

[1670] Scenario: A user is thinking about opening a new cafe and wants to find areas in Tokyo that are densely populated but have few cafes.

[1671] 1. User input:

[1672] The user types into the device's chat interface, "I'm looking for an area in Tokyo with a high population but few cafes."

[1673] 2. Data transmission:

[1674] The terminal encrypts the input data via TLS and sends it to the server.

[1675] 3. Data Analysis:

[1676] The server decrypts the received data and uses a generative AI model to extract conditions such as "within Tokyo," "large population," and "few cafes."

[1677] 4. Emotion recognition:

[1678] The server uses an emotion engine to detect emotions such as "worry" or "expectation" from the user's input text and behavior.

[1679] 5. Database Search:

[1680] The server searches a geographic database, demographic data, and competitor store data to identify areas that meet the criteria (for example, Shinjuku Ward or Shibuya Ward).

[1681] 6. Adaptive Feedback:

[1682] If the user expresses "worried," the server presents past success stories and risk mitigation measures.

[1683] 7. Site Identification:

[1684] The server extracts more detailed candidate locations from the identified area and obtains their latitude and longitude information.

[1685] 8. Map data generation:

[1686] The server uses the Google Maps API to display the identified candidate locations on a map and adds detailed information (e.g., population density, number of existing cafes) to each candidate location as a pop-up.

[1687] 9. Map data transmission:

[1688] The server sends the generated map data to the terminal.

[1689] 10. Site confirmation:

[1690] The device displays map data to the user, who can click on each marker for more information.

[1691] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1692] Step 1:

[1693] User input of information

[1694] Users input trade area information and competitor information into the chat interface on their device.

[1695] Input: Enter the prompt text "I'm looking for an area in Tokyo with a high population and few cafes."

[1696] Output: The user's input data is obtained.

[1697] Step 2:

[1698] Data transmission by the terminal

[1699] The terminal encrypts the data entered by the user using TLS and sends it to the server.

[1700] Input: User input data is captured at the terminal.

[1701] Output: TLS encrypted data is generated and sent to the server.

[1702] Step 3:

[1703] Data reception and analysis by the server

[1704] The server receives and decrypts the encrypted data sent from the device, then uses a generative AI model (e.g., GPT-4) to analyze the received data and extract important keywords and conditions.

[1705] Input: TLS encrypted data is sent to the server.

[1706] Output: As a result of the analysis, conditions such as "within Tokyo," "large population," and "few cafes" are extracted.

[1707] Step 4:

[1708] Recognizing user emotions with an emotion engine

[1709] The server uses an emotion engine to recognize emotions based on user input and interactions, for example, detecting emotions such as "worry" or "anticipation."

[1710] Input: Analysis results and user input data.

[1711] Output: Recognition result of the user's emotional state.

[1712] Step 5:

[1713] Database search by server

[1714] Taking into account the output of the emotion engine, the server searches databases (e.g., geographic information databases, demographic data, competitor store data).

[1715] Input: Analysis results and emotion recognition results.

[1716] Output: Search results include a list of potential locations that match the criteria.

[1717] Step 6:

[1718] Adaptive feedback by the server

[1719] The server provides adaptive feedback based on the user's emotional state, for example, providing additional information such as success stories and risk mitigation strategies if the user is anxious.

[1720] Input: Emotion recognition results and search results.

[1721] Output: Adaptive feedback content.

[1722] Step 7:

[1723] Identification of potential store locations by the server

[1724] The server identifies the latitude and longitude information of specific candidate locations and then filters them to see if they match more specific criteria, such as Shinjuku Ward or Shibuya Ward.

[1725] Input: Search results.

[1726] Output: A detailed list of potential locations with their latitude and longitude coordinates.

[1727] Step 8:

[1728] Map data generation by the server

[1729] The server generates map data for the identified candidate locations using the Google Maps API, etc. Pop-up information such as population density and the number of existing cafes is added to each candidate location.

[1730] Input: A detailed list of potential store locations and their latitude and longitude information.

[1731] Output: The generated map data.

