System

Abstract

A system is provided.SOLUTION: A system comprising: an information reception unit that receives a request input by a user; an analysis unit that analyzes the request and extracts a keyword related to the request; a search unit that searches for a store corresponding to an electronic payment based on the extracted keyword; a recommendation unit that recommends an optimal store based on the search result; and an information transmission unit that transmits the recommended store information to a user terminal.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] Although the adoption of electronic payments has progressed in recent years, there are still users and stores that use them infrequently. Users often need time and effort to find the right store or service. Stores also face difficulties in acquiring new customers, preventing them from maximizing the effectiveness of advertising and promotions. The present invention aims to increase the frequency of electronic payment use by improving the convenience of electronic payment systems and enabling users to quickly and easily find stores that meet their needs. [Means for solving the problem]

[0005] The present invention is a system that includes an information receiving means for receiving requests entered by a user, an analysis means for analyzing the request and extracting keywords related to the request, a search means for searching for stores that accept electronic payment based on the extracted keywords, a recommendation means for recommending optimal stores based on the search results, and an information sending means for transmitting the recommended store information to a user terminal. Furthermore, a personalization means is used to reference the user's past payment data and behavioral history to provide personalized store recommendations. The system also includes deep link information to mini-apps in the store information, a search range based on location information, and an advertising means for providing advertising and promotional information to affiliated stores, thereby achieving efficient store searches and support for acquiring new customers.

[0006] The "information receiving means" is a means for receiving information such as requests entered by the user and the current location.

[0007] The "analysis means" is a means for analyzing a received request and extracting keywords related to the request.

[0008] The "search means" is a means for searching for stores that accept electronic payments based on the extracted keywords.

[0009] "Recommendation methods" are methods of selecting the most suitable store based on search results and recommending it to users.

[0010] The "information transmission means" is a means for transmitting recommended store information to the user's terminal.

[0011] "Individualization means" refers to a method of making personalized store recommendations by referencing a user's past payment data and behavioral history.

[0012] "Deep link information" is link information that allows direct access to related mini-apps and coupon information.

[0013] "Advertising means" refers to means for providing advertising and promotional information to affiliated stores. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] System Embodiments

[0036] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and, if necessary, a personalization means.

[0037] System configuration

[0038] 1. User Input

[0039] User: The user accesses the system using a mobile app and enters their request in a text box (e.g., "I would like to have an udon lunch with a budget of 800 yen").

[0040] 2. Means of receiving information

[0041] Device: The information entered by the user and the location information obtained from the device are sent to the server. This request includes the user's desired conditions and geographic location.

[0042] 3. Analysis method

[0043] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0044] 4. Search Methods

[0045] Server: Based on the extracted keywords, the server searches for appropriate stores from a store database that supports electronic payment. The search range is set based on the user's location information.

[0046] 5. Recommendation methods

[0047] Server: Generates an optimal list of stores based on the search results, taking into account the user's past payment history and behavioral history to achieve personalized recommendations.

[0048] 6. Means of information transmission

[0049] Server: The final list of selected stores is sent to the user's device along with navigation links and coupon information.

[0050] 7. Display

[0051] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0052] Specific examples

[0053] Below is an overview of the system's operation, including specific examples.

[0054] Example input:

[0055] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0056] System behavior:

[0057] 1. User: Submits the requested information.

[0058] 2. Device: Sends a request containing the desired location to the server.

[0059] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0060] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0061] 5. Server: Using a recommendation method, the server creates a personalized list of the best cafes, for example, based on past usage history.

[0062] 6. Server: The information transmission means transmits a store list including additional information (e.g., coupon links) to the terminal.

[0063] 7. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0064] This system allows users to efficiently find the store they want, and also makes it easier for stores to acquire new customers. In particular, by utilizing the user's past history, the accuracy of recommendations can be improved, providing a more satisfying consumer experience.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0068] Step 2:

[0069] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0070] Step 3:

[0071] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0072] Step 4:

[0073] Server: Based on the extracted keywords, the server searches the database for store information that accepts electronic payments. At this time, the server sets the search range based on the user's location information.

[0074] Step 5:

[0075] Server: Information on multiple stores is obtained as search results. Based on this information, the optimal store is filtered based on the user's past payment history and behavioral history, creating a personalized store list.

[0076] Step 6:

[0077] Server: Generates data to provide to users, including store lists, navigation links, and coupon information.

[0078] Step 7:

[0079] Server: Sends the generated data to the user's terminal.

[0080] Step 8:

[0081] Device: Based on the received data, the device displays the store name, address, opening hours, price range, review rating, and coupon information in the most appropriate format for the user, making it easy for the user to access.

[0082] Step 9:

[0083] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0084] This series of processes allows users to easily and efficiently find the store they are looking for. In addition, by utilizing past history, personalized recommendations are provided, enabling a more satisfying consumption experience.

[0085] Example 1

[0086] 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."

[0087] Today's consumers face challenges in quickly and accurately finding facilities that meet their specific needs. Furthermore, the lack of personalized recommendations leveraging past data means that more sophisticated personalized recommendations are needed to increase user satisfaction. Furthermore, the information users receive is fragmented, and there is a lack of a unified platform for providing that information.

[0088] 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.

[0089] In this invention, the server includes a data receiving means for receiving requests entered by a user, a data acquisition means for collecting the requests and location information, a data analysis means for analyzing the requests and extracting keywords related to the requests, a data search means for searching for facilities that support electronic transactions based on the extracted keywords and location information, a recommendation means for recommending the most suitable facility based on the search results, and a data transmission means for transmitting the recommended facility information to a user device. This allows users to quickly and accurately find facilities that meet their specific needs. Furthermore, personalized recommendations based on past transaction data and behavioral history enhance user satisfaction. Furthermore, by including deep link information to mini-apps in the facility information, necessary information can be provided on a unified platform.

[0090] The "data receiving means" is a device or program for receiving requests input by a user.

[0091] "Data acquisition means" refers to a device or program for collecting user requests and location information.

[0092] The "data analysis means" is a device or program for analyzing a received request and extracting keywords related to the request.

[0093] The "data search means" is a device or program for searching a database for suitable facilities that support electronic transactions based on the extracted keywords and location information.

[0094] A "recommendation means" is a device or program for recommending optimal facilities to users based on search results.

[0095] The "data transmission means" is a device or program for transmitting recommended facility information to a user device.

[0096] The "personalization means" is a device or program that refers to the user's past transaction data and behavioral history and makes personalized recommendations for establishments based on that data.

[0097] "Deep link information to mini-app" is link information that directly accesses specific functions or pages within the app.

[0098] The present invention provides a system for enabling a user to quickly search for facilities that support electronic transactions and recommend the most suitable facility, which system includes a data receiving means, a data acquiring means, a data analyzing means, a data searching means, a recommending means, a data transmitting means, and, if necessary, a personalizing means.

[0099] Users access the system using a mobile device such as a smartphone. The data receiving means is a means for accepting requests entered by users. For example, a user might enter "I want to eat udon lunch for 800 yen" in a text box.

[0100] Next, the data acquisition means operates to acquire the user's current location information through the GPS function, and this location information is transmitted to the server in the form of latitude and longitude.

[0101] The server uses the data receiving means to receive the request and location information entered by the user.Then, the data analysis means applies natural language processing (NLP) technology to the received text data of the request to extract important keywords.For example, keywords such as "budget 800 yen" and "udon lunch" are extracted.

[0102] The data search means then operates to search for suitable facilities from a database of facilities that support electronic transactions based on the extracted keywords and location information. At this time, the search range is set based on the user's location information, and stores within a radius of 1 km are targeted, for example.

[0103] Once the search results are obtained, the recommendation mechanism works to generate an optimal list of facilities. This takes into account the user's past transaction data and behavioral history, and the personalization mechanism provides more accurate recommendations. Priority is given to facilities that the user has visited in the past and those with high ratings.

[0104] Finally, the generated facility list is sent to the user's device via the data transmission means. This list includes the store's name, address, rating, and a link to the coupon they offer. The device displays the received information in a user-friendly format. For example, the store list may be displayed on a map, and clicking on it will display detailed information.

[0105] Examples:

[0106] If a user enters "I would like to enjoy a cafe lunch with a budget of 1,000 yen," the system will behave as follows:

[0107] 1. The user enters their request into a text box and sends it along with their location information to the server.

[0108] 2. The server receives the text data and location information and uses NLP technology to extract "budget 1,000 yen" and "cafe lunch."

[0109] 3. The data search means searches for e-commerce enabled cafes within the specified budget and location range.

[0110] 4. The recommendation method is to individually list the most suitable cafes based on past usage history.

[0111] 5. The data transmission means transmits the store list including the additional information (e.g., coupon link) to the terminal.

[0112] 6. The terminal displays a list of stores to the user and provides detailed information and coupons.

[0113] Example prompt sentence:

[0114] "Please tell me where I can enjoy a cafe lunch for 1000 yen. Please also take my current location into consideration."

[0115] This system allows users to efficiently find the facilities they want, and makes it easier for facilities to acquire new customers. In addition, by utilizing past history, the accuracy of recommendations can be improved, allowing for the provision of highly satisfying services.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The user opens the mobile app and enters their request into the text box. For example, they might enter "I want to eat udon lunch for 800 yen." This is the user's request (input). The entered request is sent to the server.

[0119] Step 2:

[0120] The device uses the GPS function to obtain the current location information. The location information is obtained in the form of latitude and longitude and sent to the server. This becomes the location information (input).

[0121] Step 3:

[0122] The server receives the user's request and location information using the data receiving means, and proceeds to the next process based on the received data (request and location information).

[0123] Step 4:

[0124] The server uses data analysis tools to apply natural language processing (NLP) technology to the received request data. Specifically, it extracts the condition "budget 800 yen" and the keyword "udon lunch." The input is the request data, and the output is the extracted keywords.

[0125] Step 5:

[0126] The server uses a data search tool to search for stores in an electronic transaction-compatible facility database based on the extracted keywords. The search range is set based on the user's location information. For example, search for facilities that offer "udon lunch" within a budget of 800 yen and within a 1km radius of the current location (latitude, longitude). The input is the keyword and location information, and the output is the search results (a list of facilities).

[0127] Step 6:

[0128] The server uses the recommendation method to generate an optimal facility list based on the search results. In doing so, it references the user's past transaction data and behavioral history to enhance the recommendation level. For example, it prioritizes facilities that have been visited in the past or highly rated facilities to include in the list. The input is the search results, and the output is a personalized list of recommended facilities.

[0129] Step 7:

[0130] The server uses a data transmission means to transmit the recommended facility information to the user's terminal. The transmitted information includes the facility name, address, rating, navigation link, coupon link, etc. The input is the recommended facility list, and the output is the transmitted facility information.

[0131] Step 8:

[0132] The terminal displays the received facility information to the user in an appropriate format. Specifically, a list of stores is marked on a map, and when the user clicks, detailed information is displayed. This allows the user to easily find facilities that meet their criteria. The input is facility information sent from the server, and the output is display information that the user can view.

[0133] (Application example 1)

[0134] 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."

[0135] Users have difficulty easily searching for and finding the best electronic payment-accepting facilities that meet their desired criteria. Furthermore, there is a lack of facility recommendations that take into account the user's current location information and past payment history, making it difficult to provide more accurate, personalized recommendations. This results in reduced user satisfaction and inconvenience. The purpose of this invention is to solve these problems and provide an environment in which users can quickly and accurately find electronic payment-accepting facilities that meet their desired criteria.

[0136] 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.

[0137] In this invention, the server includes an information receiving means for receiving requests entered by a user, an analysis means for analyzing the request and extracting keywords related to the request, and a search means for searching for facilities that accept electronic payment based on the extracted keywords and location information. This enables searches based on the user's desired conditions and current location, making it possible to quickly and accurately recommend optimal facilities that accept electronic payment. Furthermore, by adding a personalization means that references past payment data and behavioral history, it is possible to provide more accurate and personalized recommendations. This improves user satisfaction and realizes efficient facility searches.

[0138] The "information receiving means" is a means for accepting requests input by the user, and serves to receive the user's desired conditions.

[0139] The "analysis means" is a means having a function of analyzing a received request and extracting keywords related to the request.

[0140] The "search means" is a means having a function of searching for facilities that accept electronic payment based on the extracted keywords and location information.

[0141] "Recommendation methods" are methods that recommend the most suitable facilities to users based on search results.

[0142] The "information transmission means" is a means for transmitting recommended facility information to the user terminal.

[0143] "Individualization means" refers to a means of making personalized recommendations by referencing a user's past payment data and behavioral history.

[0144] "Location information" is information that indicates the user's current geographic location and is obtained from the user's device, such as a smartphone.

[0145] "Navigation link" refers to link information that allows a user to confirm or navigate to a recommended facility.

[0146] "Coupon information" is information that allows users to receive discounts and benefits available at recommended facilities.

[0147] "Facilities" refers to commercial establishments and stores that accept electronic payments.

[0148] Overall system configuration

[0149] This invention relates to a system that allows users to easily search for facilities that accept electronic payments and recommends the most suitable facility. The system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and a personalization means.

[0150] Information receiving means

[0151] The user uses a smartphone application to input their request. For example, they might input, "I want to eat sushi lunch for 2,000 yen." The smartphone's GPS function also acquires the user's current location information. This information receiving means plays a role in transmitting the user's request and location information to the server.

[0152] Analysis means

[0153] The server uses natural language processing (NLP) techniques to analyze the received user request. It uses an NLP model like SpaCy to extract important keywords (e.g., "budget 2000 yen" and "sushi") from the request.

[0154] Search methods

[0155] The server searches the database for facilities that accept electronic payments based on the extracted keywords and location information, and uses Geopy to process the location information and generate a list of facilities that accept electronic payments.

[0156] Recommendation methods

[0157] Based on the search results, the server recommends the most suitable facilities for the user. By taking into account past payment history and behavioral history, personalized recommendations are provided, allowing users to find facilities that will provide them with the highest level of satisfaction.

[0158] Information transmission means

[0159] The server then sends the final recommended facility information, including navigation links and coupon information, to the user's smartphone.

[0160] Specific examples

[0161] When a user enters "I want to enjoy an Italian dinner on a budget of 3,000 yen" and sends their request and location information from their smartphone to the server, the server analyzes the information and extracts keywords. It then searches for Italian restaurants that accept electronic payments and generates personalized recommendations based on the user's past usage history. Finally, it sends a list of recommended restaurants, including navigation links and coupon information, to the user's smartphone.

[0162] Hardware and software used

[0163] The hardware includes a smartphone operated by the user and a server that processes data. The software uses libraries such as SpaCy and Geopy. A generative AI model is also used for NLP analysis. An example of a prompt for the generative AI model is:

[0164] "Please generate a script that analyzes the input text request, extracts the budget and type of cuisine, searches for stores that accept electronic payments within the specified range, and generates optimal recommendations taking into account the user's history."

[0165] is used.

[0166] This embodiment allows users to quickly and accurately find electronic payment-enabled establishments that meet their desired criteria, thereby increasing user satisfaction and efficiency.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The user enters their request into the text box on their smartphone. For example, they might type, "I'd like to have a sushi lunch for 2,000 yen," and press the send button. At this time, the smartphone's GPS function also obtains the user's current location information.

[0170] Input: User's request (text data) and location information (latitude and longitude)

[0171] Output: Request data with your wishes and location sent to the server

[0172] Step 2:

[0173] The server receives the user's request and location information using the information receiving means, and the received data is passed to the analyzing means.

[0174] Input: Request data including user's wishes and location information

[0175] Output: Pre-analysis data to be passed to the analysis tool

[0176] Step 3:

[0177] The server analyzes the received request using its analysis tools. During this process, it uses natural language processing (NLP) technology and utilizes SpaCy to extract important keywords from the request (e.g., "budget 2000 yen" and "sushi").

[0178] Input: Pre-analysis data (user request and location information)

[0179] Output: Extracted keywords ("budget 2000 yen", "sushi")

[0180] Step 4:

[0181] The server uses a search function to search the database for facilities that accept electronic payment based on the extracted keywords and location information, processes the location information using the Geopy library, and lists the facilities within the search range.

[0182] Input: Extracted keywords and location information

[0183] Output: A list of facilities as search results

[0184] Step 5:

[0185] The server uses the recommendation means to recommend optimal facilities to the user based on the search results, and further uses the personalization means to generate personalized recommendations taking into account the user's past payment history and behavioral history.

[0186] Input: Facility list and user's past payment history and behavior history

[0187] Output: A personalized list of recommended facilities

[0188] Step 6:

[0189] The server then uses the information transmission means to send the final recommended facility information, including navigation links and coupon information, to the user's smartphone. The user can then check the recommended facility information on their smartphone.

[0190] Input: personalized recommended facility list

[0191] Output: Recommended facility information sent to the user's device (including navigation links and coupon information)

[0192] Processing steps for specific examples (example of prompt sentences)

[0193] Step 1:

[0194] The user enters "I want to enjoy an Italian dinner on a budget of 3000 yen" and sends a request including their current location to the server.

