System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting questionnaire data from consumers, a means for acquiring word-of-mouth data related with a store from a position information service, a means for integrating the collected questionnaire data and the acquired word-of-mouth data, and for analyzing the demand of the consumers, and a means for specifying and proposing a store opening candidate place based on the analyzed result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Companies and individuals planning to open new stores must invest a large amount of data and resources to determine where to open a store. Therefore, there is a need for a means to efficiently and accurately identify potential store locations. Furthermore, there is a problem that deciding on a store location without properly understanding consumer demand and the competitive situation increases business risk. To solve these problems, this invention aims to provide a system that integrates and analyzes consumer survey data and word-of-mouth data from location information services to suggest optimal store locations. [Means for solving the problem]

[0005] The system of the present invention includes the following means: a means for collecting survey data from consumers, a means for acquiring store-related word-of-mouth data from location information services, a means for integrating the collected survey data and acquired word-of-mouth data to analyze consumer demand, and a means for identifying and proposing potential store locations based on the analysis results. The means for analyzing consumer demand identifies demand based on age, gender, nearest station, and frequently used station, and also includes an analysis of competing stores. This allows companies and individuals considering opening new stores to efficiently and accurately find the optimal potential store locations.

[0006] "Consumer survey data" refers to information on consumers' responses to specific questions, and includes attribute information such as age, gender, nearest station, frequently used station, and type of store desired.

[0007] "Location information services" are services that provide information based on geographic location and refer to a means of obtaining word-of-mouth and rating data about specific areas or stores.

[0008] "Word-of-mouth data" refers to ratings and comments posted by consumers through location-based services about specific stores or areas, and serves as the basis for evaluating consumer satisfaction and demand.

[0009] "Means for analyzing demand" refers to methods and processes for identifying and assessing consumer demand based on consumer attributes such as age, gender, nearest station, and frequently used station, by integrating survey data collected from consumers and word-of-mouth data obtained from location-based services.

[0010] "Analysis of competing stores" refers to the process of collecting data on existing competing stores in the vicinity of a potential store location, analyzing the store's characteristics, services offered, consumer evaluations, etc., and evaluating the competitive conditions with a new store.

[0011] "Means for identifying and proposing potential store locations" refers to methods and processes for identifying the most suitable store location based on the results of consumer demand analysis and analysis of competing stores, and proposing the attractiveness and growth prospects of that location to companies and individuals. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This invention is a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to propose optimal candidate locations for opening a store. This system includes the following elements: a means for collecting survey data from consumers, a means for acquiring word-of-mouth data about stores from location information services, a means for integrating this data and analyzing consumer demand, a means for analyzing competing stores, and a means for identifying and proposing optimal candidate locations for opening a store based on the results of the analysis.

[0034] System program processing

[0035] 1. Survey collection

[0036] 1.1 A user visits a website or app and proceeds to the survey page.

[0037] 1.2 The terminal displays several questions to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.

[0038] 1.3 The user enters answers to each question, and once the input is complete, the device sends the data to the server.

[0039] 2. Data storage

[0040] 2.1 The server stores the received questionnaire response data in a database. The data is structured as attribute information such as age, gender, nearest station, frequently used station, and details of desired stores.

[0041] 3. Collecting word-of-mouth data

[0042] 3.1 The server uses an external API to obtain word-of-mouth information from a location-based service. For example, it obtains word-of-mouth data for cafes around Takadanobaba Station.

[0043] 3.2 The server organizes the acquired review data and stores it in a database. The review data is categorized into categories such as store name, review content, and rating.

[0044] 4. Data Analysis

[0045] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis using data analysis tools (e.g., Python and R) to identify consumer demand.

[0046] 4.2 The server will identify and evaluate consumer demand based on the consumer's age group, gender, nearest station, and frequently used station.

[0047] 5. Competitive analysis

[0048] 5.1 The server creates a list of competing stores around the target area.

[0049] 5.2 The server analyzes the characteristics of rival stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions with the new store.

[0050] 6. Proposal of the best location

[0051] 6.1 The server uses all the analysis results to identify the best potential locations for a restaurant, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[0052] 6.2 The server also calculates the predicted sales and growth prospects for potential locations and proposes them to businesses and individuals along with a list of potential locations.

[0053] 7. Providing Results

[0054] 7.1 The server compiles the analysis results in a report format and sends it to the user's terminal.

[0055] 7.2 The terminal displays the received report to the user. For example, it may present information such as, "The area around Takadanobaba Station is optimal. Reason: It meets consumer needs and has little competition."

[0056] Specific examples

[0057] Example: Planning to open a cafe near Takadanobaba Station

[0058] 1.1 The user visits the website and answers the survey.

[0059] 1.2 The terminal asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The terminal then sends this answer to the server.

[0060] 1.3 The server stores the data for "Station: Takadanobaba."

[0061] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[0062] 3.2 The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[0063] 4.1 The server combines the survey data and word-of-mouth data and analyzes that women in their 20s rate "cafes with spacious seating" highly.

[0064] 5.1 The server lists "competing cafes near Takadanobaba Station."

[0065] 5.2 The server analyzes that "none of the three competing cafes have spacious seating arrangements."

[0066] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0067] 6.2 The server calculates the forecast sales and growth prospects and calculates "expected monthly sales of 1 million yen or more."

[0068] 7.1 The server compiles all the results into a report and sends it to the user's device.

[0069] 7.2 The device displays the report to the user and informs them of the conclusion that "the Takadanobaba Station South Exit area is optimal."

[0070] This allows users to create optimal store opening plans in a data-driven manner.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used station, and types of stores they are interested in.

[0074] Step 2:

[0075] The terminal displays each question in the survey to the user in turn, allowing them to enter their answers. For example, "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?"

[0076] Step 3:

[0077] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently use, and "spacious cafe" as the store they want to visit.

[0078] Step 4:

[0079] The device temporarily stores the user's input, and once all answers have been entered, the data is sent to the server. This data is structured, for example, age is sent as numeric data and station names are sent as character strings.

[0080] Step 5:

[0081] The server stores the received survey data in a database, organizing it by categories such as age, gender, nearest station, frequently used station, and details of desired stores.

[0082] Step 6:

[0083] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0084] Step 7:

[0085] The server organizes the acquired review data and stores it in a database. The review data is stored in categories such as store name, review content, and rating points.

[0086] Step 8:

[0087] The server integrates the stored survey data and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[0088] Step 9:

[0089] The server assesses consumer demand based on age group, gender, nearest station, and frequently used stations, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0090] Step 10:

[0091] The server creates a list of competing stores in the target area and obtains the characteristics, services offered, consumer ratings, etc. of each competing store from a database.

[0092] Step 11:

[0093] The server analyzes competing stores and evaluates the competitive situation around potential locations, drawing conclusions such as, "There are no cafes with spacious seating arrangements near Takadanobaba Station."

[0094] Step 12:

[0095] The server integrates the results of consumer demand analysis and competitive analysis to identify the best potential locations for store openings.

[0096] Step 13:

[0097] The server calculates projected sales and growth potential for potential locations and compiles the results in a report that includes recommended locations, competitive analysis, and detailed consumer demand information.

[0098] Step 14:

[0099] The server sends the generated report to the user's terminal.

[0100] Step 15:

[0101] The terminal displays the received report to the user and provides suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0102] Example 1

[0103] 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."

[0104] With conventional store opening planning systems, it was difficult to accurately grasp consumer demand and identify the optimal store location. Furthermore, because the system was unable to analyze information on competing stores, it was not possible to formulate an effective store opening strategy. As a result, there was a high possibility that companies would make a mistake in choosing a store location, which would affect the success of their business.

[0105] 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.

[0106] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from location information services, data analysis means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, means for collecting information on competing stores in the target area and conducting a competitive analysis, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This makes it possible to more accurately identify consumer demand and propose optimal candidate locations for store openings while taking the competitive situation into consideration.

[0107] "Consumer survey data" refers to information such as age, gender, nearest station, frequently used station, and type of store desired that is entered and submitted by users via websites or apps.

[0108] "Location-based services" refers to external information services that provide store information and reviews within a specific geographic area, such as map apps and review sites.

[0109] "Word-of-mouth data" refers to information such as consumer ratings, impressions, and comments about each store obtained from location information services.

[0110] "Data analysis tools" are technological methods and tools that use collected and consolidated survey data and word-of-mouth data to analyze consumer demand and identify consumer needs. Specifically, this includes programming languages ​​and data analysis software.

[0111] "Competitive analysis" is a method of evaluating the competitiveness of a new store by collecting information on competing stores in a specific area and analyzing the characteristics, services offered, consumer evaluations, etc. of each competing store.

[0112] A "prospective store location" is a geographic location that is optimal for establishing a new store based on the results of data analysis and competitive analysis.

[0113] The "proposal means" is a means for generating a list of optimal candidate locations for store openings and forecast information based on the analysis results, and proposing these to companies and individuals.

[0114] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data from location information services to propose optimal candidate locations for store openings. The system aims to support effective store opening strategies by more accurately understanding consumer demand and taking into account the competitive situation.

[0115] Survey collection

[0116] 1. The user accesses a website or app and proceeds to the survey page. When the user accesses the page, the device displays pre-prepared questions (e.g., "How old are you?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.).

[0117] 2. The user enters answers to each question and presses the "Submit" button when they are finished. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0118] Data storage

[0119] 1. The server analyzes the received HTTP POST request and extracts the JSON data sent. The data is categorized into age, gender, nearest station, frequently used station, details of the desired store, etc.

[0120] 2. The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables, with each attribute inserted into the appropriate table column.

[0121] Collecting word-of-mouth data

[0122] 1. The server calls the API of a location information service (for example, Google Places API or Yelp API) to obtain store data for the specified area (for example, around Takadanobaba Station). Specifically, it sends an HTTP GET request to the API endpoint to obtain information such as the store name, reviews, and ratings.

[0123] 2. The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and saves it in the corresponding table in the database.

[0124] Data analysis

[0125] 1. The server uses a data analysis tool (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data, clean and preprocess the data, and calculate the necessary statistics.

[0126] 2. The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database.

[0127] Competitive analysis

[0128] 1. The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each store. This information is used to evaluate the competitiveness of new stores.

[0129] 2. The server analyzes the strengths and weaknesses of competing stores and evaluates the competitive environment in the potential store location.

[0130] Proposal of the best location

[0131] 1. The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal potential store locations, evaluating factors such as whether spacious seating is required and whether there are few competitors.

[0132] 2. The server calculates the projected sales and growth potential for each candidate site and generates a report with the final list of candidate sites and the projected information.

[0133] Providing results

[0134] 1. The server outputs the generated report in PDF or HTML format and sends it to the user's device, which receives and displays the report.

[0135] 2. For example, the report might include information such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0136] Specific examples

[0137] Example: Planning to open a cafe near Takadanobaba Station

[0138] Users visit the website and answer the survey.

[0139] The terminal asks, "Is Takadanobaba Station the station you frequently use?" and the user answers, "Yes." The terminal then sends this answer to the server.

[0140] The server stores the data for "Station: Takadanobaba."

[0141] The server uses the API of a location information service to obtain word-of-mouth data about cafes near Takadanobaba Station.

[0142] The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[0143] The server combines survey data and word-of-mouth data to analyze that women in their 20s rate "cafes with spacious seating" highly.

[0144] The server lists "competing cafes near Takadanobaba Station" and analyzes that "none of the three competing cafes have spacious seating arrangements."

[0145] The server concludes that the "Takadanobaba Station South Exit area" is optimal, calculates predicted sales and growth prospects, and calculates "expected monthly sales of over 1 million yen."

[0146] The server compiles all the results into a report and sends it to the user's terminal.

[0147] The terminal displays the report to the user and tells them the conclusion: "The Takadanobaba Station South Exit area is ideal."

[0148] Prompt Sentence Examples

[0149] "I'd like to analyze the optimal location for opening a cafe in a specific area. Please suggest the best candidate locations for opening a cafe based on survey data and word-of-mouth data from a location information service, including a competitive analysis."

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1: Survey collection

[0152] 1.1 A user visits a website or app and proceeds to a survey page. Input: User information and survey questions. Output: User-entered data.

[0153] 1.2 The device displays pre-prepared questions (e.g., "How old are you?", "What's your gender?", "What's the nearest station?", "Which station do you use most often?", "What kind of stores do you want to see?"). Specifically, it renders HTML and CSS to generate a user interface.

[0154] 1.3 The user enters answers to each question and presses the "Submit" button when complete. Input: User's answers to each question. Output: Answer data in JSON format. The device converts the input data to JSON format and sends it to the server as an HTTP POST request.

[0155] Step 2: Save data

[0156] 2.1 The server parses the received HTTP POST request and extracts the JSON data sent. Input: Survey data in JSON format. Output: Data to a structured database.

[0157] 2.2 The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables. Each attribute is inserted into the appropriate table column by connecting to the database and executing an SQL query to insert the data.

[0158] Step 3: Collect customer reviews

[0159] 3.1 The server calls the API of a location information service (for example, Google Places API or Yelp API) and obtains store data for the specified area (for example, around Takadanobaba Station). Input: API request. Output: Obtained review data. Specifically, the review data is obtained by sending an HTTP GET request to the API endpoint.

[0160] 3.2 The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and stores it in a database. Input: JSON-formatted review data. Output: Data in a structured database. Saving to the database is done using SQL queries.

[0161] Step 4: Data analysis

[0162] 4.1 The server uses data analysis tools (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data. Input: Survey data and review data in the database. Output: Analysis results. Specifically, the server performs data cleaning and preprocessing, and calculates statistics.

[0163] 4.2 The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database. Input: Preprocessed data. Output: Demand analysis results. Specific operations include applying algorithms to perform the analysis.

[0164] Step 5: Competitive analysis

[0165] 5.1 The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each competing store. Input: Competitor store data. Output: Competitor analysis results. Specific operations include collecting, organizing, and analyzing data.

[0166] 5.2 The server identifies the strengths and weaknesses of competing stores and evaluates the competitive conditions in potential store locations. Input: Competitive store characteristics information. Output: Competitive analysis report. Specific operations include applying a competitive evaluation algorithm.

[0167] Step 6: Propose the best location

[0168] 6.1 The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal candidate locations for store openings. Input: Demand analysis results and competitive analysis results. Output: List of optimal location candidates. Specifically, the server processes the integrated data using an algorithm to identify candidate locations that meet the conditions.

[0169] 6.2 The server calculates the sales and growth forecasts for each candidate site and generates a report. Input: Data for each candidate site. Output: Sales forecast and growth forecast. Specifically, the server applies the forecast model to calculate the figures and generate a report.

[0170] Step 7: Delivering results

[0171] 7.1 The server outputs the generated report in PDF or HTML format and sends it to the user's device. Input: Report of optimal location candidates. Output: Sent report. Specific operations include format conversion and sending as email or HTTP response.

[0172] 7.2 The terminal displays the received report to the user. Input: The sent report. Output: The result displayed on the user interface. Specifically, the terminal displays the report using an HTML rendering engine.

[0173] (Application example 1)

[0174] 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."

[0175] Previous systems for identifying potential store locations were designed for fixed stores and lacked the functionality to identify optimal stopping points for mobile stores. This made it difficult for companies and individuals operating mobile stores to create effective stopping plans based on consumer demand. Furthermore, since a sufficient analysis of competing stores was not performed, it was difficult to select the optimal location while taking competitive conditions into account.

[0176] 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.

[0177] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, and means for identifying and proposing stopping points for the mobile store. This makes it possible to identify and propose optimal stopping points for the mobile store based on consumer demand and the status of competing stores.

[0178] "Consumer" means any person or entity that purchases or uses a product or service.

[0179] "Survey data" refers to data collected from consumers that includes information such as age, gender, nearest station, frequently used station, and desired type of store.

[0180] "Location-Based Service" means an online or offline service that provides information about the geographic location of an object.

[0181] "Word-of-mouth data" is text data that includes consumer ratings, opinions, and reviews of stores and services.

[0182] "Consumer demand" refers to the wants and expectations that consumers have for a particular product or service.

[0183] A "mobile store" is a store that can operate in various locations rather than being confined to a specific fixed location.

[0184] A "stop" is a location where a mobile store temporarily stops its vehicles to serve customers.

[0185] A "competitor store" is a store that offers products or services in the same category and serves customers in the same geographic area.

[0186] "Analysis" is the process of examining data in detail to reveal its content and characteristics.

[0187] "Suggestion" is the act of giving instructions or advice on the best course of action or plan.

[0188] A specific system configuration and processing will be described below as an embodiment of the present invention.

[0189] This invention relates to a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to suggest optimal stopping points for mobile stores.

[0190] Program processing

[0191] 1. Survey collection

[0192] 1.1 Users access the survey using a smartphone application and answer questions about their age, gender, nearest station, frequently used station, desired type of store, etc.

[0193] 1.2 The smartphone sends the user's answer to the server.

[0194] 2. Data storage

[0195] 2.1 The server stores the received survey data in a cloud database (e.g., Amazon RDS). The data is stored as structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[0196] 3. Collecting word-of-mouth data

[0197] 3.1 The server uses an external API (e.g., Google Maps API) to retrieve review data from location-based services.

[0198] 3.2 The server organizes the acquired review data and stores it in a cloud database. The review data is categorized into store name, review content, rating, etc.

[0199] 4. Data Analysis

[0200] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python and R).

[0201] 4.2 The server evaluates the consumer's demand based on the consumer's age group, gender, nearest station, and frequently used station.

[0202] 5. Competitive analysis

[0203] 5.1 The server creates a list of competing stores in the target area.

[0204] 5.2 The server analyzes the characteristics of competing stores, the services they offer, and consumer ratings, and evaluates the competitive conditions of the new mobile store.

[0205] 6. Optimal stopping point suggestions

[0206] 6.1 The server will then recommend optimal stops for the autonomous vehicle based on all the analysis results, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[0207] 6.2 The server calculates the projected sales and growth potential of the potential stops and provides the list to the user.

[0208] 7. Providing Results

[0209] 7.1 The server compiles the analysis results in the form of a report and sends it to the user's smartphone.

[0210] 7.2 The smartphone displays the received report to the user, presenting information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition."

[0211] Specific examples

[0212] When planning to open a mobile cafe near Meguro Station, a user first accesses the "SmartDrive Business" app and answers a questionnaire. If the user answers "Yes" to the question, "Is Meguro Station your favorite station?", that information is sent to the server. The server saves the data for "Station: Meguro" and uses the Google Maps API to retrieve reviews of cafes near Meguro Station. The server analyzes the data and determines that men in their 30s prefer cafes with spacious seating. The server then evaluates the situation of competing stores and suggests that the area around the east exit of Meguro Station is optimal.

[0213] For example, consider the following prompt:

[0214] "Analyze data showing that men in their 30s prefer cafes with spacious seating around Meguro Station, and identify the optimal stopping point for a mobile cafe in an autonomous vehicle."

[0215] This allows businesses and individuals to use a data-driven approach to plan mobile store stops that best meet consumer needs.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The user starts the smartphone application and accesses the survey. The survey displays questions such as age, gender, nearest station, frequently used station, and desired type of store. The user enters the survey data by typing in the answers to each question.

[0219] Step 2:

[0220] The terminal sends the questionnaire data entered by the user to the server. Specifically, the sent data includes structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[0221] Step 3:

[0222] The server stores the received survey data in a cloud database (e.g., Amazon RDS).,In this process, the user's survey data is used as input, and the,data stored in the cloud database is obtained as output.

