System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring information of a specific shop based on position information designated by a user; means for acquiring a security camera video of the shop; means for inputting the acquired security camera video to a generative AI model and analyzing a fashion tendency of a customer; and means for transmitting an analysis result to a user device and displaying the analysis result on the user device.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] Users often struggle to choose the right outfit when visiting a store for the first time, making it difficult to balance their individuality with the time, place, and occasion. Furthermore, some users lack confidence in their fashion sense, making them feel uneasy about choosing what to wear. Furthermore, stores are being asked to analyze data on diverse and rapidly changing customer demographics in real time and use that data to develop branding and promotional activities. [Means for solving the problem]

[0005] The present invention is a system that includes a means for acquiring information about a specific store based on location information specified by a user, a means for acquiring security camera footage, a means for inputting the acquired footage into a generative AI model to analyze the fashion trends of customers visiting the store, and a means for transmitting and displaying the analysis results to a user's terminal. The system also includes a means for users to purchase related fashion items from an online shopping site based on the analysis results, and a means for periodically collecting and analyzing clothing data of customers visiting the store from security camera footage and providing the customer fashion data to the store. This allows users to easily select clothing that matches the atmosphere of the desired store, and enables stores to understand customer fashion trends in real time and develop effective marketing strategies.

[0006] "User" refers to a person who uses this system to obtain store information and check suitable fashion styles.

[0007] "Specified location information" refers to specific geographic information determined by a user through a search or selection.

[0008] "Specific stores" refer to restaurants and commercial facilities searched for based on location information specified by the user.

[0009] "Means for acquiring information" refers to a method for acquiring detailed information about a store related to the location information specified by the user using a server or database.

[0010] "Security cameras" refer to video recording devices installed inside stores that capture the behavior of customers in real time.

[0011] "Means for acquiring video footage" refers to the method for importing video data from security cameras into a server in real time.

[0012] "Generative AI model" refers to the artificial intelligence algorithm used to analyze customer video data.

[0013] "Fashion trends" refers to the clothing styles and trends of customers determined from analyzed data.

[0014] "Means of analysis" refers to the use of generative AI models to process video data of store visitors and identify fashion trends.

[0015] "User terminal" refers to a computing device such as a smartphone or PC owned by a user.

[0016] "Analysis results" refers to data on the fashion trends of store customers obtained by the generative AI model.

[0017] "Means for transmitting and displaying" refers to a method for transmitting the analysis results to a user terminal via communication and displaying the results on the terminal.

[0018] "Online shopping site" refers to a website where users can purchase fashion items over the Internet.

[0019] "Means of purchase" refers to the method by which a user selects a fashion item on an online shopping site and completes the purchase process.

[0020] "Means of collection and analysis" refers to the method of periodically capturing and analyzing clothing data of customers from security camera footage.

[0021] "Customer fashion data" refers to information about the clothing and style of customers that is obtained from the analysis of security camera footage.

[0022] "Means of providing" refers to the method of transmitting the analyzed customer fashion data to the store via communication. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] The present invention is a system for providing a user with a fashion style suited to a specific store that the user visits. This system improves user convenience and also provides marketing support to the store. Specific embodiments of the present invention will be described below.

[0045] System configuration

[0046] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0047] Program processing

[0048] 1. User Request

[0049] The user opens the Yahoo! Maps app or website on their device and searches for the store they want to visit. For example, they enter keywords such as "Aoyama Cafe A" and press the search button.

[0050] The device sends this search query to the Yahoo! Maps API and sends a request to the server to obtain specific store information based on the specified location information.

[0051] 2. Obtaining store information

[0052] The server receives the user's request and retrieves the details of the relevant store from the database, including basic information such as the address, opening hours, and current occupancy status.

[0053] The server then accesses the store's security cameras and obtains real-time video data.

[0054] 3. Analysis of video data

[0055] The server sends the video data acquired from the security cameras to the generative AI model, which then preprocesses the video data and analyzes the clothing of customers.

[0056] The generative AI model classifies customers' clothing into categories such as casual, formal, and street style, and generates data on current fashion trends.

[0057] 4. Displaying the analysis results

[0058] The server sends the analysis results to the user's device, generally in JSON format.

[0059] The device analyzes the received data and displays appropriate fashion style information to the user, such as a message like, "Most of our customers are currently wearing casual styles."

[0060] 5. Online shopping support

[0061] The user chooses an outfit based on presented fashion trends, and if desired, is provided with a link to an online shopping site.

[0062] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0063] 6. Store-side data analysis

[0064] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, as well as weekly reports on specific fashion trends.

[0065] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts and promotions at times when certain styles are in high demand.

[0066] Specific examples

[0067] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0068] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0069] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0070] 3. The analysis results are sent to the user's device, and the message "Most of our current customers are dressed casually" is displayed.

[0071] 4. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0072] This allows users to choose clothes that match the atmosphere of the store they are visiting, and also allows the store to implement an effective marketing strategy.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit in the search bar, and presses the search button.

[0076] Step 2:

[0077] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0078] Step 3:

[0079] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0080] Step 4:

[0081] The server accesses the security cameras of the relevant store, sends a request to the security camera API, and obtains real-time video data.

[0082] Step 5:

[0083] The server sends the acquired security camera video data to the generative AI model, where it undergoes preprocessing and is converted into a format suitable for analysis.

[0084] Step 6:

[0085] The generative AI model analyzes the fashion trends of customers and categorizes the clothing of people in the video into categories such as casual, formal, and street style.

[0086] Step 7:

[0087] The server sends the analysis results in JSON format to the user's device, which receives the results.

[0088] Step 8:

[0089] The device parses the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Currently, most customers are wearing casual styles."

[0090] Step 9:

[0091] The user chooses an outfit based on displayed fashion trends, and if necessary, links to online shopping sites are provided.

[0092] Step 10:

[0093] The user clicks the "Shop Online" button. The device displays a page of related fashion items.

[0094] Step 11:

[0095] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[0096] Step 12:

[0097] The server periodically collects and analyzes security camera footage and stores customer fashion data in a database in real time.

[0098] Step 13:

[0099] The server provides regularly updated fashion data to the stores, who can then access real-time demographic data and weekly reports via a management screen.

[0100] Step 14:

[0101] Stores can use the data provided to plan and execute marketing strategies and promotional activities, such as holding discount events tailored to specific fashion trends.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] Conventional fashion suggestion systems did not fully satisfy user convenience, making it difficult to provide appropriate fashion styles that match the atmosphere of the store the user visits. Furthermore, stores lacked sufficient means to utilize customer fashion trends as data, making it difficult to develop effective marketing strategies.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage of the store, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers, means for classifying the clothing of customers using the generative AI model and suggesting fashion styles, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for providing a link to an online shopping site so that the user can purchase fashion items. This enables users to select an appropriate fashion style that matches the atmosphere of the store they visit, and also enables the store to utilize the fashion trends of customers as marketing data.

[0107] "User" refers to a person who uses the system to obtain information about a specific store and receive fashion style suggestions.

[0108] A "terminal" is a device operated by a user, and includes a smartphone, a personal computer, etc.

[0109] "Server" refers to a computer system that processes and analyzes data and communicates with user terminals.

[0110] "Location information" is data indicating the geographical location of a store that a user wants to visit.

[0111] A "security camera" refers to a device installed in a specific store that captures video data of customers.

[0112] A "generative AI model" refers to a machine learning model that analyzes acquired video data and classifies and suggests fashion trends for customers.

[0113] "Analysis results" refers to data regarding the fashion trends of store customers obtained after the generative AI model analyzes the video data.

[0114] "Online shopping site" refers to a website that sells fashion items over the Internet.

[0115] "Fashion style" refers to the classification of customers' clothing characteristics into casual, formal, street style, etc.

[0116] "Fashion items" refer to products such as clothing and accessories that users can purchase.

[0117] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, improving convenience for the user and providing marketing support to the store.

[0118] System configuration

[0119] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0120] Program processing

[0121] First, a user opens a map app or website on their device and searches for a store they want to visit. For example, they search for "Aoyama Cafe." In this case, the device sends a search query and a request to the server to obtain specific store information based on the specified location information.

[0122] Upon receiving a user request, the server retrieves detailed information about the relevant store from the database. This information includes the store's name, address, business hours, and current occupancy status. The server also accesses the store's security cameras to obtain video data in real time. This video data is obtained using RTSP (Real-Time Streaming Protocol).