[0195] Input: User request "I want to enjoy an Italian dinner for 3000 yen", current location information

[0196] Output: Received request data

[0197] Step 2:

[0198] The server receives the request data and converts it into pre-analysis data.

[0199] Input: Request data

[0200] Output: Pre-analysis data

[0201] Step 3:

[0202] The server uses natural language processing to extract "budget 3,000 yen" and "Italian dinner."

[0203] Input: Data before analysis ("Budget 3000 yen", "Italian dinner")

[0204] Output: Extracted keywords

[0205] Step 4:

[0206] The server uses a search means to search for Italian restaurants that accept electronic payment.

[0207] Input: Extracted keywords, location information

[0208] Output: Facility list

[0209] Step 5:

[0210] The server generates personalized recommended facilities based on the user's past usage history.

[0211] Input: Facility list, past payment history and behavior history

[0212] Output: A personalized list of recommended facilities

[0213] Step 6:

[0214] The server sends the final facility information to the user's smartphone, along with navigation links and coupon information, allowing the user to check all the information on their smartphone.

[0215] Input: personalized recommended facility list

[0216] Output: Recommended facility information sent to the user's device

[0217] 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.

[0218] System Embodiments

[0219] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, a personalization means, and an emotion engine.

[0220] System configuration

[0221] 1. User Input

[0222] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0223] 2. Means of receiving information

[0224] Device: Sends the user's input request and current location information to the server. This request includes the user's desired conditions and geographic location.

[0225] 3. Analysis method

[0226] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0227] 4. Search Methods

[0228] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payment. The search range is set based on the user's location information.

[0229] 5. Emotion Engine

[0230] Server: Analyzes the user's input and past behavioral history to estimate the user's emotional state. This estimation result is taken into account in the next recommendation method.

[0231] 6. Recommendation methods

[0232] Server: Generates a list of optimal stores based on the search results and the emotional state estimated by the emotion engine. This list also takes into account the user's past payment history and behavioral history.

[0233] 7. Means of information transmission

[0234] Server: The generated store list is sent to the user's device along with navigation links and coupon information.

[0235] 8. Display

[0236] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0237] Specific examples

[0238] Below is an overview of the system's operation, including specific examples.

[0239] Example input:

[0240] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0241] System behavior:

[0242] 1. User: Submits the requested information.

[0243] 2. Device: Sends a request containing the desired location to the server.

[0244] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0245] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0246] 5. Server: The emotion engine uses the user's past behavioral history and input data to estimate the user's emotional state. For example, if the server estimates that the user is tired, it selects an appropriate store.

[0247] 6. Server: Recommends the best cafes to the user based on their past usage history and emotional state.

[0248] 7. Server: The information transmission means transmits the store list including additional information (e.g., coupon links) to the terminal.

[0249] 8. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0250] This system allows users to efficiently find the store they want. In addition, by utilizing an emotion engine, recommendations that match the user's emotional state are provided, resulting in a more personalized service. This makes it easier for stores to attract new customers and increases user satisfaction.

[0251] The processing flow will be explained below.

[0252] Step 1:

[0253] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0254] Step 2:

[0255] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0256] Step 3:

[0257] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0258] Step 4:

[0259] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payments. The search range is set based on the user's location information.

[0260] Step 5:

[0261] Server: Based on the user's input and related data, the emotion engine estimates the user's emotional state.

[0262] Step 6:

[0263] Server: Adjust search results based on the emotional state estimated by the emotion engine. For example, if you are in a relaxing mood, prioritize stores with quiet environments.

[0264] Step 7:

[0265] Server: Generates an optimal list of stores based on search results and filtering based on emotional state. It also provides personalized recommendations based on the user's past payment history and behavioral history.

[0266] Step 8:

[0267] Server: Adds navigation links and coupon information to the generated store list and sends it to the user's device.

[0268] Step 9:

[0269] Device: The received store list is displayed to the user, including the store name, address, opening hours, price range, review rating, and coupon information.

[0270] Step 10:

[0271] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0272] This series of processes allows users to easily find the best store within their budget. Using an emotion engine, recommendations that match the user's emotional state are realized, providing a more personalized experience. This also makes it easier for stores to acquire new customers and increases user satisfaction.

[0273] Example 2

[0274] 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."

[0275] Conventional store search systems have had issues with their inability to provide recommendations that take into account the user's emotional state. They also lack the ability to provide personalized recommendations based on past behavioral history and payment data. Furthermore, they also lack the ability to efficiently search for stores that accept electronic payments based on the user's current location.

[0276] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information receiving means for receiving a request input by a user, a natural language processing means for analyzing the request and extracting keywords related to the request, a search means for searching for stores that accept electronic payment based on the extracted keywords and the user's geographical location information, an emotion analysis means for estimating the user's emotional state from the user's past behavioral history and input content, a recommendation means for recommending the most suitable store based on the search results and the user's emotional state, and an information sending means for sending the recommended store information, including navigation links and coupon information, to the user terminal. This enables efficient search and recommendation of personalized stores that accept electronic payment, taking the user's emotional state into consideration.

[0277] The "information receiving means" is a means having the function of receiving a request input by a user and transmitting the request to a server.

[0278] "Natural language processing means" refers to a technology that analyzes requests entered by users and extracts keywords related to the requests.

[0279] The "search means" is a means having a function of searching for stores that accept electronic payments based on the extracted keywords and the user's geographical location information.

[0280] "Emotion analysis means" refers to a technique for estimating a user's emotional state from the user's past behavioral history and input content.

[0281] A "recommendation tool" is a tool that has the function of recommending the most suitable store to the user based on search results and emotional state.

[0282] The "information transmission means" is a means having a function of transmitting recommended store information, including navigation links and coupon information, to a user terminal.

[0283] The system of the present invention allows users to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes information receiving means, natural language processing means, search means, emotion analysis means, recommendation means, and information transmitting means.

[0284] First, a user launches a smartphone application and enters their request in the search box. For example, they might enter "I want to eat udon lunch for 800 yen" and press the send button. Next, the device sends this request and their current location information to the server. This request includes the user's desired conditions and geographic location.

[0285] The server analyzes the received request. Specifically, it uses natural language processing to extract keywords such as "budget 800 yen" and "udon lunch" from the user's input. This process uses NLP libraries such as Google Cloud Natural Language API and spaCy.

[0286] Next, the server searches a database for store information that accepts electronic payments based on the extracted keywords and the user's location information. This search is performed using a database management system such as MySQL or PostgreSQL.

[0287] The server then uses emotion analysis to estimate the user's emotional state based on the user's input and past behavioral history, using emotion analysis engines such as IBM Watson and Microsoft Azure Text Analytics.

[0288] The server generates a list of optimal stores based on the search results and emotional state using recommendation engines such as Apache Mahout and TensorFlow, taking into account the user's past payment history and behavioral history.

[0289] Finally, the server adds navigation links and coupon information to the generated store list and sends it to the terminal. This information is sent using a message queue such as a REST API or Apache Kafka. Finally, the terminal displays the received information in an easy-to-read format for the user, allowing the user to easily find the store they want.

[0290] For example, if a user inputs "I want to enjoy a cafe lunch with a budget of 1000 yen," the system will behave as follows:

[0291] 1. The user sends the above request from their smartphone.

[0292] 2. The device sends the request and current location information to the server.

[0293] 3. The server receives the request and uses NLP technology to extract the keywords "budget 1,000 yen" and "cafe lunch."

[0294] 4. The server searches the database for cafes that accept electronic payment and match the budget and location information.

[0295] 5. The server uses an emotion engine to estimate the user's emotional state based on the user's past behavior history and input. For example, if the server estimates that the user is tired, it will select an appropriate store.

[0296] 6. The server will then provide a personalized list of the best cafes for you, taking into account your emotional state and past visit history.

[0297] 7. The server sends a store list including navigation links and coupon links to the terminal.

[0298] 8. The terminal will display a list of stores to the user, providing detailed information and coupons.

[0299] Through the above process, users can efficiently find the store they want and are provided with personalized recommendations that match their emotional state.

[0300] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0301] Step 1:

[0302] User: Launches the smartphone application, enters a request in the search box, and submits it. For example, the user might enter, "I want to eat udon lunch with a budget of 800 yen." The input data (user request) is then sent to the next step.

[0303] Step 2:

[0304] Terminal: Acquires the request entered by the user and current location information and sends this to the server. For example, if the request data is "I want to eat udon lunch with a budget of 800 yen" and the location data is "latitude 35.6895, longitude 139.6917", this information is sent to the server. The input is the user's request and location information, and the output is the request data sent to the server.

[0305] Step 3:

[0306] Server: Analyzes the received request data (demands and location information) using natural language processing. Specifically, keywords such as "budget 800 yen" and "udon lunch" are extracted from the input. For example, using "Google Cloud Natural Language API" or "spaCy," "budget 800 yen" and "udon lunch" are recognized as key elements. The input is the request data, and the output is the extracted keywords.

[0307] Step 4:

[0308] Server: Using the search tool, search the database for stores that accept electronic payments based on the extracted keywords and the user's location information. For example, using "MySQL" or "PostgreSQL," search for stores that meet the conditions of "udon lunch" and "budget under 800 yen" based on location information. The input is the extracted keywords and location information, and the output is a list of matching stores.

[0309] Step 5:

[0310] Server: Using an emotion analysis engine, the server estimates the user's emotional state based on their input and past behavioral history. For example, if past data indicates that the user is "tired," it prioritizes stores where they can relax. This is achieved using technologies such as IBM Watson and Microsoft Azure Text Analytics. The input is the user's requests and past behavioral history, and the output is the estimated emotional state.

[0311] Step 6:

[0312] Server: Using a recommendation method, the server generates an optimal store list based on the estimated emotional state and search results. This list also reflects the user's past payment history and behavioral history. For example, suitable stores are selected using "Apache Mahout" or "TensorFlow." The input is the emotional state and search results, and the output is a personalized store list.

[0313] Step 7:

[0314] Server: Using an information transmission means, the server sends a list of optimal stores, including navigation links and coupon information, to the device. For example, detailed store information is sent using a REST API or Apache Kafka. The input is the personalized store list, and the output is the information sent to the device.

[0315] Step 8:

[0316] Terminal: Displays the received store list to the user in an appropriate format. Specifically, it provides detailed information and coupons, allowing the user to easily select a store. The input is the store list sent from the server, and the output is the information displayed in a format that the user can check.

[0317] The above is the processing flow of the system that finds appropriate stores based on the requests entered by the user, recommends them taking into consideration the user's emotional state, and finally provides information to the user.

[0318] (Application example 2)

[0319] 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."

[0320] When modern consumers choose a store, they are not only concerned with the price and location of products and services, but also with finding a store that suits their emotional state at the time. However, conventional search systems make recommendations without taking the user's emotional state into consideration, making it difficult to select a store that will provide high satisfaction. Furthermore, there is no system that can search for stores that accept electronic payments and make recommendations that simultaneously consider the user's emotional state. Therefore, there is a need to provide a system that allows users to quickly and easily find an appropriate store that suits their emotional state.

[0321] 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.

[0322] In this invention, the server includes information receiving means for receiving requests input by a user, analysis means for analyzing the request and extracting keywords related to the request, search means for searching for stores that accept electronic payment based on the extracted keywords, emotion analysis means for estimating the emotional state of the user, recommendation means for recommending the most suitable store based on the search results and emotion analysis results, and information sending means for sending information about the recommended store to a user terminal. This makes it possible to recommend the most suitable store taking into account the emotional state of the user.

[0323] The "information receiving means" is a means for receiving requests input by the user.

[0324] The "analysis means" is a means for analyzing the request and extracting keywords related to the request.

[0325] The "search means" is a means for searching for stores that accept electronic payments based on the extracted keywords.

[0326] The "emotion analysis means" is a means for analyzing the user's input content and past behavioral history to estimate the user's emotional state.

[0327] The "recommendation means" is a means for recommending the most suitable store based on the search results and the sentiment analysis results.

[0328] The "information transmission means" is a means for transmitting the recommended store information to the user terminal.

[0329] The "individualization means" refers to a means for making individualized store recommendations by the recommendation means by referring to the user's past payment data and behavioral history.

[0330] "Deep link information to a mini appli" is link information for directly launching a mini appli.

[0331] The system for realizing the present invention includes a plurality of processing steps for accepting requests input by a user, analyzing the requests, and searching for related stores. The hardware and software used in this embodiment of the system will be specifically described below.

[0332] Hardware and Software Use

[0333] 1. Terminal

[0334] Hardware: Smartphone

[0335] Software: Applications that accept user input (e.g., SmartPay, Shop Guide)

[0336] 2. Server

[0337] Software: Python, natural language processing engine (e.g., spaCy or NLTK), sentiment analysis model (e.g., BERT or RoBERTa), HTTP request library (e.g., requests), geolocation library (e.g., geopy)

[0338] Processing flow

[0339] Information receiving means

[0340] It accepts requests entered by the user on the terminal (e.g., "I would like to enjoy a cafe lunch with a budget of 1,000 yen") and sends this information to the server.

[0341] Analysis means

[0342] The server analyzes the received request and uses natural language processing (NLP) technology to extract keywords related to the request (e.g., "budget 1,000 yen" or "cafe lunch").

[0343] Search methods

[0344] The server searches the database for store information that accepts electronic payments based on the user's location information and the extracted keywords. The geopy library is used to obtain location information.

[0345] Emotion analysis means

[0346] The server estimates the user's emotional state based on the user's input and past behavioral history. An emotion analysis model (e.g., BERT or RoBERTa) is used to analyze the emotional state.

[0347] Recommendation methods

[0348] The server then recommends the most suitable store for the user based on the search results and sentiment analysis, taking into account past payment data and behavioral history.

[0349] Information transmission means

[0350] The server sends the recommended store information, including navigation links and coupon information, to the user's device.

[0351] Specific examples

[0352] Example input

[0353] User input: "I want to enjoy a cafe lunch on a budget of 1000 yen."

[0354] User mood: "Tired"

[0355] Prompt Sentence Examples

[0356] Text format

[0357] How I feel right now in one word: Tired

[0358] Example output

[0359] The server performs emotion analysis based on the above information and estimates the user's emotional state (e.g., tired). Next, it searches the database for cafes that accept electronic payment based on the user's location information. It then takes the user's emotional state into consideration and prioritizes recommendations of cafes where the user can relax. Finally, the following information is sent to the user's device:

[0360] Recommended stores include:

[0361] Store name: Relax Cafe, Address: 1-2-3 Shibuya-ku, Tokyo, Coupon: 50% off drinks

[0362] Store name: Healthy Cafe, Address: 4-5-6, Shinjuku-ku, Tokyo, Coupon: Free dessert

[0363] In this way, through a specific embodiment, a user can quickly and easily find a store that suits their emotional state.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] The user starts the smartphone application, enters their request in the search box, and sends it. An example of input is "I would like to enjoy a cafe lunch with a budget of 1,000 yen." This input is accepted by the information receiving means and sent to the server. The input is in natural Japanese text format, and includes location information.

[0367] Step 2:

[0368] The server analyzes the user's request received by the information receiving means and extracts keywords related to the request using the analysis means. Specifically, it uses natural language processing technology (e.g., spaCy or NLTK) to extract keywords such as "budget 1,000 yen" and "cafe lunch." The input is the request text from the user, and the output is a list of extracted keywords.

[0369] Step 3:

[0370] The server uses a search function to search for stores that accept electronic payments using the user's location information based on the extracted keywords. It obtains the location information using a geolocation API (e.g., geopy library) and retrieves the corresponding store information from the database. The input is a list of keywords and location information, and the output is a list of corresponding stores.

[0371] Step 4:

[0372] The server uses emotion analysis to estimate the user's emotional state from their input and past behavioral history. It uses an emotion analysis model (e.g., BERT or RoBERTa) to analyze the input text and historical data to estimate the emotional state. It analyzes the user's emotional state based on a prompt such as "How do you feel right now in one word?" The input is text data and behavioral history, and the output is the estimated emotional state.

[0373] Step 5:

[0374] The server uses the recommendation means to recommend the most suitable store based on the search results and sentiment analysis results. At this time, the server also references the user's past payment data and generates personalized store information using the personalization means. This creates a list of stores that are suitable for the user's emotional state. The inputs are the search results, sentiment analysis results, and payment data, and the output is a list of recommended stores.

[0375] Step 6:

[0376] The server uses an information transmission means to send recommended store information to the user's terminal. The sent information includes detailed store information, navigation links, coupon information, etc. The user can check the received information on the application. The input is a list of recommended stores, and the output is store information displayed on the user's terminal.

[0377] Through these steps, the system is able to take into account the user's desires and emotional state and quickly recommend the most suitable store.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] [Second embodiment]

[0382] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0393] 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."

[0394] System Embodiments

[0395] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and, if necessary, a personalization means.

[0396] System configuration

[0397] 1. User Input

[0398] User: The user accesses the system using a mobile app and enters their request in a text box (e.g., "I would like to have an udon lunch with a budget of 800 yen").