[0223] Step 4:

[0224] The server calls an external API (e.g., Google Maps API) to obtain review data from the location information service. Specifically, review data about nearby stores is input.

[0225] Step 5:

[0226] The server organizes the acquired review data and stores it in a cloud database, where the data acquired from the API is used as input and the structured review data is output.

[0227] Step 6:

[0228] The server integrates the saved survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python or R). Specifically, it calculates average ratings and keyword frequency based on the input data to identify demand.

[0229] Step 7:

[0230] The server evaluates the demand based on the consumer's age group, gender, nearest station, and frequently used station, and identifies the consumer's specific demand. Using the integrated data as input, the server outputs the consumer's evaluation trend.

[0231] Step 8:

[0232] The server further uses the location information service API to create a list of competing stores in the target area. The acquired data is input, and the list of competing stores is output.

[0233] Step 9:

[0234] The server analyzes the characteristics of competing stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions of the new mobile store. It uses the list of competing stores and the integrated data as input, and outputs the competitive conditions.

[0235] Step 10:

[0236] The server then uses all the analysis results to identify and suggest optimal stops for the autonomous vehicle, evaluating criteria such as whether spacious seating is required or whether there is a lack of competitors. The aggregated data is used as input and the suggested stops are output.

[0237] Step 11:

[0238] The server calculates the projected revenue and growth potential of the proposed stops and compiles the list as a report, using the proposed stops and demand data as input and projected revenue as output.

[0239] Step 12:

[0240] The server sends the final report to the user's smartphone. The user's device displays the received report and provides information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition." Using the analysis results as input, a user-visible report is output.

[0241] 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.

[0242] This system integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal locations for opening stores. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[0243] System program processing

[0244] 1. Survey collection

[0245] 1.1 A user accesses a website or app and proceeds to a survey page, which displays questions to collect information such as age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the survey.

[0246] 1.2 The terminal displays each question in the survey to the user in turn and allows the user to enter answers, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?".

[0247] 1.3 The user answers each question and completes the input. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want, and "excited" as their emotion.

[0248] 1.4 The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numeric data, station names as character strings, and emotions as character strings.

[0249] 2. Data storage

[0250] 2.1 The server stores the received survey data and emotion data in a database. When storing the data, it organizes the data by categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[0251] 3. Collecting word-of-mouth data

[0252] 3.1 The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0253] 3.2 The server organizes the acquired review data, analyzes the emotional data in the reviews using the emotion engine, and stores the data in the database. The review data is classified into store name, review content, rating, and emotional data.

[0254] 4. Data Analysis

[0255] 4.1 The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[0256] 4.2 The server evaluates consumer demand based on the consumer's age group, gender, nearest station, frequently used station, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0257] 5. Competitive analysis

[0258] 5.1 The server creates a list of competitor stores around the target area and retrieves the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from the database.

[0259] 5.2 The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[0260] 6. Proposal of the best location

[0261] 6.1 The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal candidate location for a store. For example, it evaluates conditions such as "a spacious seating arrangement is required" and "there are few competitors" by taking into account consumer sentiment data.

[0262] 6.2 The server calculates the projected sales and growth potential for potential store locations and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis results, and consumer demand sentiment data.

[0263] 7. Providing Results

[0264] 7.1 The server sends the generated report to the user's device.

[0265] 7.2 The terminal displays the received report to the user, providing a proposal for opening a store, such as "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0266] Specific examples

[0267] Example: Planning to open a cafe near Takadanobaba Station

[0268] 1.1 The user visits the website and answers the survey.

[0269] 1.2 The device asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The device then asks, "How are you feeling right now?" and the user answers, "I'm excited."

[0270] 1.3 The terminal sends these response data to the server.

[0271] 2.1 The server stores the received data in a database.

[0272] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[0273] 3.2 The server organizes and stores the review content, rating points, and even emotion data using an emotion engine. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[0274] 4.1 The server combines the survey data, word-of-mouth data, and sentiment data and analyzes that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0275] 5.1 The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[0276] 5.2 The server analyzes that "there are no cafes with spacious seating arrangements around Takadanobaba Station."

[0277] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0278] 6.2 The server calculates the forecast sales and growth prospects and compiles them into a report.

[0279] 7.1 The server sends the report to the user's device.

[0280] 7.2 The device displays to the user, "The Takadanobaba Station South Exit area is the best location. Reason: It meets consumer needs (including emotional data) and has little competition."

[0281] In this way, by taking into consideration the user's emotional data, the accuracy of the store opening plan can be improved.

[0282] The processing flow will be explained below.

[0283] Step 1:

[0284] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used stations, types of stores they are interested in, and their emotional state.

[0285] Step 2:

[0286] The terminal sequentially displays each question in the questionnaire to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "Which station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?"

[0287] Step 3:

[0288] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want to visit, and "excited" as their emotion.

[0289] Step 4:

[0290] The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numerical data, station names as character strings, and emotions as character strings.

[0291] Step 5:

[0292] The server stores the received survey data and emotion data in a database. When storing the data, it organizes it into categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[0293] Step 6:

[0294] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0295] Step 7:

[0296] The server organizes the acquired review data, analyzes the emotional data in the reviews using an emotion engine, and stores the data in a database. The review data is categorized into store name, review content, rating, and emotional data.

[0297] Step 8:

[0298] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[0299] Step 9:

[0300] The server evaluates consumer demand based on age group, gender, nearest station, frequently used stations, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0301] Step 10:

[0302] The server creates a list of competing stores around the target area and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competing store from the database.

[0303] Step 11:

[0304] The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[0305] Step 12:

[0306] The server integrates the results of consumer demand analysis and competitive analysis, and identifies the most suitable potential locations for store openings, taking into account sentiment data as well.

[0307] Step 13:

[0308] The server calculates the projected sales and growth potential of each potential store location and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis, and sentiment data on consumer demand.

[0309] Step 14:

[0310] The server sends the generated report to the user's terminal.

[0311] Step 15:

[0312] The terminal displays the received report to the user, providing suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and sentiment and has little competition."

[0313] Example 2

[0314] 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."

[0315] In modern market analysis, identifying the right store location based on consumer demand is extremely important. However, traditional systems lacked the means to perform detailed demand analysis that combined consumer sentiment data and competitive analysis. As a result, store location selection was not based on true consumer demand, which risked reducing business success.

[0316] 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.

[0317] In this invention, the server includes means for collecting survey data from consumers, means for acquiring evaluation data on a target area from a location information service, means for integrating the collected survey data including emotional data at the time of responses with the acquired evaluation data to analyze consumer demand, means for analyzing the consumer emotional data, means for creating demand analysis results based on the integrated data, means for performing analysis including the characteristics of competing stores, means for evaluating areas with little competition and identifying and proposing candidate store locations, and means for transmitting the generated report to a terminal and displaying it. This enables highly accurate demand analysis that takes emotional data into consideration and the proposal of optimal candidate store locations with little competition.

[0318] "Means for collecting survey data from consumers" refers to a system or function for collecting information on consumers' age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings at the time of response through a website or application.

[0319] "Means for obtaining evaluation data for a target area from a location information service" refers to a system or function for obtaining evaluation data, word-of-mouth data, store information, etc. for a specific area from an external location information service (e.g., a map API).

[0320] "Means for integrating the collected questionnaire data, including emotional data at the time of response, with the acquired evaluation data to analyze consumer demand" refers to a system or function that integrates the collected questionnaire data with the acquired evaluation data and analyzes it based on the consumer's age, gender, nearest station, frequently used station, desired store, and emotional data at the time of response.

[0321] "Means for analyzing consumer emotion data" refers to a system or function that uses an emotion engine or emotion analysis algorithm to analyze consumer emotions from survey and word-of-mouth data and utilizes that data.

[0322] "Means for creating demand analysis results based on the integrated data" refers to a system or function for analyzing the integrated questionnaire data and evaluation data and generating results that identify demand forecasts and demand trends.

[0323] "Means for conducting analysis including the characteristics of competing stores" refers to a system or function that analyzes the characteristics of competing stores in the vicinity of a potential store location, such as the services offered, reviews, and consumer sentiment data, and evaluates the competitive environment.

[0324] "Means for evaluating areas with little competition, identifying and proposing potential store locations" refers to a system or function that identifies optimal store locations with little competition based on the results of demand analysis and competitive analysis, and proposes those locations.

[0325] The "means for transmitting the generated report to the terminal and displaying it" is a system or function that generates the results of the demand analysis and the proposed store location in report format, and transmits and displays them on the user's terminal.

[0326] A "database" is a system or facility for structuring and storing collected, acquired, and analyzed data.

[0327] An "external API" is a programmatic interface for obtaining data from other services or platforms.

[0328] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal candidate locations for opening a store. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[0329] 1. Collecting survey data

[0330] A user accesses a website or application and proceeds to a survey page. This survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their emotions when answering the questions. For example, if a user answers "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "spacious cafe," and "excited," the data is temporarily stored on the device and then sent to the server.

[0331] 2. Data storage

[0332] The server stores the received survey data and user emotion data in a database. The database contains fields for age, gender, nearest station, frequently used station, desired store type, emotion, etc., and stores the data in a structured format.

[0333] 3. Collecting review data

[0334] The server uses an external API (such as a map API) to obtain review data for the target area. The server sends a request to obtain, for example, "review data for cafes around Takadanobaba Station." The obtained review data is then analyzed using an emotion engine and stored in a database along with emotion data. For example, data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun" are stored.

[0335] 4. Data Analysis

[0336] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python's pandas library or R). As a result of the analysis, trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station" are extracted.

[0337] 5. Competitive analysis

[0338] The server creates a list of competing stores in the target area and analyzes their features, services offered, ratings, and sentiment data. For example, the analysis may reveal that there is a lack of cafes with spacious seating arrangements around Takadanobaba Station.

[0339] 6. Proposal of potential locations for stores

[0340] The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is suitable because there is little competition." It then calculates forecast sales and growth prospects and generates a detailed report.

[0341] 7. Providing Results

[0342] The generated report is sent from the server to the user's device. The device then displays the received report to the user. For example, it may display information such as "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[0343] Specific examples

[0344] Example: Planning to open a cafe near Takadanobaba Station

[0345] 1. Survey collection

[0346] Users visit the website and answer the survey.

[0347] The device asks, "Is Takadanobaba Station your favorite station?", to which the user replies, "Yes." The device then asks, "How are you feeling right now?", to which the user replies, "I'm excited."

[0348] The terminal transmits these response data to the server.

[0349] 2. Data storage

[0350] The server stores the received data in a database.

[0351] 3. Collecting word-of-mouth data

[0352] The server uses a map API to obtain reviews of cafes near Takadanobaba Station.

[0353] The server organizes and stores the review content, rating points, and emotion data. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[0354] 4. Data Analysis

[0355] The server combines survey data, word-of-mouth data, and sentiment data to analyze that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0356] 5. Competitive analysis

[0357] The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[0358] 6. Proposal of potential locations for stores

[0359] The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0360] The server calculates the forecast sales and growth prospects and compiles them into a report.

[0361] 7. Providing Results

[0362] The server sends the report to the user's terminal.

[0363] The device will display to the user, "The Takadanobaba Station South Exit area is ideal. Reason: It meets consumer needs (including emotional data) and has little competition."

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

[0365] Step 1: Access the survey page

[0366] A user accesses a website or application and proceeds to a survey page. The survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the questions. For example, the screen may ask, "How old are you?" and the user may enter "30 years old."

[0367] Step 2: View the survey questions

[0368] The device displays each question of the survey to the user in turn, allowing the user to enter an answer. For example, the survey page may ask "What is your gender?", and the user may enter "female." The displayed answers are temporarily stored in the device.

[0369] Step 3: Send survey data

[0370] Once the user has completed answering all the questions, the device sends the temporarily saved data to the server, which receives data such as "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "want a spacious cafe," and "excited."

[0371] Step 4: Save your survey data

[0372] The server stores the received survey data and emotion data in a database. The stored data is structured into fields such as age, gender, nearest station, frequently used station, desired store type, emotion, etc. This makes subsequent analysis easier.

[0373] Step 5: Obtaining review data

[0374] The server uses an external API to obtain review data for a specific area from a location information service. For example, a request to obtain "review data for cafes around Takadanobaba Station" is sent to an external API (e.g., map API). The external API returns data such as the store name, review content, and rating score to the server.

[0375] Step 6: Analyze and store review data

[0376] The server uses an emotion engine to analyze the acquired review data and analyzes the emotional data in the reviews. For example, it extracts data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Enjoyable," and stores this data in a database. The saved data can be used for subsequent analysis.

[0377] Step 7: Data synthesis and analysis

[0378] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python's pandas library or R). For example, it extracts consumer demand trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station."

[0379] Step 8: Conduct a competitive analysis

[0380] The server creates a list of competing stores in the target area and analyzes the features, services offered, ratings, and sentiment data of each store. For example, it obtains a list of cafes around Takadanobaba Station and obtains the rating that there is a lack of cafes with spacious seating arrangements.

[0381] Step 9: Identify the best potential locations

[0382] The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is ideal because there is little competition."

[0383] Step 10: Propose potential locations and generate reports

[0384] The server calculates projected sales and growth potential for each identified potential store location and generates a detailed report that includes detailed information on recommended store locations, competitive analysis, and consumer demand and sentiment data.

[0385] Step 11: Serving and displaying results

[0386] The server sends the generated report to the user's device. The device then displays the received report to the user. For example, it might say, "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[0387] (Application example 2)

[0388] 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."

[0389] Conventional systems for proposing potential store locations take into account survey data and word-of-mouth data from location-based services, but do not perform highly accurate demand analysis using consumer sentiment data. As a result, it is difficult to grasp the essential needs of consumers, and there is a problem with low accuracy in identifying optimal candidate store locations.

[0390] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0391] In this invention, the server includes means for collecting survey data, means for acquiring word-of-mouth data from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data and analyzing demand taking into consideration consumer emotional data, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This enables advanced demand analysis that reflects consumer emotional data, and enables more accurate proposals of candidate locations for store openings.

[0392] "Survey Data" refers to information collected through surveys completed by consumers, including age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when completing the survey.

[0393] "Location-based services" means services that provide information based on geographic location, such as services that provide review data for a particular location.

[0394] "Word-of-mouth data" refers to information on ratings and reviews written by consumers about specific stores or services.

[0395] "Emotional data" refers to data that expresses consumer emotions and feelings in numerical or categorical terms, including consumer emotional information obtained using text analysis or emotion engines.

[0396] "Demand analysis" refers to the process of analyzing collected data to identify consumer needs and trends.

[0397] "Prospective Store Location" means a geographic area proposed for the opening of a new store.

[0398] "Competitor Store" refers to other stores in the same market that offer similar products or services.

[0399] An "emotion engine" refers to software or algorithms that analyze emotions from text, audio data, etc. and extract them as emotional data.

[0400] "Synthesis" refers to the process of bringing together data obtained from multiple different sources and analyzing it comprehensively.

[0401] "Optimal" refers to the most appropriate and effective state or location based on specific conditions or criteria.

[0402] This invention is a system that uses a smartphone application to collect survey data from consumers and integrates it with word-of-mouth data obtained from location information services to perform advanced demand analysis, including emotional data, and identify optimal candidate locations for opening a store. The system is configured as follows:

[0403] 1. Collecting survey data

[0404] Users answer the survey through a smartphone app. The device displays the survey items, such as age, gender, nearest station, frequently used station, type of store they are interested in, and their feelings when answering the survey. Once the user enters this information, the device sends the data to the server.

[0405] 2. Collecting and storing review data

[0406] The server uses an external API to obtain review data from location-based services. The obtained review data is analyzed using an emotion analysis engine (such as EmotionEngine) to extract emotional data. The review data and emotional data are organized and stored in a database.

[0407] 3. Data analysis

[0408] The server integrates survey data, word-of-mouth data, and sentiment data, and uses data analysis tools (e.g., Python and R libraries) to evaluate consumer demand, extracting demand trends based on specific age groups, genders, nearest stations, and frequently used stations.

[0409] 4. Identifying and proposing potential locations for stores

[0410] The server uses the saved data to analyze competing stores and sentiment analysis of word-of-mouth data. This allows it to propose optimal store locations that take into account the competitive situation in the surrounding area and consumer sentiment trends. The final proposal is generated in the form of a report and sent to the user's device.

[0411] Specific examples

[0412] For example, if the user is a 30-year-old woman who wants to open a cafe near Shinjuku Station, the system will collect data such as "Age: 30," "Gender: Female," "Nearest station: Shinjuku Station," "Frequently used station: Shinjuku Station," "Desired store: Spacious cafe," and "Current mood: Excited" through a questionnaire. The server will then integrate and analyze this data with word-of-mouth data obtained from location-based services (e.g., "Reviews about cafes around Takadanobaba Station") and, taking into account consumer emotional data, suggest that "the south exit of Takadanobaba Station is optimal." This allows the user to accurately identify potential locations for their store based on advanced demand analysis that incorporates emotional data.

[0413] Example prompts for generative AI models

[0414] "A 30-year-old female consumer is looking for a spacious cafe near Shinjuku Station. She is currently feeling excited. Please suggest the best location for a cafe based on the word-of-mouth data and sentiment analysis results around Shinjuku Station."

[0415] In this way, by taking into account user emotional data, the accuracy of store opening plans can be significantly improved.

[0416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0417] Program processing steps

[0418] Step 1:

[0419] The user opens the smartphone app and answers the survey.

[0420] The information entered by the user includes age, gender, nearest station, frequently used station, types of stores of interest, and emotions expressed when answering the questionnaire.

[0421] Input: Survey data entered by the user (age, gender, nearest station, frequently used station, stores of interest, emotions).

[0422] Output: Survey data temporarily saved on the device.

[0423] Step 2:

[0424] Once all questionnaire responses have been completed, the terminal transmits the data to the server.

[0425] The survey data is structured and sent to the server.

[0426] Input: Survey data temporarily saved on the device.

[0427] Output: Structured data sent to the server.

[0428] Step 3:

[0429] The server stores the received survey data in a database.

[0430] When saving, the data is organized by categories such as age, gender, nearest station, frequently used station, types of stores of interest, and emotional data.

[0431] Input: Structured data sent to the server.

[0432] Output: Survey data stored in a database.

[0433] Step 4:

[0434] The server uses an external API to obtain review data from location services.

[0435] For example, request cafe reviews data for a specific area.

[0436] Input: Review data request from server.

[0437] Output: Review data obtained from location services.

[0438] Step 5:

[0439] The server organizes the acquired word-of-mouth data and analyzes the emotional data in the reviews using an emotion engine.

[0440] The word-of-mouth data is classified into store name, word-of-mouth content, rating score, and sentiment data.

[0441] Input: Review data obtained from location services.

[0442] Output: Organized reviews and sentiment data stored in a database.

[0443] Step 6:

[0444] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[0445] This analysis extracts demand trends based on specific age groups, gender, nearest stations, and frequently used stations.

[0446] Input: Survey data, sentiment data, and word-of-mouth data stored in a database.

[0447] Output: Analysis results (demand trend).

[0448] Step 7:

[0449] The server creates a list of competitor stores and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from a database.

[0450] Conduct competitive analysis based on the data obtained.

[0451] Input: Competitor store data stored in the database.

[0452] Output: Competitive analysis results.

[0453] Step 8:

[0454] The server integrates the results of consumer demand analysis and competitive analysis to identify the most suitable candidate location for opening a store.