[1732] Step 9:

[1733] Sending map data to the device

[1734] The server sends the generated map data to the terminal.

[1735] Input: Generated map data.

[1736] Output: Interactive map data is sent to the device.

[1737] Step 10:

[1738] User review of candidate sites

[1739] The terminal displays the received map data to the user, who can click on markers on the map to check detailed information about each potential store location.

[1740] Input: Submitted map data.

[1741] Output: An interface where the user can view detailed information.

[1742] (Application example 2)

[1743] 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."

[1744] In today's business environment, selecting an appropriate location is extremely important, especially when opening a brick-and-mortar store. However, selecting a location requires a lot of time and effort, and the amount of commercial area and competitive information is complex and vast, making it difficult to efficiently analyze data and find the optimal candidate location. Furthermore, while there is a need to provide information that takes into account the psychological anxieties and expectations of prospective store owners, existing systems do not adequately address this need. Therefore, the present invention aims to provide a system that quickly and accurately identifies candidate locations for store openings while taking into account the user's emotions.

[1745] The identification process by the identification 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 providing an interactive interface for a user to input market information and competitive information, means for using a generative AI model to analyze market conditions and competitive information specified based on the user input, emotion analysis means for recognizing the user's emotion from the analyzed information, feedback provision means for providing adaptive feedback based on the user's emotion, database search means for identifying an optimal store candidate site, map data generation means for displaying the identified store candidate site on an online map, and means for providing the map data to the user online. This enables the user to quickly and accurately find an optimal store candidate site while reducing emotional anxiety.

[1746] "Market information" is data about commercial activity in a particular geographic area, such as market size, customer demographic characteristics, purchasing trends, and local economic trends.

[1747] "Competitive information" refers to information such as the number, location, size, type of business, and market share of competitors in a particular area.

[1748] An "interactive interface" is an input method that allows a user to communicate with a system using natural language, and is an interface that can take the form of a text box, chatbot, or similar.

[1749] A "generative AI model" is an artificial intelligence model that analyzes information entered by a user and extracts intent from that information, and uses natural language processing technology.

[1750] "Emotion analysis means" is a technology that recognizes a user's emotions from their input and interactions, and provides data based on those emotions.

[1751] A "feedback providing means" is a method for providing appropriate information or advice to a user, taking into consideration the user's feelings.

[1752] "Database search means" refers to a technique for searching and acquiring necessary information from related databases based on specified conditions.

[1753] The "map data generating means" is a method for generating data for displaying the specified information on a map and visually presenting it to the user.

[1754] "Online provision means" refers to the technology used to provide information and services to users via the Internet.

[1755] The system of the present invention supports the process of selecting a potential store location and includes the following means: It integrates various technologies to allow users to input market and competitive information and identify the most suitable potential store location.

[1756] System Configuration

[1757] The system consists of an interactive interface, a generative AI model, an emotion analysis means, a feedback provision means, a database search means, a map data generation means, and an online provision means.

[1758] Program processing flow

[1759] 1. User input

[1760] Users input market and competitive information using an interactive interface on their smartphones or PCs. A concrete example of a prompt might be, "Please tell me an area in Osaka City that has a lot of young people and few restaurants."

[1761] 2. Data analysis by the server

[1762] The user's input data is encrypted and securely transmitted to a server, where it is analyzed using a generative AI model (e.g., Hugging Face's "bert-base-multilingual-cased") to extract key terms.

[1763] 3. Emotion Analysis and Adaptive Feedback

[1764] The server uses emotion analysis to recognize emotions from the user's input. Based on the analysis results, if the user is feeling anxious or hopeful, it provides appropriate feedback accordingly. For example, providing additional information such as past success stories and risk mitigation measures can reassure the user.

[1765] 4. Criteria-based database search

[1766] Based on the criteria extracted by the generative AI model, a database search tool searches relevant databases such as market data, competitive information, and demographic data, thereby identifying areas that meet the criteria.