[0399] 2. Means of receiving information

[0400] Device: The information entered by the user and the location information obtained from the device are sent to the server. This request includes the user's desired conditions and geographic location.

[0401] 3. Analysis method

[0402] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0403] 4. Search Methods

[0404] Server: Based on the extracted keywords, the server searches for appropriate stores from a store database that supports electronic payment. The search range is set based on the user's location information.

[0405] 5. Recommendation methods

[0406] Server: Generates an optimal list of stores based on the search results, taking into account the user's past payment history and behavioral history to achieve personalized recommendations.

[0407] 6. Means of information transmission

[0408] Server: The final list of selected stores is sent to the user's device along with navigation links and coupon information.

[0409] 7. Display

[0410] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0411] Specific examples

[0412] Below is an overview of the system's operation, including specific examples.

[0413] Example input:

[0414] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0415] System behavior:

[0416] 1. User: Submits the requested information.

[0417] 2. Device: Sends a request containing the desired location to the server.

[0418] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0419] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0420] 5. Server: Using a recommendation method, the server creates a personalized list of the best cafes, for example, based on past usage history.

[0421] 6. Server: The information transmission means transmits a store list including additional information (e.g., coupon links) to the terminal.

[0422] 7. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0423] This system allows users to efficiently find the store they want, and also makes it easier for stores to acquire new customers. In particular, by utilizing the user's past history, the accuracy of recommendations can be improved, providing a more satisfying consumer experience.

[0424] The processing flow will be explained below.

[0425] Step 1:

[0426] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0427] Step 2:

[0428] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0429] Step 3:

[0430] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0431] Step 4:

[0432] Server: Based on the extracted keywords, the server searches the database for store information that accepts electronic payments. At this time, the server sets the search range based on the user's location information.

[0433] Step 5:

[0434] Server: Information on multiple stores is obtained as search results. Based on this information, the optimal store is filtered based on the user's past payment history and behavioral history, creating a personalized store list.

[0435] Step 6:

[0436] Server: Generates data to provide to users, including store lists, navigation links, and coupon information.

[0437] Step 7:

[0438] Server: Sends the generated data to the user's terminal.

[0439] Step 8:

[0440] Device: Based on the received data, the device displays the store name, address, opening hours, price range, review rating, and coupon information in the most appropriate format for the user, making it easy for the user to access.

[0441] Step 9:

[0442] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0443] This series of processes allows users to easily and efficiently find the store they are looking for. In addition, by utilizing past history, personalized recommendations are provided, enabling a more satisfying consumption experience.

[0444] Example 1

[0445] 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."

[0446] Today's consumers face challenges in quickly and accurately finding facilities that meet their specific needs. Furthermore, the lack of personalized recommendations leveraging past data means that more sophisticated personalized recommendations are needed to increase user satisfaction. Furthermore, the information users receive is fragmented, and there is a lack of a unified platform for providing that information.

[0447] 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.

[0448] In this invention, the server includes a data receiving means for receiving requests entered by a user, a data acquisition means for collecting the requests and location information, a data analysis means for analyzing the requests and extracting keywords related to the requests, a data search means for searching for facilities that support electronic transactions based on the extracted keywords and location information, a recommendation means for recommending the most suitable facility based on the search results, and a data transmission means for transmitting the recommended facility information to a user device. This allows users to quickly and accurately find facilities that meet their specific needs. Furthermore, personalized recommendations based on past transaction data and behavioral history enhance user satisfaction. Furthermore, by including deep link information to mini-apps in the facility information, necessary information can be provided on a unified platform.

[0449] The "data receiving means" is a device or program for receiving requests input by a user.

[0450] "Data acquisition means" refers to a device or program for collecting user requests and location information.

[0451] The "data analysis means" is a device or program for analyzing a received request and extracting keywords related to the request.

[0452] The "data search means" is a device or program for searching a database for suitable facilities that support electronic transactions based on the extracted keywords and location information.

[0453] A "recommendation means" is a device or program for recommending optimal facilities to users based on search results.

[0454] The "data transmission means" is a device or program for transmitting recommended facility information to a user device.

[0455] The "personalization means" is a device or program that refers to the user's past transaction data and behavioral history and makes personalized recommendations for establishments based on that data.

[0456] "Deep link information to mini-app" is link information that directly accesses specific functions or pages within the app.

[0457] The present invention provides a system for enabling a user to quickly search for facilities that support electronic transactions and recommend the most suitable facility, which system includes a data receiving means, a data acquiring means, a data analyzing means, a data searching means, a recommending means, a data transmitting means, and, if necessary, a personalizing means.

[0458] Users access the system using a mobile device such as a smartphone. The data receiving means is a means for accepting requests entered by users. For example, a user might enter "I want to eat udon lunch for 800 yen" in a text box.

[0459] Next, the data acquisition means operates to acquire the user's current location information through the GPS function, and this location information is transmitted to the server in the form of latitude and longitude.

[0460] The server uses the data receiving means to receive the request and location information entered by the user.Then, the data analysis means applies natural language processing (NLP) technology to the received text data of the request to extract important keywords.For example, keywords such as "budget 800 yen" and "udon lunch" are extracted.

[0461] The data search means then operates to search for suitable facilities from a database of facilities that support electronic transactions based on the extracted keywords and location information. At this time, the search range is set based on the user's location information, and stores within a radius of 1 km are targeted, for example.

[0462] Once the search results are obtained, the recommendation mechanism works to generate an optimal list of facilities. This takes into account the user's past transaction data and behavioral history, and the personalization mechanism provides more accurate recommendations. Priority is given to facilities that the user has visited in the past and those with high ratings.

[0463] Finally, the generated facility list is sent to the user's device via the data transmission means. This list includes the store's name, address, rating, and a link to the coupon they offer. The device displays the received information in a user-friendly format. For example, the store list may be displayed on a map, and clicking on it will display detailed information.

[0464] Examples:

[0465] If a user enters "I would like to enjoy a cafe lunch with a budget of 1,000 yen," the system will behave as follows:

[0466] 1. The user enters their request into a text box and sends it along with their location information to the server.

[0467] 2. The server receives the text data and location information and uses NLP technology to extract "budget 1,000 yen" and "cafe lunch."

[0468] 3. The data search means searches for e-commerce enabled cafes within the specified budget and location range.

[0469] 4. The recommendation method is to individually list the most suitable cafes based on past usage history.

[0470] 5. The data transmission means transmits the store list including the additional information (e.g., coupon link) to the terminal.

[0471] 6. The terminal displays a list of stores to the user and provides detailed information and coupons.

[0472] Example prompt sentence:

[0473] "Please tell me where I can enjoy a cafe lunch for 1000 yen. Please also take my current location into consideration."

[0474] This system allows users to efficiently find the facilities they want, and makes it easier for facilities to acquire new customers. In addition, by utilizing past history, the accuracy of recommendations can be improved, allowing for the provision of highly satisfying services.

[0475] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0476] Step 1:

[0477] The user opens the mobile app and enters their request into the text box. For example, they might enter "I want to eat udon lunch for 800 yen." This is the user's request (input). The entered request is sent to the server.

[0478] Step 2:

[0479] The device uses the GPS function to obtain the current location information. The location information is obtained in the form of latitude and longitude and sent to the server. This becomes the location information (input).

[0480] Step 3:

[0481] The server receives the user's request and location information using the data receiving means, and proceeds to the next process based on the received data (request and location information).

[0482] Step 4:

[0483] The server uses data analysis tools to apply natural language processing (NLP) technology to the received request data. Specifically, it extracts the condition "budget 800 yen" and the keyword "udon lunch." The input is the request data, and the output is the extracted keywords.

[0484] Step 5:

[0485] The server uses a data search tool to search for stores in an electronic transaction-compatible facility database based on the extracted keywords. The search range is set based on the user's location information. For example, search for facilities that offer "udon lunch" within a budget of 800 yen and within a 1km radius of the current location (latitude, longitude). The input is the keyword and location information, and the output is the search results (a list of facilities).

[0486] Step 6:

[0487] The server uses the recommendation method to generate an optimal facility list based on the search results. In doing so, it references the user's past transaction data and behavioral history to enhance the recommendation level. For example, it prioritizes facilities that have been visited in the past or highly rated facilities to include in the list. The input is the search results, and the output is a personalized list of recommended facilities.

[0488] Step 7:

[0489] The server uses a data transmission means to transmit the recommended facility information to the user's terminal. The transmitted information includes the facility name, address, rating, navigation link, coupon link, etc. The input is the recommended facility list, and the output is the transmitted facility information.

[0490] Step 8:

[0491] The terminal displays the received facility information to the user in an appropriate format. Specifically, a list of stores is marked on a map, and when the user clicks, detailed information is displayed. This allows the user to easily find facilities that meet their criteria. The input is facility information sent from the server, and the output is display information that the user can view.

[0492] (Application example 1)

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

[0494] Users have difficulty easily searching for and finding the best electronic payment-accepting facilities that meet their desired criteria. Furthermore, there is a lack of facility recommendations that take into account the user's current location information and past payment history, making it difficult to provide more accurate, personalized recommendations. This results in reduced user satisfaction and inconvenience. The purpose of this invention is to solve these problems and provide an environment in which users can quickly and accurately find electronic payment-accepting facilities that meet their desired criteria.

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

[0496] In this invention, the server includes an information receiving means for receiving requests entered by a user, an analysis means for analyzing the request and extracting keywords related to the request, and a search means for searching for facilities that accept electronic payment based on the extracted keywords and location information. This enables searches based on the user's desired conditions and current location, making it possible to quickly and accurately recommend optimal facilities that accept electronic payment. Furthermore, by adding a personalization means that references past payment data and behavioral history, it is possible to provide more accurate and personalized recommendations. This improves user satisfaction and realizes efficient facility searches.

[0497] The "information receiving means" is a means for accepting requests input by the user, and serves to receive the user's desired conditions.

[0498] The "analysis means" is a means having a function of analyzing a received request and extracting keywords related to the request.

[0499] The "search means" is a means having a function of searching for facilities that accept electronic payment based on the extracted keywords and location information.

[0500] "Recommendation methods" are methods that recommend the most suitable facilities to users based on search results.

[0501] The "information transmission means" is a means for transmitting recommended facility information to the user terminal.

[0502] "Individualization means" refers to a means of making personalized recommendations by referencing a user's past payment data and behavioral history.

[0503] "Location information" is information that indicates the user's current geographic location and is obtained from the user's device, such as a smartphone.

[0504] "Navigation link" refers to link information that allows a user to confirm or navigate to a recommended facility.

[0505] "Coupon information" is information that allows users to receive discounts and benefits available at recommended facilities.

[0506] "Facilities" refers to commercial establishments and stores that accept electronic payments.

[0507] Overall system configuration

[0508] This invention relates to a system that allows users to easily search for facilities that accept electronic payments and recommends the most suitable facility. The system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and a personalization means.

[0509] Information receiving means

[0510] The user uses a smartphone application to input their request. For example, they might input, "I want to eat sushi lunch for 2,000 yen." The smartphone's GPS function also acquires the user's current location information. This information receiving means plays a role in transmitting the user's request and location information to the server.

[0511] Analysis means

[0512] The server uses natural language processing (NLP) techniques to analyze the received user request. It uses an NLP model like SpaCy to extract important keywords (e.g., "budget 2000 yen" and "sushi") from the request.

[0513] Search methods

[0514] The server searches the database for facilities that accept electronic payments based on the extracted keywords and location information, and uses Geopy to process the location information and generate a list of facilities that accept electronic payments.

[0515] Recommendation methods

[0516] Based on the search results, the server recommends the most suitable facilities for the user. By taking into account past payment history and behavioral history, personalized recommendations are provided, allowing users to find facilities that will provide them with the highest level of satisfaction.

[0517] Information transmission means

[0518] The server then sends the final recommended facility information, including navigation links and coupon information, to the user's smartphone.

[0519] Specific examples

[0520] When a user enters "I want to enjoy an Italian dinner on a budget of 3,000 yen" and sends their request and location information from their smartphone to the server, the server analyzes the information and extracts keywords. It then searches for Italian restaurants that accept electronic payments and generates personalized recommendations based on the user's past usage history. Finally, it sends a list of recommended restaurants, including navigation links and coupon information, to the user's smartphone.

[0521] Hardware and software used

[0522] The hardware includes a smartphone operated by the user and a server that processes data. The software uses libraries such as SpaCy and Geopy. A generative AI model is also used for NLP analysis. An example of a prompt for the generative AI model is:

[0523] "Please generate a script that analyzes the input text request, extracts the budget and type of cuisine, searches for stores that accept electronic payments within the specified range, and generates optimal recommendations taking into account the user's history."

[0524] is used.

[0525] This embodiment allows users to quickly and accurately find electronic payment-enabled establishments that meet their desired criteria, thereby increasing user satisfaction and efficiency.

[0526] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0527] Step 1:

[0528] The user enters their request into the text box on their smartphone. For example, they might type, "I'd like to have a sushi lunch for 2,000 yen," and press the send button. At this time, the smartphone's GPS function also obtains the user's current location information.

[0529] Input: User's request (text data) and location information (latitude and longitude)

[0530] Output: Request data with your wishes and location sent to the server

[0531] Step 2:

[0532] The server receives the user's request and location information using the information receiving means, and the received data is passed to the analyzing means.

[0533] Input: Request data including user's wishes and location information

[0534] Output: Pre-analysis data to be passed to the analysis tool

[0535] Step 3:

[0536] The server analyzes the received request using its analysis tools. During this process, it uses natural language processing (NLP) technology and utilizes SpaCy to extract important keywords from the request (e.g., "budget 2000 yen" and "sushi").

[0537] Input: Pre-analysis data (user request and location information)

[0538] Output: Extracted keywords ("budget 2000 yen", "sushi")

[0539] Step 4:

[0540] The server uses a search function to search the database for facilities that accept electronic payment based on the extracted keywords and location information, processes the location information using the Geopy library, and lists the facilities within the search range.

[0541] Input: Extracted keywords and location information

[0542] Output: A list of facilities as search results

[0543] Step 5:

[0544] The server uses the recommendation means to recommend optimal facilities to the user based on the search results, and further uses the personalization means to generate personalized recommendations taking into account the user's past payment history and behavioral history.

[0545] Input: Facility list and user's past payment history and behavior history

[0546] Output: A personalized list of recommended facilities

[0547] Step 6:

[0548] The server then uses the information transmission means to send the final recommended facility information, including navigation links and coupon information, to the user's smartphone. The user can then check the recommended facility information on their smartphone.

[0549] Input: personalized recommended facility list

[0550] Output: Recommended facility information sent to the user's device (including navigation links and coupon information)

[0551] Processing steps for specific examples (example of prompt sentences)

[0552] Step 1:

[0553] The user enters "I want to enjoy an Italian dinner on a budget of 3000 yen" and sends a request including their current location to the server.

[0554] Input: User request "I want to enjoy an Italian dinner for 3000 yen", current location information

[0555] Output: Received request data

[0556] Step 2:

[0557] The server receives the request data and converts it into pre-analysis data.

[0558] Input: Request data

[0559] Output: Pre-analysis data

[0560] Step 3:

[0561] The server uses natural language processing to extract "budget 3,000 yen" and "Italian dinner."

[0562] Input: Data before analysis ("Budget 3000 yen", "Italian dinner")

[0563] Output: Extracted keywords

[0564] Step 4:

[0565] The server uses a search means to search for Italian restaurants that accept electronic payment.

[0566] Input: Extracted keywords, location information

[0567] Output: Facility list

[0568] Step 5:

[0569] The server generates personalized recommended facilities based on the user's past usage history.

[0570] Input: Facility list, past payment history and behavior history

[0571] Output: A personalized list of recommended facilities

[0572] Step 6:

[0573] The server sends the final facility information to the user's smartphone, along with navigation links and coupon information, allowing the user to check all the information on their smartphone.

[0574] Input: personalized recommended facility list

[0575] Output: Recommended facility information sent to the user's device

[0576] 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.

[0577] System Embodiments

[0578] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, a personalization means, and an emotion engine.

[0579] System configuration

[0580] 1. User Input

[0581] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0582] 2. Means of receiving information

[0583] Device: Sends the user's input request and current location information to the server. This request includes the user's desired conditions and geographic location.

[0584] 3. Analysis method

[0585] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0586] 4. Search Methods

[0587] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payment. The search range is set based on the user's location information.

[0588] 5. Emotion Engine

[0589] Server: Analyzes the user's input and past behavioral history to estimate the user's emotional state. This estimation result is taken into account in the next recommendation method.

[0590] 6. Recommendation methods

[0591] Server: Generates a list of optimal stores based on the search results and the emotional state estimated by the emotion engine. This list also takes into account the user's past payment history and behavioral history.

[0592] 7. Means of information transmission

[0593] Server: The generated store list is sent to the user's device along with navigation links and coupon information.

[0594] 8. Display

[0595] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0596] Specific examples

[0597] Below is an overview of the system's operation, including specific examples.

[0598] Example input:

[0599] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0600] System behavior:

[0601] 1. User: Submits the requested information.