[0455] The proposed store locations are also calculated with projected sales and growth prospects, which are then compiled into a report.

[0456] Input: Demand analysis results, competitive analysis results.

[0457] Output: Potential store location proposals in report format.

[0458] Step 9:

[0459] The server sends the generated report to the user's terminal.

[0460] The user checks the proposed store location through the terminal.

[0461] Input: The report generated by the server.

[0462] Output: Report suggestion results displayed on the user's device.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] [Second embodiment]

[0467] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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).

[0473] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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."

[0479] This invention is a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to propose optimal candidate locations for opening a store. This system includes the following elements: a means for collecting survey data from consumers, a means for acquiring word-of-mouth data about stores from location information services, a means for integrating this data and analyzing consumer demand, a means for analyzing competing stores, and a means for identifying and proposing optimal candidate locations for opening a store based on the results of the analysis.

[0480] System program processing

[0481] 1. Survey collection

[0482] 1.1 A user visits a website or app and proceeds to the survey page.

[0483] 1.2 The terminal displays several questions to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.

[0484] 1.3 The user enters answers to each question, and once the input is complete, the device sends the data to the server.

[0485] 2. Data storage

[0486] 2.1 The server stores the received questionnaire response data in a database. The data is structured as attribute information such as age, gender, nearest station, frequently used station, and details of desired stores.

[0487] 3. Collecting word-of-mouth data

[0488] 3.1 The server uses an external API to obtain word-of-mouth information from a location-based service. For example, it obtains word-of-mouth data for cafes around Takadanobaba Station.

[0489] 3.2 The server organizes the acquired review data and stores it in a database. The review data is categorized into categories such as store name, review content, and rating.

[0490] 4. Data Analysis

[0491] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis using data analysis tools (e.g., Python and R) to identify consumer demand.

[0492] 4.2 The server will identify and evaluate consumer demand based on the consumer's age group, gender, nearest station, and frequently used station.

[0493] 5. Competitive analysis

[0494] 5.1 The server creates a list of competing stores around the target area.

[0495] 5.2 The server analyzes the characteristics of rival stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions with the new store.

[0496] 6. Proposal of the best location

[0497] 6.1 The server uses all the analysis results to identify the best potential locations for a restaurant, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[0498] 6.2 The server also calculates the predicted sales and growth prospects for potential locations and proposes them to businesses and individuals along with a list of potential locations.

[0499] 7. Providing Results

[0500] 7.1 The server compiles the analysis results in a report format and sends it to the user's terminal.

[0501] 7.2 The terminal displays the received report to the user. For example, it may present information such as, "The area around Takadanobaba Station is optimal. Reason: It meets consumer needs and has little competition."

[0502] Specific examples

[0503] Example: Planning to open a cafe near Takadanobaba Station

[0504] 1.1 The user visits the website and answers the survey.

[0505] 1.2 The terminal asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The terminal then sends this answer to the server.

[0506] 1.3 The server stores the data for "Station: Takadanobaba."

[0507] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[0508] 3.2 The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[0509] 4.1 The server combines the survey data and word-of-mouth data and analyzes that women in their 20s rate "cafes with spacious seating" highly.

[0510] 5.1 The server lists "competing cafes near Takadanobaba Station."

[0511] 5.2 The server analyzes that "none of the three competing cafes have spacious seating arrangements."

[0512] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0513] 6.2 The server calculates the forecast sales and growth prospects and calculates "expected monthly sales of 1 million yen or more."

[0514] 7.1 The server compiles all the results into a report and sends it to the user's device.

[0515] 7.2 The device displays the report to the user and informs them of the conclusion that "the Takadanobaba Station South Exit area is optimal."

[0516] This allows users to create optimal store opening plans in a data-driven manner.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used station, and types of stores they are interested in.

[0520] Step 2:

[0521] The terminal displays each question in the survey to the user in turn, allowing them to enter their answers. For example, "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?"

[0522] Step 3:

[0523] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently use, and "spacious cafe" as the store they want to visit.

[0524] Step 4:

[0525] The device temporarily stores the user's input, and once all answers have been entered, the data is sent to the server. This data is structured, for example, age is sent as numeric data and station names are sent as character strings.

[0526] Step 5:

[0527] The server stores the received survey data in a database, organizing it by categories such as age, gender, nearest station, frequently used station, and details of desired stores.

[0528] Step 6:

[0529] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0530] Step 7:

[0531] The server organizes the acquired review data and stores it in a database. The review data is stored in categories such as store name, review content, and rating points.

[0532] Step 8:

[0533] The server integrates the stored survey data and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[0534] Step 9:

[0535] The server assesses consumer demand based on age group, gender, nearest station, and frequently used stations, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0536] Step 10:

[0537] The server creates a list of competing stores in the target area and obtains the characteristics, services offered, consumer ratings, etc. of each competing store from a database.

[0538] Step 11:

[0539] The server analyzes competing stores and evaluates the competitive situation around potential locations, drawing conclusions such as, "There are no cafes with spacious seating arrangements near Takadanobaba Station."

[0540] Step 12:

[0541] The server integrates the results of consumer demand analysis and competitive analysis to identify the best potential locations for store openings.

[0542] Step 13:

[0543] The server calculates projected sales and growth potential for potential locations and compiles the results in a report that includes recommended locations, competitive analysis, and detailed consumer demand information.

[0544] Step 14:

[0545] The server sends the generated report to the user's terminal.

[0546] Step 15:

[0547] The terminal displays the received report to the user and provides suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0548] Example 1

[0549] 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."

[0550] With conventional store opening planning systems, it was difficult to accurately grasp consumer demand and identify the optimal store location. Furthermore, because the system was unable to analyze information on competing stores, it was not possible to formulate an effective store opening strategy. As a result, there was a high possibility that companies would make a mistake in choosing a store location, which would affect the success of their business.

[0551] 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.

[0552] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from location information services, data analysis means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, means for collecting information on competing stores in the target area and conducting a competitive analysis, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This makes it possible to more accurately identify consumer demand and propose optimal candidate locations for store openings while taking the competitive situation into consideration.

[0553] "Consumer survey data" refers to information such as age, gender, nearest station, frequently used station, and type of store desired that is entered and submitted by users via websites or apps.

[0554] "Location-based services" refers to external information services that provide store information and reviews within a specific geographic area, such as map apps and review sites.

[0555] "Word-of-mouth data" refers to information such as consumer ratings, impressions, and comments about each store obtained from location information services.

[0556] "Data analysis tools" are technological methods and tools that use collected and consolidated survey data and word-of-mouth data to analyze consumer demand and identify consumer needs. Specifically, this includes programming languages ​​and data analysis software.

[0557] "Competitive analysis" is a method of evaluating the competitiveness of a new store by collecting information on competing stores in a specific area and analyzing the characteristics, services offered, consumer evaluations, etc. of each competing store.

[0558] A "prospective store location" is a geographic location that is optimal for establishing a new store based on the results of data analysis and competitive analysis.

[0559] The "proposal means" is a means for generating a list of optimal candidate locations for store openings and forecast information based on the analysis results, and proposing these to companies and individuals.

[0560] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data from location information services to propose optimal candidate locations for store openings. The system aims to support effective store opening strategies by more accurately understanding consumer demand and taking into account the competitive situation.

[0561] Survey collection

[0562] 1. The user accesses a website or app and proceeds to the survey page. When the user accesses the page, the device displays pre-prepared questions (e.g., "How old are you?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.).

[0563] 2. The user enters answers to each question and presses the "Submit" button when they are finished. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0564] Data storage

[0565] 1. The server analyzes the received HTTP POST request and extracts the JSON data sent. The data is categorized into age, gender, nearest station, frequently used station, details of the desired store, etc.

[0566] 2. The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables, with each attribute inserted into the appropriate table column.

[0567] Collecting word-of-mouth data

[0568] 1. The server calls the API of a location information service (for example, Google Places API or Yelp API) to obtain store data for the specified area (for example, around Takadanobaba Station). Specifically, it sends an HTTP GET request to the API endpoint to obtain information such as the store name, reviews, and ratings.

[0569] 2. The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and saves it in the corresponding table in the database.

[0570] Data analysis

[0571] 1. The server uses a data analysis tool (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data, clean and preprocess the data, and calculate the necessary statistics.

[0572] 2. The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database.

[0573] Competitive analysis

[0574] 1. The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each store. This information is used to evaluate the competitiveness of new stores.

[0575] 2. The server analyzes the strengths and weaknesses of competing stores and evaluates the competitive environment in the potential store location.

[0576] Proposal of the best location

[0577] 1. The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal potential store locations, evaluating factors such as whether spacious seating is required and whether there are few competitors.

[0578] 2. The server calculates the projected sales and growth potential for each candidate site and generates a report with the final list of candidate sites and the projected information.

[0579] Providing results

[0580] 1. The server outputs the generated report in PDF or HTML format and sends it to the user's device, which receives and displays the report.

[0581] 2. For example, the report might include information such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0582] Specific examples

[0583] Example: Planning to open a cafe near Takadanobaba Station

[0584] Users visit the website and answer the survey.

[0585] The terminal asks, "Is Takadanobaba Station the station you frequently use?" and the user answers, "Yes." The terminal then sends this answer to the server.

[0586] The server stores the data for "Station: Takadanobaba."

[0587] The server uses the API of a location information service to obtain word-of-mouth data about cafes near Takadanobaba Station.

[0588] The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[0589] The server combines survey data and word-of-mouth data to analyze that women in their 20s rate "cafes with spacious seating" highly.

[0590] The server lists "competing cafes near Takadanobaba Station" and analyzes that "none of the three competing cafes have spacious seating arrangements."

[0591] The server concludes that the "Takadanobaba Station South Exit area" is optimal, calculates predicted sales and growth prospects, and calculates "expected monthly sales of over 1 million yen."

[0592] The server compiles all the results into a report and sends it to the user's terminal.

[0593] The terminal displays the report to the user and tells them the conclusion: "The Takadanobaba Station South Exit area is ideal."

[0594] Prompt Sentence Examples

[0595] "I'd like to analyze the optimal location for opening a cafe in a specific area. Please suggest the best candidate locations for opening a cafe based on survey data and word-of-mouth data from a location information service, including a competitive analysis."

[0596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0597] Step 1: Survey collection

[0598] 1.1 A user visits a website or app and proceeds to a survey page. Input: User information and survey questions. Output: User-entered data.

[0599] 1.2 The device displays pre-prepared questions (e.g., "How old are you?", "What's your gender?", "What's the nearest station?", "Which station do you use most often?", "What kind of stores do you want to see?"). Specifically, it renders HTML and CSS to generate a user interface.

[0600] 1.3 The user enters answers to each question and presses the "Submit" button when complete. Input: User's answers to each question. Output: Answer data in JSON format. The device converts the input data to JSON format and sends it to the server as an HTTP POST request.

[0601] Step 2: Save data

[0602] 2.1 The server parses the received HTTP POST request and extracts the JSON data sent. Input: Survey data in JSON format. Output: Data to a structured database.

[0603] 2.2 The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables. Each attribute is inserted into the appropriate table column by connecting to the database and executing an SQL query to insert the data.

[0604] Step 3: Collect customer reviews

[0605] 3.1 The server calls the API of a location information service (for example, Google Places API or Yelp API) and obtains store data for the specified area (for example, around Takadanobaba Station). Input: API request. Output: Obtained review data. Specifically, the review data is obtained by sending an HTTP GET request to the API endpoint.

[0606] 3.2 The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and stores it in a database. Input: JSON-formatted review data. Output: Data in a structured database. Saving to the database is done using SQL queries.

[0607] Step 4: Data analysis

[0608] 4.1 The server uses data analysis tools (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data. Input: Survey data and review data in the database. Output: Analysis results. Specifically, the server performs data cleaning and preprocessing, and calculates statistics.

[0609] 4.2 The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database. Input: Preprocessed data. Output: Demand analysis results. Specific operations include applying algorithms to perform the analysis.

[0610] Step 5: Competitive analysis

[0611] 5.1 The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each competing store. Input: Competitor store data. Output: Competitor analysis results. Specific operations include collecting, organizing, and analyzing data.

[0612] 5.2 The server identifies the strengths and weaknesses of competing stores and evaluates the competitive conditions in potential store locations. Input: Competitive store characteristics information. Output: Competitive analysis report. Specific operations include applying a competitive evaluation algorithm.

[0613] Step 6: Propose the best location

[0614] 6.1 The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal candidate locations for store openings. Input: Demand analysis results and competitive analysis results. Output: List of optimal location candidates. Specifically, the server processes the integrated data using an algorithm to identify candidate locations that meet the conditions.

[0615] 6.2 The server calculates the sales and growth forecasts for each candidate site and generates a report. Input: Data for each candidate site. Output: Sales forecast and growth forecast. Specifically, the server applies the forecast model to calculate the figures and generate a report.

[0616] Step 7: Delivering results

[0617] 7.1 The server outputs the generated report in PDF or HTML format and sends it to the user's device. Input: Report of optimal location candidates. Output: Sent report. Specific operations include format conversion and sending as email or HTTP response.

[0618] 7.2 The terminal displays the received report to the user. Input: The sent report. Output: The result displayed on the user interface. Specifically, the terminal displays the report using an HTML rendering engine.

[0619] (Application example 1)

[0620] 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."

[0621] Previous systems for identifying potential store locations were designed for fixed stores and lacked the functionality to identify optimal stopping points for mobile stores. This made it difficult for companies and individuals operating mobile stores to create effective stopping plans based on consumer demand. Furthermore, since a sufficient analysis of competing stores was not performed, it was difficult to select the optimal location while taking competitive conditions into account.

[0622] 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.

[0623] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, and means for identifying and proposing stopping points for the mobile store. This makes it possible to identify and propose optimal stopping points for the mobile store based on consumer demand and the status of competing stores.

[0624] "Consumer" means any person or entity that purchases or uses a product or service.

[0625] "Survey data" refers to data collected from consumers that includes information such as age, gender, nearest station, frequently used station, and desired type of store.

[0626] "Location-Based Service" means an online or offline service that provides information about the geographic location of an object.

[0627] "Word-of-mouth data" is text data that includes consumer ratings, opinions, and reviews of stores and services.

[0628] "Consumer demand" refers to the wants and expectations that consumers have for a particular product or service.

[0629] A "mobile store" is a store that can operate in various locations rather than being confined to a specific fixed location.

[0630] A "stop" is a location where a mobile store temporarily stops its vehicles to serve customers.

[0631] A "competitor store" is a store that offers products or services in the same category and serves customers in the same geographic area.

[0632] "Analysis" is the process of examining data in detail to reveal its content and characteristics.

[0633] "Suggestion" is the act of giving instructions or advice on the best course of action or plan.

[0634] A specific system configuration and processing will be described below as an embodiment of the present invention.

[0635] This invention relates to a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to suggest optimal stopping points for mobile stores.

[0636] Program processing

[0637] 1. Survey collection

[0638] 1.1 Users access the survey using a smartphone application and answer questions about their age, gender, nearest station, frequently used station, desired type of store, etc.

[0639] 1.2 The smartphone sends the user's answer to the server.

[0640] 2. Data storage

[0641] 2.1 The server stores the received survey data in a cloud database (e.g., Amazon RDS). The data is stored as structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[0642] 3. Collecting word-of-mouth data

[0643] 3.1 The server uses an external API (e.g., Google Maps API) to retrieve review data from location-based services.

[0644] 3.2 The server organizes the acquired review data and stores it in a cloud database. The review data is categorized into store name, review content, rating, etc.

[0645] 4. Data Analysis

[0646] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python and R).

[0647] 4.2 The server evaluates the consumer's demand based on the consumer's age group, gender, nearest station, and frequently used station.

[0648] 5. Competitive analysis

[0649] 5.1 The server creates a list of competing stores in the target area.

[0650] 5.2 The server analyzes the characteristics of competing stores, the services they offer, and consumer ratings, and evaluates the competitive conditions of the new mobile store.

[0651] 6. Optimal stopping point suggestions

[0652] 6.1 The server will then recommend optimal stops for the autonomous vehicle based on all the analysis results, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[0653] 6.2 The server calculates the projected sales and growth potential of the potential stops and provides the list to the user.

[0654] 7. Providing Results

[0655] 7.1 The server compiles the analysis results in the form of a report and sends it to the user's smartphone.

[0656] 7.2 The smartphone displays the received report to the user, presenting information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition."

[0657] Specific examples

[0658] When planning to open a mobile cafe near Meguro Station, a user first accesses the "SmartDrive Business" app and answers a questionnaire. If the user answers "Yes" to the question, "Is Meguro Station your favorite station?", that information is sent to the server. The server saves the data for "Station: Meguro" and uses the Google Maps API to retrieve reviews of cafes near Meguro Station. The server analyzes the data and determines that men in their 30s prefer cafes with spacious seating. The server then evaluates the situation of competing stores and suggests that the area around the east exit of Meguro Station is optimal.

[0659] For example, consider the following prompt:

[0660] "Analyze data showing that men in their 30s prefer cafes with spacious seating around Meguro Station, and identify the optimal stopping point for a mobile cafe in an autonomous vehicle."

[0661] This allows businesses and individuals to use a data-driven approach to plan mobile store stops that best meet consumer needs.

[0662] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0663] Step 1:

[0664] The user starts the smartphone application and accesses the survey. The survey displays questions such as age, gender, nearest station, frequently used station, and desired type of store. The user enters the survey data by typing in the answers to each question.

[0665] Step 2:

[0666] The terminal sends the questionnaire data entered by the user to the server. Specifically, the sent data includes structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[0667] Step 3:

[0668] The server stores the received survey data in a cloud database (e.g., Amazon RDS).,In this process, the user's survey data is used as input, and the,data stored in the cloud database is obtained as output.

[0669] Step 4:

[0670] The server calls an external API (e.g., Google Maps API) to obtain review data from the location information service. Specifically, review data about nearby stores is input.

[0671] Step 5:

[0672] The server organizes the acquired review data and stores it in a cloud database, where the data acquired from the API is used as input and the structured review data is output.

[0673] Step 6:

[0674] The server integrates the saved survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python or R). Specifically, it calculates average ratings and keyword frequency based on the input data to identify demand.

[0675] Step 7:

[0676] The server evaluates the demand based on the consumer's age group, gender, nearest station, and frequently used station, and identifies the consumer's specific demand. Using the integrated data as input, the server outputs the consumer's evaluation trend.

[0677] Step 8:

[0678] The server further uses the location information service API to create a list of competing stores in the target area. The acquired data is input, and the list of competing stores is output.

[0679] Step 9:

[0680] The server analyzes the characteristics of competing stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions of the new mobile store. It uses the list of competing stores and the integrated data as input, and outputs the competitive conditions.

[0681] Step 10:

[0682] The server then uses all the analysis results to identify and suggest optimal stops for the autonomous vehicle, evaluating criteria such as whether spacious seating is required or whether there is a lack of competitors. The aggregated data is used as input and the suggested stops are output.

[0683] Step 11:

[0684] The server calculates the projected revenue and growth potential of the proposed stops and compiles the list as a report, using the proposed stops and demand data as input and projected revenue as output.

[0685] Step 12:

[0686] The server sends the final report to the user's smartphone. The user's device displays the received report and provides information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition." Using the analysis results as input, a user-visible report is output.

[0687] 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.

[0688] This system integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal locations for opening stores. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[0689] System program processing

[0690] 1. Survey collection

[0691] 1.1 A user accesses a website or app and proceeds to a survey page, which displays questions to collect information such as age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the survey.