[0123] The server then sends the acquired security camera footage to a generative AI model, which uses image processing libraries such as OpenCV to preprocess the video data and remove noise. The video data then classifies the customer's fashion style into categories such as casual, formal, and street style, and analyzes current fashion trends.

[0124] The server converts the analysis results received from the generative AI model into JSON format and sends it to the user's device. The user's device analyzes this data and displays appropriate fashion style information to the user. For example, a message such as "Most customers currently in the store are wearing casual styles" may be displayed.

[0125] Furthermore, the user selects an appropriate outfit based on the presented fashion trends and clicks on a link to an online shopping site if necessary. The server obtains a link to an online shopping site for related fashion items and provides it to the user. This link click event is tracked and necessary data is recorded.

[0126] Finally, the server analyzes the continuously collected fashion data and displays demographic information in real time on a dashboard for store managers. Store managers can use this data to plan marketing strategies and promotional activities, making it possible to effectively run promotions tailored to times when certain styles are popular.

[0127] Specific examples

[0128] For example, for a user visiting "Aoyama Cafe," the system works as follows: The user searches for "Aoyama Cafe," and the search results are sent from the device to the server. The server obtains store information and security camera footage, and analyzes fashion trends using a generative AI model. The analysis results are then sent to the user's device, displaying a message saying, "Most customers currently visiting the store are wearing casual styles." The user references this information, purchases appropriate clothing on an online shopping site, and visits the store with peace of mind.

[0129] Examples of prompt statements

[0130] "What is the recommended fashion style for visiting Aoyama Cafe?"

[0131] As described above, the system of the present invention suggests fashion styles that match the atmosphere of a store before the user visits, and also supports online shopping. This allows users to choose appropriate clothing for the store they are visiting, and stores can also use real-time data to conduct effective marketing.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Step 1:

[0134] User Request

[0135] A user opens a map app or website on their device and searches for a store they want to visit. For example, they enter a keyword such as "Aoyama Cafe A." The device then sends this search query to the server. Specifically, the device sends an HTTP GET request to the specified URI, sending the search query. The input data is the keyword entered by the user, and the output is the request data sent to the server.

[0136] Step 2:

[0137] Obtaining store information

[0138] The server receives the user's request and retrieves detailed information about the corresponding store from a database. The server executes an SQL query on the database to retrieve information such as the store's address, business hours, and current occupancy status. The server then accesses the store's security cameras to obtain real-time video data. This video data is processed using RTSP (Real-Time Streaming Protocol). The input data is the user's request, and the output data is store information and security camera video data.

[0139] Step 3:

[0140] Video data preprocessing

[0141] The server receives the video data acquired from the security camera and performs preprocessing. This processing uses image processing libraries such as OpenCV to remove noise and normalize the image. The input is the security camera video data, and the output is the preprocessed, clean video data.

[0142] Step 4:

[0143] Video data analysis

[0144] The server inputs the preprocessed video data into a generative AI model to analyze the fashion trends of customers. The generative AI model uses frameworks such as TensorFlow and PyTorch to classify the video data into categories such as casual, formal, and street style. The input is the preprocessed video data, and the output is the analysis results, which are fashion trend data.

[0145] Step 5:

[0146] Sending analysis results

[0147] The server receives the analysis results returned by the generative AI model, converts them into JSON format, and then sends the analysis results to the user's device. The input is the analysis results of the generative AI model, and the output is JSON format data sent to the user's device.

[0148] Step 6:

[0149] Displaying analysis results

[0150] The user device parses the JSON format analysis results received from the server and displays them visually in the user interface. For example, a message or icon such as "Most of our current customers are dressed casually" is displayed. The input is JSON format data, and the output is visual information displayed to the user.

[0151] Step 7:

[0152] Online shopping support

[0153] The user clicks on a link to an online shopping site based on the presented fashion trend. The server tracks the click event, obtains links to online shopping sites for related fashion items, and provides them to the user. The input is the user's click event, and the output is the link to the online shopping site.

[0154] Step 8:

[0155] Store-side data analysis

[0156] The server analyzes continuously collected fashion data and displays demographic information in real time on the store management screen. Store managers use this data to plan marketing strategies and promotional activities. The input is continuously collected fashion data, and the output is real-time data and analysis results provided to the store managers.

[0157] (Application example 1)

[0158] 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."

[0159] Conventionally, there have been limited ways to know what kind of clothing is appropriate when visiting a particular store, making it difficult to grasp the store's atmosphere and the fashion trends of customers in advance. As a result, users were unable to choose appropriate clothing and were likely to have an unpleasant experience. It was also difficult for stores to develop marketing strategies that effectively utilized customer fashion data. The present invention aims to solve these problems.

[0160] 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.

[0161] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for suggesting a fashion style suitable for the user based on the fashion trends. This enables users to choose clothes that match the atmosphere of the store they visit, and also enables stores to implement effective marketing strategies based on the fashion data of customers visiting the store.

[0162] A "user terminal" is a device used to input and display location information and analysis results specified by the user, such as a smartphone or personal computer.

[0163] "Security camera footage" refers to video data captured in real time by security cameras installed within a specific store.

[0164] A "generative AI model" is an artificial intelligence algorithm used to analyze captured video data and classify the fashion trends of customers.

[0165] "Analysis results" refers to the fashion trend data of customers analyzed by the generative AI model, and includes classification results such as casual, formal, and street style.

[0166] The "fashion style suggestion means" refers to a function for recommending a fashion style suitable for the user based on the analysis results.

[0167] "Online shopping means" refers to a means by which a user purchases related fashion items based on the analysis results from a shopping site on the Internet.

[0168] "Customer fashion data" refers to information about the clothing worn by customers at stores that is regularly collected and analyzed from security camera footage, and is data that stores can use in their marketing strategies.

[0169] This invention is a system for providing fashion styles suited to specific stores. This system analyzes the fashion trends of stores that users want to visit in real time and suggests fashion styles suited to the user based on the results. The system is mainly composed of a user terminal, a server, and security cameras.

[0170] System configuration

[0171] 1. User Device

[0172] The user terminal can be a smartphone or a personal computer. The user inputs the location information specified by the user and displays the analysis results sent from the server. The user then uses the terminal to search for the store they want to visit.

[0173] 2. Server

[0174] The server receives requests from users, obtains store information, and collects security camera footage. The acquired video data is then input into a generative AI model to analyze the fashion trends of customers. The analysis results are sent to the user's device, and appropriate styles are suggested to the user based on their fashion trends.

[0175] 3. Security cameras

[0176] Security cameras are installed inside the store and capture real-time video data of customers, which is then sent to a server and analyzed by a generative AI model.

[0177] Program processing explanation

[0178] 1. User Request Processing

[0179] A user searches for a store they want to visit using a smartphone app. The app uses the Yahoo! Maps API to retrieve store information based on the specified location.

[0180] 2. Obtaining store information and security camera footage

[0181] The server receives the store information and obtains the URL of the security camera footage. The video data is captured from the security camera in real time.

[0182] 3. Analysis of video data

[0183] The server inputs the acquired video data into a generative AI model, which is built using TensorFlow, and analyzes the video data to classify the customer's outfit (e.g., casual, formal, street style, etc.).

[0184] 4. Displaying the analysis results

[0185] The server sends the analysis results in JSON format to the user's device, which receives the results and displays suggestions for suitable fashion styles for the user.

[0186] Specific examples

[0187] For example, if a user wants to visit a cafe, the system works as follows: When the user searches for "cafe" in the app, the app retrieves real-time security camera footage and analyzes it using an AI model. As a result, it displays a message saying, "Most customers currently visiting are dressed casually," and also provides a link to a related online shopping site. This allows the user to choose an appropriate outfit with peace of mind.

[0188] Prompt Sentence Examples

[0189] "Please analyze the fashion styles of current cafe customers."

[0190] This makes it easier for users to choose clothing that matches the atmosphere of the store they visit, and real-time analysis using security cameras and generative AI models is possible. Furthermore, the analysis results can be used to support online shopping, improving the user experience.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The user's device searches for the store they want to visit based on the location information specified by the user. The input includes location information and search keywords. The output is basic information about the store (address, business hours, etc.). The user's device uses the Yahoo! Maps API to obtain store information based on the specified location information.