[0602] 2. Device: Sends a request containing the desired location to the server.

[0603] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0604] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0605] 5. Server: The emotion engine uses the user's past behavioral history and input data to estimate the user's emotional state. For example, if the server estimates that the user is tired, it selects an appropriate store.

[0606] 6. Server: Recommends the best cafes to the user based on their past usage history and emotional state.

[0607] 7. Server: The information transmission means transmits the store list including additional information (e.g., coupon links) to the terminal.

[0608] 8. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0609] This system allows users to efficiently find the store they want. In addition, by utilizing an emotion engine, recommendations that match the user's emotional state are provided, resulting in a more personalized service. This makes it easier for stores to attract new customers and increases user satisfaction.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0613] Step 2:

[0614] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0615] Step 3:

[0616] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0617] Step 4:

[0618] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payments. The search range is set based on the user's location information.

[0619] Step 5:

[0620] Server: Based on the user's input and related data, the emotion engine estimates the user's emotional state.

[0621] Step 6:

[0622] Server: Adjust search results based on the emotional state estimated by the emotion engine. For example, if you are in a relaxing mood, prioritize stores with quiet environments.

[0623] Step 7:

[0624] Server: Generates an optimal list of stores based on search results and filtering based on emotional state. It also provides personalized recommendations based on the user's past payment history and behavioral history.

[0625] Step 8:

[0626] Server: Adds navigation links and coupon information to the generated store list and sends it to the user's device.

[0627] Step 9:

[0628] Device: The received store list is displayed to the user, including the store name, address, opening hours, price range, review rating, and coupon information.

[0629] Step 10:

[0630] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0631] This series of processes allows users to easily find the best store within their budget. Using an emotion engine, recommendations that match the user's emotional state are realized, providing a more personalized experience. This also makes it easier for stores to acquire new customers and increases user satisfaction.

[0632] Example 2

[0633] 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."

[0634] Conventional store search systems have had issues with their inability to provide recommendations that take into account the user's emotional state. They also lack the ability to provide personalized recommendations based on past behavioral history and payment data. Furthermore, they also lack the ability to efficiently search for stores that accept electronic payments based on the user's current location.

[0635] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information receiving means for receiving a request input by a user, a natural language processing means for analyzing the request and extracting keywords related to the request, a search means for searching for stores that accept electronic payment based on the extracted keywords and the user's geographical location information, an emotion analysis means for estimating the user's emotional state from the user's past behavioral history and input content, a recommendation means for recommending the most suitable store based on the search results and the user's emotional state, and an information sending means for sending the recommended store information, including navigation links and coupon information, to the user terminal. This enables efficient search and recommendation of personalized stores that accept electronic payment, taking the user's emotional state into consideration.

[0636] The "information receiving means" is a means having the function of receiving a request input by a user and transmitting the request to a server.

[0637] "Natural language processing means" refers to a technology that analyzes requests entered by users and extracts keywords related to the requests.

[0638] The "search means" is a means having a function of searching for stores that accept electronic payments based on the extracted keywords and the user's geographical location information.

[0639] "Emotion analysis means" refers to a technique for estimating a user's emotional state from the user's past behavioral history and input content.

[0640] A "recommendation tool" is a tool that has the function of recommending the most suitable store to the user based on search results and emotional state.

[0641] The "information transmission means" is a means having a function of transmitting recommended store information, including navigation links and coupon information, to a user terminal.

[0642] The system of the present invention allows users to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes information receiving means, natural language processing means, search means, emotion analysis means, recommendation means, and information transmitting means.

[0643] First, a user launches a smartphone application and enters their request in the search box. For example, they might enter "I want to eat udon lunch for 800 yen" and press the send button. Next, the device sends this request and their current location information to the server. This request includes the user's desired conditions and geographic location.

[0644] The server analyzes the received request. Specifically, it uses natural language processing to extract keywords such as "budget 800 yen" and "udon lunch" from the user's input. This process uses NLP libraries such as Google Cloud Natural Language API and spaCy.

[0645] Next, the server searches a database for store information that accepts electronic payments based on the extracted keywords and the user's location information. This search is performed using a database management system such as MySQL or PostgreSQL.

[0646] The server then uses emotion analysis to estimate the user's emotional state based on the user's input and past behavioral history, using emotion analysis engines such as IBM Watson and Microsoft Azure Text Analytics.

[0647] The server generates a list of optimal stores based on the search results and emotional state using recommendation engines such as Apache Mahout and TensorFlow, taking into account the user's past payment history and behavioral history.

[0648] Finally, the server adds navigation links and coupon information to the generated store list and sends it to the terminal. This information is sent using a message queue such as a REST API or Apache Kafka. Finally, the terminal displays the received information in an easy-to-read format for the user, allowing the user to easily find the store they want.

[0649] For example, if a user inputs "I want to enjoy a cafe lunch with a budget of 1000 yen," the system will behave as follows:

[0650] 1. The user sends the above request from their smartphone.

[0651] 2. The device sends the request and current location information to the server.

[0652] 3. The server receives the request and uses NLP technology to extract the keywords "budget 1,000 yen" and "cafe lunch."

[0653] 4. The server searches the database for cafes that accept electronic payment and match the budget and location information.

[0654] 5. The server uses an emotion engine to estimate the user's emotional state based on the user's past behavior history and input. For example, if the server estimates that the user is tired, it will select an appropriate store.

[0655] 6. The server will then provide a personalized list of the best cafes for you, taking into account your emotional state and past visit history.

[0656] 7. The server sends a store list including navigation links and coupon links to the terminal.

[0657] 8. The terminal will display a list of stores to the user, providing detailed information and coupons.

[0658] Through the above process, users can efficiently find the store they want and are provided with personalized recommendations that match their emotional state.

[0659] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0660] Step 1:

[0661] User: Launches the smartphone application, enters a request in the search box, and submits it. For example, the user might enter, "I want to eat udon lunch with a budget of 800 yen." The input data (user request) is then sent to the next step.

[0662] Step 2:

[0663] Terminal: Acquires the request entered by the user and current location information and sends this to the server. For example, if the request data is "I want to eat udon lunch with a budget of 800 yen" and the location data is "latitude 35.6895, longitude 139.6917", this information is sent to the server. The input is the user's request and location information, and the output is the request data sent to the server.

[0664] Step 3:

[0665] Server: Analyzes the received request data (demands and location information) using natural language processing. Specifically, keywords such as "budget 800 yen" and "udon lunch" are extracted from the input. For example, using "Google Cloud Natural Language API" or "spaCy," "budget 800 yen" and "udon lunch" are recognized as key elements. The input is the request data, and the output is the extracted keywords.

[0666] Step 4:

[0667] Server: Using the search tool, search the database for stores that accept electronic payments based on the extracted keywords and the user's location information. For example, using "MySQL" or "PostgreSQL," search for stores that meet the conditions of "udon lunch" and "budget under 800 yen" based on location information. The input is the extracted keywords and location information, and the output is a list of matching stores.

[0668] Step 5:

[0669] Server: Using an emotion analysis engine, the server estimates the user's emotional state based on their input and past behavioral history. For example, if past data indicates that the user is "tired," it prioritizes stores where they can relax. This is achieved using technologies such as IBM Watson and Microsoft Azure Text Analytics. The input is the user's requests and past behavioral history, and the output is the estimated emotional state.

[0670] Step 6:

[0671] Server: Using a recommendation method, the server generates an optimal store list based on the estimated emotional state and search results. This list also reflects the user's past payment history and behavioral history. For example, suitable stores are selected using "Apache Mahout" or "TensorFlow." The input is the emotional state and search results, and the output is a personalized store list.

[0672] Step 7:

[0673] Server: Using an information transmission means, the server sends a list of optimal stores, including navigation links and coupon information, to the device. For example, detailed store information is sent using a REST API or Apache Kafka. The input is the personalized store list, and the output is the information sent to the device.

[0674] Step 8:

[0675] Terminal: Displays the received store list to the user in an appropriate format. Specifically, it provides detailed information and coupons, allowing the user to easily select a store. The input is the store list sent from the server, and the output is the information displayed in a format that the user can check.

[0676] The above is the processing flow of the system that finds appropriate stores based on the requests entered by the user, recommends them taking into consideration the user's emotional state, and finally provides information to the user.

[0677] (Application example 2)

[0678] 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."

[0679] When modern consumers choose a store, they are not only concerned with the price and location of products and services, but also with finding a store that suits their emotional state at the time. However, conventional search systems make recommendations without taking the user's emotional state into consideration, making it difficult to select a store that will provide high satisfaction. Furthermore, there is no system that can search for stores that accept electronic payments and make recommendations that simultaneously consider the user's emotional state. Therefore, there is a need to provide a system that allows users to quickly and easily find an appropriate store that suits their emotional state.

[0680] 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.

[0681] In this invention, the server includes information receiving means for receiving requests input by a user, analysis means for analyzing the request and extracting keywords related to the request, search means for searching for stores that accept electronic payment based on the extracted keywords, emotion analysis means for estimating the emotional state of the user, recommendation means for recommending the most suitable store based on the search results and emotion analysis results, and information sending means for sending information about the recommended store to a user terminal. This makes it possible to recommend the most suitable store taking into account the emotional state of the user.

[0682] The "information receiving means" is a means for receiving requests input by the user.

[0683] The "analysis means" is a means for analyzing the request and extracting keywords related to the request.

[0684] The "search means" is a means for searching for stores that accept electronic payments based on the extracted keywords.

[0685] The "emotion analysis means" is a means for analyzing the user's input content and past behavioral history to estimate the user's emotional state.

[0686] The "recommendation means" is a means for recommending the most suitable store based on the search results and the sentiment analysis results.

[0687] The "information transmission means" is a means for transmitting the recommended store information to the user terminal.

[0688] The "individualization means" refers to a means for making individualized store recommendations by the recommendation means by referring to the user's past payment data and behavioral history.

[0689] "Deep link information to a mini appli" is link information for directly launching a mini appli.

[0690] The system for realizing the present invention includes a plurality of processing steps for accepting requests input by a user, analyzing the requests, and searching for related stores. The hardware and software used in this embodiment of the system will be specifically described below.

[0691] Hardware and Software Use

[0692] 1. Terminal

[0693] Hardware: Smartphone

[0694] Software: Applications that accept user input (e.g., SmartPay, Shop Guide)

[0695] 2. Server

[0696] Software: Python, natural language processing engine (e.g., spaCy or NLTK), sentiment analysis model (e.g., BERT or RoBERTa), HTTP request library (e.g., requests), geolocation library (e.g., geopy)

[0697] Processing flow

[0698] Information receiving means

[0699] It accepts requests entered by the user on the terminal (e.g., "I would like to enjoy a cafe lunch with a budget of 1,000 yen") and sends this information to the server.

[0700] Analysis means

[0701] The server analyzes the received request and uses natural language processing (NLP) technology to extract keywords related to the request (e.g., "budget 1,000 yen" or "cafe lunch").

[0702] Search methods

[0703] The server searches the database for store information that accepts electronic payments based on the user's location information and the extracted keywords. The geopy library is used to obtain location information.

[0704] Emotion analysis means

[0705] The server estimates the user's emotional state based on the user's input and past behavioral history. An emotion analysis model (e.g., BERT or RoBERTa) is used to analyze the emotional state.

[0706] Recommendation methods

[0707] The server then recommends the most suitable store for the user based on the search results and sentiment analysis, taking into account past payment data and behavioral history.

[0708] Information transmission means

[0709] The server sends the recommended store information, including navigation links and coupon information, to the user's device.

[0710] Specific examples

[0711] Example input

[0712] User input: "I want to enjoy a cafe lunch on a budget of 1000 yen."

[0713] User mood: "Tired"

[0714] Prompt Sentence Examples

[0715] Text format

[0716] How I feel right now in one word: Tired

[0717] Example output

[0718] The server performs emotion analysis based on the above information and estimates the user's emotional state (e.g., tired). Next, it searches the database for cafes that accept electronic payment based on the user's location information. It then takes the user's emotional state into consideration and prioritizes recommendations of cafes where the user can relax. Finally, the following information is sent to the user's device:

[0719] Recommended stores include:

[0720] Store name: Relax Cafe, Address: 1-2-3 Shibuya-ku, Tokyo, Coupon: 50% off drinks

[0721] Store name: Healthy Cafe, Address: 4-5-6, Shinjuku-ku, Tokyo, Coupon: Free dessert

[0722] In this way, through a specific embodiment, a user can quickly and easily find a store that suits their emotional state.

[0723] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0724] Step 1:

[0725] The user starts the smartphone application, enters their request in the search box, and sends it. An example of input is "I would like to enjoy a cafe lunch with a budget of 1,000 yen." This input is accepted by the information receiving means and sent to the server. The input is in natural Japanese text format, and includes location information.

[0726] Step 2:

[0727] The server analyzes the user's request received by the information receiving means and extracts keywords related to the request using the analysis means. Specifically, it uses natural language processing technology (e.g., spaCy or NLTK) to extract keywords such as "budget 1,000 yen" and "cafe lunch." The input is the request text from the user, and the output is a list of extracted keywords.

[0728] Step 3:

[0729] The server uses a search function to search for stores that accept electronic payments using the user's location information based on the extracted keywords. It obtains the location information using a geolocation API (e.g., geopy library) and retrieves the corresponding store information from the database. The input is a list of keywords and location information, and the output is a list of corresponding stores.

[0730] Step 4:

[0731] The server uses emotion analysis to estimate the user's emotional state from their input and past behavioral history. It uses an emotion analysis model (e.g., BERT or RoBERTa) to analyze the input text and historical data to estimate the emotional state. It analyzes the user's emotional state based on a prompt such as "How do you feel right now in one word?" The input is text data and behavioral history, and the output is the estimated emotional state.

[0732] Step 5:

[0733] The server uses the recommendation means to recommend the most suitable store based on the search results and sentiment analysis results. At this time, the server also references the user's past payment data and generates personalized store information using the personalization means. This creates a list of stores that are suitable for the user's emotional state. The inputs are the search results, sentiment analysis results, and payment data, and the output is a list of recommended stores.

[0734] Step 6:

[0735] The server uses an information transmission means to send recommended store information to the user's terminal. The sent information includes detailed store information, navigation links, coupon information, etc. The user can check the received information on the application. The input is a list of recommended stores, and the output is store information displayed on the user's terminal.

[0736] Through these steps, the system is able to take into account the user's desires and emotional state and quickly recommend the most suitable store.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] [Third embodiment]

[0741] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0742] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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).

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] System Embodiments

[0754] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and, if necessary, a personalization means.

[0755] System configuration

[0756] 1. User Input

[0757] User: The user accesses the system using a mobile app and enters their request in a text box (e.g., "I would like to have an udon lunch with a budget of 800 yen").

[0758] 2. Means of receiving information

[0759] Device: The information entered by the user and the location information obtained from the device are sent to the server. This request includes the user's desired conditions and geographic location.

[0760] 3. Analysis method

[0761] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0762] 4. Search Methods

[0763] Server: Based on the extracted keywords, the server searches for appropriate stores from a store database that supports electronic payment. The search range is set based on the user's location information.

[0764] 5. Recommendation methods

[0765] Server: Generates an optimal list of stores based on the search results, taking into account the user's past payment history and behavioral history to achieve personalized recommendations.

[0766] 6. Means of information transmission

[0767] Server: The final list of selected stores is sent to the user's device along with navigation links and coupon information.

[0768] 7. Display

[0769] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0770] Specific examples

[0771] Below is an overview of the system's operation, including specific examples.

[0772] Example input:

[0773] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0774] System behavior:

[0775] 1. User: Submits the requested information.

[0776] 2. Device: Sends a request containing the desired location to the server.

[0777] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0778] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0779] 5. Server: Using a recommendation method, the server creates a personalized list of the best cafes, for example, based on past usage history.

[0780] 6. Server: The information transmission means transmits a store list including additional information (e.g., coupon links) to the terminal.

[0781] 7. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0782] This system allows users to efficiently find the store they want, and also makes it easier for stores to acquire new customers. In particular, by utilizing the user's past history, the accuracy of recommendations can be improved, providing a more satisfying consumer experience.

[0783] The processing flow will be explained below.

[0784] Step 1:

[0785] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0786] Step 2:

[0787] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0788] Step 3:

[0789] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0790] Step 4:

[0791] Server: Based on the extracted keywords, the server searches the database for store information that accepts electronic payments. At this time, the server sets the search range based on the user's location information.

[0792] Step 5:

[0793] Server: Information on multiple stores is obtained as search results. Based on this information, the optimal store is filtered based on the user's past payment history and behavioral history, creating a personalized store list.

[0794] Step 6:

[0795] Server: Generates data to provide to users, including store lists, navigation links, and coupon information.

[0796] Step 7:

[0797] Server: Sends the generated data to the user's terminal.

[0798] Step 8:

[0799] Device: Based on the received data, the device displays the store name, address, opening hours, price range, review rating, and coupon information in the most appropriate format for the user, making it easy for the user to access.