[0692] 1.2 The terminal displays each question in the survey to the user in turn and allows the user to enter answers, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?".

[0693] 1.3 The user answers each question and completes the input. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want, and "excited" as their emotion.

[0694] 1.4 The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numeric data, station names as character strings, and emotions as character strings.

[0695] 2. Data storage

[0696] 2.1 The server stores the received survey data and emotion data in a database. When storing the data, it organizes the data by categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[0697] 3. Collecting word-of-mouth data

[0698] 3.1 The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0699] 3.2 The server organizes the acquired review data, analyzes the emotional data in the reviews using the emotion engine, and stores the data in the database. The review data is classified into store name, review content, rating, and emotional data.

[0700] 4. Data Analysis

[0701] 4.1 The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[0702] 4.2 The server evaluates consumer demand based on the consumer's age group, gender, nearest station, frequently used station, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0703] 5. Competitive analysis

[0704] 5.1 The server creates a list of competitor stores around the target area and retrieves the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from the database.

[0705] 5.2 The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[0706] 6. Proposal of the best location

[0707] 6.1 The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal candidate location for a store. For example, it evaluates conditions such as "a spacious seating arrangement is required" and "there are few competitors" by taking into account consumer sentiment data.

[0708] 6.2 The server calculates the projected sales and growth potential for potential store locations and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis results, and consumer demand sentiment data.

[0709] 7. Providing Results

[0710] 7.1 The server sends the generated report to the user's device.

[0711] 7.2 The terminal displays the received report to the user, providing a proposal for opening a store, such as "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0712] Specific examples

[0713] Example: Planning to open a cafe near Takadanobaba Station

[0714] 1.1 The user visits the website and answers the survey.

[0715] 1.2 The device asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The device then asks, "How are you feeling right now?" and the user answers, "I'm excited."

[0716] 1.3 The terminal sends these response data to the server.

[0717] 2.1 The server stores the received data in a database.

[0718] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[0719] 3.2 The server organizes and stores the review content, rating points, and even emotion data using an emotion engine. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[0720] 4.1 The server combines the survey data, word-of-mouth data, and sentiment data and analyzes that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0721] 5.1 The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[0722] 5.2 The server analyzes that "there are no cafes with spacious seating arrangements around Takadanobaba Station."

[0723] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0724] 6.2 The server calculates the forecast sales and growth prospects and compiles them into a report.

[0725] 7.1 The server sends the report to the user's device.

[0726] 7.2 The device displays to the user, "The Takadanobaba Station South Exit area is the best location. Reason: It meets consumer needs (including emotional data) and has little competition."

[0727] In this way, by taking into consideration the user's emotional data, the accuracy of the store opening plan can be improved.

[0728] The processing flow will be explained below.

[0729] Step 1:

[0730] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used stations, types of stores they are interested in, and their emotional state.

[0731] Step 2:

[0732] The terminal sequentially displays each question in the questionnaire to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "Which station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?"

[0733] Step 3:

[0734] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want to visit, and "excited" as their emotion.

[0735] Step 4:

[0736] The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numerical data, station names as character strings, and emotions as character strings.

[0737] Step 5:

[0738] The server stores the received survey data and emotion data in a database. When storing the data, it organizes it into categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[0739] Step 6:

[0740] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0741] Step 7:

[0742] The server organizes the acquired review data, analyzes the emotional data in the reviews using an emotion engine, and stores the data in a database. The review data is categorized into store name, review content, rating, and emotional data.

[0743] Step 8:

[0744] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[0745] Step 9:

[0746] The server evaluates consumer demand based on age group, gender, nearest station, frequently used stations, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0747] Step 10:

[0748] The server creates a list of competing stores around the target area and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competing store from the database.

[0749] Step 11:

[0750] The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[0751] Step 12:

[0752] The server integrates the results of consumer demand analysis and competitive analysis, and identifies the most suitable potential locations for store openings, taking into account sentiment data as well.

[0753] Step 13:

[0754] The server calculates the projected sales and growth potential of each potential store location and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis, and sentiment data on consumer demand.

[0755] Step 14:

[0756] The server sends the generated report to the user's terminal.

[0757] Step 15:

[0758] The terminal displays the received report to the user, providing suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and sentiment and has little competition."

[0759] Example 2

[0760] 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."

[0761] In modern market analysis, identifying the right store location based on consumer demand is extremely important. However, traditional systems lacked the means to perform detailed demand analysis that combined consumer sentiment data and competitive analysis. As a result, store location selection was not based on true consumer demand, which risked reducing business success.

[0762] 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.

[0763] In this invention, the server includes means for collecting survey data from consumers, means for acquiring evaluation data on a target area from a location information service, means for integrating the collected survey data including emotional data at the time of responses with the acquired evaluation data to analyze consumer demand, means for analyzing the consumer emotional data, means for creating demand analysis results based on the integrated data, means for performing analysis including the characteristics of competing stores, means for evaluating areas with little competition and identifying and proposing candidate store locations, and means for transmitting the generated report to a terminal and displaying it. This enables highly accurate demand analysis that takes emotional data into consideration and the proposal of optimal candidate store locations with little competition.

[0764] "Means for collecting survey data from consumers" refers to a system or function for collecting information on consumers' age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings at the time of response through a website or application.

[0765] "Means for obtaining evaluation data for a target area from a location information service" refers to a system or function for obtaining evaluation data, word-of-mouth data, store information, etc. for a specific area from an external location information service (e.g., a map API).

[0766] "Means for integrating the collected questionnaire data, including emotional data at the time of response, with the acquired evaluation data to analyze consumer demand" refers to a system or function that integrates the collected questionnaire data with the acquired evaluation data and analyzes it based on the consumer's age, gender, nearest station, frequently used station, desired store, and emotional data at the time of response.

[0767] "Means for analyzing consumer emotion data" refers to a system or function that uses an emotion engine or emotion analysis algorithm to analyze consumer emotions from survey and word-of-mouth data and utilizes that data.

[0768] "Means for creating demand analysis results based on the integrated data" refers to a system or function for analyzing the integrated questionnaire data and evaluation data and generating results that identify demand forecasts and demand trends.

[0769] "Means for conducting analysis including the characteristics of competing stores" refers to a system or function that analyzes the characteristics of competing stores in the vicinity of a potential store location, such as the services offered, reviews, and consumer sentiment data, and evaluates the competitive environment.

[0770] "Means for evaluating areas with little competition, identifying and proposing potential store locations" refers to a system or function that identifies optimal store locations with little competition based on the results of demand analysis and competitive analysis, and proposes those locations.

[0771] The "means for transmitting the generated report to the terminal and displaying it" is a system or function that generates the results of the demand analysis and the proposed store location in report format, and transmits and displays them on the user's terminal.

[0772] A "database" is a system or facility for structuring and storing collected, acquired, and analyzed data.

[0773] An "external API" is a programmatic interface for obtaining data from other services or platforms.

[0774] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal candidate locations for opening a store. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[0775] 1. Collecting survey data

[0776] A user accesses a website or application and proceeds to a survey page. This survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their emotions when answering the questions. For example, if a user answers "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "spacious cafe," and "excited," the data is temporarily stored on the device and then sent to the server.

[0777] 2. Data storage

[0778] The server stores the received survey data and user emotion data in a database. The database contains fields for age, gender, nearest station, frequently used station, desired store type, emotion, etc., and stores the data in a structured format.

[0779] 3. Collecting review data

[0780] The server uses an external API (such as a map API) to obtain review data for the target area. The server sends a request to obtain, for example, "review data for cafes around Takadanobaba Station." The obtained review data is then analyzed using an emotion engine and stored in a database along with emotion data. For example, data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun" are stored.

[0781] 4. Data Analysis

[0782] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python's pandas library or R). As a result of the analysis, trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station" are extracted.

[0783] 5. Competitive analysis

[0784] The server creates a list of competing stores in the target area and analyzes their features, services offered, ratings, and sentiment data. For example, the analysis may reveal that there is a lack of cafes with spacious seating arrangements around Takadanobaba Station.

[0785] 6. Proposal of potential locations for stores

[0786] The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is suitable because there is little competition." It then calculates forecast sales and growth prospects and generates a detailed report.

[0787] 7. Providing Results

[0788] The generated report is sent from the server to the user's device. The device then displays the received report to the user. For example, it may display information such as "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[0789] Specific examples

[0790] Example: Planning to open a cafe near Takadanobaba Station

[0791] 1. Survey collection

[0792] Users visit the website and answer the survey.

[0793] The device asks, "Is Takadanobaba Station your favorite station?", to which the user replies, "Yes." The device then asks, "How are you feeling right now?", to which the user replies, "I'm excited."

[0794] The terminal transmits these response data to the server.

[0795] 2. Data storage

[0796] The server stores the received data in a database.

[0797] 3. Collecting word-of-mouth data

[0798] The server uses a map API to obtain reviews of cafes near Takadanobaba Station.

[0799] The server organizes and stores the review content, rating points, and emotion data. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[0800] 4. Data Analysis

[0801] The server combines survey data, word-of-mouth data, and sentiment data to analyze that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0802] 5. Competitive analysis

[0803] The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[0804] 6. Proposal of potential locations for stores

[0805] The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0806] The server calculates the forecast sales and growth prospects and compiles them into a report.

[0807] 7. Providing Results

[0808] The server sends the report to the user's terminal.

[0809] The device will display to the user, "The Takadanobaba Station South Exit area is ideal. Reason: It meets consumer needs (including emotional data) and has little competition."

[0810] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0811] Step 1: Access the survey page

[0812] A user accesses a website or application and proceeds to a survey page. The survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the questions. For example, the screen may ask, "How old are you?" and the user may enter "30 years old."

[0813] Step 2: View the survey questions

[0814] The device displays each question of the survey to the user in turn, allowing the user to enter an answer. For example, the survey page may ask "What is your gender?", and the user may enter "female." The displayed answers are temporarily stored in the device.

[0815] Step 3: Send survey data

[0816] Once the user has completed answering all the questions, the device sends the temporarily saved data to the server, which receives data such as "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "want a spacious cafe," and "excited."

[0817] Step 4: Save your survey data

[0818] The server stores the received survey data and emotion data in a database. The stored data is structured into fields such as age, gender, nearest station, frequently used station, desired store type, emotion, etc. This makes subsequent analysis easier.

[0819] Step 5: Obtaining review data

[0820] The server uses an external API to obtain review data for a specific area from a location information service. For example, a request to obtain "review data for cafes around Takadanobaba Station" is sent to an external API (e.g., map API). The external API returns data such as the store name, review content, and rating score to the server.

[0821] Step 6: Analyze and store review data

[0822] The server uses an emotion engine to analyze the acquired review data and analyzes the emotional data in the reviews. For example, it extracts data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Enjoyable," and stores this data in a database. The saved data can be used for subsequent analysis.

[0823] Step 7: Data synthesis and analysis

[0824] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python's pandas library or R). For example, it extracts consumer demand trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station."

[0825] Step 8: Conduct a competitive analysis

[0826] The server creates a list of competing stores in the target area and analyzes the features, services offered, ratings, and sentiment data of each store. For example, it obtains a list of cafes around Takadanobaba Station and obtains the rating that there is a lack of cafes with spacious seating arrangements.

[0827] Step 9: Identify the best potential locations

[0828] The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is ideal because there is little competition."

[0829] Step 10: Propose potential locations and generate reports

[0830] The server calculates projected sales and growth potential for each identified potential store location and generates a detailed report that includes detailed information on recommended store locations, competitive analysis, and consumer demand and sentiment data.

[0831] Step 11: Serving and displaying results

[0832] The server sends the generated report to the user's device. The device then displays the received report to the user. For example, it might say, "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[0833] (Application example 2)

[0834] 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."

[0835] Conventional systems for proposing potential store locations take into account survey data and word-of-mouth data from location-based services, but do not perform highly accurate demand analysis using consumer sentiment data. As a result, it is difficult to grasp the essential needs of consumers, and there is a problem with low accuracy in identifying optimal candidate store locations.

[0836] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0837] In this invention, the server includes means for collecting survey data, means for acquiring word-of-mouth data from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data and analyzing demand taking into consideration consumer emotional data, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This enables advanced demand analysis that reflects consumer emotional data, and enables more accurate proposals of candidate locations for store openings.

[0838] "Survey Data" refers to information collected through surveys completed by consumers, including age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when completing the survey.

[0839] "Location-based services" means services that provide information based on geographic location, such as services that provide review data for a particular location.

[0840] "Word-of-mouth data" refers to information on ratings and reviews written by consumers about specific stores or services.

[0841] "Emotional data" refers to data that expresses consumer emotions and feelings in numerical or categorical terms, including consumer emotional information obtained using text analysis or emotion engines.

[0842] "Demand analysis" refers to the process of analyzing collected data to identify consumer needs and trends.

[0843] "Prospective Store Location" means a geographic area proposed for the opening of a new store.

[0844] "Competitor Store" refers to other stores in the same market that offer similar products or services.

[0845] An "emotion engine" refers to software or algorithms that analyze emotions from text, audio data, etc. and extract them as emotional data.

[0846] "Synthesis" refers to the process of bringing together data obtained from multiple different sources and analyzing it comprehensively.

[0847] "Optimal" refers to the most appropriate and effective state or location based on specific conditions or criteria.

[0848] This invention is a system that uses a smartphone application to collect survey data from consumers and integrates it with word-of-mouth data obtained from location information services to perform advanced demand analysis, including emotional data, and identify optimal candidate locations for opening a store. The system is configured as follows:

[0849] 1. Collecting survey data

[0850] Users answer the survey through a smartphone app. The device displays the survey items, such as age, gender, nearest station, frequently used station, type of store they are interested in, and their feelings when answering the survey. Once the user enters this information, the device sends the data to the server.

[0851] 2. Collecting and storing review data

[0852] The server uses an external API to obtain review data from location-based services. The obtained review data is analyzed using an emotion analysis engine (such as EmotionEngine) to extract emotional data. The review data and emotional data are organized and stored in a database.

[0853] 3. Data analysis

[0854] The server integrates survey data, word-of-mouth data, and sentiment data, and uses data analysis tools (e.g., Python and R libraries) to evaluate consumer demand, extracting demand trends based on specific age groups, genders, nearest stations, and frequently used stations.

[0855] 4. Identifying and proposing potential locations for stores

[0856] The server uses the saved data to analyze competing stores and sentiment analysis of word-of-mouth data. This allows it to propose optimal store locations that take into account the competitive situation in the surrounding area and consumer sentiment trends. The final proposal is generated in the form of a report and sent to the user's device.

[0857] Specific examples

[0858] For example, if the user is a 30-year-old woman who wants to open a cafe near Shinjuku Station, the system will collect data such as "Age: 30," "Gender: Female," "Nearest station: Shinjuku Station," "Frequently used station: Shinjuku Station," "Desired store: Spacious cafe," and "Current mood: Excited" through a questionnaire. The server will then integrate and analyze this data with word-of-mouth data obtained from location-based services (e.g., "Reviews about cafes around Takadanobaba Station") and, taking into account consumer emotional data, suggest that "the south exit of Takadanobaba Station is optimal." This allows the user to accurately identify potential locations for their store based on advanced demand analysis that incorporates emotional data.

[0859] Example prompts for generative AI models

[0860] "A 30-year-old female consumer is looking for a spacious cafe near Shinjuku Station. She is currently feeling excited. Please suggest the best location for a cafe based on the word-of-mouth data and sentiment analysis results around Shinjuku Station."

[0861] In this way, by taking into account user emotional data, the accuracy of store opening plans can be significantly improved.

[0862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0863] Program processing steps

[0864] Step 1:

[0865] The user opens the smartphone app and answers the survey.

[0866] The information entered by the user includes age, gender, nearest station, frequently used station, types of stores of interest, and emotions expressed when answering the questionnaire.

[0867] Input: Survey data entered by the user (age, gender, nearest station, frequently used station, stores of interest, emotions).

[0868] Output: Survey data temporarily saved on the device.

[0869] Step 2:

[0870] Once all questionnaire responses have been completed, the terminal transmits the data to the server.

[0871] The survey data is structured and sent to the server.

[0872] Input: Survey data temporarily saved on the device.

[0873] Output: Structured data sent to the server.

[0874] Step 3:

[0875] The server stores the received survey data in a database.

[0876] When saving, the data is organized by categories such as age, gender, nearest station, frequently used station, types of stores of interest, and emotional data.

[0877] Input: Structured data sent to the server.

[0878] Output: Survey data stored in a database.

[0879] Step 4:

[0880] The server uses an external API to obtain review data from location services.

[0881] For example, request cafe reviews data for a specific area.

[0882] Input: Review data request from server.

[0883] Output: Review data obtained from location services.

[0884] Step 5:

[0885] The server organizes the acquired word-of-mouth data and analyzes the emotional data in the reviews using an emotion engine.

[0886] The word-of-mouth data is classified into store name, word-of-mouth content, rating score, and sentiment data.

[0887] Input: Review data obtained from location services.

[0888] Output: Organized reviews and sentiment data stored in a database.

[0889] Step 6:

[0890] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[0891] This analysis extracts demand trends based on specific age groups, gender, nearest stations, and frequently used stations.

[0892] Input: Survey data, sentiment data, and word-of-mouth data stored in a database.

[0893] Output: Analysis results (demand trend).

[0894] Step 7:

[0895] The server creates a list of competitor stores and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from a database.

[0896] Conduct competitive analysis based on the data obtained.

[0897] Input: Competitor store data stored in the database.

[0898] Output: Competitive analysis results.

[0899] Step 8:

[0900] The server integrates the results of consumer demand analysis and competitive analysis to identify the most suitable candidate location for opening a store.

[0901] The proposed store locations are also calculated with projected sales and growth prospects, which are then compiled into a report.

[0902] Input: Demand analysis results, competitive analysis results.

[0903] Output: Potential store location proposals in report format.

[0904] Step 9:

[0905] The server sends the generated report to the user's terminal.

[0906] The user checks the proposed store location through the terminal.

[0907] Input: The report generated by the server.

[0908] Output: Report suggestion results displayed on the user's device.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] [Third embodiment]

[0913] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0914] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0915] 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).

[0916] 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.

[0917] 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.

[0918] 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).

[0919] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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."

[0925] This invention is a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to propose optimal candidate locations for opening a store. This system includes the following elements: a means for collecting survey data from consumers, a means for acquiring word-of-mouth data about stores from location information services, a means for integrating this data and analyzing consumer demand, a means for analyzing competing stores, and a means for identifying and proposing optimal candidate locations for opening a store based on the results of the analysis.

[0926] System program processing

[0927] 1. Survey collection

[0928] 1.1 A user visits a website or app and proceeds to the survey page.

[0929] 1.2 The terminal displays several questions to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.

[0930] 1.3 The user enters answers to each question, and once the input is complete, the device sends the data to the server.

[0931] 2. Data storage

[0932] 2.1 The server stores the received questionnaire response data in a database. The data is structured as attribute information such as age, gender, nearest station, frequently used station, and details of desired stores.

[0933] 3. Collecting word-of-mouth data

[0934] 3.1 The server uses an external API to obtain word-of-mouth information from a location-based service. For example, it obtains word-of-mouth data for cafes around Takadanobaba Station.

[0935] 3.2 The server organizes the acquired review data and stores it in a database. The review data is categorized into categories such as store name, review content, and rating.

[0936] 4. Data Analysis

[0937] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis using data analysis tools (e.g., Python and R) to identify consumer demand.