[0194] Step 2:

[0195] The server gets the URL of the security camera footage. In this step, the server receives the store information and gets the URL of the security camera footage. The input contains the store information and the output is the URL of the security camera.

[0196] Step 3:

[0197] The server retrieves real-time video data from security cameras. The server captures real-time video data based on the camera's URL. The input contains the camera's URL, and the output is real-time video data. This data is used for downstream analysis.

[0198] Step 4:

[0199] The server inputs the acquired video data into the generative AI model. The server preprocesses the video data and analyzes it using the TensorFlow model. The video data is included as input, and the customer's clothing data (casual, formal, street style, etc.) is obtained as output.

[0200] Step 5:

[0201] The server sends the analysis results to the user's device. The server structures the analysis results in JSON format and sends it to the user's device. The analysis results are included as input, and the structured data is sent in JSON format as output.

[0202] Step 6:

[0203] The user's device will suggest a fashion style based on the analysis results. The user's device will display the received analysis results and suggest a fashion style that suits the user. The input contains JSON format data, and the output is fashion style suggestion information that is displayed to the user.

[0204] Step 7:

[0205] The user then performs online shopping as needed. The user's device provides links to fashion items based on the analysis results, which the user then uses to shop. The input includes links to suggested items, and the output is access to online shopping sites.

[0206] Step 8:

[0207] The store utilizes customer fashion data. The server periodically collects and analyzes the fashion data of customers visiting the store and provides it to the store. The input includes security camera footage and analysis data, and the output is data that is provided to the store in the form of a weekly report or similar.

[0208] This allows users to choose clothing that matches the atmosphere of the store they are visiting, and stores can implement effective marketing strategies based on customer fashion data.

[0209] 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.

[0210] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, and further provides more personalized fashion suggestions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention will be described below.

[0211] System configuration

[0212] The system consists of a user's device, a server, security cameras, a generative AI model, and an emotion engine. The user's device refers to a device such as a smartphone or PC, and the server processes and analyzes the data. Security cameras are installed inside the store and capture video data of customers. The generative AI model is an algorithm that analyzes the fashion trends of customers, and the emotion engine has the function of recognizing user emotions and reflecting them in the system.

[0213] Program processing

[0214] 1. User Request

[0215] Users can open the Yahoo! Maps app or website and search for the name or location of the store they want to visit. For example, they can enter "Aoyama Cafe A" in the search bar and press the search button.

[0216] The device sends the user's search query to the Yahoo! Maps API and sends a request to the server to retrieve specific store information based on the specified location information.

[0217] 2. Obtaining store information

[0218] The server receives the user's request and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0219] The server then accesses the store's security cameras and obtains real-time video data.

[0220] 3. Analysis of video data

[0221] The server sends the video data acquired from the security camera to the generative AI model.

[0222] The generative AI model preprocesses the video data, classifies customers' clothing into categories such as casual, formal, and street style, and generates data representing current fashion trends.

[0223] 4. User Emotion Recognition

[0224] The device captures the user's facial expressions and voice using a built-in camera and microphone.

[0225] The acquired data is sent to the emotion engine to analyze the user's emotions, which determine the user's emotional status (e.g., joy, sadness, surprise, anger) based on their facial expressions and tone of voice.

[0226] 5. Integration and display of analysis results

[0227] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine.

[0228] More personalized fashion style suggestions based on the user's emotions are sent to the user's device in JSON format.

[0229] The device analyzes the received data and displays appropriate fashion style information to the user. For example, it might say, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0230] 6. Online shopping support

[0231] The user chooses an outfit based on presented fashion trends and emotions, and if desired, is provided with a link to an online shopping site.

[0232] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0233] 7. Store-side data analysis

[0234] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, which is also provided as a weekly report on specific fashion trends and customer sentiment.

[0235] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts or promotions tailored to specific styles or times of day when certain emotions are more prevalent.

[0236] Specific examples

[0237] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0238] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0239] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0240] 3. The emotion engine recognizes the user's emotion and the result is sent to the server.

[0241] 4. The analysis results are sent to the user's device, and a message is displayed saying, "Most of our customers are currently wearing casual clothing. Taking your mood into consideration, we recommend this casual jacket."

[0242] 5. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0243] This allows users to choose clothes that match the atmosphere of the store they are visiting, and allows stores to implement effective marketing strategies. The introduction of an emotion engine will enable even more personalized fashion suggestions, improving the user experience.

[0244] The processing flow will be explained below.

[0245] Step 1:

[0246] A user opens the Yahoo! Maps app or website and searches for the name or location of the store they want to visit. For example, they enter "Aoyama Cafe A" in the search bar and press the search button.

[0247] Step 2:

[0248] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0249] Step 3:

[0250] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current occupancy status, etc.) from the database. The server queries the database and retrieves the corresponding information.

[0251] Step 4:

[0252] The server accesses the security cameras at the relevant store and sends a request to the security camera API to obtain real-time video data.

[0253] Step 5:

[0254] The server sends the acquired security camera video data to the generative AI model, which then preprocesses the video data and converts it into a format suitable for analysis.

[0255] Step 6:

[0256] A generative AI model analyzes customers' fashion trends and categorizes their outfits into categories such as casual, formal, and street style based on video data.

[0257] Step 7:

[0258] The device captures the user's facial expressions and voice using the built-in camera and microphone. The user selects to use the emotion recognition function, and facial expressions and voice are collected.

[0259] Step 8:

[0260] The device sends the acquired facial and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the facial expressions and tone of voice.

[0261] Step 9:

[0262] The server combines the fashion trend analysis results from the generated AI model with the emotion recognition results from the emotion engine, and generates data to provide optimal fashion suggestions to users.

[0263] Step 10:

[0264] The server sends the integrated analysis results in JSON format to the user's device, which receives the analysis results.

[0265] Step 11:

[0266] The device analyzes the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0267] Step 12:

[0268] The user chooses an outfit based on the displayed fashion suggestions, and if desired, is provided with a link to an online shopping site.

[0269] Step 13:

[0270] The user clicks the "Shop Online" button. The device displays a page with related fashion items.

[0271] Step 14:

[0272] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[0273] Step 15:

[0274] The server periodically collects and analyzes security camera footage and stores customer clothing data in a database in real time. The server periodically acquires security camera footage and analyzes it using a generative AI model.

[0275] Step 16:

[0276] The server provides regularly updated fashion data to the store, as well as real-time demographic data and weekly reports to the store.

[0277] Step 17:

[0278] Based on the data provided by the store, we plan and execute marketing strategies and promotional activities, and develop promotional activities based on specific fashion trends and emotions.

[0279] This makes it easier for users to choose clothes that match the atmosphere of the store they are visiting, and allows them to receive personalized fashion suggestions based on their emotions.It also enables stores to plan and implement effective marketing strategies.

[0280] Example 2

[0281] 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."

[0282] Conventional fashion suggestion systems often end up making uniform suggestions because they are unable to fully reflect the user's preferences and emotions. Furthermore, it is difficult to analyze the fashion trends of customers in real time and, based on the results, suggest fashion styles that fit the store's atmosphere. This makes it difficult to improve the user experience and reduces the desire to purchase fashion items.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0284] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring surveillance footage, means for inputting the acquired surveillance footage into a generative AI model and analyzing the fashion trends of customers, means for acquiring user emotion data using a camera or microphone on the user terminal and analyzing it with an emotion engine, and means for integrating the analysis results and displaying personalized fashion style suggestions on the user terminal. This enables personalized fashion suggestions in real time based on the user's emotions and the fashion trends of customers.

[0285] "User terminal" refers to an electronic device operated by a user, such as a smartphone, personal computer, or tablet.

[0286] "Server" refers to a computer system on a network that processes and analyzes data.

[0287] "Monitoring footage" refers to real-time video data captured by cameras installed within the store.

[0288] A "generative AI model" refers to an artificial intelligence model that has an algorithm that analyzes video data obtained from security cameras and other sources, and classifies and analyzes the fashion trends of customers.

[0289] "Emotion engine" refers to software or hardware functionality that determines a user's emotional status by analyzing their facial expressions and tone of voice.

[0290] "Real-time" means that data is collected, processed, analyzed, and results are output almost instantly.

[0291] "Individualized fashion style suggestions" refers to recommending the most suitable fashion items and styles to each individual user based on the user's emotions and the fashion trends of customers.