[0800] Step 9:

[0801] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0802] This series of processes allows users to easily and efficiently find the store they are looking for. In addition, by utilizing past history, personalized recommendations are provided, enabling a more satisfying consumption experience.

[0803] Example 1

[0804] 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."

[0805] Today's consumers face challenges in quickly and accurately finding facilities that meet their specific needs. Furthermore, the lack of personalized recommendations leveraging past data means that more sophisticated personalized recommendations are needed to increase user satisfaction. Furthermore, the information users receive is fragmented, and there is a lack of a unified platform for providing that information.

[0806] 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.

[0807] In this invention, the server includes a data receiving means for receiving requests entered by a user, a data acquisition means for collecting the requests and location information, a data analysis means for analyzing the requests and extracting keywords related to the requests, a data search means for searching for facilities that support electronic transactions based on the extracted keywords and location information, a recommendation means for recommending the most suitable facility based on the search results, and a data transmission means for transmitting the recommended facility information to a user device. This allows users to quickly and accurately find facilities that meet their specific needs. Furthermore, personalized recommendations based on past transaction data and behavioral history enhance user satisfaction. Furthermore, by including deep link information to mini-apps in the facility information, necessary information can be provided on a unified platform.

[0808] The "data receiving means" is a device or program for receiving requests input by a user.

[0809] "Data acquisition means" refers to a device or program for collecting user requests and location information.

[0810] The "data analysis means" is a device or program for analyzing a received request and extracting keywords related to the request.

[0811] The "data search means" is a device or program for searching a database for suitable facilities that support electronic transactions based on the extracted keywords and location information.

[0812] A "recommendation means" is a device or program for recommending optimal facilities to users based on search results.

[0813] The "data transmission means" is a device or program for transmitting recommended facility information to a user device.

[0814] The "personalization means" is a device or program that refers to the user's past transaction data and behavioral history and makes personalized recommendations for establishments based on that data.

[0815] "Deep link information to mini-app" is link information that directly accesses specific functions or pages within the app.

[0816] The present invention provides a system for enabling a user to quickly search for facilities that support electronic transactions and recommend the most suitable facility, which system includes a data receiving means, a data acquiring means, a data analyzing means, a data searching means, a recommending means, a data transmitting means, and, if necessary, a personalizing means.

[0817] Users access the system using a mobile device such as a smartphone. The data receiving means is a means for accepting requests entered by users. For example, a user might enter "I want to eat udon lunch for 800 yen" in a text box.

[0818] Next, the data acquisition means operates to acquire the user's current location information through the GPS function, and this location information is transmitted to the server in the form of latitude and longitude.

[0819] The server uses the data receiving means to receive the request and location information entered by the user.Then, the data analysis means applies natural language processing (NLP) technology to the received text data of the request to extract important keywords.For example, keywords such as "budget 800 yen" and "udon lunch" are extracted.

[0820] The data search means then operates to search for suitable facilities from a database of facilities that support electronic transactions based on the extracted keywords and location information. At this time, the search range is set based on the user's location information, and stores within a radius of 1 km are targeted, for example.

[0821] Once the search results are obtained, the recommendation mechanism works to generate an optimal list of facilities. This takes into account the user's past transaction data and behavioral history, and the personalization mechanism provides more accurate recommendations. Priority is given to facilities that the user has visited in the past and those with high ratings.

[0822] Finally, the generated facility list is sent to the user's device via the data transmission means. This list includes the store's name, address, rating, and a link to the coupon they offer. The device displays the received information in a user-friendly format. For example, the store list may be displayed on a map, and clicking on it will display detailed information.

[0823] Examples:

[0824] If a user enters "I would like to enjoy a cafe lunch with a budget of 1,000 yen," the system will behave as follows:

[0825] 1. The user enters their request into a text box and sends it along with their location information to the server.

[0826] 2. The server receives the text data and location information and uses NLP technology to extract "budget 1,000 yen" and "cafe lunch."

[0827] 3. The data search means searches for e-commerce enabled cafes within the specified budget and location range.

[0828] 4. The recommendation method is to individually list the most suitable cafes based on past usage history.

[0829] 5. The data transmission means transmits the store list including the additional information (e.g., coupon link) to the terminal.

[0830] 6. The terminal displays a list of stores to the user and provides detailed information and coupons.

[0831] Example prompt sentence:

[0832] "Please tell me where I can enjoy a cafe lunch for 1000 yen. Please also take my current location into consideration."

[0833] This system allows users to efficiently find the facilities they want, and makes it easier for facilities to acquire new customers. In addition, by utilizing past history, the accuracy of recommendations can be improved, allowing for the provision of highly satisfying services.

[0834] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0835] Step 1:

[0836] The user opens the mobile app and enters their request into the text box. For example, they might enter "I want to eat udon lunch for 800 yen." This is the user's request (input). The entered request is sent to the server.

[0837] Step 2:

[0838] The device uses the GPS function to obtain the current location information. The location information is obtained in the form of latitude and longitude and sent to the server. This becomes the location information (input).

[0839] Step 3:

[0840] The server receives the user's request and location information using the data receiving means, and proceeds to the next process based on the received data (request and location information).

[0841] Step 4:

[0842] The server uses data analysis tools to apply natural language processing (NLP) technology to the received request data. Specifically, it extracts the condition "budget 800 yen" and the keyword "udon lunch." The input is the request data, and the output is the extracted keywords.

[0843] Step 5:

[0844] The server uses a data search tool to search for stores in an electronic transaction-compatible facility database based on the extracted keywords. The search range is set based on the user's location information. For example, search for facilities that offer "udon lunch" within a budget of 800 yen and within a 1km radius of the current location (latitude, longitude). The input is the keyword and location information, and the output is the search results (a list of facilities).

[0845] Step 6:

[0846] The server uses the recommendation method to generate an optimal facility list based on the search results. In doing so, it references the user's past transaction data and behavioral history to enhance the recommendation level. For example, it prioritizes facilities that have been visited in the past or highly rated facilities to include in the list. The input is the search results, and the output is a personalized list of recommended facilities.

[0847] Step 7:

[0848] The server uses a data transmission means to transmit the recommended facility information to the user's terminal. The transmitted information includes the facility name, address, rating, navigation link, coupon link, etc. The input is the recommended facility list, and the output is the transmitted facility information.

[0849] Step 8:

[0850] The terminal displays the received facility information to the user in an appropriate format. Specifically, a list of stores is marked on a map, and when the user clicks, detailed information is displayed. This allows the user to easily find facilities that meet their criteria. The input is facility information sent from the server, and the output is display information that the user can view.

[0851] (Application example 1)

[0852] 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."

[0853] Users have difficulty easily searching for and finding the best electronic payment-accepting facilities that meet their desired criteria. Furthermore, there is a lack of facility recommendations that take into account the user's current location information and past payment history, making it difficult to provide more accurate, personalized recommendations. This results in reduced user satisfaction and inconvenience. The purpose of this invention is to solve these problems and provide an environment in which users can quickly and accurately find electronic payment-accepting facilities that meet their desired criteria.

[0854] 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.

[0855] In this invention, the server includes an information receiving means for receiving requests entered by a user, an analysis means for analyzing the request and extracting keywords related to the request, and a search means for searching for facilities that accept electronic payment based on the extracted keywords and location information. This enables searches based on the user's desired conditions and current location, making it possible to quickly and accurately recommend optimal facilities that accept electronic payment. Furthermore, by adding a personalization means that references past payment data and behavioral history, it is possible to provide more accurate and personalized recommendations. This improves user satisfaction and realizes efficient facility searches.

[0856] The "information receiving means" is a means for accepting requests input by the user, and serves to receive the user's desired conditions.

[0857] The "analysis means" is a means having a function of analyzing a received request and extracting keywords related to the request.

[0858] The "search means" is a means having a function of searching for facilities that accept electronic payment based on the extracted keywords and location information.

[0859] "Recommendation methods" are methods that recommend the most suitable facilities to users based on search results.

[0860] The "information transmission means" is a means for transmitting recommended facility information to the user terminal.

[0861] "Individualization means" refers to a means of making personalized recommendations by referencing a user's past payment data and behavioral history.

[0862] "Location information" is information that indicates the user's current geographic location and is obtained from the user's device, such as a smartphone.

[0863] "Navigation link" refers to link information that allows a user to confirm or navigate to a recommended facility.

[0864] "Coupon information" is information that allows users to receive discounts and benefits available at recommended facilities.

[0865] "Facilities" refers to commercial establishments and stores that accept electronic payments.

[0866] Overall system configuration

[0867] This invention relates to a system that allows users to easily search for facilities that accept electronic payments and recommends the most suitable facility. The system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and a personalization means.

[0868] Information receiving means

[0869] The user uses a smartphone application to input their request. For example, they might input, "I want to eat sushi lunch for 2,000 yen." The smartphone's GPS function also acquires the user's current location information. This information receiving means plays a role in transmitting the user's request and location information to the server.

[0870] Analysis means

[0871] The server uses natural language processing (NLP) techniques to analyze the received user request. It uses an NLP model like SpaCy to extract important keywords (e.g., "budget 2000 yen" and "sushi") from the request.

[0872] Search methods

[0873] The server searches the database for facilities that accept electronic payments based on the extracted keywords and location information, and uses Geopy to process the location information and generate a list of facilities that accept electronic payments.

[0874] Recommendation methods

[0875] Based on the search results, the server recommends the most suitable facilities for the user. By taking into account past payment history and behavioral history, personalized recommendations are provided, allowing users to find facilities that will provide them with the highest level of satisfaction.

[0876] Information transmission means

[0877] The server then sends the final recommended facility information, including navigation links and coupon information, to the user's smartphone.

[0878] Specific examples

[0879] When a user enters "I want to enjoy an Italian dinner on a budget of 3,000 yen" and sends their request and location information from their smartphone to the server, the server analyzes the information and extracts keywords. It then searches for Italian restaurants that accept electronic payments and generates personalized recommendations based on the user's past usage history. Finally, it sends a list of recommended restaurants, including navigation links and coupon information, to the user's smartphone.

[0880] Hardware and software used

[0881] The hardware includes a smartphone operated by the user and a server that processes data. The software uses libraries such as SpaCy and Geopy. A generative AI model is also used for NLP analysis. An example of a prompt for the generative AI model is:

[0882] "Please generate a script that analyzes the input text request, extracts the budget and type of cuisine, searches for stores that accept electronic payments within the specified range, and generates optimal recommendations taking into account the user's history."

[0883] is used.

[0884] This embodiment allows users to quickly and accurately find electronic payment-enabled establishments that meet their desired criteria, thereby increasing user satisfaction and efficiency.

[0885] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0886] Step 1:

[0887] The user enters their request into the text box on their smartphone. For example, they might type, "I'd like to have a sushi lunch for 2,000 yen," and press the send button. At this time, the smartphone's GPS function also obtains the user's current location information.

[0888] Input: User's request (text data) and location information (latitude and longitude)

[0889] Output: Request data with your wishes and location sent to the server

[0890] Step 2:

[0891] The server receives the user's request and location information using the information receiving means, and the received data is passed to the analyzing means.

[0892] Input: Request data including user's wishes and location information

[0893] Output: Pre-analysis data to be passed to the analysis tool

[0894] Step 3:

[0895] The server analyzes the received request using its analysis tools. During this process, it uses natural language processing (NLP) technology and utilizes SpaCy to extract important keywords from the request (e.g., "budget 2000 yen" and "sushi").

[0896] Input: Pre-analysis data (user request and location information)

[0897] Output: Extracted keywords ("budget 2000 yen", "sushi")

[0898] Step 4:

[0899] The server uses a search function to search the database for facilities that accept electronic payment based on the extracted keywords and location information, processes the location information using the Geopy library, and lists the facilities within the search range.

[0900] Input: Extracted keywords and location information

[0901] Output: A list of facilities as search results

[0902] Step 5:

[0903] The server uses the recommendation means to recommend optimal facilities to the user based on the search results, and further uses the personalization means to generate personalized recommendations taking into account the user's past payment history and behavioral history.

[0904] Input: Facility list and user's past payment history and behavior history

[0905] Output: A personalized list of recommended facilities

[0906] Step 6:

[0907] The server then uses the information transmission means to send the final recommended facility information, including navigation links and coupon information, to the user's smartphone. The user can then check the recommended facility information on their smartphone.

[0908] Input: personalized recommended facility list

[0909] Output: Recommended facility information sent to the user's device (including navigation links and coupon information)

[0910] Processing steps for specific examples (example of prompt sentences)

[0911] Step 1:

[0912] The user enters "I want to enjoy an Italian dinner on a budget of 3000 yen" and sends a request including their current location to the server.

[0913] Input: User request "I want to enjoy an Italian dinner for 3000 yen", current location information

[0914] Output: Received request data

[0915] Step 2:

[0916] The server receives the request data and converts it into pre-analysis data.

[0917] Input: Request data

[0918] Output: Pre-analysis data

[0919] Step 3:

[0920] The server uses natural language processing to extract "budget 3,000 yen" and "Italian dinner."

[0921] Input: Data before analysis ("Budget 3000 yen", "Italian dinner")

[0922] Output: Extracted keywords

[0923] Step 4:

[0924] The server uses a search means to search for Italian restaurants that accept electronic payment.

[0925] Input: Extracted keywords, location information

[0926] Output: Facility list

[0927] Step 5:

[0928] The server generates personalized recommended facilities based on the user's past usage history.

[0929] Input: Facility list, past payment history and behavior history

[0930] Output: A personalized list of recommended facilities

[0931] Step 6:

[0932] The server sends the final facility information to the user's smartphone, along with navigation links and coupon information, allowing the user to check all the information on their smartphone.

[0933] Input: personalized recommended facility list

[0934] Output: Recommended facility information sent to the user's device

[0935] 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.

[0936] System Embodiments

[0937] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, a personalization means, and an emotion engine.

[0938] System configuration

[0939] 1. User Input

[0940] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0941] 2. Means of receiving information

[0942] Device: Sends the user's input request and current location information to the server. This request includes the user's desired conditions and geographic location.

[0943] 3. Analysis method

[0944] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[0945] 4. Search Methods

[0946] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payment. The search range is set based on the user's location information.

[0947] 5. Emotion Engine

[0948] Server: Analyzes the user's input and past behavioral history to estimate the user's emotional state. This estimation result is taken into account in the next recommendation method.

[0949] 6. Recommendation methods

[0950] Server: Generates a list of optimal stores based on the search results and the emotional state estimated by the emotion engine. This list also takes into account the user's past payment history and behavioral history.

[0951] 7. Means of information transmission

[0952] Server: The generated store list is sent to the user's device along with navigation links and coupon information.

[0953] 8. Display

[0954] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[0955] Specific examples

[0956] Below is an overview of the system's operation, including specific examples.

[0957] Example input:

[0958] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[0959] System behavior:

[0960] 1. User: Submits the requested information.

[0961] 2. Device: Sends a request containing the desired location to the server.

[0962] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[0963] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[0964] 5. Server: The emotion engine uses the user's past behavioral history and input data to estimate the user's emotional state. For example, if the server estimates that the user is tired, it selects an appropriate store.

[0965] 6. Server: Recommends the best cafes to the user based on their past usage history and emotional state.

[0966] 7. Server: The information transmission means transmits the store list including additional information (e.g., coupon links) to the terminal.

[0967] 8. Terminal: Shows users a list of stores and provides detailed information and coupons.

[0968] This system allows users to efficiently find the store they want. In addition, by utilizing an emotion engine, recommendations that match the user's emotional state are provided, resulting in a more personalized service. This makes it easier for stores to attract new customers and increases user satisfaction.

[0969] The processing flow will be explained below.

[0970] Step 1:

[0971] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[0972] Step 2:

[0973] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[0974] Step 3:

[0975] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[0976] Step 4:

[0977] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payments. The search range is set based on the user's location information.

[0978] Step 5:

[0979] Server: Based on the user's input and related data, the emotion engine estimates the user's emotional state.

[0980] Step 6:

[0981] Server: Adjust search results based on the emotional state estimated by the emotion engine. For example, if you are in a relaxing mood, prioritize stores with quiet environments.

[0982] Step 7:

[0983] Server: Generates an optimal list of stores based on search results and filtering based on emotional state. It also provides personalized recommendations based on the user's past payment history and behavioral history.

[0984] Step 8:

[0985] Server: Adds navigation links and coupon information to the generated store list and sends it to the user's device.

[0986] Step 9:

[0987] Device: The received store list is displayed to the user, including the store name, address, opening hours, price range, review rating, and coupon information.

[0988] Step 10:

[0989] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[0990] This series of processes allows users to easily find the best store within their budget. Using an emotion engine, recommendations that match the user's emotional state are realized, providing a more personalized experience. This also makes it easier for stores to acquire new customers and increases user satisfaction.

[0991] Example 2

[0992] 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."

[0993] Conventional store search systems have had issues with their inability to provide recommendations that take into account the user's emotional state. They also lack the ability to provide personalized recommendations based on past behavioral history and payment data. Furthermore, they also lack the ability to efficiently search for stores that accept electronic payments based on the user's current location.