[1767] 5. Map data generation and online provision

[1768] Based on the latitude and longitude information of the identified candidate locations for store openings, the map data generation means generates a map using an online map service (e.g., Google Maps API). Pop-up information including detailed information such as population density and competitor information is also added to this map. The generated map data is provided to users online, allowing them to interactively check each candidate location.

[1769] Specific examples

[1770] For example, if a user inputs "Please tell me an area in Osaka City that has a lot of young people and few restaurants," the server analyzes this information using a generative AI model and extracts conditions such as "Osaka City," "Many young people," and "Few restaurants." At the same time, the emotion analysis means recognizes the user's emotions, such as expectations and anxieties, and provides feedback based on those. The database search means then searches for areas that meet the conditions, and the map data generation means plots candidate locations using the Google Maps API. As a result, the user can interactively check the map and obtain detailed information about each candidate location.

[1771] In this way, by using the system of the present invention, the user can quickly and accurately select the most suitable candidate site for opening a store while reducing emotional anxiety.

[1772] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1773] Step 1:

[1774] Users input market and competitive information using an interactive interface on their smartphone or PC. Specifically, they input a prompt such as, "Please tell me an area in Osaka City that has a lot of young people and few restaurants." This clarifies the conditions the user is looking for, and the subsequent processing begins.

[1775] Step 2:

[1776] The terminal encrypts the input data and sends it securely to the server. The terminal properly formats the user's input information and sends it securely using an encryption algorithm (e.g., AES). This protects the user's privacy.

[1777] Step 3:

[1778] The server decrypts the received encrypted data and analyzes the user's input using a generative AI model. Specifically, an AI model (e.g., bert-base-multilingual-cased) is used to extract conditions such as "Osaka city," "lots of young people," and "few restaurants" from the text data. This analysis clarifies the user's intent and specifies the conditions.

[1779] Step 4:

[1780] The server uses emotion analysis to recognize the user's emotions from the analyzed information. Specifically, it uses an emotion analysis model to identify emotions such as "anxiety" or "expectation" that the user is feeling. The results of emotion recognition enable it to provide adaptive feedback.

[1781] Step 5:

[1782] The server provides adaptive feedback based on the results of sentiment analysis. For example, if the user feels anxious, it provides additional information about past success stories and risk mitigation measures. This reduces the user's anxiety and provides a sense of security.

[1783] Step 6:

[1784] The server searches for relevant data from the specified database based on the conditions extracted by the generative AI model. Specifically, it searches demographic data, geographic information data, competing store data, etc. to identify areas that meet the conditions. The search results provide useful information to the user.

[1785] Step 7:

[1786] The server acquires the latitude and longitude information of the identified potential store locations and generates an online map using a map data generation method. Specifically, it uses the Google Maps API to map the potential locations. This map also includes detailed information such as the population density of each area and competitor information.

[1787] Step 8:

[1788] The server sends the generated map data to the user's device, allowing the user to interactively check the map data. By clicking on a marker on the map, the user can check detailed information about each candidate site and select the optimal store location. This step allows the user to quickly and accurately find the optimal store location.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] 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).

[1796] 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.

[1797] 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."

[1798] 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.

[1799] 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).

[1800] 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.

[1801] 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.

[1802] 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.

[1803] 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.

[1804] 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.

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] The following is further disclosed regarding the above embodiment.

[1811] (Claim 1)

[1812] means for providing an interactive interface for a user to input trade area information and competitive information;

[1813] A means for using a generative AI model to analyze trade area conditions and competitive information specified based on user input;

[1814] A database search means for identifying the most suitable candidate site for opening a store based on the above analysis;

[1815] a map data generating means for displaying the identified store candidate site on an online map;

[1816] means for providing the map data to users online;

[1817] A system including:

[1818] (Claim 2)

[1819] 2. The system according to claim 1, further comprising means for encrypting and transmitting the trade area information and competitive information input by the user.

[1820] (Claim 3)

[1821] 10. The system of claim 1, further comprising means for retrieving demographic and geographic information data from a designated database based on the analyzed trade area criteria and competitive information.