[0292] "Location Information" means information about a location, such as geographic coordinates or an address.

[0293] "Online shopping system" refers to an e-commerce platform that allows customers to purchase fashion items via the Internet.

[0294] "Analysis Results" refers to the output of data processed and analyzed by the Generative AI Model and Emotion Engine.

[0295] This invention is a system that provides a user with a fashion style suited to the specific store they visit, and by combining it with an emotion engine that recognizes the user's emotions, it makes more personalized fashion suggestions. The system consists of a user terminal, a server, a monitoring device, a generative AI model, and an emotion engine.

[0296] The user terminal refers to a device such as a smartphone or PC, and provides an interface for users to input search queries. The server processes and analyzes data. Upon receiving a request from the user terminal, it retrieves the specified store information from a database. The server also inputs surveillance footage into a generative AI model to analyze the fashion trends of customers.

[0297] The generative AI model preprocesses the video data, classifies the clothing of customers into categories such as casual, formal, and street style, and generates data on current fashion trends. The analysis results are sent to a server and integrated.

[0298] The user device captures the user's facial expressions and voice using a built-in camera and microphone, and transmits them to the emotion engine, which then determines the user's emotional status from the user's facial expressions and tone of voice.

[0299] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine, and sends personalized fashion style suggestions in JSON format to the user's device. The user's device analyzes the received data and displays appropriate fashion style information to the user.

[0300] For example, when a user visits "XX Cafe A," the user's device requests information about "XX Cafe A" from the server. The server obtains the store information and sends the surveillance footage to the generative AI model. The generative AI model analyzes the video data and determines fashion trends. The user's device obtains emotion data and analyzes it with an emotion engine. The server then integrates the analysis results and displays personalized fashion style suggestions on the user's device.

[0301] An example of a prompt is as follows:

[0302] "What fashion style would be appropriate for Cafe A?"

[0303] "Please suggest some fashion items that suit my current mood."

[0304] "Analyze real-time footage from surveillance equipment to tell us the fashion trends in the store."

[0305] This embodiment allows users to choose clothes that match the atmosphere of the store they are visiting and receive fashion style suggestions that match their individual emotions and preferences, which is expected to improve the user experience and increase purchasing motivation.

[0306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0307] Step 1:

[0308] Users search for stores using devices such as smartphones or PCs.

[0309] Specific operation: A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit, for example, "XX Cafe A" in the search bar, and presses the search button.

[0310] Input: User's search query (e.g. "XX Cafe A").

[0311] Output: The search query is sent from the device to the server.

[0312] Step 2:

[0313] The server receives the user's request and obtains store information.

[0314] Specific operation: The server uses the Yahoo! Maps API to obtain basic information about the relevant store (e.g., address, business hours, congestion status, etc.) based on the specified location information.

[0315] Input: The user's search query.

[0316] Output: Basic store information.

[0317] Step 3:

[0318] The server acquires the video from the surveillance device of the store.

[0319] Specific operation: The server accesses the surveillance equipment of the relevant store, acquires real-time video data, and streams it.

[0320] Input: Basic store information.

[0321] Output: Surveillance video data.

[0322] Step 4:

[0323] The server sends the surveillance footage to a generative AI model that analyzes fashion trends.

[0324] How it works: The server inputs surveillance footage into a generative AI model and applies an algorithm to classify customers' clothing into categories such as casual, formal, and street style.

[0325] Input: Surveillance video data.

[0326] Output: Analysis of customer fashion trends.

[0327] Step 5:

[0328] The device acquires the user's facial expressions and voice and sends them to the emotion engine.

[0329] Specific operation: Uses the device's camera and microphone to collect the user's facial expressions and voice in real time.

[0330] Input: User's facial expression data and voice data.

[0331] Output: Emotion data sent to the emotion engine.

[0332] Step 6:

[0333] The emotion engine analyzes the user's emotions.

[0334] Specific operation: The emotion engine applies algorithms to determine the user's emotional status (happiness, sadness, surprise, anger, etc.) from their facial expressions and tone of voice.

[0335] Input: Emotion data.

[0336] Output: The user's emotional status.

[0337] Step 7:

[0338] The server integrates the fashion trend analysis result and the user emotion recognition result.

[0339] Specific operation: The server combines the analysis results from the generative AI model with the emotional status from the emotion engine to generate personalized fashion style suggestions.

[0340] Input: Fashion trend analysis results and sentiment status.

[0341] Output: personalized fashion style suggestions.

[0342] Step 8:

[0343] The server transmits the personalized fashion style suggestions to the user terminal.

[0344] Specific operation: The server sends fashion style suggestions in JSON format to the user's device.

[0345] Enter: personalized fashion style suggestions.

[0346] Output: Fashion style information displayed on the user's device.

[0347] Step 9:

[0348] The user terminal displays the fashion style information.

[0349] Specific operation: The user device analyzes the received data and displays appropriate fashion style information to the user. For example, it displays, "Most customers currently in the store are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0350] Input: Fashion style information sent from the server.

[0351] Output: Visual and textual suggestions displayed to the user.

[0352] (Application example 2)

[0353] 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."

[0354] In conventional store visits, users have limited means of knowing the fashion trends and atmosphere of the store they are visiting in advance, making it difficult to choose appropriate clothing.In addition, personalized fashion suggestions based on the user's emotions are not provided, which hinders the user experience.

[0355] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring information about a specific store based on location information specified by the user, means for acquiring surveillance camera footage of the store, means for inputting the acquired surveillance camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for recognizing the user's emotions using the camera and microphone of the user's terminal, means for integrating the analyzed fashion trends with emotion data and generating fashion suggestions personalized for the user, and means for transmitting the suggestion results to the user terminal and displaying them on the user terminal. This allows the user to know in advance the fashion trends of the store they will visit and to receive personalized fashion suggestions tailored to their emotions.

[0356] A "user" is an individual who uses the system to obtain information about a specific store and receive fashion suggestions.

[0357] "Location information" is data that indicates the address and coordinates of a specific location or store that a user specifies they want to visit.

[0358] A "specific store" refers to an individual commercial facility, restaurant, etc. that the user is interested in based on location information.

[0359] "Information" refers to basic data about a specific store, such as its address, opening hours, and how busy it is.

[0360] "Monitoring camera footage" refers to video data captured in real time by cameras installed inside a store.

[0361] A "generative AI model" refers to an artificial intelligence algorithm that analyzes captured surveillance camera footage and automatically classifies and recognizes the fashion trends of customers.

[0362] "Fashion trends" refers to the styles and categories of clothing and accessories worn by customers.

[0363] "Emotion" refers to an emotional status such as joy, sadness, surprise, or anger that is analyzed from the user's facial expression and tone of voice.

[0364] "Means for recognizing emotions" refers to software or hardware that uses the camera or microphone installed on the user's device to acquire and analyze emotional data.

[0365] "Terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0366] "Personalized fashion suggestions" are recommendations of specific clothing and accessories that are best suited to a user, generated by integrating analyzed fashion trends with the user's emotional data.

[0367] An "online shopping site" is a website where you can purchase products over the Internet.

[0368] This invention relates to a system for providing a user with a fashion style suited to the store they plan to visit. The system is composed of a user terminal, a server, a surveillance camera, a generative AI model, and an emotion engine.

[0369] First, a user uses a device such as a smartphone or PC to search for the name and location of the store they want to visit and obtain that information. At this time, the device sends location information to the server. Based on this location information, the server obtains basic information about the specific store and obtains surveillance camera footage of the store in real time.

[0370] The server then inputs the captured surveillance camera footage into a generative AI model, which preprocesses the video data, classifies the customers' clothing, and generates data to analyze current fashion trends. Based on its algorithm, the generative AI model classifies the clothing into categories such as casual, formal, and street style.

[0371] Furthermore, the user device uses a built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine, which determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the user's facial expressions and tone of voice.

[0372] The server integrates these analysis results and generates more personalized fashion style suggestions based on the user's emotions. These suggestions are sent to the user's device in JSON format. The user's device analyzes the received data and displays appropriate fashion style information to the user. For example, it may say, "Currently, most customers are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0373] The user can select an outfit based on the suggested fashion trends and emotions, and a link to an online shopping site is provided accordingly. The server retrieves the links to the online shopping sites for related fashion items and presents them to the user. At this time, the links clicked by the user are tracked and necessary data is recorded.