[0994] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information receiving means for receiving a request input by a user, a natural language processing means for analyzing the request and extracting keywords related to the request, a search means for searching for stores that accept electronic payment based on the extracted keywords and the user's geographical location information, an emotion analysis means for estimating the user's emotional state from the user's past behavioral history and input content, a recommendation means for recommending the most suitable store based on the search results and the user's emotional state, and an information sending means for sending the recommended store information, including navigation links and coupon information, to the user terminal. This enables efficient search and recommendation of personalized stores that accept electronic payment, taking the user's emotional state into consideration.

[0995] The "information receiving means" is a means having the function of receiving a request input by a user and transmitting the request to a server.

[0996] "Natural language processing means" refers to a technology that analyzes requests entered by users and extracts keywords related to the requests.

[0997] The "search means" is a means having a function of searching for stores that accept electronic payments based on the extracted keywords and the user's geographical location information.

[0998] "Emotion analysis means" refers to a technique for estimating a user's emotional state from the user's past behavioral history and input content.

[0999] A "recommendation tool" is a tool that has the function of recommending the most suitable store to the user based on search results and emotional state.

[1000] The "information transmission means" is a means having a function of transmitting recommended store information, including navigation links and coupon information, to a user terminal.

[1001] The system of the present invention allows users to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes information receiving means, natural language processing means, search means, emotion analysis means, recommendation means, and information transmitting means.

[1002] First, a user launches a smartphone application and enters their request in the search box. For example, they might enter "I want to eat udon lunch for 800 yen" and press the send button. Next, the device sends this request and their current location information to the server. This request includes the user's desired conditions and geographic location.

[1003] The server analyzes the received request. Specifically, it uses natural language processing to extract keywords such as "budget 800 yen" and "udon lunch" from the user's input. This process uses NLP libraries such as Google Cloud Natural Language API and spaCy.

[1004] Next, the server searches a database for store information that accepts electronic payments based on the extracted keywords and the user's location information. This search is performed using a database management system such as MySQL or PostgreSQL.

[1005] The server then uses emotion analysis to estimate the user's emotional state based on the user's input and past behavioral history, using emotion analysis engines such as IBM Watson and Microsoft Azure Text Analytics.

[1006] The server generates a list of optimal stores based on the search results and emotional state using recommendation engines such as Apache Mahout and TensorFlow, taking into account the user's past payment history and behavioral history.

[1007] Finally, the server adds navigation links and coupon information to the generated store list and sends it to the terminal. This information is sent using a message queue such as a REST API or Apache Kafka. Finally, the terminal displays the received information in an easy-to-read format for the user, allowing the user to easily find the store they want.

[1008] For example, if a user inputs "I want to enjoy a cafe lunch with a budget of 1000 yen," the system will behave as follows:

[1009] 1. The user sends the above request from their smartphone.

[1010] 2. The device sends the request and current location information to the server.

[1011] 3. The server receives the request and uses NLP technology to extract the keywords "budget 1,000 yen" and "cafe lunch."

[1012] 4. The server searches the database for cafes that accept electronic payment and match the budget and location information.

[1013] 5. The server uses an emotion engine to estimate the user's emotional state based on the user's past behavior history and input. For example, if the server estimates that the user is tired, it will select an appropriate store.

[1014] 6. The server will then provide a personalized list of the best cafes for you, taking into account your emotional state and past visit history.

[1015] 7. The server sends a store list including navigation links and coupon links to the terminal.

[1016] 8. The terminal will display a list of stores to the user, providing detailed information and coupons.

[1017] Through the above process, users can efficiently find the store they want and are provided with personalized recommendations that match their emotional state.

[1018] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1019] Step 1:

[1020] User: Launches the smartphone application, enters a request in the search box, and submits it. For example, the user might enter, "I want to eat udon lunch with a budget of 800 yen." The input data (user request) is then sent to the next step.

[1021] Step 2:

[1022] Terminal: Acquires the request entered by the user and current location information and sends this to the server. For example, if the request data is "I want to eat udon lunch with a budget of 800 yen" and the location data is "latitude 35.6895, longitude 139.6917", this information is sent to the server. The input is the user's request and location information, and the output is the request data sent to the server.

[1023] Step 3:

[1024] Server: Analyzes the received request data (demands and location information) using natural language processing. Specifically, keywords such as "budget 800 yen" and "udon lunch" are extracted from the input. For example, using "Google Cloud Natural Language API" or "spaCy," "budget 800 yen" and "udon lunch" are recognized as key elements. The input is the request data, and the output is the extracted keywords.

[1025] Step 4:

[1026] Server: Using the search tool, search the database for stores that accept electronic payments based on the extracted keywords and the user's location information. For example, using "MySQL" or "PostgreSQL," search for stores that meet the conditions of "udon lunch" and "budget under 800 yen" based on location information. The input is the extracted keywords and location information, and the output is a list of matching stores.

[1027] Step 5:

[1028] Server: Using an emotion analysis engine, the server estimates the user's emotional state based on their input and past behavioral history. For example, if past data indicates that the user is "tired," it prioritizes stores where they can relax. This is achieved using technologies such as IBM Watson and Microsoft Azure Text Analytics. The input is the user's requests and past behavioral history, and the output is the estimated emotional state.

[1029] Step 6:

[1030] Server: Using a recommendation method, the server generates an optimal store list based on the estimated emotional state and search results. This list also reflects the user's past payment history and behavioral history. For example, suitable stores are selected using "Apache Mahout" or "TensorFlow." The input is the emotional state and search results, and the output is a personalized store list.

[1031] Step 7:

[1032] Server: Using an information transmission means, the server sends a list of optimal stores, including navigation links and coupon information, to the device. For example, detailed store information is sent using a REST API or Apache Kafka. The input is the personalized store list, and the output is the information sent to the device.

[1033] Step 8:

[1034] Terminal: Displays the received store list to the user in an appropriate format. Specifically, it provides detailed information and coupons, allowing the user to easily select a store. The input is the store list sent from the server, and the output is the information displayed in a format that the user can check.

[1035] The above is the processing flow of the system that finds appropriate stores based on the requests entered by the user, recommends them taking into consideration the user's emotional state, and finally provides information to the user.

[1036] (Application example 2)

[1037] 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."

[1038] When modern consumers choose a store, they are not only concerned with the price and location of products and services, but also with finding a store that suits their emotional state at the time. However, conventional search systems make recommendations without taking the user's emotional state into consideration, making it difficult to select a store that will provide high satisfaction. Furthermore, there is no system that can search for stores that accept electronic payments and make recommendations that simultaneously consider the user's emotional state. Therefore, there is a need to provide a system that allows users to quickly and easily find an appropriate store that suits their emotional state.

[1039] 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.

[1040] In this invention, the server includes information receiving means for receiving requests input by a user, analysis means for analyzing the request and extracting keywords related to the request, search means for searching for stores that accept electronic payment based on the extracted keywords, emotion analysis means for estimating the emotional state of the user, recommendation means for recommending the most suitable store based on the search results and emotion analysis results, and information sending means for sending information about the recommended store to a user terminal. This makes it possible to recommend the most suitable store taking into account the emotional state of the user.

[1041] The "information receiving means" is a means for receiving requests input by the user.

[1042] The "analysis means" is a means for analyzing the request and extracting keywords related to the request.

[1043] The "search means" is a means for searching for stores that accept electronic payments based on the extracted keywords.

[1044] The "emotion analysis means" is a means for analyzing the user's input content and past behavioral history to estimate the user's emotional state.

[1045] The "recommendation means" is a means for recommending the most suitable store based on the search results and the sentiment analysis results.

[1046] The "information transmission means" is a means for transmitting the recommended store information to the user terminal.

[1047] The "individualization means" refers to a means for making individualized store recommendations by the recommendation means by referring to the user's past payment data and behavioral history.

[1048] "Deep link information to a mini appli" is link information for directly launching a mini appli.

[1049] The system for realizing the present invention includes a plurality of processing steps for accepting requests input by a user, analyzing the requests, and searching for related stores. The hardware and software used in this embodiment of the system will be specifically described below.

[1050] Hardware and Software Use

[1051] 1. Terminal

[1052] Hardware: Smartphone

[1053] Software: Applications that accept user input (e.g., SmartPay, Shop Guide)

[1054] 2. Server

[1055] Software: Python, natural language processing engine (e.g., spaCy or NLTK), sentiment analysis model (e.g., BERT or RoBERTa), HTTP request library (e.g., requests), geolocation library (e.g., geopy)

[1056] Processing flow

[1057] Information receiving means

[1058] It accepts requests entered by the user on the terminal (e.g., "I would like to enjoy a cafe lunch with a budget of 1,000 yen") and sends this information to the server.

[1059] Analysis means

[1060] The server analyzes the received request and uses natural language processing (NLP) technology to extract keywords related to the request (e.g., "budget 1,000 yen" or "cafe lunch").

[1061] Search methods

[1062] The server searches the database for store information that accepts electronic payments based on the user's location information and the extracted keywords. The geopy library is used to obtain location information.

[1063] Emotion analysis means

[1064] The server estimates the user's emotional state based on the user's input and past behavioral history. An emotion analysis model (e.g., BERT or RoBERTa) is used to analyze the emotional state.

[1065] Recommendation methods

[1066] The server then recommends the most suitable store for the user based on the search results and sentiment analysis, taking into account past payment data and behavioral history.

[1067] Information transmission means

[1068] The server sends the recommended store information, including navigation links and coupon information, to the user's device.

[1069] Specific examples

[1070] Example input

[1071] User input: "I want to enjoy a cafe lunch on a budget of 1000 yen."

[1072] User mood: "Tired"

[1073] Prompt Sentence Examples

[1074] Text format

[1075] How I feel right now in one word: Tired

[1076] Example output

[1077] The server performs emotion analysis based on the above information and estimates the user's emotional state (e.g., tired). Next, it searches the database for cafes that accept electronic payment based on the user's location information. It then takes the user's emotional state into consideration and prioritizes recommendations of cafes where the user can relax. Finally, the following information is sent to the user's device:

[1078] Recommended stores include:

[1079] Store name: Relax Cafe, Address: 1-2-3 Shibuya-ku, Tokyo, Coupon: 50% off drinks

[1080] Store name: Healthy Cafe, Address: 4-5-6, Shinjuku-ku, Tokyo, Coupon: Free dessert

[1081] In this way, through a specific embodiment, a user can quickly and easily find a store that suits their emotional state.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] The user starts the smartphone application, enters their request in the search box, and sends it. An example of input is "I would like to enjoy a cafe lunch with a budget of 1,000 yen." This input is accepted by the information receiving means and sent to the server. The input is in natural Japanese text format, and includes location information.

[1085] Step 2:

[1086] The server analyzes the user's request received by the information receiving means and extracts keywords related to the request using the analysis means. Specifically, it uses natural language processing technology (e.g., spaCy or NLTK) to extract keywords such as "budget 1,000 yen" and "cafe lunch." The input is the request text from the user, and the output is a list of extracted keywords.

[1087] Step 3:

[1088] The server uses a search function to search for stores that accept electronic payments using the user's location information based on the extracted keywords. It obtains the location information using a geolocation API (e.g., geopy library) and retrieves the corresponding store information from the database. The input is a list of keywords and location information, and the output is a list of corresponding stores.

[1089] Step 4:

[1090] The server uses emotion analysis to estimate the user's emotional state from their input and past behavioral history. It uses an emotion analysis model (e.g., BERT or RoBERTa) to analyze the input text and historical data to estimate the emotional state. It analyzes the user's emotional state based on a prompt such as "How do you feel right now in one word?" The input is text data and behavioral history, and the output is the estimated emotional state.

[1091] Step 5:

[1092] The server uses the recommendation means to recommend the most suitable store based on the search results and sentiment analysis results. At this time, the server also references the user's past payment data and generates personalized store information using the personalization means. This creates a list of stores that are suitable for the user's emotional state. The inputs are the search results, sentiment analysis results, and payment data, and the output is a list of recommended stores.

[1093] Step 6:

[1094] The server uses an information transmission means to send recommended store information to the user's terminal. The sent information includes detailed store information, navigation links, coupon information, etc. The user can check the received information on the application. The input is a list of recommended stores, and the output is store information displayed on the user's terminal.

[1095] Through these steps, the system is able to take into account the user's desires and emotional state and quickly recommend the most suitable store.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] [Fourth embodiment]

[1100] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1101] 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.

[1102] 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).

[1103] 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.

[1104] 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.

[1105] 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).

[1106] 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.

[1107] 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.

[1108] 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.

[1109] 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.

[1110] 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.

[1111] 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.

[1112] 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."

[1113] System Embodiments

[1114] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and, if necessary, a personalization means.

[1115] System configuration

[1116] 1. User Input

[1117] User: The user accesses the system using a mobile app and enters their request in a text box (e.g., "I would like to have an udon lunch with a budget of 800 yen").

[1118] 2. Means of receiving information

[1119] Device: The information entered by the user and the location information obtained from the device are sent to the server. This request includes the user's desired conditions and geographic location.

[1120] 3. Analysis method

[1121] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[1122] 4. Search Methods

[1123] Server: Based on the extracted keywords, the server searches for appropriate stores from a store database that supports electronic payment. The search range is set based on the user's location information.

[1124] 5. Recommendation methods

[1125] Server: Generates an optimal list of stores based on the search results, taking into account the user's past payment history and behavioral history to achieve personalized recommendations.

[1126] 6. Means of information transmission

[1127] Server: The final list of selected stores is sent to the user's device along with navigation links and coupon information.

[1128] 7. Display

[1129] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[1130] Specific examples

[1131] Below is an overview of the system's operation, including specific examples.

[1132] Example input:

[1133] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[1134] System behavior:

[1135] 1. User: Submits the requested information.

[1136] 2. Device: Sends a request containing the desired location to the server.

[1137] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[1138] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[1139] 5. Server: Using a recommendation method, the server creates a personalized list of the best cafes, for example, based on past usage history.

[1140] 6. Server: The information transmission means transmits a store list including additional information (e.g., coupon links) to the terminal.

[1141] 7. Terminal: Shows users a list of stores and provides detailed information and coupons.

[1142] This system allows users to efficiently find the store they want, and also makes it easier for stores to acquire new customers. In particular, by utilizing the user's past history, the accuracy of recommendations can be improved, providing a more satisfying consumer experience.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[1146] Step 2:

[1147] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[1148] Step 3:

[1149] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[1150] Step 4:

[1151] Server: Based on the extracted keywords, the server searches the database for store information that accepts electronic payments. At this time, the server sets the search range based on the user's location information.

[1152] Step 5:

[1153] Server: Information on multiple stores is obtained as search results. Based on this information, the optimal store is filtered based on the user's past payment history and behavioral history, creating a personalized store list.

[1154] Step 6:

[1155] Server: Generates data to provide to users, including store lists, navigation links, and coupon information.

[1156] Step 7:

[1157] Server: Sends the generated data to the user's terminal.

[1158] Step 8:

[1159] Device: Based on the received data, the device displays the store name, address, opening hours, price range, review rating, and coupon information in the most appropriate format for the user, making it easy for the user to access.

[1160] Step 9:

[1161] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[1162] This series of processes allows users to easily and efficiently find the store they are looking for. In addition, by utilizing past history, personalized recommendations are provided, enabling a more satisfying consumption experience.

[1163] Example 1

[1164] 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."

[1165] Today's consumers face challenges in quickly and accurately finding facilities that meet their specific needs. Furthermore, the lack of personalized recommendations leveraging past data means that more sophisticated personalized recommendations are needed to increase user satisfaction. Furthermore, the information users receive is fragmented, and there is a lack of a unified platform for providing that information.

[1166] 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.

[1167] In this invention, the server includes a data receiving means for receiving requests entered by a user, a data acquisition means for collecting the requests and location information, a data analysis means for analyzing the requests and extracting keywords related to the requests, a data search means for searching for facilities that support electronic transactions based on the extracted keywords and location information, a recommendation means for recommending the most suitable facility based on the search results, and a data transmission means for transmitting the recommended facility information to a user device. This allows users to quickly and accurately find facilities that meet their specific needs. Furthermore, personalized recommendations based on past transaction data and behavioral history enhance user satisfaction. Furthermore, by including deep link information to mini-apps in the facility information, necessary information can be provided on a unified platform.

[1168] The "data receiving means" is a device or program for receiving requests input by a user.

[1169] "Data acquisition means" refers to a device or program for collecting user requests and location information.

[1170] The "data analysis means" is a device or program for analyzing a received request and extracting keywords related to the request.

[1171] The "data search means" is a device or program for searching a database for suitable facilities that support electronic transactions based on the extracted keywords and location information.

[1172] A "recommendation means" is a device or program for recommending optimal facilities to users based on search results.

[1173] The "data transmission means" is a device or program for transmitting recommended facility information to a user device.

[1174] The "personalization means" is a device or program that refers to the user's past transaction data and behavioral history and makes personalized recommendations for establishments based on that data.

[1175] "Deep link information to mini-app" is link information that directly accesses specific functions or pages within the app.