[0938] 4.2 The server will identify and evaluate consumer demand based on the consumer's age group, gender, nearest station, and frequently used station.

[0939] 5. Competitive analysis

[0940] 5.1 The server creates a list of competing stores around the target area.

[0941] 5.2 The server analyzes the characteristics of rival stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions with the new store.

[0942] 6. Proposal of the best location

[0943] 6.1 The server uses all the analysis results to identify the best potential locations for a restaurant, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[0944] 6.2 The server also calculates the predicted sales and growth prospects for potential locations and proposes them to businesses and individuals along with a list of potential locations.

[0945] 7. Providing Results

[0946] 7.1 The server compiles the analysis results in a report format and sends it to the user's terminal.

[0947] 7.2 The terminal displays the received report to the user. For example, it may present information such as, "The area around Takadanobaba Station is optimal. Reason: It meets consumer needs and has little competition."

[0948] Specific examples

[0949] Example: Planning to open a cafe near Takadanobaba Station

[0950] 1.1 The user visits the website and answers the survey.

[0951] 1.2 The terminal asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The terminal then sends this answer to the server.

[0952] 1.3 The server stores the data for "Station: Takadanobaba."

[0953] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[0954] 3.2 The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[0955] 4.1 The server combines the survey data and word-of-mouth data and analyzes that women in their 20s rate "cafes with spacious seating" highly.

[0956] 5.1 The server lists "competing cafes near Takadanobaba Station."

[0957] 5.2 The server analyzes that "none of the three competing cafes have spacious seating arrangements."

[0958] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[0959] 6.2 The server calculates the forecast sales and growth prospects and calculates "expected monthly sales of 1 million yen or more."

[0960] 7.1 The server compiles all the results into a report and sends it to the user's device.

[0961] 7.2 The device displays the report to the user and informs them of the conclusion that "the Takadanobaba Station South Exit area is optimal."

[0962] This allows users to create optimal store opening plans in a data-driven manner.

[0963] The processing flow will be explained below.

[0964] Step 1:

[0965] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used station, and types of stores they are interested in.

[0966] Step 2:

[0967] The terminal displays each question in the survey to the user in turn, allowing them to enter their answers. For example, "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?"

[0968] Step 3:

[0969] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently use, and "spacious cafe" as the store they want to visit.

[0970] Step 4:

[0971] The device temporarily stores the user's input, and once all answers have been entered, the data is sent to the server. This data is structured, for example, age is sent as numeric data and station names are sent as character strings.

[0972] Step 5:

[0973] The server stores the received survey data in a database, organizing it by categories such as age, gender, nearest station, frequently used station, and details of desired stores.

[0974] Step 6:

[0975] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[0976] Step 7:

[0977] The server organizes the acquired review data and stores it in a database. The review data is stored in categories such as store name, review content, and rating points.

[0978] Step 8:

[0979] The server integrates the stored survey data and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[0980] Step 9:

[0981] The server assesses consumer demand based on age group, gender, nearest station, and frequently used stations, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[0982] Step 10:

[0983] The server creates a list of competing stores in the target area and obtains the characteristics, services offered, consumer ratings, etc. of each competing store from a database.

[0984] Step 11:

[0985] The server analyzes competing stores and evaluates the competitive situation around potential locations, drawing conclusions such as, "There are no cafes with spacious seating arrangements near Takadanobaba Station."

[0986] Step 12:

[0987] The server integrates the results of consumer demand analysis and competitive analysis to identify the best potential locations for store openings.

[0988] Step 13:

[0989] The server calculates projected sales and growth potential for potential locations and compiles the results in a report that includes recommended locations, competitive analysis, and detailed consumer demand information.

[0990] Step 14:

[0991] The server sends the generated report to the user's terminal.

[0992] Step 15:

[0993] The terminal displays the received report to the user and provides suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[0994] Example 1

[0995] 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."

[0996] With conventional store opening planning systems, it was difficult to accurately grasp consumer demand and identify the optimal store location. Furthermore, because the system was unable to analyze information on competing stores, it was not possible to formulate an effective store opening strategy. As a result, there was a high possibility that companies would make a mistake in choosing a store location, which would affect the success of their business.

[0997] 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.

[0998] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from location information services, data analysis means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, means for collecting information on competing stores in the target area and conducting a competitive analysis, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This makes it possible to more accurately identify consumer demand and propose optimal candidate locations for store openings while taking the competitive situation into consideration.

[0999] "Consumer survey data" refers to information such as age, gender, nearest station, frequently used station, and type of store desired that is entered and submitted by users via websites or apps.

[1000] "Location-based services" refers to external information services that provide store information and reviews within a specific geographic area, such as map apps and review sites.

[1001] "Word-of-mouth data" refers to information such as consumer ratings, impressions, and comments about each store obtained from location information services.

[1002] "Data analysis tools" are technological methods and tools that use collected and consolidated survey data and word-of-mouth data to analyze consumer demand and identify consumer needs. Specifically, this includes programming languages ​​and data analysis software.

[1003] "Competitive analysis" is a method of evaluating the competitiveness of a new store by collecting information on competing stores in a specific area and analyzing the characteristics, services offered, consumer evaluations, etc. of each competing store.

[1004] A "prospective store location" is a geographic location that is optimal for establishing a new store based on the results of data analysis and competitive analysis.

[1005] The "proposal means" is a means for generating a list of optimal candidate locations for store openings and forecast information based on the analysis results, and proposing these to companies and individuals.

[1006] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data from location information services to propose optimal candidate locations for store openings. The system aims to support effective store opening strategies by more accurately understanding consumer demand and taking into account the competitive situation.

[1007] Survey collection

[1008] 1. The user accesses a website or app and proceeds to the survey page. When the user accesses the page, the device displays pre-prepared questions (e.g., "How old are you?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.).

[1009] 2. The user enters answers to each question and presses the "Submit" button when they are finished. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1010] Data storage

[1011] 1. The server analyzes the received HTTP POST request and extracts the JSON data sent. The data is categorized into age, gender, nearest station, frequently used station, details of the desired store, etc.

[1012] 2. The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables, with each attribute inserted into the appropriate table column.

[1013] Collecting word-of-mouth data

[1014] 1. The server calls the API of a location information service (for example, Google Places API or Yelp API) to obtain store data for the specified area (for example, around Takadanobaba Station). Specifically, it sends an HTTP GET request to the API endpoint to obtain information such as the store name, reviews, and ratings.

[1015] 2. The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and saves it in the corresponding table in the database.

[1016] Data analysis

[1017] 1. The server uses a data analysis tool (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data, clean and preprocess the data, and calculate the necessary statistics.

[1018] 2. The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database.

[1019] Competitive analysis

[1020] 1. The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each store. This information is used to evaluate the competitiveness of new stores.

[1021] 2. The server analyzes the strengths and weaknesses of competing stores and evaluates the competitive environment in the potential store location.

[1022] Proposal of the best location

[1023] 1. The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal potential store locations, evaluating factors such as whether spacious seating is required and whether there are few competitors.

[1024] 2. The server calculates the projected sales and growth potential for each candidate site and generates a report with the final list of candidate sites and the projected information.

[1025] Providing results

[1026] 1. The server outputs the generated report in PDF or HTML format and sends it to the user's device, which receives and displays the report.

[1027] 2. For example, the report might include information such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[1028] Specific examples

[1029] Example: Planning to open a cafe near Takadanobaba Station

[1030] Users visit the website and answer the survey.

[1031] The terminal asks, "Is Takadanobaba Station the station you frequently use?" and the user answers, "Yes." The terminal then sends this answer to the server.

[1032] The server stores the data for "Station: Takadanobaba."

[1033] The server uses the API of a location information service to obtain word-of-mouth data about cafes near Takadanobaba Station.

[1034] The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[1035] The server combines survey data and word-of-mouth data to analyze that women in their 20s rate "cafes with spacious seating" highly.

[1036] The server lists "competing cafes near Takadanobaba Station" and analyzes that "none of the three competing cafes have spacious seating arrangements."

[1037] The server concludes that the "Takadanobaba Station South Exit area" is optimal, calculates predicted sales and growth prospects, and calculates "expected monthly sales of over 1 million yen."

[1038] The server compiles all the results into a report and sends it to the user's terminal.

[1039] The terminal displays the report to the user and tells them the conclusion: "The Takadanobaba Station South Exit area is ideal."

[1040] Prompt Sentence Examples

[1041] "I'd like to analyze the optimal location for opening a cafe in a specific area. Please suggest the best candidate locations for opening a cafe based on survey data and word-of-mouth data from a location information service, including a competitive analysis."

[1042] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1043] Step 1: Survey collection

[1044] 1.1 A user visits a website or app and proceeds to a survey page. Input: User information and survey questions. Output: User-entered data.

[1045] 1.2 The device displays pre-prepared questions (e.g., "How old are you?", "What's your gender?", "What's the nearest station?", "Which station do you use most often?", "What kind of stores do you want to see?"). Specifically, it renders HTML and CSS to generate a user interface.

[1046] 1.3 The user enters answers to each question and presses the "Submit" button when complete. Input: User's answers to each question. Output: Answer data in JSON format. The device converts the input data to JSON format and sends it to the server as an HTTP POST request.

[1047] Step 2: Save data

[1048] 2.1 The server parses the received HTTP POST request and extracts the JSON data sent. Input: Survey data in JSON format. Output: Data to a structured database.

[1049] 2.2 The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables. Each attribute is inserted into the appropriate table column by connecting to the database and executing an SQL query to insert the data.

[1050] Step 3: Collect customer reviews

[1051] 3.1 The server calls the API of a location information service (for example, Google Places API or Yelp API) and obtains store data for the specified area (for example, around Takadanobaba Station). Input: API request. Output: Obtained review data. Specifically, the review data is obtained by sending an HTTP GET request to the API endpoint.

[1052] 3.2 The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and stores it in a database. Input: JSON-formatted review data. Output: Data in a structured database. Saving to the database is done using SQL queries.

[1053] Step 4: Data analysis

[1054] 4.1 The server uses data analysis tools (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data. Input: Survey data and review data in the database. Output: Analysis results. Specifically, the server performs data cleaning and preprocessing, and calculates statistics.

[1055] 4.2 The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database. Input: Preprocessed data. Output: Demand analysis results. Specific operations include applying algorithms to perform the analysis.

[1056] Step 5: Competitive analysis

[1057] 5.1 The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each competing store. Input: Competitor store data. Output: Competitor analysis results. Specific operations include collecting, organizing, and analyzing data.

[1058] 5.2 The server identifies the strengths and weaknesses of competing stores and evaluates the competitive conditions in potential store locations. Input: Competitive store characteristics information. Output: Competitive analysis report. Specific operations include applying a competitive evaluation algorithm.

[1059] Step 6: Propose the best location

[1060] 6.1 The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal candidate locations for store openings. Input: Demand analysis results and competitive analysis results. Output: List of optimal location candidates. Specifically, the server processes the integrated data using an algorithm to identify candidate locations that meet the conditions.

[1061] 6.2 The server calculates the sales and growth forecasts for each candidate site and generates a report. Input: Data for each candidate site. Output: Sales forecast and growth forecast. Specifically, the server applies the forecast model to calculate the figures and generate a report.

[1062] Step 7: Delivering results

[1063] 7.1 The server outputs the generated report in PDF or HTML format and sends it to the user's device. Input: Report of optimal location candidates. Output: Sent report. Specific operations include format conversion and sending as email or HTTP response.

[1064] 7.2 The terminal displays the received report to the user. Input: The sent report. Output: The result displayed on the user interface. Specifically, the terminal displays the report using an HTML rendering engine.

[1065] (Application example 1)

[1066] 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."

[1067] Previous systems for identifying potential store locations were designed for fixed stores and lacked the functionality to identify optimal stopping points for mobile stores. This made it difficult for companies and individuals operating mobile stores to create effective stopping plans based on consumer demand. Furthermore, since a sufficient analysis of competing stores was not performed, it was difficult to select the optimal location while taking competitive conditions into account.

[1068] 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.

[1069] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, and means for identifying and proposing stopping points for the mobile store. This makes it possible to identify and propose optimal stopping points for the mobile store based on consumer demand and the status of competing stores.

[1070] "Consumer" means any person or entity that purchases or uses a product or service.

[1071] "Survey data" refers to data collected from consumers that includes information such as age, gender, nearest station, frequently used station, and desired type of store.

[1072] "Location-Based Service" means an online or offline service that provides information about the geographic location of an object.

[1073] "Word-of-mouth data" is text data that includes consumer ratings, opinions, and reviews of stores and services.

[1074] "Consumer demand" refers to the wants and expectations that consumers have for a particular product or service.

[1075] A "mobile store" is a store that can operate in various locations rather than being confined to a specific fixed location.

[1076] A "stop" is a location where a mobile store temporarily stops its vehicles to serve customers.

[1077] A "competitor store" is a store that offers products or services in the same category and serves customers in the same geographic area.

[1078] "Analysis" is the process of examining data in detail to reveal its content and characteristics.

[1079] "Suggestion" is the act of giving instructions or advice on the best course of action or plan.

[1080] A specific system configuration and processing will be described below as an embodiment of the present invention.

[1081] This invention relates to a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to suggest optimal stopping points for mobile stores.

[1082] Program processing

[1083] 1. Survey collection

[1084] 1.1 Users access the survey using a smartphone application and answer questions about their age, gender, nearest station, frequently used station, desired type of store, etc.

[1085] 1.2 The smartphone sends the user's answer to the server.

[1086] 2. Data storage

[1087] 2.1 The server stores the received survey data in a cloud database (e.g., Amazon RDS). The data is stored as structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[1088] 3. Collecting word-of-mouth data

[1089] 3.1 The server uses an external API (e.g., Google Maps API) to retrieve review data from location-based services.

[1090] 3.2 The server organizes the acquired review data and stores it in a cloud database. The review data is categorized into store name, review content, rating, etc.

[1091] 4. Data Analysis

[1092] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python and R).

[1093] 4.2 The server evaluates the consumer's demand based on the consumer's age group, gender, nearest station, and frequently used station.

[1094] 5. Competitive analysis

[1095] 5.1 The server creates a list of competing stores in the target area.

[1096] 5.2 The server analyzes the characteristics of competing stores, the services they offer, and consumer ratings, and evaluates the competitive conditions of the new mobile store.

[1097] 6. Optimal stopping point suggestions

[1098] 6.1 The server will then recommend optimal stops for the autonomous vehicle based on all the analysis results, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[1099] 6.2 The server calculates the projected sales and growth potential of the potential stops and provides the list to the user.

[1100] 7. Providing Results

[1101] 7.1 The server compiles the analysis results in the form of a report and sends it to the user's smartphone.

[1102] 7.2 The smartphone displays the received report to the user, presenting information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition."

[1103] Specific examples

[1104] When planning to open a mobile cafe near Meguro Station, a user first accesses the "SmartDrive Business" app and answers a questionnaire. If the user answers "Yes" to the question, "Is Meguro Station your favorite station?", that information is sent to the server. The server saves the data for "Station: Meguro" and uses the Google Maps API to retrieve reviews of cafes near Meguro Station. The server analyzes the data and determines that men in their 30s prefer cafes with spacious seating. The server then evaluates the situation of competing stores and suggests that the area around the east exit of Meguro Station is optimal.

[1105] For example, consider the following prompt:

[1106] "Analyze data showing that men in their 30s prefer cafes with spacious seating around Meguro Station, and identify the optimal stopping point for a mobile cafe in an autonomous vehicle."

[1107] This allows businesses and individuals to use a data-driven approach to plan mobile store stops that best meet consumer needs.

[1108] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1109] Step 1:

[1110] The user starts the smartphone application and accesses the survey. The survey displays questions such as age, gender, nearest station, frequently used station, and desired type of store. The user enters the survey data by typing in the answers to each question.

[1111] Step 2:

[1112] The terminal sends the questionnaire data entered by the user to the server. Specifically, the sent data includes structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[1113] Step 3:

[1114] The server stores the received survey data in a cloud database (e.g., Amazon RDS).,In this process, the user's survey data is used as input, and the,data stored in the cloud database is obtained as output.

[1115] Step 4:

[1116] The server calls an external API (e.g., Google Maps API) to obtain review data from the location information service. Specifically, review data about nearby stores is input.

[1117] Step 5:

[1118] The server organizes the acquired review data and stores it in a cloud database, where the data acquired from the API is used as input and the structured review data is output.

[1119] Step 6:

[1120] The server integrates the saved survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python or R). Specifically, it calculates average ratings and keyword frequency based on the input data to identify demand.

[1121] Step 7:

[1122] The server evaluates the demand based on the consumer's age group, gender, nearest station, and frequently used station, and identifies the consumer's specific demand. Using the integrated data as input, the server outputs the consumer's evaluation trend.

[1123] Step 8:

[1124] The server further uses the location information service API to create a list of competing stores in the target area. The acquired data is input, and the list of competing stores is output.

[1125] Step 9:

[1126] The server analyzes the characteristics of competing stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions of the new mobile store. It uses the list of competing stores and the integrated data as input, and outputs the competitive conditions.

[1127] Step 10:

[1128] The server then uses all the analysis results to identify and suggest optimal stops for the autonomous vehicle, evaluating criteria such as whether spacious seating is required or whether there is a lack of competitors. The aggregated data is used as input and the suggested stops are output.

[1129] Step 11:

[1130] The server calculates the projected revenue and growth potential of the proposed stops and compiles the list as a report, using the proposed stops and demand data as input and projected revenue as output.

[1131] Step 12:

[1132] The server sends the final report to the user's smartphone. The user's device displays the received report and provides information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition." Using the analysis results as input, a user-visible report is output.

[1133] 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.

[1134] This system integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal locations for opening stores. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[1135] System program processing

[1136] 1. Survey collection

[1137] 1.1 A user accesses a website or app and proceeds to a survey page, which displays questions to collect information such as age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the survey.

[1138] 1.2 The terminal displays each question in the survey to the user in turn and allows the user to enter answers, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?".

[1139] 1.3 The user answers each question and completes the input. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want, and "excited" as their emotion.

[1140] 1.4 The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numeric data, station names as character strings, and emotions as character strings.

[1141] 2. Data storage

[1142] 2.1 The server stores the received survey data and emotion data in a database. When storing the data, it organizes the data by categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[1143] 3. Collecting word-of-mouth data

[1144] 3.1 The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[1145] 3.2 The server organizes the acquired review data, analyzes the emotional data in the reviews using the emotion engine, and stores the data in the database. The review data is classified into store name, review content, rating, and emotional data.

[1146] 4. Data Analysis

[1147] 4.1 The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[1148] 4.2 The server evaluates consumer demand based on the consumer's age group, gender, nearest station, frequently used station, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1149] 5. Competitive analysis

[1150] 5.1 The server creates a list of competitor stores around the target area and retrieves the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from the database.

[1151] 5.2 The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[1152] 6. Proposal of the best location

[1153] 6.1 The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal candidate location for a store. For example, it evaluates conditions such as "a spacious seating arrangement is required" and "there are few competitors" by taking into account consumer sentiment data.

[1154] 6.2 The server calculates the projected sales and growth potential for potential store locations and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis results, and consumer demand sentiment data.

[1155] 7. Providing Results

[1156] 7.1 The server sends the generated report to the user's device.

[1157] 7.2 The terminal displays the received report to the user, providing a proposal for opening a store, such as "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[1158] Specific examples

[1159] Example: Planning to open a cafe near Takadanobaba Station

[1160] 1.1 The user visits the website and answers the survey.