[0374] Stores can also continuously collect and analyze fashion data from the server, obtaining real-time data on customers' fashion trends and users' emotional status. This data is provided as weekly reports, which can be used to plan marketing strategies and promotional activities.

[0375] Specific examples

[0376] For example, when a user visits "Aoyama Cafe A," he or she inputs a prompt sentence such as, "I'm planning to go to Aoyama Cafe A. Please tell me fashion suggestions based on the current fashion trends of customers and my feelings accordingly." As a result, fashion suggestions are displayed in the form of, "Most customers currently visiting the store are wearing casual styles. Taking your mood into consideration, I recommend this casual style jacket."

[0377] This system allows users to choose clothing that matches the atmosphere of the store they are visiting in advance, resulting in a comfortable experience. It also allows stores to implement effective marketing strategies.

[0378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0379] Step 1:

[0380] The user uses the device to search for the name and location of the store they want to visit. By inputting the user's specified location information, the device sends that location information to the server. The server then obtains basic information about the specific store based on the location information and returns it to the user. This basic information includes the address, business hours, current congestion status, etc.

[0381] Step 2:

[0382] The server acquires surveillance camera footage from the relevant store in real time. The video data obtained from the surveillance cameras is used as input and sent to the generative AI model. The generative AI model preprocesses the video data and classifies the clothing worn by customers into categories such as casual, formal, and street style. The model outputs the classified fashion trend data.

[0383] Step 3:

[0384] The device uses a built-in camera and microphone to capture the user's facial expressions and voice data. This data is sent as input to the emotion engine, which analyzes and determines the user's emotional status, such as joy, sadness, surprise, or anger, from the user's facial expressions and voice. The emotion data resulting from the analysis is output.

[0385] Step 4:

[0386] The server integrates the fashion trend data analyzed by the generative AI model with the emotion data obtained from the emotion engine. This generates personalized fashion suggestions based on the user's emotions. The generated suggestion data is output. The suggestions include specific clothing items based on each fashion style.

[0387] Step 5:

[0388] The server sends the generated personalized fashion suggestions in JSON format to the user's device. The device analyzes the received data and displays appropriate fashion suggestions to the user. For example, it displays a message like, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0389] Step 6:

[0390] The user selects a clothing item based on the suggested fashion trends. The server provides the user with a link to an online shopping site for the related clothing item. When the user clicks on the link, the user can purchase the item from the online shop. The server tracks the clicked link and records the necessary data.

[0391] Step 7:

[0392] The server continuously captures surveillance camera footage and periodically collects and analyzes customer clothing data. This data is provided to the store. The store uses this data to plan and execute marketing strategies and promotional activities tailored to specific fashion trends and time periods. For example, the store can offer special discounts during times when many customers are wearing casual clothing.

[0393] In this way, users can know the fashion trends of the store they are visiting in advance and receive personalized fashion suggestions that match their own emotions, while also enabling the store to implement effective marketing strategies.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Second embodiment]

[0398] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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."

[0410] The present invention is a system for providing a user with a fashion style suited to a specific store that the user visits. This system improves user convenience and also provides marketing support to the store. Specific embodiments of the present invention will be described below.

[0411] System configuration

[0412] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0413] Program processing

[0414] 1. User Request

[0415] The user opens the Yahoo! Maps app or website on their device and searches for the store they want to visit. For example, they enter keywords such as "Aoyama Cafe A" and press the search button.

[0416] The device sends this search query to the Yahoo! Maps API and sends a request to the server to obtain specific store information based on the specified location information.

[0417] 2. Obtaining store information

[0418] The server receives the user's request and retrieves the details of the relevant store from the database, including basic information such as the address, opening hours, and current occupancy status.

[0419] The server then accesses the store's security cameras and obtains real-time video data.

[0420] 3. Analysis of video data

[0421] The server sends the video data acquired from the security cameras to the generative AI model, which then preprocesses the video data and analyzes the clothing of customers.

[0422] The generative AI model classifies customers' clothing into categories such as casual, formal, and street style, and generates data on current fashion trends.

[0423] 4. Displaying the analysis results

[0424] The server sends the analysis results to the user's device, generally in JSON format.

[0425] The device analyzes the received data and displays appropriate fashion style information to the user, such as a message like, "Most of our customers are currently wearing casual styles."

[0426] 5. Online shopping support

[0427] The user chooses an outfit based on presented fashion trends, and if desired, is provided with a link to an online shopping site.

[0428] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0429] 6. Store-side data analysis

[0430] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, as well as weekly reports on specific fashion trends.

[0431] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts and promotions at times when certain styles are in high demand.

[0432] Specific examples

[0433] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0434] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0435] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0436] 3. The analysis results are sent to the user's device, and the message "Most of our current customers are dressed casually" is displayed.

[0437] 4. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0438] This allows users to choose clothes that match the atmosphere of the store they are visiting, and also allows the store to implement an effective marketing strategy.

[0439] The processing flow will be explained below.

[0440] Step 1:

[0441] A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit in the search bar, and presses the search button.

[0442] Step 2:

[0443] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0444] Step 3:

[0445] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0446] Step 4:

[0447] The server accesses the security cameras of the relevant store, sends a request to the security camera API, and obtains real-time video data.

[0448] Step 5:

[0449] The server sends the acquired security camera video data to the generative AI model, where it undergoes preprocessing and is converted into a format suitable for analysis.

[0450] Step 6:

[0451] The generative AI model analyzes the fashion trends of customers and categorizes the clothing of people in the video into categories such as casual, formal, and street style.

[0452] Step 7:

[0453] The server sends the analysis results in JSON format to the user's device, which receives the results.

[0454] Step 8:

[0455] The device parses the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Currently, most customers are wearing casual styles."

[0456] Step 9:

[0457] The user chooses an outfit based on displayed fashion trends, and if necessary, links to online shopping sites are provided.

[0458] Step 10:

[0459] The user clicks the "Shop Online" button. The device displays a page of related fashion items.

[0460] Step 11:

[0461] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[0462] Step 12:

[0463] The server periodically collects and analyzes security camera footage and stores customer fashion data in a database in real time.

[0464] Step 13:

[0465] The server provides regularly updated fashion data to the stores, who can then access real-time demographic data and weekly reports via a management screen.

[0466] Step 14:

[0467] Stores can use the data provided to plan and execute marketing strategies and promotional activities, such as holding discount events tailored to specific fashion trends.

[0468] Example 1

[0469] 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."

[0470] Conventional fashion suggestion systems did not fully satisfy user convenience, making it difficult to provide appropriate fashion styles that match the atmosphere of the store the user visits. Furthermore, stores lacked sufficient means to utilize customer fashion trends as data, making it difficult to develop effective marketing strategies.

[0471] 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.

[0472] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage of the store, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers, means for classifying the clothing of customers using the generative AI model and suggesting fashion styles, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for providing a link to an online shopping site so that the user can purchase fashion items. This enables users to select an appropriate fashion style that matches the atmosphere of the store they visit, and also enables the store to utilize the fashion trends of customers as marketing data.

[0473] "User" refers to a person who uses the system to obtain information about a specific store and receive fashion style suggestions.

[0474] A "terminal" is a device operated by a user, and includes a smartphone, a personal computer, etc.

[0475] "Server" refers to a computer system that processes and analyzes data and communicates with user terminals.

[0476] "Location information" is data indicating the geographical location of a store that a user wants to visit.

[0477] A "security camera" refers to a device installed in a specific store that captures video data of customers.

[0478] A "generative AI model" refers to a machine learning model that analyzes acquired video data and classifies and suggests fashion trends for customers.

[0479] "Analysis results" refers to data regarding the fashion trends of store customers obtained after the generative AI model analyzes the video data.

[0480] "Online shopping site" refers to a website that sells fashion items over the Internet.

[0481] "Fashion style" refers to the classification of customers' clothing characteristics into casual, formal, street style, etc.

[0482] "Fashion items" refer to products such as clothing and accessories that users can purchase.

[0483] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, improving convenience for the user and providing marketing support to the store.

[0484] System configuration

[0485] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0486] Program processing

[0487] First, a user opens a map app or website on their device and searches for a store they want to visit. For example, they search for "Aoyama Cafe." In this case, the device sends a search query and a request to the server to obtain specific store information based on the specified location information.