[1176] The present invention provides a system for enabling a user to quickly search for facilities that support electronic transactions and recommend the most suitable facility, which system includes a data receiving means, a data acquiring means, a data analyzing means, a data searching means, a recommending means, a data transmitting means, and, if necessary, a personalizing means.

[1177] Users access the system using a mobile device such as a smartphone. The data receiving means is a means for accepting requests entered by users. For example, a user might enter "I want to eat udon lunch for 800 yen" in a text box.

[1178] Next, the data acquisition means operates to acquire the user's current location information through the GPS function, and this location information is transmitted to the server in the form of latitude and longitude.

[1179] The server uses the data receiving means to receive the request and location information entered by the user.Then, the data analysis means applies natural language processing (NLP) technology to the received text data of the request to extract important keywords.For example, keywords such as "budget 800 yen" and "udon lunch" are extracted.

[1180] The data search means then operates to search for suitable facilities from a database of facilities that support electronic transactions based on the extracted keywords and location information. At this time, the search range is set based on the user's location information, and stores within a radius of 1 km are targeted, for example.

[1181] Once the search results are obtained, the recommendation mechanism works to generate an optimal list of facilities. This takes into account the user's past transaction data and behavioral history, and the personalization mechanism provides more accurate recommendations. Priority is given to facilities that the user has visited in the past and those with high ratings.

[1182] Finally, the generated facility list is sent to the user's device via the data transmission means. This list includes the store's name, address, rating, and a link to the coupon they offer. The device displays the received information in a user-friendly format. For example, the store list may be displayed on a map, and clicking on it will display detailed information.

[1183] Examples:

[1184] If a user enters "I would like to enjoy a cafe lunch with a budget of 1,000 yen," the system will behave as follows:

[1185] 1. The user enters their request into a text box and sends it along with their location information to the server.

[1186] 2. The server receives the text data and location information and uses NLP technology to extract "budget 1,000 yen" and "cafe lunch."

[1187] 3. The data search means searches for e-commerce enabled cafes within the specified budget and location range.

[1188] 4. The recommendation method is to individually list the most suitable cafes based on past usage history.

[1189] 5. The data transmission means transmits the store list including the additional information (e.g., coupon link) to the terminal.

[1190] 6. The terminal displays a list of stores to the user and provides detailed information and coupons.

[1191] Example prompt sentence:

[1192] "Please tell me where I can enjoy a cafe lunch for 1000 yen. Please also take my current location into consideration."

[1193] This system allows users to efficiently find the facilities they want, and makes it easier for facilities to acquire new customers. In addition, by utilizing past history, the accuracy of recommendations can be improved, allowing for the provision of highly satisfying services.

[1194] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1195] Step 1:

[1196] The user opens the mobile app and enters their request into the text box. For example, they might enter "I want to eat udon lunch for 800 yen." This is the user's request (input). The entered request is sent to the server.

[1197] Step 2:

[1198] The device uses the GPS function to obtain the current location information. The location information is obtained in the form of latitude and longitude and sent to the server. This becomes the location information (input).

[1199] Step 3:

[1200] The server receives the user's request and location information using the data receiving means, and proceeds to the next process based on the received data (request and location information).

[1201] Step 4:

[1202] The server uses data analysis tools to apply natural language processing (NLP) technology to the received request data. Specifically, it extracts the condition "budget 800 yen" and the keyword "udon lunch." The input is the request data, and the output is the extracted keywords.

[1203] Step 5:

[1204] The server uses a data search tool to search for stores in an electronic transaction-compatible facility database based on the extracted keywords. The search range is set based on the user's location information. For example, search for facilities that offer "udon lunch" within a budget of 800 yen and within a 1km radius of the current location (latitude, longitude). The input is the keyword and location information, and the output is the search results (a list of facilities).

[1205] Step 6:

[1206] The server uses the recommendation method to generate an optimal facility list based on the search results. In doing so, it references the user's past transaction data and behavioral history to enhance the recommendation level. For example, it prioritizes facilities that have been visited in the past or highly rated facilities to include in the list. The input is the search results, and the output is a personalized list of recommended facilities.

[1207] Step 7:

[1208] The server uses a data transmission means to transmit the recommended facility information to the user's terminal. The transmitted information includes the facility name, address, rating, navigation link, coupon link, etc. The input is the recommended facility list, and the output is the transmitted facility information.

[1209] Step 8:

[1210] The terminal displays the received facility information to the user in an appropriate format. Specifically, a list of stores is marked on a map, and when the user clicks, detailed information is displayed. This allows the user to easily find facilities that meet their criteria. The input is facility information sent from the server, and the output is display information that the user can view.

[1211] (Application example 1)

[1212] 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."

[1213] Users have difficulty easily searching for and finding the best electronic payment-accepting facilities that meet their desired criteria. Furthermore, there is a lack of facility recommendations that take into account the user's current location information and past payment history, making it difficult to provide more accurate, personalized recommendations. This results in reduced user satisfaction and inconvenience. The purpose of this invention is to solve these problems and provide an environment in which users can quickly and accurately find electronic payment-accepting facilities that meet their desired criteria.

[1214] 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.

[1215] In this invention, the server includes an information receiving means for receiving requests entered by a user, an analysis means for analyzing the request and extracting keywords related to the request, and a search means for searching for facilities that accept electronic payment based on the extracted keywords and location information. This enables searches based on the user's desired conditions and current location, making it possible to quickly and accurately recommend optimal facilities that accept electronic payment. Furthermore, by adding a personalization means that references past payment data and behavioral history, it is possible to provide more accurate and personalized recommendations. This improves user satisfaction and realizes efficient facility searches.

[1216] The "information receiving means" is a means for accepting requests input by the user, and serves to receive the user's desired conditions.

[1217] The "analysis means" is a means having a function of analyzing a received request and extracting keywords related to the request.

[1218] The "search means" is a means having a function of searching for facilities that accept electronic payment based on the extracted keywords and location information.

[1219] "Recommendation methods" are methods that recommend the most suitable facilities to users based on search results.

[1220] The "information transmission means" is a means for transmitting recommended facility information to the user terminal.

[1221] "Individualization means" refers to a means of making personalized recommendations by referencing a user's past payment data and behavioral history.

[1222] "Location information" is information that indicates the user's current geographic location and is obtained from the user's device, such as a smartphone.

[1223] "Navigation link" refers to link information that allows a user to confirm or navigate to a recommended facility.

[1224] "Coupon information" is information that allows users to receive discounts and benefits available at recommended facilities.

[1225] "Facilities" refers to commercial establishments and stores that accept electronic payments.

[1226] Overall system configuration

[1227] This invention relates to a system that allows users to easily search for facilities that accept electronic payments and recommends the most suitable facility. The system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, and a personalization means.

[1228] Information receiving means

[1229] The user uses a smartphone application to input their request. For example, they might input, "I want to eat sushi lunch for 2,000 yen." The smartphone's GPS function also acquires the user's current location information. This information receiving means plays a role in transmitting the user's request and location information to the server.

[1230] Analysis means

[1231] The server uses natural language processing (NLP) techniques to analyze the received user request. It uses an NLP model like SpaCy to extract important keywords (e.g., "budget 2000 yen" and "sushi") from the request.

[1232] Search methods

[1233] The server searches the database for facilities that accept electronic payments based on the extracted keywords and location information, and uses Geopy to process the location information and generate a list of facilities that accept electronic payments.

[1234] Recommendation methods

[1235] Based on the search results, the server recommends the most suitable facilities for the user. By taking into account past payment history and behavioral history, personalized recommendations are provided, allowing users to find facilities that will provide them with the highest level of satisfaction.

[1236] Information transmission means

[1237] The server then sends the final recommended facility information, including navigation links and coupon information, to the user's smartphone.

[1238] Specific examples

[1239] When a user enters "I want to enjoy an Italian dinner on a budget of 3,000 yen" and sends their request and location information from their smartphone to the server, the server analyzes the information and extracts keywords. It then searches for Italian restaurants that accept electronic payments and generates personalized recommendations based on the user's past usage history. Finally, it sends a list of recommended restaurants, including navigation links and coupon information, to the user's smartphone.

[1240] Hardware and software used

[1241] The hardware includes a smartphone operated by the user and a server that processes data. The software uses libraries such as SpaCy and Geopy. A generative AI model is also used for NLP analysis. An example of a prompt for the generative AI model is:

[1242] "Please generate a script that analyzes the input text request, extracts the budget and type of cuisine, searches for stores that accept electronic payments within the specified range, and generates optimal recommendations taking into account the user's history."

[1243] is used.

[1244] This embodiment allows users to quickly and accurately find electronic payment-enabled establishments that meet their desired criteria, thereby increasing user satisfaction and efficiency.

[1245] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1246] Step 1:

[1247] The user enters their request into the text box on their smartphone. For example, they might type, "I'd like to have a sushi lunch for 2,000 yen," and press the send button. At this time, the smartphone's GPS function also obtains the user's current location information.

[1248] Input: User's request (text data) and location information (latitude and longitude)

[1249] Output: Request data with your wishes and location sent to the server

[1250] Step 2:

[1251] The server receives the user's request and location information using the information receiving means, and the received data is passed to the analyzing means.

[1252] Input: Request data including user's wishes and location information

[1253] Output: Pre-analysis data to be passed to the analysis tool

[1254] Step 3:

[1255] The server analyzes the received request using its analysis tools. During this process, it uses natural language processing (NLP) technology and utilizes SpaCy to extract important keywords from the request (e.g., "budget 2000 yen" and "sushi").

[1256] Input: Pre-analysis data (user request and location information)

[1257] Output: Extracted keywords ("budget 2000 yen", "sushi")

[1258] Step 4:

[1259] The server uses a search function to search the database for facilities that accept electronic payment based on the extracted keywords and location information, processes the location information using the Geopy library, and lists the facilities within the search range.

[1260] Input: Extracted keywords and location information

[1261] Output: A list of facilities as search results

[1262] Step 5:

[1263] The server uses the recommendation means to recommend optimal facilities to the user based on the search results, and further uses the personalization means to generate personalized recommendations taking into account the user's past payment history and behavioral history.

[1264] Input: Facility list and user's past payment history and behavior history

[1265] Output: A personalized list of recommended facilities

[1266] Step 6:

[1267] The server then uses the information transmission means to send the final recommended facility information, including navigation links and coupon information, to the user's smartphone. The user can then check the recommended facility information on their smartphone.

[1268] Input: personalized recommended facility list

[1269] Output: Recommended facility information sent to the user's device (including navigation links and coupon information)

[1270] Processing steps for specific examples (example of prompt sentences)

[1271] Step 1:

[1272] The user enters "I want to enjoy an Italian dinner on a budget of 3000 yen" and sends a request including their current location to the server.

[1273] Input: User request "I want to enjoy an Italian dinner for 3000 yen", current location information

[1274] Output: Received request data

[1275] Step 2:

[1276] The server receives the request data and converts it into pre-analysis data.

[1277] Input: Request data

[1278] Output: Pre-analysis data

[1279] Step 3:

[1280] The server uses natural language processing to extract "budget 3,000 yen" and "Italian dinner."

[1281] Input: Data before analysis ("Budget 3000 yen", "Italian dinner")

[1282] Output: Extracted keywords

[1283] Step 4:

[1284] The server uses a search means to search for Italian restaurants that accept electronic payment.

[1285] Input: Extracted keywords, location information

[1286] Output: Facility list

[1287] Step 5:

[1288] The server generates personalized recommended facilities based on the user's past usage history.

[1289] Input: Facility list, past payment history and behavior history

[1290] Output: A personalized list of recommended facilities

[1291] Step 6:

[1292] The server sends the final facility information to the user's smartphone, along with navigation links and coupon information, allowing the user to check all the information on their smartphone.

[1293] Input: personalized recommended facility list

[1294] Output: Recommended facility information sent to the user's device

[1295] 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.

[1296] System Embodiments

[1297] As an embodiment of the present invention, a system is provided that allows a user to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes an information receiving means, an analysis means, a search means, a recommendation means, an information transmitting means, a personalization means, and an emotion engine.

[1298] System configuration

[1299] 1. User Input

[1300] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[1301] 2. Means of receiving information

[1302] Device: Sends the user's input request and current location information to the server. This request includes the user's desired conditions and geographic location.

[1303] 3. Analysis method

[1304] Server: Analyzes the received information and uses natural language processing (NLP) technology to understand the request. Specifically, it extracts keywords such as "budget 800 yen" and "udon lunch."

[1305] 4. Search Methods

[1306] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payment. The search range is set based on the user's location information.

[1307] 5. Emotion Engine

[1308] Server: Analyzes the user's input and past behavioral history to estimate the user's emotional state. This estimation result is taken into account in the next recommendation method.

[1309] 6. Recommendation methods

[1310] Server: Generates a list of optimal stores based on the search results and the emotional state estimated by the emotion engine. This list also takes into account the user's past payment history and behavioral history.

[1311] 7. Means of information transmission

[1312] Server: The generated store list is sent to the user's device along with navigation links and coupon information.

[1313] 8. Display

[1314] Device: The received information is displayed in an appropriate format to the user, making it easier for the user to find an udon restaurant that fits their budget.

[1315] Specific examples

[1316] Below is an overview of the system's operation, including specific examples.

[1317] Example input:

[1318] User: Enter "I want to enjoy a cafe lunch on a budget of 1,000 yen."

[1319] System behavior:

[1320] 1. User: Submits the requested information.

[1321] 2. Device: Sends a request containing the desired location to the server.

[1322] 3. Server: Receives the request and extracts "budget 1000 yen" and "cafe lunch" using analysis means.

[1323] 4. Server: Uses the search tool to search for cafes that accept electronic payment within the specified budget and location range.

[1324] 5. Server: The emotion engine uses the user's past behavioral history and input data to estimate the user's emotional state. For example, if the server estimates that the user is tired, it selects an appropriate store.

[1325] 6. Server: Recommends the best cafes to the user based on their past usage history and emotional state.

[1326] 7. Server: The information transmission means transmits the store list including additional information (e.g., coupon links) to the terminal.

[1327] 8. Terminal: Shows users a list of stores and provides detailed information and coupons.

[1328] This system allows users to efficiently find the store they want. In addition, by utilizing an emotion engine, recommendations that match the user's emotional state are provided, resulting in a more personalized service. This makes it easier for stores to attract new customers and increases user satisfaction.

[1329] The processing flow will be explained below.

[1330] Step 1:

[1331] User: Launches the smartphone application, enters a request in the search box (e.g., "I want to eat udon lunch for 800 yen"), and presses the send button.

[1332] Step 2:

[1333] Device: Obtains the current location information along with the user's request, and sends this information to the server as a single request data.

[1334] Step 3:

[1335] Server: Analyzes the received request. First, it uses natural language processing (NLP) technology to analyze the request and extract keywords such as "budget 800 yen" and "udon lunch."

[1336] Step 4:

[1337] Server: Based on the extracted keywords, the database is searched for store information that accepts electronic payments. The search range is set based on the user's location information.

[1338] Step 5:

[1339] Server: Based on the user's input and related data, the emotion engine estimates the user's emotional state.

[1340] Step 6:

[1341] Server: Adjust search results based on the emotional state estimated by the emotion engine. For example, if you are in a relaxing mood, prioritize stores with quiet environments.

[1342] Step 7:

[1343] Server: Generates an optimal list of stores based on search results and filtering based on emotional state. It also provides personalized recommendations based on the user's past payment history and behavioral history.

[1344] Step 8:

[1345] Server: Adds navigation links and coupon information to the generated store list and sends it to the user's device.

[1346] Step 9:

[1347] Device: The received store list is displayed to the user, including the store name, address, opening hours, price range, review rating, and coupon information.

[1348] Step 10:

[1349] User: Checks the displayed store information, uses navigation links and coupon information to visit the desired store, and uses the mini-app to obtain further information as needed.

[1350] This series of processes allows users to easily find the best store within their budget. Using an emotion engine, recommendations that match the user's emotional state are realized, providing a more personalized experience. This also makes it easier for stores to acquire new customers and increases user satisfaction.

[1351] Example 2

[1352] 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."

[1353] Conventional store search systems have had issues with their inability to provide recommendations that take into account the user's emotional state. They also lack the ability to provide personalized recommendations based on past behavioral history and payment data. Furthermore, they also lack the ability to efficiently search for stores that accept electronic payments based on the user's current location.

[1354] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information receiving means for receiving a request input by a user, a natural language processing means for analyzing the request and extracting keywords related to the request, a search means for searching for stores that accept electronic payment based on the extracted keywords and the user's geographical location information, an emotion analysis means for estimating the user's emotional state from the user's past behavioral history and input content, a recommendation means for recommending the most suitable store based on the search results and the user's emotional state, and an information sending means for sending the recommended store information, including navigation links and coupon information, to the user terminal. This enables efficient search and recommendation of personalized stores that accept electronic payment, taking the user's emotional state into consideration.

[1355] The "information receiving means" is a means having the function of receiving a request input by a user and transmitting the request to a server.