[1161] 1.2 The device asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The device then asks, "How are you feeling right now?" and the user answers, "I'm excited."

[1162] 1.3 The terminal sends these response data to the server.

[1163] 2.1 The server stores the received data in a database.

[1164] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[1165] 3.2 The server organizes and stores the review content, rating points, and even emotion data using an emotion engine. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[1166] 4.1 The server combines the survey data, word-of-mouth data, and sentiment data and analyzes that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1167] 5.1 The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[1168] 5.2 The server analyzes that "there are no cafes with spacious seating arrangements around Takadanobaba Station."

[1169] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[1170] 6.2 The server calculates the forecast sales and growth prospects and compiles them into a report.

[1171] 7.1 The server sends the report to the user's device.

[1172] 7.2 The device displays to the user, "The Takadanobaba Station South Exit area is the best location. Reason: It meets consumer needs (including emotional data) and has little competition."

[1173] In this way, by taking into consideration the user's emotional data, the accuracy of the store opening plan can be improved.

[1174] The processing flow will be explained below.

[1175] Step 1:

[1176] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used stations, types of stores they are interested in, and their emotional state.

[1177] Step 2:

[1178] The terminal sequentially displays each question in the questionnaire to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "Which station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?"

[1179] Step 3:

[1180] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want to visit, and "excited" as their emotion.

[1181] Step 4:

[1182] The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numerical data, station names as character strings, and emotions as character strings.

[1183] Step 5:

[1184] The server stores the received survey data and emotion data in a database. When storing the data, it organizes it into categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[1185] Step 6:

[1186] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[1187] Step 7:

[1188] The server organizes the acquired review data, analyzes the emotional data in the reviews using an emotion engine, and stores the data in a database. The review data is categorized into store name, review content, rating, and emotional data.

[1189] Step 8:

[1190] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[1191] Step 9:

[1192] The server evaluates consumer demand based on age group, gender, nearest station, frequently used stations, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1193] Step 10:

[1194] The server creates a list of competing stores around the target area and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competing store from the database.

[1195] Step 11:

[1196] The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[1197] Step 12:

[1198] The server integrates the results of consumer demand analysis and competitive analysis, and identifies the most suitable potential locations for store openings, taking into account sentiment data as well.

[1199] Step 13:

[1200] The server calculates the projected sales and growth potential of each potential store location and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis, and sentiment data on consumer demand.

[1201] Step 14:

[1202] The server sends the generated report to the user's terminal.

[1203] Step 15:

[1204] The terminal displays the received report to the user, providing suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and sentiment and has little competition."

[1205] Example 2

[1206] 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."

[1207] In modern market analysis, identifying the right store location based on consumer demand is extremely important. However, traditional systems lacked the means to perform detailed demand analysis that combined consumer sentiment data and competitive analysis. As a result, store location selection was not based on true consumer demand, which risked reducing business success.

[1208] 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.

[1209] In this invention, the server includes means for collecting survey data from consumers, means for acquiring evaluation data on a target area from a location information service, means for integrating the collected survey data including emotional data at the time of responses with the acquired evaluation data to analyze consumer demand, means for analyzing the consumer emotional data, means for creating demand analysis results based on the integrated data, means for performing analysis including the characteristics of competing stores, means for evaluating areas with little competition and identifying and proposing candidate store locations, and means for transmitting the generated report to a terminal and displaying it. This enables highly accurate demand analysis that takes emotional data into consideration and the proposal of optimal candidate store locations with little competition.

[1210] "Means for collecting survey data from consumers" refers to a system or function for collecting information on consumers' age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings at the time of response through a website or application.

[1211] "Means for obtaining evaluation data for a target area from a location information service" refers to a system or function for obtaining evaluation data, word-of-mouth data, store information, etc. for a specific area from an external location information service (e.g., a map API).

[1212] "Means for integrating the collected questionnaire data, including emotional data at the time of response, with the acquired evaluation data to analyze consumer demand" refers to a system or function that integrates the collected questionnaire data with the acquired evaluation data and analyzes it based on the consumer's age, gender, nearest station, frequently used station, desired store, and emotional data at the time of response.

[1213] "Means for analyzing consumer emotion data" refers to a system or function that uses an emotion engine or emotion analysis algorithm to analyze consumer emotions from survey and word-of-mouth data and utilizes that data.

[1214] "Means for creating demand analysis results based on the integrated data" refers to a system or function for analyzing the integrated questionnaire data and evaluation data and generating results that identify demand forecasts and demand trends.

[1215] "Means for conducting analysis including the characteristics of competing stores" refers to a system or function that analyzes the characteristics of competing stores in the vicinity of a potential store location, such as the services offered, reviews, and consumer sentiment data, and evaluates the competitive environment.

[1216] "Means for evaluating areas with little competition, identifying and proposing potential store locations" refers to a system or function that identifies optimal store locations with little competition based on the results of demand analysis and competitive analysis, and proposes those locations.

[1217] The "means for transmitting the generated report to the terminal and displaying it" is a system or function that generates the results of the demand analysis and the proposed store location in report format, and transmits and displays them on the user's terminal.

[1218] A "database" is a system or facility for structuring and storing collected, acquired, and analyzed data.

[1219] An "external API" is a programmatic interface for obtaining data from other services or platforms.

[1220] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal candidate locations for opening a store. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[1221] 1. Collecting survey data

[1222] A user accesses a website or application and proceeds to a survey page. This survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their emotions when answering the questions. For example, if a user answers "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "spacious cafe," and "excited," the data is temporarily stored on the device and then sent to the server.

[1223] 2. Data storage

[1224] The server stores the received survey data and user emotion data in a database. The database contains fields for age, gender, nearest station, frequently used station, desired store type, emotion, etc., and stores the data in a structured format.

[1225] 3. Collecting review data

[1226] The server uses an external API (such as a map API) to obtain review data for the target area. The server sends a request to obtain, for example, "review data for cafes around Takadanobaba Station." The obtained review data is then analyzed using an emotion engine and stored in a database along with emotion data. For example, data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun" are stored.

[1227] 4. Data Analysis

[1228] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python's pandas library or R). As a result of the analysis, trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station" are extracted.

[1229] 5. Competitive analysis

[1230] The server creates a list of competing stores in the target area and analyzes their features, services offered, ratings, and sentiment data. For example, the analysis may reveal that there is a lack of cafes with spacious seating arrangements around Takadanobaba Station.

[1231] 6. Proposal of potential locations for stores

[1232] The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is suitable because there is little competition." It then calculates forecast sales and growth prospects and generates a detailed report.

[1233] 7. Providing Results

[1234] The generated report is sent from the server to the user's device. The device then displays the received report to the user. For example, it may display information such as "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1235] Specific examples

[1236] Example: Planning to open a cafe near Takadanobaba Station

[1237] 1. Survey collection

[1238] Users visit the website and answer the survey.

[1239] The device asks, "Is Takadanobaba Station your favorite station?", to which the user replies, "Yes." The device then asks, "How are you feeling right now?", to which the user replies, "I'm excited."

[1240] The terminal transmits these response data to the server.

[1241] 2. Data storage

[1242] The server stores the received data in a database.

[1243] 3. Collecting word-of-mouth data

[1244] The server uses a map API to obtain reviews of cafes near Takadanobaba Station.

[1245] The server organizes and stores the review content, rating points, and emotion data. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[1246] 4. Data Analysis

[1247] The server combines survey data, word-of-mouth data, and sentiment data to analyze that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1248] 5. Competitive analysis

[1249] The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[1250] 6. Proposal of potential locations for stores

[1251] The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[1252] The server calculates the forecast sales and growth prospects and compiles them into a report.

[1253] 7. Providing Results

[1254] The server sends the report to the user's terminal.

[1255] The device will display to the user, "The Takadanobaba Station South Exit area is ideal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1: Access the survey page

[1258] A user accesses a website or application and proceeds to a survey page. The survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the questions. For example, the screen may ask, "How old are you?" and the user may enter "30 years old."

[1259] Step 2: View the survey questions

[1260] The device displays each question of the survey to the user in turn, allowing the user to enter an answer. For example, the survey page may ask "What is your gender?", and the user may enter "female." The displayed answers are temporarily stored in the device.

[1261] Step 3: Send survey data

[1262] Once the user has completed answering all the questions, the device sends the temporarily saved data to the server, which receives data such as "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "want a spacious cafe," and "excited."

[1263] Step 4: Save your survey data

[1264] The server stores the received survey data and emotion data in a database. The stored data is structured into fields such as age, gender, nearest station, frequently used station, desired store type, emotion, etc. This makes subsequent analysis easier.

[1265] Step 5: Obtaining review data

[1266] The server uses an external API to obtain review data for a specific area from a location information service. For example, a request to obtain "review data for cafes around Takadanobaba Station" is sent to an external API (e.g., map API). The external API returns data such as the store name, review content, and rating score to the server.

[1267] Step 6: Analyze and store review data

[1268] The server uses an emotion engine to analyze the acquired review data and analyzes the emotional data in the reviews. For example, it extracts data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Enjoyable," and stores this data in a database. The saved data can be used for subsequent analysis.

[1269] Step 7: Data synthesis and analysis

[1270] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python's pandas library or R). For example, it extracts consumer demand trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station."

[1271] Step 8: Conduct a competitive analysis

[1272] The server creates a list of competing stores in the target area and analyzes the features, services offered, ratings, and sentiment data of each store. For example, it obtains a list of cafes around Takadanobaba Station and obtains the rating that there is a lack of cafes with spacious seating arrangements.

[1273] Step 9: Identify the best potential locations

[1274] The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is ideal because there is little competition."

[1275] Step 10: Propose potential locations and generate reports

[1276] The server calculates projected sales and growth potential for each identified potential store location and generates a detailed report that includes detailed information on recommended store locations, competitive analysis, and consumer demand and sentiment data.

[1277] Step 11: Serving and displaying results

[1278] The server sends the generated report to the user's device. The device then displays the received report to the user. For example, it might say, "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1279] (Application example 2)

[1280] 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."

[1281] Conventional systems for proposing potential store locations take into account survey data and word-of-mouth data from location-based services, but do not perform highly accurate demand analysis using consumer sentiment data. As a result, it is difficult to grasp the essential needs of consumers, and there is a problem with low accuracy in identifying optimal candidate store locations.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1283] In this invention, the server includes means for collecting survey data, means for acquiring word-of-mouth data from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data and analyzing demand taking into consideration consumer emotional data, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This enables advanced demand analysis that reflects consumer emotional data, and enables more accurate proposals of candidate locations for store openings.

[1284] "Survey Data" refers to information collected through surveys completed by consumers, including age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when completing the survey.

[1285] "Location-based services" means services that provide information based on geographic location, such as services that provide review data for a particular location.

[1286] "Word-of-mouth data" refers to information on ratings and reviews written by consumers about specific stores or services.

[1287] "Emotional data" refers to data that expresses consumer emotions and feelings in numerical or categorical terms, including consumer emotional information obtained using text analysis or emotion engines.

[1288] "Demand analysis" refers to the process of analyzing collected data to identify consumer needs and trends.

[1289] "Prospective Store Location" means a geographic area proposed for the opening of a new store.

[1290] "Competitor Store" refers to other stores in the same market that offer similar products or services.

[1291] An "emotion engine" refers to software or algorithms that analyze emotions from text, audio data, etc. and extract them as emotional data.

[1292] "Synthesis" refers to the process of bringing together data obtained from multiple different sources and analyzing it comprehensively.

[1293] "Optimal" refers to the most appropriate and effective state or location based on specific conditions or criteria.

[1294] This invention is a system that uses a smartphone application to collect survey data from consumers and integrates it with word-of-mouth data obtained from location information services to perform advanced demand analysis, including emotional data, and identify optimal candidate locations for opening a store. The system is configured as follows:

[1295] 1. Collecting survey data

[1296] Users answer the survey through a smartphone app. The device displays the survey items, such as age, gender, nearest station, frequently used station, type of store they are interested in, and their feelings when answering the survey. Once the user enters this information, the device sends the data to the server.

[1297] 2. Collecting and storing review data

[1298] The server uses an external API to obtain review data from location-based services. The obtained review data is analyzed using an emotion analysis engine (such as EmotionEngine) to extract emotional data. The review data and emotional data are organized and stored in a database.

[1299] 3. Data analysis

[1300] The server integrates survey data, word-of-mouth data, and sentiment data, and uses data analysis tools (e.g., Python and R libraries) to evaluate consumer demand, extracting demand trends based on specific age groups, genders, nearest stations, and frequently used stations.

[1301] 4. Identifying and proposing potential locations for stores

[1302] The server uses the saved data to analyze competing stores and sentiment analysis of word-of-mouth data. This allows it to propose optimal store locations that take into account the competitive situation in the surrounding area and consumer sentiment trends. The final proposal is generated in the form of a report and sent to the user's device.

[1303] Specific examples

[1304] For example, if the user is a 30-year-old woman who wants to open a cafe near Shinjuku Station, the system will collect data such as "Age: 30," "Gender: Female," "Nearest station: Shinjuku Station," "Frequently used station: Shinjuku Station," "Desired store: Spacious cafe," and "Current mood: Excited" through a questionnaire. The server will then integrate and analyze this data with word-of-mouth data obtained from location-based services (e.g., "Reviews about cafes around Takadanobaba Station") and, taking into account consumer emotional data, suggest that "the south exit of Takadanobaba Station is optimal." This allows the user to accurately identify potential locations for their store based on advanced demand analysis that incorporates emotional data.

[1305] Example prompts for generative AI models

[1306] "A 30-year-old female consumer is looking for a spacious cafe near Shinjuku Station. She is currently feeling excited. Please suggest the best location for a cafe based on the word-of-mouth data and sentiment analysis results around Shinjuku Station."

[1307] In this way, by taking into account user emotional data, the accuracy of store opening plans can be significantly improved.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Program processing steps

[1310] Step 1:

[1311] The user opens the smartphone app and answers the survey.

[1312] The information entered by the user includes age, gender, nearest station, frequently used station, types of stores of interest, and emotions expressed when answering the questionnaire.

[1313] Input: Survey data entered by the user (age, gender, nearest station, frequently used station, stores of interest, emotions).

[1314] Output: Survey data temporarily saved on the device.

[1315] Step 2:

[1316] Once all questionnaire responses have been completed, the terminal transmits the data to the server.

[1317] The survey data is structured and sent to the server.

[1318] Input: Survey data temporarily saved on the device.

[1319] Output: Structured data sent to the server.

[1320] Step 3:

[1321] The server stores the received survey data in a database.

[1322] When saving, the data is organized by categories such as age, gender, nearest station, frequently used station, types of stores of interest, and emotional data.

[1323] Input: Structured data sent to the server.

[1324] Output: Survey data stored in a database.

[1325] Step 4:

[1326] The server uses an external API to obtain review data from location services.

[1327] For example, request cafe reviews data for a specific area.

[1328] Input: Review data request from server.

[1329] Output: Review data obtained from location services.

[1330] Step 5:

[1331] The server organizes the acquired word-of-mouth data and analyzes the emotional data in the reviews using an emotion engine.

[1332] The word-of-mouth data is classified into store name, word-of-mouth content, rating score, and sentiment data.

[1333] Input: Review data obtained from location services.

[1334] Output: Organized reviews and sentiment data stored in a database.

[1335] Step 6:

[1336] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[1337] This analysis extracts demand trends based on specific age groups, gender, nearest stations, and frequently used stations.

[1338] Input: Survey data, sentiment data, and word-of-mouth data stored in a database.

[1339] Output: Analysis results (demand trend).

[1340] Step 7:

[1341] The server creates a list of competitor stores and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from a database.

[1342] Conduct competitive analysis based on the data obtained.

[1343] Input: Competitor store data stored in the database.

[1344] Output: Competitive analysis results.

[1345] Step 8:

[1346] The server integrates the results of consumer demand analysis and competitive analysis to identify the most suitable candidate location for opening a store.

[1347] The proposed store locations are also calculated with projected sales and growth prospects, which are then compiled into a report.

[1348] Input: Demand analysis results, competitive analysis results.

[1349] Output: Potential store location proposals in report format.

[1350] Step 9:

[1351] The server sends the generated report to the user's terminal.

[1352] The user checks the proposed store location through the terminal.

[1353] Input: The report generated by the server.

[1354] Output: Report suggestion results displayed on the user's device.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] [Fourth embodiment]

[1359] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1360] 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.

[1361] 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).

[1362] 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.

[1363] 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.

[1364] 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).

[1365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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."

[1372] This invention is a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to propose optimal candidate locations for opening a store. This system includes the following elements: a means for collecting survey data from consumers, a means for acquiring word-of-mouth data about stores from location information services, a means for integrating this data and analyzing consumer demand, a means for analyzing competing stores, and a means for identifying and proposing optimal candidate locations for opening a store based on the results of the analysis.

[1373] System program processing

[1374] 1. Survey collection

[1375] 1.1 A user visits a website or app and proceeds to the survey page.

[1376] 1.2 The terminal displays several questions to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.

[1377] 1.3 The user enters answers to each question, and once the input is complete, the device sends the data to the server.

[1378] 2. Data storage

[1379] 2.1 The server stores the received questionnaire response data in a database. The data is structured as attribute information such as age, gender, nearest station, frequently used station, and details of desired stores.

[1380] 3. Collecting word-of-mouth data

[1381] 3.1 The server uses an external API to obtain word-of-mouth information from a location-based service. For example, it obtains word-of-mouth data for cafes around Takadanobaba Station.

[1382] 3.2 The server organizes the acquired review data and stores it in a database. The review data is categorized into categories such as store name, review content, and rating.

[1383] 4. Data Analysis

[1384] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis using data analysis tools (e.g., Python and R) to identify consumer demand.

[1385] 4.2 The server will identify and evaluate consumer demand based on the consumer's age group, gender, nearest station, and frequently used station.

[1386] 5. Competitive analysis

[1387] 5.1 The server creates a list of competing stores around the target area.

[1388] 5.2 The server analyzes the characteristics of rival stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions with the new store.

[1389] 6. Proposal of the best location

[1390] 6.1 The server uses all the analysis results to identify the best potential locations for a restaurant, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[1391] 6.2 The server also calculates the predicted sales and growth prospects for potential locations and proposes them to businesses and individuals along with a list of potential locations.

[1392] 7. Providing Results

[1393] 7.1 The server compiles the analysis results in a report format and sends it to the user's terminal.

[1394] 7.2 The terminal displays the received report to the user. For example, it may present information such as, "The area around Takadanobaba Station is optimal. Reason: It meets consumer needs and has little competition."

[1395] Specific examples

[1396] Example: Planning to open a cafe near Takadanobaba Station

[1397] 1.1 The user visits the website and answers the survey.

[1398] 1.2 The terminal asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The terminal then sends this answer to the server.

[1399] 1.3 The server stores the data for "Station: Takadanobaba."

[1400] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[1401] 3.2 The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[1402] 4.1 The server combines the survey data and word-of-mouth data and analyzes that women in their 20s rate "cafes with spacious seating" highly.

[1403] 5.1 The server lists "competing cafes near Takadanobaba Station."

[1404] 5.2 The server analyzes that "none of the three competing cafes have spacious seating arrangements."

[1405] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[1406] 6.2 The server calculates the forecast sales and growth prospects and calculates "expected monthly sales of 1 million yen or more."

[1407] 7.1 The server compiles all the results into a report and sends it to the user's device.