[0488] Upon receiving a user request, the server retrieves detailed information about the relevant store from the database. This information includes the store's name, address, business hours, and current occupancy status. The server also accesses the store's security cameras to obtain video data in real time. This video data is obtained using RTSP (Real-Time Streaming Protocol).

[0489] The server then sends the acquired security camera footage to a generative AI model, which uses image processing libraries such as OpenCV to preprocess the video data and remove noise. The video data then classifies the customer's fashion style into categories such as casual, formal, and street style, and analyzes current fashion trends.

[0490] The server converts the analysis results received from the generative AI model into JSON format and sends it to the user's device. The user's device analyzes this data and displays appropriate fashion style information to the user. For example, a message such as "Most customers currently in the store are wearing casual styles" may be displayed.

[0491] Furthermore, the user selects an appropriate outfit based on the presented fashion trends and clicks on a link to an online shopping site if necessary. The server obtains a link to an online shopping site for related fashion items and provides it to the user. This link click event is tracked and necessary data is recorded.

[0492] Finally, the server analyzes the continuously collected fashion data and displays demographic information in real time on a dashboard for store managers. Store managers can use this data to plan marketing strategies and promotional activities, making it possible to effectively run promotions tailored to times when certain styles are popular.

[0493] Specific examples

[0494] For example, for a user visiting "Aoyama Cafe," the system works as follows: The user searches for "Aoyama Cafe," and the search results are sent from the device to the server. The server obtains store information and security camera footage, and analyzes fashion trends using a generative AI model. The analysis results are then sent to the user's device, displaying a message saying, "Most customers currently visiting the store are wearing casual styles." The user references this information, purchases appropriate clothing on an online shopping site, and visits the store with peace of mind.

[0495] Examples of prompt statements

[0496] "What is the recommended fashion style for visiting Aoyama Cafe?"

[0497] As described above, the system of the present invention suggests fashion styles that match the atmosphere of a store before the user visits, and also supports online shopping. This allows users to choose appropriate clothing for the store they are visiting, and stores can also use real-time data to conduct effective marketing.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Step 1:

[0500] User Request

[0501] A user opens a map app or website on their device and searches for a store they want to visit. For example, they enter a keyword such as "Aoyama Cafe A." The device then sends this search query to the server. Specifically, the device sends an HTTP GET request to the specified URI, sending the search query. The input data is the keyword entered by the user, and the output is the request data sent to the server.

[0502] Step 2:

[0503] Obtaining store information

[0504] The server receives the user's request and retrieves detailed information about the corresponding store from a database. The server executes an SQL query on the database to retrieve information such as the store's address, business hours, and current occupancy status. The server then accesses the store's security cameras to obtain real-time video data. This video data is processed using RTSP (Real-Time Streaming Protocol). The input data is the user's request, and the output data is store information and security camera video data.

[0505] Step 3:

[0506] Video data preprocessing

[0507] The server receives the video data acquired from the security camera and performs preprocessing. This processing uses image processing libraries such as OpenCV to remove noise and normalize the image. The input is the security camera video data, and the output is the preprocessed, clean video data.

[0508] Step 4:

[0509] Video data analysis

[0510] The server inputs the preprocessed video data into a generative AI model to analyze the fashion trends of customers. The generative AI model uses frameworks such as TensorFlow and PyTorch to classify the video data into categories such as casual, formal, and street style. The input is the preprocessed video data, and the output is the analysis results, which are fashion trend data.

[0511] Step 5:

[0512] Sending analysis results

[0513] The server receives the analysis results returned by the generative AI model, converts them into JSON format, and then sends the analysis results to the user's device. The input is the analysis results of the generative AI model, and the output is JSON format data sent to the user's device.

[0514] Step 6:

[0515] Displaying analysis results

[0516] The user device parses the JSON format analysis results received from the server and displays them visually in the user interface. For example, a message or icon such as "Most of our current customers are dressed casually" is displayed. The input is JSON format data, and the output is visual information displayed to the user.

[0517] Step 7:

[0518] Online shopping support

[0519] The user clicks on a link to an online shopping site based on the presented fashion trend. The server tracks the click event, obtains links to online shopping sites for related fashion items, and provides them to the user. The input is the user's click event, and the output is the link to the online shopping site.

[0520] Step 8:

[0521] Store-side data analysis

[0522] The server analyzes continuously collected fashion data and displays demographic information in real time on the store management screen. Store managers use this data to plan marketing strategies and promotional activities. The input is continuously collected fashion data, and the output is real-time data and analysis results provided to the store managers.

[0523] (Application example 1)

[0524] 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."

[0525] Conventionally, there have been limited ways to know what kind of clothing is appropriate when visiting a particular store, making it difficult to grasp the store's atmosphere and the fashion trends of customers in advance. As a result, users were unable to choose appropriate clothing and were likely to have an unpleasant experience. It was also difficult for stores to develop marketing strategies that effectively utilized customer fashion data. The present invention aims to solve these problems.

[0526] 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.

[0527] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for suggesting a fashion style suitable for the user based on the fashion trends. This enables users to choose clothes that match the atmosphere of the store they visit, and also enables stores to implement effective marketing strategies based on the fashion data of customers visiting the store.

[0528] A "user terminal" is a device used to input and display location information and analysis results specified by the user, such as a smartphone or personal computer.

[0529] "Security camera footage" refers to video data captured in real time by security cameras installed within a specific store.

[0530] A "generative AI model" is an artificial intelligence algorithm used to analyze captured video data and classify the fashion trends of customers.

[0531] "Analysis results" refers to the fashion trend data of customers analyzed by the generative AI model, and includes classification results such as casual, formal, and street style.

[0532] The "fashion style suggestion means" refers to a function for recommending a fashion style suitable for the user based on the analysis results.

[0533] "Online shopping means" refers to a means by which a user purchases related fashion items based on the analysis results from a shopping site on the Internet.

[0534] "Customer fashion data" refers to information about the clothing worn by customers at stores that is regularly collected and analyzed from security camera footage, and is data that stores can use in their marketing strategies.

[0535] This invention is a system for providing fashion styles suited to specific stores. This system analyzes the fashion trends of stores that users want to visit in real time and suggests fashion styles suited to the user based on the results. The system is mainly composed of a user terminal, a server, and security cameras.

[0536] System configuration

[0537] 1. User Device

[0538] The user terminal can be a smartphone or a personal computer. The user inputs the location information specified by the user and displays the analysis results sent from the server. The user then uses the terminal to search for the store they want to visit.

[0539] 2. Server

[0540] The server receives requests from users, obtains store information, and collects security camera footage. The acquired video data is then input into a generative AI model to analyze the fashion trends of customers. The analysis results are sent to the user's device, and appropriate styles are suggested to the user based on their fashion trends.

[0541] 3. Security cameras

[0542] Security cameras are installed inside the store and capture real-time video data of customers, which is then sent to a server and analyzed by a generative AI model.

[0543] Program processing explanation

[0544] 1. User Request Processing

[0545] A user searches for a store they want to visit using a smartphone app. The app uses the Yahoo! Maps API to retrieve store information based on the specified location.

[0546] 2. Obtaining store information and security camera footage

[0547] The server receives the store information and obtains the URL of the security camera footage. The video data is captured from the security camera in real time.

[0548] 3. Analysis of video data

[0549] The server inputs the acquired video data into a generative AI model, which is built using TensorFlow, and analyzes the video data to classify the customer's outfit (e.g., casual, formal, street style, etc.).

[0550] 4. Displaying the analysis results

[0551] The server sends the analysis results in JSON format to the user's device, which receives the results and displays suggestions for suitable fashion styles for the user.

[0552] Specific examples

[0553] For example, if a user wants to visit a cafe, the system works as follows: When the user searches for "cafe" in the app, the app retrieves real-time security camera footage and analyzes it using an AI model. As a result, it displays a message saying, "Most customers currently visiting are dressed casually," and also provides a link to a related online shopping site. This allows the user to choose an appropriate outfit with peace of mind.

[0554] Prompt Sentence Examples

[0555] "Please analyze the fashion styles of current cafe customers."

[0556] This makes it easier for users to choose clothing that matches the atmosphere of the store they visit, and real-time analysis using security cameras and generative AI models is possible. Furthermore, the analysis results can be used to support online shopping, improving the user experience.