[1356] "Natural language processing means" refers to a technology that analyzes requests entered by users and extracts keywords related to the requests.

[1357] The "search means" is a means having a function of searching for stores that accept electronic payments based on the extracted keywords and the user's geographical location information.

[1358] "Emotion analysis means" refers to a technique for estimating a user's emotional state from the user's past behavioral history and input content.

[1359] A "recommendation tool" is a tool that has the function of recommending the most suitable store to the user based on search results and emotional state.

[1360] The "information transmission means" is a means having a function of transmitting recommended store information, including navigation links and coupon information, to a user terminal.

[1361] The system of the present invention allows users to easily search for stores that accept electronic payments and recommends the most suitable store taking into consideration the user's emotional state. This system includes information receiving means, natural language processing means, search means, emotion analysis means, recommendation means, and information transmitting means.

[1362] First, a user launches a smartphone application and enters their request in the search box. For example, they might enter "I want to eat udon lunch for 800 yen" and press the send button. Next, the device sends this request and their current location information to the server. This request includes the user's desired conditions and geographic location.

[1363] The server analyzes the received request. Specifically, it uses natural language processing to extract keywords such as "budget 800 yen" and "udon lunch" from the user's input. This process uses NLP libraries such as Google Cloud Natural Language API and spaCy.

[1364] Next, the server searches a database for store information that accepts electronic payments based on the extracted keywords and the user's location information. This search is performed using a database management system such as MySQL or PostgreSQL.

[1365] The server then uses emotion analysis to estimate the user's emotional state based on the user's input and past behavioral history, using emotion analysis engines such as IBM Watson and Microsoft Azure Text Analytics.

[1366] The server generates a list of optimal stores based on the search results and emotional state using recommendation engines such as Apache Mahout and TensorFlow, taking into account the user's past payment history and behavioral history.

[1367] Finally, the server adds navigation links and coupon information to the generated store list and sends it to the terminal. This information is sent using a message queue such as a REST API or Apache Kafka. Finally, the terminal displays the received information in an easy-to-read format for the user, allowing the user to easily find the store they want.

[1368] For example, if a user inputs "I want to enjoy a cafe lunch with a budget of 1000 yen," the system will behave as follows:

[1369] 1. The user sends the above request from their smartphone.

[1370] 2. The device sends the request and current location information to the server.

[1371] 3. The server receives the request and uses NLP technology to extract the keywords "budget 1,000 yen" and "cafe lunch."

[1372] 4. The server searches the database for cafes that accept electronic payment and match the budget and location information.

[1373] 5. The server uses an emotion engine to estimate the user's emotional state based on the user's past behavior history and input. For example, if the server estimates that the user is tired, it will select an appropriate store.

[1374] 6. The server will then provide a personalized list of the best cafes for you, taking into account your emotional state and past visit history.

[1375] 7. The server sends a store list including navigation links and coupon links to the terminal.

[1376] 8. The terminal will display a list of stores to the user, providing detailed information and coupons.

[1377] Through the above process, users can efficiently find the store they want and are provided with personalized recommendations that match their emotional state.

[1378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] User: Launches the smartphone application, enters a request in the search box, and submits it. For example, the user might enter, "I want to eat udon lunch with a budget of 800 yen." The input data (user request) is then sent to the next step.

[1381] Step 2:

[1382] Terminal: Acquires the request entered by the user and current location information and sends this to the server. For example, if the request data is "I want to eat udon lunch with a budget of 800 yen" and the location data is "latitude 35.6895, longitude 139.6917", this information is sent to the server. The input is the user's request and location information, and the output is the request data sent to the server.

[1383] Step 3:

[1384] Server: Analyzes the received request data (demands and location information) using natural language processing. Specifically, keywords such as "budget 800 yen" and "udon lunch" are extracted from the input. For example, using "Google Cloud Natural Language API" or "spaCy," "budget 800 yen" and "udon lunch" are recognized as key elements. The input is the request data, and the output is the extracted keywords.

[1385] Step 4:

[1386] Server: Using the search tool, search the database for stores that accept electronic payments based on the extracted keywords and the user's location information. For example, using "MySQL" or "PostgreSQL," search for stores that meet the conditions of "udon lunch" and "budget under 800 yen" based on location information. The input is the extracted keywords and location information, and the output is a list of matching stores.

[1387] Step 5:

[1388] Server: Using an emotion analysis engine, the server estimates the user's emotional state based on their input and past behavioral history. For example, if past data indicates that the user is "tired," it prioritizes stores where they can relax. This is achieved using technologies such as IBM Watson and Microsoft Azure Text Analytics. The input is the user's requests and past behavioral history, and the output is the estimated emotional state.

[1389] Step 6:

[1390] Server: Using a recommendation method, the server generates an optimal store list based on the estimated emotional state and search results. This list also reflects the user's past payment history and behavioral history. For example, suitable stores are selected using "Apache Mahout" or "TensorFlow." The input is the emotional state and search results, and the output is a personalized store list.

[1391] Step 7:

[1392] Server: Using an information transmission means, the server sends a list of optimal stores, including navigation links and coupon information, to the device. For example, detailed store information is sent using a REST API or Apache Kafka. The input is the personalized store list, and the output is the information sent to the device.

[1393] Step 8:

[1394] Terminal: Displays the received store list to the user in an appropriate format. Specifically, it provides detailed information and coupons, allowing the user to easily select a store. The input is the store list sent from the server, and the output is the information displayed in a format that the user can check.

[1395] The above is the processing flow of the system that finds appropriate stores based on the requests entered by the user, recommends them taking into consideration the user's emotional state, and finally provides information to the user.

[1396] (Application example 2)

[1397] 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."

[1398] When modern consumers choose a store, they are not only concerned with the price and location of products and services, but also with finding a store that suits their emotional state at the time. However, conventional search systems make recommendations without taking the user's emotional state into consideration, making it difficult to select a store that will provide high satisfaction. Furthermore, there is no system that can search for stores that accept electronic payments and make recommendations that simultaneously consider the user's emotional state. Therefore, there is a need to provide a system that allows users to quickly and easily find an appropriate store that suits their emotional state.

[1399] 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.

[1400] In this invention, the server includes information receiving means for receiving requests input by a user, analysis means for analyzing the request and extracting keywords related to the request, search means for searching for stores that accept electronic payment based on the extracted keywords, emotion analysis means for estimating the emotional state of the user, recommendation means for recommending the most suitable store based on the search results and emotion analysis results, and information sending means for sending information about the recommended store to a user terminal. This makes it possible to recommend the most suitable store taking into account the emotional state of the user.

[1401] The "information receiving means" is a means for receiving requests input by the user.

[1402] The "analysis means" is a means for analyzing the request and extracting keywords related to the request.

[1403] The "search means" is a means for searching for stores that accept electronic payments based on the extracted keywords.

[1404] The "emotion analysis means" is a means for analyzing the user's input content and past behavioral history to estimate the user's emotional state.

[1405] The "recommendation means" is a means for recommending the most suitable store based on the search results and the sentiment analysis results.

[1406] The "information transmission means" is a means for transmitting the recommended store information to the user terminal.

[1407] The "individualization means" refers to a means for making individualized store recommendations by the recommendation means by referring to the user's past payment data and behavioral history.

[1408] "Deep link information to a mini appli" is link information for directly launching a mini appli.

[1409] The system for realizing the present invention includes a plurality of processing steps for accepting requests input by a user, analyzing the requests, and searching for related stores. The hardware and software used in this embodiment of the system will be specifically described below.

[1410] Hardware and Software Use

[1411] 1. Terminal

[1412] Hardware: Smartphone

[1413] Software: Applications that accept user input (e.g., SmartPay, Shop Guide)

[1414] 2. Server

[1415] Software: Python, natural language processing engine (e.g., spaCy or NLTK), sentiment analysis model (e.g., BERT or RoBERTa), HTTP request library (e.g., requests), geolocation library (e.g., geopy)

[1416] Processing flow

[1417] Information receiving means

[1418] It accepts requests entered by the user on the terminal (e.g., "I would like to enjoy a cafe lunch with a budget of 1,000 yen") and sends this information to the server.

[1419] Analysis means

[1420] The server analyzes the received request and uses natural language processing (NLP) technology to extract keywords related to the request (e.g., "budget 1,000 yen" or "cafe lunch").

[1421] Search methods

[1422] The server searches the database for store information that accepts electronic payments based on the user's location information and the extracted keywords. The geopy library is used to obtain location information.

[1423] Emotion analysis means

[1424] The server estimates the user's emotional state based on the user's input and past behavioral history. An emotion analysis model (e.g., BERT or RoBERTa) is used to analyze the emotional state.

[1425] Recommendation methods

[1426] The server then recommends the most suitable store for the user based on the search results and sentiment analysis, taking into account past payment data and behavioral history.

[1427] Information transmission means

[1428] The server sends the recommended store information, including navigation links and coupon information, to the user's device.

[1429] Specific examples

[1430] Example input

[1431] User input: "I want to enjoy a cafe lunch on a budget of 1000 yen."

[1432] User mood: "Tired"

[1433] Prompt Sentence Examples

[1434] Text format

[1435] How I feel right now in one word: Tired

[1436] Example output

[1437] The server performs emotion analysis based on the above information and estimates the user's emotional state (e.g., tired). Next, it searches the database for cafes that accept electronic payment based on the user's location information. It then takes the user's emotional state into consideration and prioritizes recommendations of cafes where the user can relax. Finally, the following information is sent to the user's device:

[1438] Recommended stores include:

[1439] Store name: Relax Cafe, Address: 1-2-3 Shibuya-ku, Tokyo, Coupon: 50% off drinks

[1440] Store name: Healthy Cafe, Address: 4-5-6, Shinjuku-ku, Tokyo, Coupon: Free dessert

[1441] In this way, through a specific embodiment, a user can quickly and easily find a store that suits their emotional state.

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] The user starts the smartphone application, enters their request in the search box, and sends it. An example of input is "I would like to enjoy a cafe lunch with a budget of 1,000 yen." This input is accepted by the information receiving means and sent to the server. The input is in natural Japanese text format, and includes location information.

[1445] Step 2:

[1446] The server analyzes the user's request received by the information receiving means and extracts keywords related to the request using the analysis means. Specifically, it uses natural language processing technology (e.g., spaCy or NLTK) to extract keywords such as "budget 1,000 yen" and "cafe lunch." The input is the request text from the user, and the output is a list of extracted keywords.

[1447] Step 3:

[1448] The server uses a search function to search for stores that accept electronic payments using the user's location information based on the extracted keywords. It obtains the location information using a geolocation API (e.g., geopy library) and retrieves the corresponding store information from the database. The input is a list of keywords and location information, and the output is a list of corresponding stores.

[1449] Step 4:

[1450] The server uses emotion analysis to estimate the user's emotional state from their input and past behavioral history. It uses an emotion analysis model (e.g., BERT or RoBERTa) to analyze the input text and historical data to estimate the emotional state. It analyzes the user's emotional state based on a prompt such as "How do you feel right now in one word?" The input is text data and behavioral history, and the output is the estimated emotional state.

[1451] Step 5:

[1452] The server uses the recommendation means to recommend the most suitable store based on the search results and sentiment analysis results. At this time, the server also references the user's past payment data and generates personalized store information using the personalization means. This creates a list of stores that are suitable for the user's emotional state. The inputs are the search results, sentiment analysis results, and payment data, and the output is a list of recommended stores.

[1453] Step 6:

[1454] The server uses an information transmission means to send recommended store information to the user's terminal. The sent information includes detailed store information, navigation links, coupon information, etc. The user can check the received information on the application. The input is a list of recommended stores, and the output is store information displayed on the user's terminal.

[1455] Through these steps, the system is able to take into account the user's desires and emotional state and quickly recommend the most suitable store.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1461] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1462] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1463] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1464] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1465] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1466] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1467] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1468] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1469] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1470] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1471] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1472] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1473] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1474] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1475] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1476] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1477] The following is further disclosed regarding the above embodiment.

[1478] (Claim 1)

[1479] an information receiving means for receiving a request input by a user;

[1480] an analysis means for analyzing the request and extracting keywords related to the request;

[1481] a search means for searching for stores that accept electronic payment based on the extracted keywords;

[1482] a recommendation means for recommending an optimal store based on the search results;

[1483] an information transmission means for transmitting the recommended store information to a user terminal;

[1484] A system including:

[1485] (Claim 2)

[1486] 2. The system according to claim 1, further comprising an individualization unit that refers to the user's past payment data and behavior history to make an individualized store recommendation by the recommendation unit.

[1487] (Claim 3)

[1488] 2. The system according to claim 1, wherein the store information transmitted by the information transmission means includes deep link information to a mini appli.

[1489] (Claim 4)

[1490] 2. The system according to claim 1, wherein the analysis means sets the search range based on the user's location information.

[1491] (Claim 5)

[1492] 10. The system according to claim 1, further comprising advertising means for providing advertising and promotional information to member stores to assist them in acquiring new customers.

[1493] "Example 1"

[1494] (Claim 1)

[1495] a data receiving means for receiving a request input by a user;

[1496] a data acquisition means for acquiring the request and location information;

[1497] a data analysis means for analyzing the request and extracting keywords related to the request;

[1498] a data search means for searching for facilities that support electronic commerce based on the extracted keywords and location information;

[1499] a recommendation means for recommending an optimal facility based on the search results;

[1500] a data transmission means for transmitting the recommended facility information to a user device;

[1501] A system including:

[1502] (Claim 2)

[1503] 2. The system of claim 1, further comprising a personalization means for providing personalized establishment recommendations by said recommendation means by referencing past transaction data and behavioral history of the user.

[1504] (Claim 3)

[1505] 2. The system according to claim 1, wherein the facility information transmitted by the data transmission means includes deep link information to a mini appli.

[1506] "Application Example 1"

[1507] (Claim 1)

[1508] an information receiving means for receiving a request input by a user;

[1509] an analysis means for analyzing the request and extracting keywords related to the request;

[1510] a search means for searching for facilities that accept electronic payment based on the extracted keywords and location information;

[1511] a recommendation means for recommending an optimal facility based on the search results;

[1512] an information transmitting means for transmitting the recommended facility information to a user terminal;

[1513] A system including:

[1514] (Claim 2)

[1515] 2. The system according to claim 1, further comprising a personalization unit that refers to the user's past payment data and behavior history to make a personalized facility recommendation by the recommendation unit.

[1516] (Claim 3)

[1517] 2. The system according to claim 1, wherein the facility information transmitted by said information transmitting means includes additional information (navigation links and coupon information).

[1518] "Example 2: Combining Emotion Engines"

[1519] (Claim 1)

[1520] an information receiving means for receiving a request input by a user;

[1521] natural language processing means for analyzing the request and extracting keywords related to the request;

[1522] a search means for searching for stores that accept electronic payment based on the extracted keywords and the user's geographical location information;

[1523] An emotion analysis means for estimating an emotional state from past behavioral history and input content;

[1524] a recommendation means for recommending an optimal store based on the search results and the emotional state;

[1525] an information transmitting means for transmitting the recommended store information together with a navigation link and coupon information to a user terminal;

[1526] A system including:

[1527] (Claim 2)

[1528] 2. The system according to claim 1, further comprising an individualization unit that refers to the user's past payment data and behavior history to make an individualized store recommendation by the recommendation unit.

[1529] (Claim 3)

[1530] 2. The system according to claim 1, wherein the store information transmitted by the information transmission means includes deep link information to a mini appli.

[1531] "Application example 2 when combining emotion engines"

[1532] (Claim 1)

[1533] an information receiving means for receiving a request input by a user;

[1534] an analysis means for analyzing the request and extracting keywords related to the request;

[1535] a search means for searching for stores that accept electronic payment based on the extracted keywords;

[1536] emotion analysis means for estimating the emotional state of a user;

[1537] a recommendation means for recommending an optimal store based on the search results and the emotion analysis results;

[1538] an information transmission means for transmitting the recommended store information to a user terminal;

[1539] A system including:

[1540] (Claim 2)

[1541] 2. The system according to claim 1, further comprising an individualization unit that refers to the user's past payment data and behavior history to make an individualized store recommendation by the recommendation unit.

[1542] (Claim 3)

[1543] 2. The system according to claim 1, wherein the store information transmitted by the information transmission means includes deep link information to a mini appli. [Explanation of symbols]

[1544] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an information receiving means for receiving a request input by a user; an analysis means for analyzing the request and extracting keywords related to the request; a search means for searching for stores that accept electronic payment based on the extracted keywords; a recommendation means for recommending an optimal store based on the search results; an information transmission means for transmitting the recommended store information to a user terminal; A system including:

2. The system according to claim 1 , further comprising an individualization unit that refers to the user's past payment data and behavior history to make an individualized store recommendation by the recommendation unit.

3. 2. The system according to claim 1, wherein the store information transmitted by the information transmission means includes deep link information to a mini appli.

4. The system according to claim 1, wherein the analysis means sets the search range based on the user's location information.

5. 2. The system according to claim 1, further comprising advertising means for providing advertising and promotional information to member stores to assist them in acquiring new customers.

Images