[1822] "Example 1"

[1823] (Claim 1)

[1824] means for providing an interactive interface for a user to input trade area information and competitive information;

[1825] A means for using a generative AI model to analyze trade area conditions and competitive information specified based on user input;

[1826] A database search means for identifying the most suitable candidate site for opening a store based on the above analysis;

[1827] a map data generating means for displaying the identified store candidate site on an online map;

[1828] means for providing the map data to users online;

[1829] A means by which a user can manipulate a marker on an online map to view detailed information;

[1830] A system including:

[1831] (Claim 2)

[1832] 2. The system according to claim 1, further comprising means for encrypting and transmitting the trade area information and competitive information input by the user.

[1833] (Claim 3)

[1834] 10. The system of claim 1, further comprising means for retrieving demographic and geographic information data from a designated database based on the analyzed trade area criteria and competitive information.

[1835] "Application Example 1"

[1836] (Claim 1)

[1837] means for providing an interactive interface for a user to input facility location information and efficiency criteria;

[1838] a means for using a generative AI model to analyze specified efficiency criteria and facility information based on user input;

[1839] a database search means for identifying the most suitable candidate placement site based on the analysis;

[1840] a map data generating means for displaying the identified placement candidate sites on an online map;

[1841] means for providing the map data to users online;

[1842] A system including:

[1843] (Claim 2)

[1844] 2. The system according to claim 1, further comprising means for encrypting and transmitting the facility location information and efficiency conditions input by the user.

[1845] (Claim 3)

[1846] 10. The system of claim 1, further comprising means for retrieving geographic information and related data from a designated database based on the analyzed efficiency conditions and facility information.

[1847] "Example 2: Combining Emotion Engines"

[1848] (Claim 1)

[1849] means for providing an interactive interface for a user to input trade area information and competitive information;

[1850] A means for using a generative AI model to analyze trade area conditions and competitive information specified based on user input;

[1851] A database search means for identifying the most suitable candidate site for opening a store based on the above analysis;

[1852] a map data generating means for displaying the identified store candidate site on an online map;

[1853] means for providing the map data to users online;

[1854] a means for using an emotion engine that analyzes user input and interactions to recognize emotions;

[1855] means for providing adaptive feedback based on said emotion recognition;

[1856] A system including:

[1857] (Claim 2)

[1858] 2. The system according to claim 1, further comprising means for encrypting and transmitting the trade area information and competitive information input by the user.

[1859] (Claim 3)

[1860] 10. The system of claim 1, further comprising means for retrieving demographic and geographic information data from a designated database based on the analyzed trade area criteria and competitive information.

[1861] "Application example 2 when combining emotion engines"

[1862] (Claim 1)

[1863] means for providing an interactive interface for a user to input market and competitive information;

[1864] a means for using a generative AI model to analyze specified market conditions and competitive information based on user input;

[1865] emotion analysis means for recognizing the emotion of the user from the analyzed information;

[1866] feedback providing means for providing adaptive feedback based on the user's emotions;

[1867] A database search means for identifying the best candidate locations for store openings;

[1868] a map data generating means for displaying the identified store candidate site on an online map;

[1869] means for providing the map data to users online;

[1870] A system including:

[1871] (Claim 2)

[1872] 10. The system of claim 1, further comprising means for encrypting and transmitting the market information and competitive information input by the user.

[1873] (Claim 3)

[1874] 10. The system of claim 1, further comprising means for retrieving demographic and geographic data from a designated database based on the analyzed market conditions and competitive information. [Explanation of symbols]

[1875] 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. means for providing an interactive interface for a user to input trade area information and competitive information; A means for using a generative AI model to analyze trade area conditions and competitive information specified based on user input; A database search means for identifying the most suitable candidate site for opening a store based on the above analysis; a map data generating means for displaying the identified store candidate site on an online map; means for providing the map data to users online; A system including:

2. 2. The system according to claim 1, further comprising means for encrypting and transmitting the trade area information and competitive information input by the user.

3. 10. The system of claim 1, further comprising means for retrieving demographic and geographic data from a designated database based on the analyzed trade area criteria and competitive information.

Images