[0557] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0558] Step 1:

[0559] The user's device searches for the store they want to visit based on the location information specified by the user. The input includes location information and search keywords. The output is basic information about the store (address, business hours, etc.). The user's device uses the Yahoo! Maps API to obtain store information based on the specified location information.

[0560] Step 2:

[0561] The server gets the URL of the security camera footage. In this step, the server receives the store information and gets the URL of the security camera footage. The input contains the store information and the output is the URL of the security camera.

[0562] Step 3:

[0563] The server retrieves real-time video data from security cameras. The server captures real-time video data based on the camera's URL. The input contains the camera's URL, and the output is real-time video data. This data is used for downstream analysis.

[0564] Step 4:

[0565] The server inputs the acquired video data into the generative AI model. The server preprocesses the video data and analyzes it using the TensorFlow model. The video data is included as input, and the customer's clothing data (casual, formal, street style, etc.) is obtained as output.

[0566] Step 5:

[0567] The server sends the analysis results to the user's device. The server structures the analysis results in JSON format and sends it to the user's device. The analysis results are included as input, and the structured data is sent in JSON format as output.

[0568] Step 6:

[0569] The user's device will suggest a fashion style based on the analysis results. The user's device will display the received analysis results and suggest a fashion style that suits the user. The input contains JSON format data, and the output is fashion style suggestion information that is displayed to the user.

[0570] Step 7:

[0571] The user then performs online shopping as needed. The user's device provides links to fashion items based on the analysis results, which the user then uses to shop. The input includes links to suggested items, and the output is access to online shopping sites.

[0572] Step 8:

[0573] The store utilizes customer fashion data. The server periodically collects and analyzes the fashion data of customers visiting the store and provides it to the store. The input includes security camera footage and analysis data, and the output is data that is provided to the store in the form of a weekly report or similar.

[0574] This allows users to choose clothing that matches the atmosphere of the store they are visiting, and stores can implement effective marketing strategies based on customer fashion data.

[0575] 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.

[0576] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, and further provides more personalized fashion suggestions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention will be described below.

[0577] System configuration

[0578] The system consists of a user's device, a server, security cameras, a generative AI model, and an emotion engine. The user's device refers to a device such as a smartphone or PC, and the server processes and analyzes the data. Security cameras are installed inside the store and capture video data of customers. The generative AI model is an algorithm that analyzes the fashion trends of customers, and the emotion engine has the function of recognizing user emotions and reflecting them in the system.

[0579] Program processing

[0580] 1. User Request

[0581] Users can open the Yahoo! Maps app or website and search for the name or location of the store they want to visit. For example, they can enter "Aoyama Cafe A" in the search bar and press the search button.

[0582] The device sends the user's search query to the Yahoo! Maps API and sends a request to the server to retrieve specific store information based on the specified location information.

[0583] 2. Obtaining store information

[0584] The server receives the user's request and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0585] The server then accesses the store's security cameras and obtains real-time video data.

[0586] 3. Analysis of video data

[0587] The server sends the video data acquired from the security camera to the generative AI model.

[0588] The generative AI model preprocesses the video data, classifies customers' clothing into categories such as casual, formal, and street style, and generates data representing current fashion trends.

[0589] 4. User Emotion Recognition

[0590] The device captures the user's facial expressions and voice using a built-in camera and microphone.

[0591] The acquired data is sent to the emotion engine to analyze the user's emotions, which determine the user's emotional status (e.g., joy, sadness, surprise, anger) based on their facial expressions and tone of voice.

[0592] 5. Integration and display of analysis results

[0593] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine.

[0594] More personalized fashion style suggestions based on the user's emotions are sent to the user's device in JSON format.

[0595] The device analyzes the received data and displays appropriate fashion style information to the user. For example, it might say, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0596] 6. Online shopping support

[0597] The user chooses an outfit based on presented fashion trends and emotions, and if desired, is provided with a link to an online shopping site.

[0598] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0599] 7. Store-side data analysis

[0600] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, which is also provided as a weekly report on specific fashion trends and customer sentiment.

[0601] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts or promotions tailored to specific styles or times of day when certain emotions are more prevalent.

[0602] Specific examples

[0603] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0604] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0605] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0606] 3. The emotion engine recognizes the user's emotion and the result is sent to the server.

[0607] 4. The analysis results are sent to the user's device, and a message is displayed saying, "Most of our customers are currently wearing casual clothing. Taking your mood into consideration, we recommend this casual jacket."

[0608] 5. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0609] This allows users to choose clothes that match the atmosphere of the store they are visiting, and allows stores to implement effective marketing strategies. The introduction of an emotion engine will enable even more personalized fashion suggestions, improving the user experience.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] A user opens the Yahoo! Maps app or website and searches for the name or location of the store they want to visit. For example, they enter "Aoyama Cafe A" in the search bar and press the search button.

[0613] Step 2:

[0614] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0615] Step 3:

[0616] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current occupancy status, etc.) from the database. The server queries the database and retrieves the corresponding information.

[0617] Step 4:

[0618] The server accesses the security cameras at the relevant store and sends a request to the security camera API to obtain real-time video data.

[0619] Step 5:

[0620] The server sends the acquired security camera video data to the generative AI model, which then preprocesses the video data and converts it into a format suitable for analysis.

[0621] Step 6:

[0622] A generative AI model analyzes customers' fashion trends and categorizes their outfits into categories such as casual, formal, and street style based on video data.

[0623] Step 7:

[0624] The device captures the user's facial expressions and voice using the built-in camera and microphone. The user selects to use the emotion recognition function, and facial expressions and voice are collected.

[0625] Step 8:

[0626] The device sends the acquired facial and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the facial expressions and tone of voice.

[0627] Step 9:

[0628] The server combines the fashion trend analysis results from the generated AI model with the emotion recognition results from the emotion engine, and generates data to provide optimal fashion suggestions to users.

[0629] Step 10:

[0630] The server sends the integrated analysis results in JSON format to the user's device, which receives the analysis results.

[0631] Step 11:

[0632] The device analyzes the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0633] Step 12:

[0634] The user chooses an outfit based on the displayed fashion suggestions, and if desired, is provided with a link to an online shopping site.

[0635] Step 13:

[0636] The user clicks the "Shop Online" button. The device displays a page with related fashion items.

[0637] Step 14:

[0638] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[0639] Step 15:

[0640] The server periodically collects and analyzes security camera footage and stores customer clothing data in a database in real time. The server periodically acquires security camera footage and analyzes it using a generative AI model.

[0641] Step 16:

[0642] The server provides regularly updated fashion data to the store, as well as real-time demographic data and weekly reports to the store.

[0643] Step 17:

[0644] Based on the data provided by the store, we plan and execute marketing strategies and promotional activities, and develop promotional activities based on specific fashion trends and emotions.

[0645] This makes it easier for users to choose clothes that match the atmosphere of the store they are visiting, and allows them to receive personalized fashion suggestions based on their emotions.It also enables stores to plan and implement effective marketing strategies.

[0646] Example 2

[0647] 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."

[0648] Conventional fashion suggestion systems often end up making uniform suggestions because they are unable to fully reflect the user's preferences and emotions. Furthermore, it is difficult to analyze the fashion trends of customers in real time and, based on the results, suggest fashion styles that fit the store's atmosphere. This makes it difficult to improve the user experience and reduces the desire to purchase fashion items.

[0649] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0650] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring surveillance footage, means for inputting the acquired surveillance footage into a generative AI model and analyzing the fashion trends of customers, means for acquiring user emotion data using a camera or microphone on the user terminal and analyzing it with an emotion engine, and means for integrating the analysis results and displaying personalized fashion style suggestions on the user terminal. This enables personalized fashion suggestions in real time based on the user's emotions and the fashion trends of customers.

[0651] "User terminal" refers to an electronic device operated by a user, such as a smartphone, personal computer, or tablet.

[0652] "Server" refers to a computer system on a network that processes and analyzes data.

[0653] "Monitoring footage" refers to real-time video data captured by cameras installed within the store.

[0654] A "generative AI model" refers to an artificial intelligence model that has an algorithm that analyzes video data obtained from security cameras and other sources, and classifies and analyzes the fashion trends of customers.

[0655] "Emotion engine" refers to software or hardware functionality that determines a user's emotional status by analyzing their facial expressions and tone of voice.