[1408] 7.2 The device displays the report to the user and informs them of the conclusion that "the Takadanobaba Station South Exit area is optimal."

[1409] This allows users to create optimal store opening plans in a data-driven manner.

[1410] The processing flow will be explained below.

[1411] Step 1:

[1412] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used station, and types of stores they are interested in.

[1413] Step 2:

[1414] The terminal displays each question in the survey to the user in turn, allowing them to enter their answers. For example, "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?"

[1415] Step 3:

[1416] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently use, and "spacious cafe" as the store they want to visit.

[1417] Step 4:

[1418] The device temporarily stores the user's input, and once all answers have been entered, the data is sent to the server. This data is structured, for example, age is sent as numeric data and station names are sent as character strings.

[1419] Step 5:

[1420] The server stores the received survey data in a database, organizing it by categories such as age, gender, nearest station, frequently used station, and details of desired stores.

[1421] Step 6:

[1422] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[1423] Step 7:

[1424] The server organizes the acquired review data and stores it in a database. The review data is stored in categories such as store name, review content, and rating points.

[1425] Step 8:

[1426] The server integrates the stored survey data and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[1427] Step 9:

[1428] The server assesses consumer demand based on age group, gender, nearest station, and frequently used stations, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1429] Step 10:

[1430] The server creates a list of competing stores in the target area and obtains the characteristics, services offered, consumer ratings, etc. of each competing store from a database.

[1431] Step 11:

[1432] The server analyzes competing stores and evaluates the competitive situation around potential locations, drawing conclusions such as, "There are no cafes with spacious seating arrangements near Takadanobaba Station."

[1433] Step 12:

[1434] The server integrates the results of consumer demand analysis and competitive analysis to identify the best potential locations for store openings.

[1435] Step 13:

[1436] The server calculates projected sales and growth potential for potential locations and compiles the results in a report that includes recommended locations, competitive analysis, and detailed consumer demand information.

[1437] Step 14:

[1438] The server sends the generated report to the user's terminal.

[1439] Step 15:

[1440] The terminal displays the received report to the user and provides suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[1441] Example 1

[1442] 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."

[1443] With conventional store opening planning systems, it was difficult to accurately grasp consumer demand and identify the optimal store location. Furthermore, because the system was unable to analyze information on competing stores, it was not possible to formulate an effective store opening strategy. As a result, there was a high possibility that companies would make a mistake in choosing a store location, which would affect the success of their business.

[1444] 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.

[1445] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from location information services, data analysis means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, means for collecting information on competing stores in the target area and conducting a competitive analysis, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This makes it possible to more accurately identify consumer demand and propose optimal candidate locations for store openings while taking the competitive situation into consideration.

[1446] "Consumer survey data" refers to information such as age, gender, nearest station, frequently used station, and type of store desired that is entered and submitted by users via websites or apps.

[1447] "Location-based services" refers to external information services that provide store information and reviews within a specific geographic area, such as map apps and review sites.

[1448] "Word-of-mouth data" refers to information such as consumer ratings, impressions, and comments about each store obtained from location information services.

[1449] "Data analysis tools" are technological methods and tools that use collected and consolidated survey data and word-of-mouth data to analyze consumer demand and identify consumer needs. Specifically, this includes programming languages ​​and data analysis software.

[1450] "Competitive analysis" is a method of evaluating the competitiveness of a new store by collecting information on competing stores in a specific area and analyzing the characteristics, services offered, consumer evaluations, etc. of each competing store.

[1451] A "prospective store location" is a geographic location that is optimal for establishing a new store based on the results of data analysis and competitive analysis.

[1452] The "proposal means" is a means for generating a list of optimal candidate locations for store openings and forecast information based on the analysis results, and proposing these to companies and individuals.

[1453] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data from location information services to propose optimal candidate locations for store openings. The system aims to support effective store opening strategies by more accurately understanding consumer demand and taking into account the competitive situation.

[1454] Survey collection

[1455] 1. The user accesses a website or app and proceeds to the survey page. When the user accesses the page, the device displays pre-prepared questions (e.g., "How old are you?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of stores do you want?", etc.).

[1456] 2. The user enters answers to each question and presses the "Submit" button when they are finished. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1457] Data storage

[1458] 1. The server analyzes the received HTTP POST request and extracts the JSON data sent. The data is categorized into age, gender, nearest station, frequently used station, details of the desired store, etc.

[1459] 2. The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables, with each attribute inserted into the appropriate table column.

[1460] Collecting word-of-mouth data

[1461] 1. The server calls the API of a location information service (for example, Google Places API or Yelp API) to obtain store data for the specified area (for example, around Takadanobaba Station). Specifically, it sends an HTTP GET request to the API endpoint to obtain information such as the store name, reviews, and ratings.

[1462] 2. The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and saves it in the corresponding table in the database.

[1463] Data analysis

[1464] 1. The server uses a data analysis tool (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data, clean and preprocess the data, and calculate the necessary statistics.

[1465] 2. The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database.

[1466] Competitive analysis

[1467] 1. The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each store. This information is used to evaluate the competitiveness of new stores.

[1468] 2. The server analyzes the strengths and weaknesses of competing stores and evaluates the competitive environment in the potential store location.

[1469] Proposal of the best location

[1470] 1. The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal potential store locations, evaluating factors such as whether spacious seating is required and whether there are few competitors.

[1471] 2. The server calculates the projected sales and growth potential for each candidate site and generates a report with the final list of candidate sites and the projected information.

[1472] Providing results

[1473] 1. The server outputs the generated report in PDF or HTML format and sends it to the user's device, which receives and displays the report.

[1474] 2. For example, the report might include information such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[1475] Specific examples

[1476] Example: Planning to open a cafe near Takadanobaba Station

[1477] Users visit the website and answer the survey.

[1478] The terminal asks, "Is Takadanobaba Station the station you frequently use?" and the user answers, "Yes." The terminal then sends this answer to the server.

[1479] The server stores the data for "Station: Takadanobaba."

[1480] The server uses the API of a location information service to obtain word-of-mouth data about cafes near Takadanobaba Station.

[1481] The server stores data such as "Cafe A," "Reviews," and "Rating: 4.5" in a database.

[1482] The server combines survey data and word-of-mouth data to analyze that women in their 20s rate "cafes with spacious seating" highly.

[1483] The server lists "competing cafes near Takadanobaba Station" and analyzes that "none of the three competing cafes have spacious seating arrangements."

[1484] The server concludes that the "Takadanobaba Station South Exit area" is optimal, calculates predicted sales and growth prospects, and calculates "expected monthly sales of over 1 million yen."

[1485] The server compiles all the results into a report and sends it to the user's terminal.

[1486] The terminal displays the report to the user and tells them the conclusion: "The Takadanobaba Station South Exit area is ideal."

[1487] Prompt Sentence Examples

[1488] "I'd like to analyze the optimal location for opening a cafe in a specific area. Please suggest the best candidate locations for opening a cafe based on survey data and word-of-mouth data from a location information service, including a competitive analysis."

[1489] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1490] Step 1: Survey collection

[1491] 1.1 A user visits a website or app and proceeds to a survey page. Input: User information and survey questions. Output: User-entered data.

[1492] 1.2 The device displays pre-prepared questions (e.g., "How old are you?", "What's your gender?", "What's the nearest station?", "Which station do you use most often?", "What kind of stores do you want to see?"). Specifically, it renders HTML and CSS to generate a user interface.

[1493] 1.3 The user enters answers to each question and presses the "Submit" button when complete. Input: User's answers to each question. Output: Answer data in JSON format. The device converts the input data to JSON format and sends it to the server as an HTTP POST request.

[1494] Step 2: Save data

[1495] 2.1 The server parses the received HTTP POST request and extracts the JSON data sent. Input: Survey data in JSON format. Output: Data to a structured database.

[1496] 2.2 The server uses a database management system (e.g., MySQL or PostgreSQL) to store this data in the corresponding tables. Each attribute is inserted into the appropriate table column by connecting to the database and executing an SQL query to insert the data.

[1497] Step 3: Collect customer reviews

[1498] 3.1 The server calls the API of a location information service (for example, Google Places API or Yelp API) and obtains store data for the specified area (for example, around Takadanobaba Station). Input: API request. Output: Obtained review data. Specifically, the review data is obtained by sending an HTTP GET request to the API endpoint.

[1499] 3.2 The server analyzes the acquired JSON-formatted review data, categorizes it into categories such as store name, review content, and rating, and stores it in a database. Input: JSON-formatted review data. Output: Data in a structured database. Saving to the database is done using SQL queries.

[1500] Step 4: Data analysis

[1501] 4.1 The server uses data analysis tools (such as Python's Pandas or R's dplyr library) to read the saved survey data and review data. Input: Survey data and review data in the database. Output: Analysis results. Specifically, the server performs data cleaning and preprocessing, and calculates statistics.

[1502] 4.2 The server identifies consumer demand using techniques such as clustering and regression analysis based on the consumer's age group, gender, nearest station, and frequently used station. The results are stored in a database. Input: Preprocessed data. Output: Demand analysis results. Specific operations include applying algorithms to perform the analysis.

[1503] Step 5: Competitive analysis

[1504] 5.1 The server creates a list of competing stores in the target area and analyzes information such as customer reviews, details of services offered, and pricing for each competing store. Input: Competitor store data. Output: Competitor analysis results. Specific operations include collecting, organizing, and analyzing data.

[1505] 5.2 The server identifies the strengths and weaknesses of competing stores and evaluates the competitive conditions in potential store locations. Input: Competitive store characteristics information. Output: Competitive analysis report. Specific operations include applying a competitive evaluation algorithm.

[1506] Step 6: Propose the best location

[1507] 6.1 The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal candidate locations for store openings. Input: Demand analysis results and competitive analysis results. Output: List of optimal location candidates. Specifically, the server processes the integrated data using an algorithm to identify candidate locations that meet the conditions.

[1508] 6.2 The server calculates the sales and growth forecasts for each candidate site and generates a report. Input: Data for each candidate site. Output: Sales forecast and growth forecast. Specifically, the server applies the forecast model to calculate the figures and generate a report.

[1509] Step 7: Delivering results

[1510] 7.1 The server outputs the generated report in PDF or HTML format and sends it to the user's device. Input: Report of optimal location candidates. Output: Sent report. Specific operations include format conversion and sending as email or HTTP response.

[1511] 7.2 The terminal displays the received report to the user. Input: The sent report. Output: The result displayed on the user interface. Specifically, the terminal displays the report using an HTML rendering engine.

[1512] (Application example 1)

[1513] 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."

[1514] Previous systems for identifying potential store locations were designed for fixed stores and lacked the functionality to identify optimal stopping points for mobile stores. This made it difficult for companies and individuals operating mobile stores to create effective stopping plans based on consumer demand. Furthermore, since a sufficient analysis of competing stores was not performed, it was difficult to select the optimal location while taking competitive conditions into account.

[1515] 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.

[1516] In this invention, the server includes means for collecting survey data from consumers, means for acquiring word-of-mouth data about stores from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data to analyze consumer demand, and means for identifying and proposing stopping points for the mobile store. This makes it possible to identify and propose optimal stopping points for the mobile store based on consumer demand and the status of competing stores.

[1517] "Consumer" means any person or entity that purchases or uses a product or service.

[1518] "Survey data" refers to data collected from consumers that includes information such as age, gender, nearest station, frequently used station, and desired type of store.

[1519] "Location-Based Service" means an online or offline service that provides information about the geographic location of an object.

[1520] "Word-of-mouth data" is text data that includes consumer ratings, opinions, and reviews of stores and services.

[1521] "Consumer demand" refers to the wants and expectations that consumers have for a particular product or service.

[1522] A "mobile store" is a store that can operate in various locations rather than being confined to a specific fixed location.

[1523] A "stop" is a location where a mobile store temporarily stops its vehicles to serve customers.

[1524] A "competitor store" is a store that offers products or services in the same category and serves customers in the same geographic area.

[1525] "Analysis" is the process of examining data in detail to reveal its content and characteristics.

[1526] "Suggestion" is the act of giving instructions or advice on the best course of action or plan.

[1527] A specific system configuration and processing will be described below as an embodiment of the present invention.

[1528] This invention relates to a system that integrates and analyzes survey data from consumers and word-of-mouth data from location information services to suggest optimal stopping points for mobile stores.

[1529] Program processing

[1530] 1. Survey collection

[1531] 1.1 Users access the survey using a smartphone application and answer questions about their age, gender, nearest station, frequently used station, desired type of store, etc.

[1532] 1.2 The smartphone sends the user's answer to the server.

[1533] 2. Data storage

[1534] 2.1 The server stores the received survey data in a cloud database (e.g., Amazon RDS). The data is stored as structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[1535] 3. Collecting word-of-mouth data

[1536] 3.1 The server uses an external API (e.g., Google Maps API) to retrieve review data from location-based services.

[1537] 3.2 The server organizes the acquired review data and stores it in a cloud database. The review data is categorized into store name, review content, rating, etc.

[1538] 4. Data Analysis

[1539] 4.1 The server integrates the stored survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python and R).

[1540] 4.2 The server evaluates the consumer's demand based on the consumer's age group, gender, nearest station, and frequently used station.

[1541] 5. Competitive analysis

[1542] 5.1 The server creates a list of competing stores in the target area.

[1543] 5.2 The server analyzes the characteristics of competing stores, the services they offer, and consumer ratings, and evaluates the competitive conditions of the new mobile store.

[1544] 6. Optimal stopping point suggestions

[1545] 6.1 The server will then recommend optimal stops for the autonomous vehicle based on all the analysis results, evaluating criteria such as whether spacious seating is required and whether there is a lack of competitors.

[1546] 6.2 The server calculates the projected sales and growth potential of the potential stops and provides the list to the user.

[1547] 7. Providing Results

[1548] 7.1 The server compiles the analysis results in the form of a report and sends it to the user's smartphone.

[1549] 7.2 The smartphone displays the received report to the user, presenting information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition."

[1550] Specific examples

[1551] When planning to open a mobile cafe near Meguro Station, a user first accesses the "SmartDrive Business" app and answers a questionnaire. If the user answers "Yes" to the question, "Is Meguro Station your favorite station?", that information is sent to the server. The server saves the data for "Station: Meguro" and uses the Google Maps API to retrieve reviews of cafes near Meguro Station. The server analyzes the data and determines that men in their 30s prefer cafes with spacious seating. The server then evaluates the situation of competing stores and suggests that the area around the east exit of Meguro Station is optimal.

[1552] For example, consider the following prompt:

[1553] "Analyze data showing that men in their 30s prefer cafes with spacious seating around Meguro Station, and identify the optimal stopping point for a mobile cafe in an autonomous vehicle."

[1554] This allows businesses and individuals to use a data-driven approach to plan mobile store stops that best meet consumer needs.

[1555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1556] Step 1:

[1557] The user starts the smartphone application and accesses the survey. The survey displays questions such as age, gender, nearest station, frequently used station, and desired type of store. The user enters the survey data by typing in the answers to each question.

[1558] Step 2:

[1559] The terminal sends the questionnaire data entered by the user to the server. Specifically, the sent data includes structured information such as age, gender, nearest station, frequently used station, and desired type of store.

[1560] Step 3:

[1561] The server stores the received survey data in a cloud database (e.g., Amazon RDS).,In this process, the user's survey data is used as input, and the,data stored in the cloud database is obtained as output.

[1562] Step 4:

[1563] The server calls an external API (e.g., Google Maps API) to obtain review data from the location information service. Specifically, review data about nearby stores is input.

[1564] Step 5:

[1565] The server organizes the acquired review data and stores it in a cloud database, where the data acquired from the API is used as input and the structured review data is output.

[1566] Step 6:

[1567] The server integrates the saved survey data and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python or R). Specifically, it calculates average ratings and keyword frequency based on the input data to identify demand.

[1568] Step 7:

[1569] The server evaluates the demand based on the consumer's age group, gender, nearest station, and frequently used station, and identifies the consumer's specific demand. Using the integrated data as input, the server outputs the consumer's evaluation trend.

[1570] Step 8:

[1571] The server further uses the location information service API to create a list of competing stores in the target area. The acquired data is input, and the list of competing stores is output.

[1572] Step 9:

[1573] The server analyzes the characteristics of competing stores, the services they offer, consumer ratings, etc., and evaluates the competitive conditions of the new mobile store. It uses the list of competing stores and the integrated data as input, and outputs the competitive conditions.

[1574] Step 10:

[1575] The server then uses all the analysis results to identify and suggest optimal stops for the autonomous vehicle, evaluating criteria such as whether spacious seating is required or whether there is a lack of competitors. The aggregated data is used as input and the suggested stops are output.

[1576] Step 11:

[1577] The server calculates the projected revenue and growth potential of the proposed stops and compiles the list as a report, using the proposed stops and demand data as input and projected revenue as output.

[1578] Step 12:

[1579] The server sends the final report to the user's smartphone. The user's device displays the received report and provides information such as, "The Meguro Station East Exit area is optimal. Reason: It meets consumer needs and has little competition." Using the analysis results as input, a user-visible report is output.

[1580] 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.

[1581] This system integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal locations for opening stores. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[1582] System program processing

[1583] 1. Survey collection

[1584] 1.1 A user accesses a website or app and proceeds to a survey page, which displays questions to collect information such as age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the survey.

[1585] 1.2 The terminal displays each question in the survey to the user in turn and allows the user to enter answers, such as "What is your age?", "What is your gender?", "What is the nearest station?", "What station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?".

[1586] 1.3 The user answers each question and completes the input. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want, and "excited" as their emotion.

[1587] 1.4 The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numeric data, station names as character strings, and emotions as character strings.

[1588] 2. Data storage

[1589] 2.1 The server stores the received survey data and emotion data in a database. When storing the data, it organizes the data by categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[1590] 3. Collecting word-of-mouth data

[1591] 3.1 The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[1592] 3.2 The server organizes the acquired review data, analyzes the emotional data in the reviews using the emotion engine, and stores the data in the database. The review data is classified into store name, review content, rating, and emotional data.

[1593] 4. Data Analysis

[1594] 4.1 The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to analyze it to identify consumer demand.

[1595] 4.2 The server evaluates consumer demand based on the consumer's age group, gender, nearest station, frequently used station, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1596] 5. Competitive analysis

[1597] 5.1 The server creates a list of competitor stores around the target area and retrieves the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from the database.

[1598] 5.2 The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[1599] 6. Proposal of the best location

[1600] 6.1 The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal candidate location for a store. For example, it evaluates conditions such as "a spacious seating arrangement is required" and "there are few competitors" by taking into account consumer sentiment data.

[1601] 6.2 The server calculates the projected sales and growth potential for potential store locations and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis results, and consumer demand sentiment data.

[1602] 7. Providing Results

[1603] 7.1 The server sends the generated report to the user's device.

[1604] 7.2 The terminal displays the received report to the user, providing a proposal for opening a store, such as "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and has little competition."

[1605] Specific examples

[1606] Example: Planning to open a cafe near Takadanobaba Station

[1607] 1.1 The user visits the website and answers the survey.

[1608] 1.2 The device asks, "Is Takadanobaba Station your favorite station?" and the user answers, "Yes." The device then asks, "How are you feeling right now?" and the user answers, "I'm excited."

[1609] 1.3 The terminal sends these response data to the server.

[1610] 2.1 The server stores the received data in a database.

[1611] 3.1 The server uses the map app's API to obtain reviews of cafes near Takadanobaba Station.

[1612] 3.2 The server organizes and stores the review content, rating points, and even emotion data using an emotion engine. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[1613] 4.1 The server combines the survey data, word-of-mouth data, and sentiment data and analyzes that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1614] 5.1 The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[1615] 5.2 The server analyzes that "there are no cafes with spacious seating arrangements around Takadanobaba Station."

[1616] 6.1 The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[1617] 6.2 The server calculates the forecast sales and growth prospects and compiles them into a report.

[1618] 7.1 The server sends the report to the user's device.

[1619] 7.2 The device displays to the user, "The Takadanobaba Station South Exit area is the best location. Reason: It meets consumer needs (including emotional data) and has little competition."

[1620] In this way, by taking into consideration the user's emotional data, the accuracy of the store opening plan can be improved.

[1621] The processing flow will be explained below.

[1622] Step 1:

[1623] Users access a website or app and proceed to a survey page, which asks questions about their age, gender, nearest station, frequently used stations, types of stores they are interested in, and their emotional state.

[1624] Step 2:

[1625] The terminal sequentially displays each question in the questionnaire to the user, such as "What is your age?", "What is your gender?", "What is the nearest station?", "Which station do you frequently use?", "What kind of store do you want to visit?", and "How are you feeling right now?"

[1626] Step 3:

[1627] The user completes the input by replying to each question. For example, the user enters "30 years old" as the age, "female" as the gender, "Shinjuku Station" as the nearest station, "Takadanobaba Station" as the station they frequently visit, "spacious cafe" as the store they want to visit, and "excited" as their emotion.

[1628] Step 4:

[1629] The device temporarily stores the user's input, and once all responses have been completed, the data is sent to the server. This data is structured, for example, age is sent as numerical data, station names as character strings, and emotions as character strings.

[1630] Step 5:

[1631] The server stores the received survey data and emotion data in a database. When storing the data, it organizes it into categories such as age, gender, nearest station, frequently used station, details of desired store, and emotion.

[1632] Step 6:

[1633] The server uses an external API to retrieve review data from a location-based service. For example, it requests review data about cafes in a specific area (around Takadanobaba Station).

[1634] Step 7:

[1635] The server organizes the acquired review data, analyzes the emotional data in the reviews using an emotion engine, and stores the data in a database. The review data is categorized into store name, review content, rating, and emotional data.

[1636] Step 8:

[1637] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[1638] Step 9:

[1639] The server evaluates consumer demand based on age group, gender, nearest station, frequently used stations, and emotional data, and extracts trends such as "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1640] Step 10:

[1641] The server creates a list of competing stores around the target area and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competing store from the database.

[1642] Step 11:

[1643] The server analyzes competing stores and evaluates the competitive situation around the proposed location. For example, it may conclude that there are no cafes with spacious seating near Takadanobaba Station.

[1644] Step 12:

[1645] The server integrates the results of consumer demand analysis and competitive analysis, and identifies the most suitable potential locations for store openings, taking into account sentiment data as well.

[1646] Step 13:

[1647] The server calculates the projected sales and growth potential of each potential store location and compiles the results in a report that includes detailed information that takes into account recommended store locations, competitive analysis, and sentiment data on consumer demand.

[1648] Step 14:

[1649] The server sends the generated report to the user's terminal.

[1650] Step 15:

[1651] The terminal displays the received report to the user, providing suggestions for opening a store, such as, "The area around the south exit of Takadanobaba Station is ideal because it meets consumer needs and sentiment and has little competition."

[1652] Example 2

[1653] 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."

[1654] In modern market analysis, identifying the right store location based on consumer demand is extremely important. However, traditional systems lacked the means to perform detailed demand analysis that combined consumer sentiment data and competitive analysis. As a result, store location selection was not based on true consumer demand, which risked reducing business success.

[1655] 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.

[1656] In this invention, the server includes means for collecting survey data from consumers, means for acquiring evaluation data on a target area from a location information service, means for integrating the collected survey data including emotional data at the time of responses with the acquired evaluation data to analyze consumer demand, means for analyzing the consumer emotional data, means for creating demand analysis results based on the integrated data, means for performing analysis including the characteristics of competing stores, means for evaluating areas with little competition and identifying and proposing candidate store locations, and means for transmitting the generated report to a terminal and displaying it. This enables highly accurate demand analysis that takes emotional data into consideration and the proposal of optimal candidate store locations with little competition.

[1657] "Means for collecting survey data from consumers" refers to a system or function for collecting information on consumers' age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings at the time of response through a website or application.

[1658] "Means for obtaining evaluation data for a target area from a location information service" refers to a system or function for obtaining evaluation data, word-of-mouth data, store information, etc. for a specific area from an external location information service (e.g., a map API).

[1659] "Means for integrating the collected questionnaire data, including emotional data at the time of response, with the acquired evaluation data to analyze consumer demand" refers to a system or function that integrates the collected questionnaire data with the acquired evaluation data and analyzes it based on the consumer's age, gender, nearest station, frequently used station, desired store, and emotional data at the time of response.

[1660] "Means for analyzing consumer emotion data" refers to a system or function that uses an emotion engine or emotion analysis algorithm to analyze consumer emotions from survey and word-of-mouth data and utilizes that data.

[1661] "Means for creating demand analysis results based on the integrated data" refers to a system or function for analyzing the integrated questionnaire data and evaluation data and generating results that identify demand forecasts and demand trends.

[1662] "Means for conducting analysis including the characteristics of competing stores" refers to a system or function that analyzes the characteristics of competing stores in the vicinity of a potential store location, such as the services offered, reviews, and consumer sentiment data, and evaluates the competitive environment.

[1663] "Means for evaluating areas with little competition, identifying and proposing potential store locations" refers to a system or function that identifies optimal store locations with little competition based on the results of demand analysis and competitive analysis, and proposes those locations.

[1664] The "means for transmitting the generated report to the terminal and displaying it" is a system or function that generates the results of the demand analysis and the proposed store location in report format, and transmits and displays them on the user's terminal.

[1665] A "database" is a system or facility for structuring and storing collected, acquired, and analyzed data.

[1666] An "external API" is a programmatic interface for obtaining data from other services or platforms.

[1667] This invention is a system that integrates and analyzes consumer survey data and word-of-mouth data obtained from location information services to propose optimal candidate locations for opening a store. Furthermore, by combining this with an emotion engine that recognizes user emotions, it achieves highly accurate demand analysis that takes into account consumer emotion data.

[1668] 1. Collecting survey data

[1669] A user accesses a website or application and proceeds to a survey page. This survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their emotions when answering the questions. For example, if a user answers "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "spacious cafe," and "excited," the data is temporarily stored on the device and then sent to the server.

[1670] 2. Data storage

[1671] The server stores the received survey data and user emotion data in a database. The database contains fields for age, gender, nearest station, frequently used station, desired store type, emotion, etc., and stores the data in a structured format.

[1672] 3. Collecting review data

[1673] The server uses an external API (such as a map API) to obtain review data for the target area. The server sends a request to obtain, for example, "review data for cafes around Takadanobaba Station." The obtained review data is then analyzed using an emotion engine and stored in a database along with emotion data. For example, data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun" are stored.

[1674] 4. Data Analysis

[1675] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (such as Python's pandas library or R). As a result of the analysis, trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station" are extracted.

[1676] 5. Competitive analysis

[1677] The server creates a list of competing stores in the target area and analyzes their features, services offered, ratings, and sentiment data. For example, the analysis may reveal that there is a lack of cafes with spacious seating arrangements around Takadanobaba Station.

[1678] 6. Proposal of potential locations for stores

[1679] The server integrates the results of consumer demand analysis and competitive analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is suitable because there is little competition." It then calculates forecast sales and growth prospects and generates a detailed report.

[1680] 7. Providing Results

[1681] The generated report is sent from the server to the user's device. The device then displays the received report to the user. For example, it may display information such as "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1682] Specific examples

[1683] Example: Planning to open a cafe near Takadanobaba Station

[1684] 1. Survey collection

[1685] Users visit the website and answer the survey.

[1686] The device asks, "Is Takadanobaba Station your favorite station?", to which the user replies, "Yes." The device then asks, "How are you feeling right now?", to which the user replies, "I'm excited."

[1687] The terminal transmits these response data to the server.

[1688] 2. Data storage

[1689] The server stores the received data in a database.

[1690] 3. Collecting word-of-mouth data

[1691] The server uses a map API to obtain reviews of cafes near Takadanobaba Station.

[1692] The server organizes and stores the review content, rating points, and emotion data. For example, it stores data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Fun."

[1693] 4. Data Analysis

[1694] The server combines survey data, word-of-mouth data, and sentiment data to analyze that "women in their 20s prefer spacious cafes near Takadanobaba Station."

[1695] 5. Competitive analysis

[1696] The server creates a list of "competing cafes near Takadanobaba Station" and obtains the characteristics, ratings, and sentiment data of each cafe.

[1697] 6. Proposal of potential locations for stores

[1698] The server concludes that the "Takadanobaba Station South Exit area" is optimal.

[1699] The server calculates the forecast sales and growth prospects and compiles them into a report.

[1700] 7. Providing Results

[1701] The server sends the report to the user's terminal.

[1702] The device will display to the user, "The Takadanobaba Station South Exit area is ideal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1704] Step 1: Access the survey page

[1705] A user accesses a website or application and proceeds to a survey page. The survey page displays questions about age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when answering the questions. For example, the screen may ask, "How old are you?" and the user may enter "30 years old."

[1706] Step 2: View the survey questions

[1707] The device displays each question of the survey to the user in turn, allowing the user to enter an answer. For example, the survey page may ask "What is your gender?", and the user may enter "female." The displayed answers are temporarily stored in the device.

[1708] Step 3: Send survey data

[1709] Once the user has completed answering all the questions, the device sends the temporarily saved data to the server, which receives data such as "30 years old," "female," "Shinjuku Station," "Takadanobaba Station," "want a spacious cafe," and "excited."

[1710] Step 4: Save your survey data

[1711] The server stores the received survey data and emotion data in a database. The stored data is structured into fields such as age, gender, nearest station, frequently used station, desired store type, emotion, etc. This makes subsequent analysis easier.

[1712] Step 5: Obtaining review data

[1713] The server uses an external API to obtain review data for a specific area from a location information service. For example, a request to obtain "review data for cafes around Takadanobaba Station" is sent to an external API (e.g., map API). The external API returns data such as the store name, review content, and rating score to the server.

[1714] Step 6: Analyze and store review data

[1715] The server uses an emotion engine to analyze the acquired review data and analyzes the emotional data in the reviews. For example, it extracts data such as "Cafe A," "Review Content," "Rating: 4.5," and "Emotion: Enjoyable," and stores this data in a database. The saved data can be used for subsequent analysis.

[1716] Step 7: Data synthesis and analysis

[1717] The server integrates the saved survey data, sentiment data, and word-of-mouth data and performs analysis to identify consumer demand using data analysis tools (e.g., Python's pandas library or R). For example, it extracts consumer demand trends such as "women in their 30s prefer spacious cafes near Takadanobaba Station."

[1718] Step 8: Conduct a competitive analysis

[1719] The server creates a list of competing stores in the target area and analyzes the features, services offered, ratings, and sentiment data of each store. For example, it obtains a list of cafes around Takadanobaba Station and obtains the rating that there is a lack of cafes with spacious seating arrangements.

[1720] Step 9: Identify the best potential locations

[1721] The server integrates the results of consumer demand analysis and competitor analysis to identify the optimal location for a store. For example, it may conclude that "consumers are looking for a spacious cafe, and the area around the south exit of Takadanobaba Station is ideal because there is little competition."

[1722] Step 10: Propose potential locations and generate reports

[1723] The server calculates projected sales and growth potential for each identified potential store location and generates a detailed report that includes detailed information on recommended store locations, competitive analysis, and consumer demand and sentiment data.

[1724] Step 11: Serving and displaying results

[1725] The server sends the generated report to the user's device. The device then displays the received report to the user. For example, it might say, "The Takadanobaba Station South Exit area is optimal. Reason: It meets consumer needs (including emotional data) and has little competition."

[1726] (Application example 2)

[1727] 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."

[1728] Conventional systems for proposing potential store locations take into account survey data and word-of-mouth data from location-based services, but do not perform highly accurate demand analysis using consumer sentiment data. As a result, it is difficult to grasp the essential needs of consumers, and there is a problem with low accuracy in identifying optimal candidate store locations.

[1729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1730] In this invention, the server includes means for collecting survey data, means for acquiring word-of-mouth data from a location information service, means for integrating the collected survey data and the acquired word-of-mouth data and analyzing demand taking into consideration consumer emotional data, and means for identifying and proposing optimal candidate locations for store openings based on the analysis results. This enables advanced demand analysis that reflects consumer emotional data, and enables more accurate proposals of candidate locations for store openings.

[1731] "Survey Data" refers to information collected through surveys completed by consumers, including age, gender, nearest station, frequently used station, types of stores they are interested in, and their feelings when completing the survey.

[1732] "Location-based services" means services that provide information based on geographic location, such as services that provide review data for a particular location.

[1733] "Word-of-mouth data" refers to information on ratings and reviews written by consumers about specific stores or services.

[1734] "Emotional data" refers to data that expresses consumer emotions and feelings in numerical or categorical terms, including consumer emotional information obtained using text analysis or emotion engines.

[1735] "Demand analysis" refers to the process of analyzing collected data to identify consumer needs and trends.

[1736] "Prospective Store Location" means a geographic area proposed for the opening of a new store.

[1737] "Competitor Store" refers to other stores in the same market that offer similar products or services.

[1738] An "emotion engine" refers to software or algorithms that analyze emotions from text, audio data, etc. and extract them as emotional data.

[1739] "Synthesis" refers to the process of bringing together data obtained from multiple different sources and analyzing it comprehensively.

[1740] "Optimal" refers to the most appropriate and effective state or location based on specific conditions or criteria.

[1741] This invention is a system that uses a smartphone application to collect survey data from consumers and integrates it with word-of-mouth data obtained from location information services to perform advanced demand analysis, including emotional data, and identify optimal candidate locations for opening a store. The system is configured as follows:

[1742] 1. Collecting survey data

[1743] Users answer the survey through a smartphone app. The device displays the survey items, such as age, gender, nearest station, frequently used station, type of store they are interested in, and their feelings when answering the survey. Once the user enters this information, the device sends the data to the server.

[1744] 2. Collecting and storing review data

[1745] The server uses an external API to obtain review data from location-based services. The obtained review data is analyzed using an emotion analysis engine (such as EmotionEngine) to extract emotional data. The review data and emotional data are organized and stored in a database.

[1746] 3. Data analysis

[1747] The server integrates survey data, word-of-mouth data, and sentiment data, and uses data analysis tools (e.g., Python and R libraries) to evaluate consumer demand, extracting demand trends based on specific age groups, genders, nearest stations, and frequently used stations.

[1748] 4. Identifying and proposing potential locations for stores

[1749] The server uses the saved data to analyze competing stores and sentiment analysis of word-of-mouth data. This allows it to propose optimal store locations that take into account the competitive situation in the surrounding area and consumer sentiment trends. The final proposal is generated in the form of a report and sent to the user's device.

[1750] Specific examples

[1751] For example, if the user is a 30-year-old woman who wants to open a cafe near Shinjuku Station, the system will collect data such as "Age: 30," "Gender: Female," "Nearest station: Shinjuku Station," "Frequently used station: Shinjuku Station," "Desired store: Spacious cafe," and "Current mood: Excited" through a questionnaire. The server will then integrate and analyze this data with word-of-mouth data obtained from location-based services (e.g., "Reviews about cafes around Takadanobaba Station") and, taking into account consumer emotional data, suggest that "the south exit of Takadanobaba Station is optimal." This allows the user to accurately identify potential locations for their store based on advanced demand analysis that incorporates emotional data.

[1752] Example prompts for generative AI models

[1753] "A 30-year-old female consumer is looking for a spacious cafe near Shinjuku Station. She is currently feeling excited. Please suggest the best location for a cafe based on the word-of-mouth data and sentiment analysis results around Shinjuku Station."

[1754] In this way, by taking into account user emotional data, the accuracy of store opening plans can be significantly improved.

[1755] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1756] Program processing steps

[1757] Step 1:

[1758] The user opens the smartphone app and answers the survey.

[1759] The information entered by the user includes age, gender, nearest station, frequently used station, types of stores of interest, and emotions expressed when answering the questionnaire.

[1760] Input: Survey data entered by the user (age, gender, nearest station, frequently used station, stores of interest, emotions).

[1761] Output: Survey data temporarily saved on the device.

[1762] Step 2:

[1763] Once all questionnaire responses have been completed, the terminal transmits the data to the server.

[1764] The survey data is structured and sent to the server.

[1765] Input: Survey data temporarily saved on the device.

[1766] Output: Structured data sent to the server.

[1767] Step 3:

[1768] The server stores the received survey data in a database.

[1769] When saving, the data is organized by categories such as age, gender, nearest station, frequently used station, types of stores of interest, and emotional data.

[1770] Input: Structured data sent to the server.

[1771] Output: Survey data stored in a database.

[1772] Step 4:

[1773] The server uses an external API to obtain review data from location services.

[1774] For example, request cafe reviews data for a specific area.

[1775] Input: Review data request from server.

[1776] Output: Review data obtained from location services.

[1777] Step 5:

[1778] The server organizes the acquired word-of-mouth data and analyzes the emotional data in the reviews using an emotion engine.

[1779] The word-of-mouth data is classified into store name, word-of-mouth content, rating score, and sentiment data.

[1780] Input: Review data obtained from location services.

[1781] Output: Organized reviews and sentiment data stored in a database.

[1782] Step 6:

[1783] The server integrates the stored survey data, sentiment data, and word-of-mouth data and uses data analysis tools to perform analysis to identify consumer demand.

[1784] This analysis extracts demand trends based on specific age groups, gender, nearest stations, and frequently used stations.

[1785] Input: Survey data, sentiment data, and word-of-mouth data stored in a database.

[1786] Output: Analysis results (demand trend).

[1787] Step 7:

[1788] The server creates a list of competitor stores and obtains the characteristics, services offered, consumer ratings, and sentiment data of each competitor store from a database.

[1789] Conduct competitive analysis based on the data obtained.

[1790] Input: Competitor store data stored in the database.

[1791] Output: Competitive analysis results.

[1792] Step 8:

[1793] The server integrates the results of consumer demand analysis and competitive analysis to identify the most suitable candidate location for opening a store.

[1794] The proposed store locations are also calculated with projected sales and growth prospects, which are then compiled into a report.

[1795] Input: Demand analysis results, competitive analysis results.

[1796] Output: Potential store location proposals in report format.

[1797] Step 9:

[1798] The server sends the generated report to the user's terminal.

[1799] The user checks the proposed store location through the terminal.

[1800] Input: The report generated by the server.

[1801] Output: Report suggestion results displayed on the user's device.

[1802] 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.

[1803] 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.

[1804] 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.

[1805] 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.

[1806] 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...

Claims

1. a means for collecting survey data from consumers; A means of obtaining store-related word-of-mouth data from location information services; a means for integrating the collected questionnaire data and the acquired word-of-mouth data to analyze consumer demand; A means for identifying and proposing potential locations for store openings based on the analysis results; A system including:

2. 2. The system of claim 1, wherein the means for analyzing consumer demand identifies demand based on the consumer's age, gender, nearest station, and frequently used station.

3. 2. The system of claim 1, wherein the means for identifying and proposing potential store locations includes an analysis of competing stores.

Images