[0656] "Real-time" means that data is collected, processed, analyzed, and results are output almost instantly.

[0657] "Individualized fashion style suggestions" refers to recommending the most suitable fashion items and styles to each individual user based on the user's emotions and the fashion trends of customers.

[0658] "Location Information" means information about a location, such as geographic coordinates or an address.

[0659] "Online shopping system" refers to an e-commerce platform that allows customers to purchase fashion items via the Internet.

[0660] "Analysis Results" refers to the output of data processed and analyzed by the Generative AI Model and Emotion Engine.

[0661] This invention is a system that provides a user with a fashion style suited to the specific store they visit, and by combining it with an emotion engine that recognizes the user's emotions, it makes more personalized fashion suggestions. The system consists of a user terminal, a server, a monitoring device, a generative AI model, and an emotion engine.

[0662] The user terminal refers to a device such as a smartphone or PC, and provides an interface for users to input search queries. The server processes and analyzes data. Upon receiving a request from the user terminal, it retrieves the specified store information from a database. The server also inputs surveillance footage into a generative AI model to analyze the fashion trends of customers.

[0663] The generative AI model preprocesses the video data, classifies the clothing of customers into categories such as casual, formal, and street style, and generates data on current fashion trends. The analysis results are sent to a server and integrated.

[0664] The user device captures the user's facial expressions and voice using a built-in camera and microphone, and transmits them to the emotion engine, which then determines the user's emotional status from the user's facial expressions and tone of voice.

[0665] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine, and sends personalized fashion style suggestions in JSON format to the user's device. The user's device analyzes the received data and displays appropriate fashion style information to the user.

[0666] For example, when a user visits "XX Cafe A," the user's device requests information about "XX Cafe A" from the server. The server obtains the store information and sends the surveillance footage to the generative AI model. The generative AI model analyzes the video data and determines fashion trends. The user's device obtains emotion data and analyzes it with an emotion engine. The server then integrates the analysis results and displays personalized fashion style suggestions on the user's device.

[0667] An example of a prompt is as follows:

[0668] "What fashion style would be appropriate for Cafe A?"

[0669] "Please suggest some fashion items that suit my current mood."

[0670] "Analyze real-time footage from surveillance equipment to tell us the fashion trends in the store."

[0671] This embodiment allows users to choose clothes that match the atmosphere of the store they are visiting and receive fashion style suggestions that match their individual emotions and preferences, which is expected to improve the user experience and increase purchasing motivation.

[0672] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0673] Step 1:

[0674] Users search for stores using devices such as smartphones or PCs.

[0675] Specific operation: A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit, for example, "XX Cafe A" in the search bar, and presses the search button.

[0676] Input: User's search query (e.g. "XX Cafe A").

[0677] Output: The search query is sent from the device to the server.

[0678] Step 2:

[0679] The server receives the user's request and obtains store information.

[0680] Specific operation: The server uses the Yahoo! Maps API to obtain basic information about the relevant store (e.g., address, business hours, congestion status, etc.) based on the specified location information.

[0681] Input: The user's search query.

[0682] Output: Basic store information.

[0683] Step 3:

[0684] The server acquires the video from the surveillance device of the store.

[0685] Specific operation: The server accesses the surveillance equipment of the relevant store, acquires real-time video data, and streams it.

[0686] Input: Basic store information.

[0687] Output: Surveillance video data.

[0688] Step 4:

[0689] The server sends the surveillance footage to a generative AI model that analyzes fashion trends.

[0690] How it works: The server inputs surveillance footage into a generative AI model and applies an algorithm to classify customers' clothing into categories such as casual, formal, and street style.

[0691] Input: Surveillance video data.

[0692] Output: Analysis of customer fashion trends.

[0693] Step 5:

[0694] The device acquires the user's facial expressions and voice and sends them to the emotion engine.

[0695] Specific operation: Uses the device's camera and microphone to collect the user's facial expressions and voice in real time.

[0696] Input: User's facial expression data and voice data.

[0697] Output: Emotion data sent to the emotion engine.

[0698] Step 6:

[0699] The emotion engine analyzes the user's emotions.

[0700] Specific operation: The emotion engine applies algorithms to determine the user's emotional status (happiness, sadness, surprise, anger, etc.) from their facial expressions and tone of voice.

[0701] Input: Emotion data.

[0702] Output: The user's emotional status.

[0703] Step 7:

[0704] The server integrates the fashion trend analysis result and the user emotion recognition result.

[0705] Specific operation: The server combines the analysis results from the generative AI model with the emotional status from the emotion engine to generate personalized fashion style suggestions.

[0706] Input: Fashion trend analysis results and sentiment status.

[0707] Output: personalized fashion style suggestions.

[0708] Step 8:

[0709] The server transmits the personalized fashion style suggestions to the user terminal.

[0710] Specific operation: The server sends fashion style suggestions in JSON format to the user's device.

[0711] Enter: personalized fashion style suggestions.

[0712] Output: Fashion style information displayed on the user's device.

[0713] Step 9:

[0714] The user terminal displays the fashion style information.

[0715] Specific operation: The user device analyzes the received data and displays appropriate fashion style information to the user. For example, it displays, "Most customers currently in the store are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0716] Input: Fashion style information sent from the server.

[0717] Output: Visual and textual suggestions displayed to the user.

[0718] (Application example 2)

[0719] 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."

[0720] In conventional store visits, users have limited means of knowing the fashion trends and atmosphere of the store they are visiting in advance, making it difficult to choose appropriate clothing.In addition, personalized fashion suggestions based on the user's emotions are not provided, which hinders the user experience.

[0721] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring information about a specific store based on location information specified by the user, means for acquiring surveillance camera footage of the store, means for inputting the acquired surveillance camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for recognizing the user's emotions using the camera and microphone of the user's terminal, means for integrating the analyzed fashion trends with emotion data and generating fashion suggestions personalized for the user, and means for transmitting the suggestion results to the user terminal and displaying them on the user terminal. This allows the user to know in advance the fashion trends of the store they will visit and to receive personalized fashion suggestions tailored to their emotions.

[0722] A "user" is an individual who uses the system to obtain information about a specific store and receive fashion suggestions.

[0723] "Location information" is data that indicates the address and coordinates of a specific location or store that a user specifies they want to visit.

[0724] A "specific store" refers to an individual commercial facility, restaurant, etc. that the user is interested in based on location information.

[0725] "Information" refers to basic data about a specific store, such as its address, opening hours, and how busy it is.

[0726] "Monitoring camera footage" refers to video data captured in real time by cameras installed inside a store.

[0727] A "generative AI model" refers to an artificial intelligence algorithm that analyzes captured surveillance camera footage and automatically classifies and recognizes the fashion trends of customers.

[0728] "Fashion trends" refers to the styles and categories of clothing and accessories worn by customers.

[0729] "Emotion" refers to an emotional status such as joy, sadness, surprise, or anger that is analyzed from the user's facial expression and tone of voice.

[0730] "Means for recognizing emotions" refers to software or hardware that uses the camera or microphone installed on the user's device to acquire and analyze emotional data.

[0731] "Terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0732] "Personalized fashion suggestions" are recommendations of specific clothing and accessories that are best suited to a user, generated by integrating analyzed fashion trends with the user's emotional data.

[0733] An "online shopping site" is a website where you can purchase products over the Internet.

[0734] This invention relates to a system for providing a user with a fashion style suited to the store they plan to visit. The system is composed of a user terminal, a server, a surveillance camera, a generative AI model, and an emotion engine.

[0735] First, a user uses a device such as a smartphone or PC to search for the name and location of the store they want to visit and obtain that information. At this time, the device sends location information to the server. Based on this location information, the server obtains basic information about the specific store and obtains surveillance camera footage of the store in real time.

[0736] The server then inputs the captured surveillance camera footage into a generative AI model, which preprocesses the video data, classifies the customers' clothing, and generates data to analyze current fashion trends. Based on its algorithm, the generative AI model classifies the clothing into categories such as casual, formal, and street style.

[0737] Furthermore, the user device uses a built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine, which determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the user's facial expressions and tone of voice.

[0738] The server integrates these analysis results and generates more personalized fashion style suggestions based on the user's emotions. These suggestions are sent to the user's device in JSON format. The user's device analyzes the received data and displays appropriate fashion style information to the user. For example, it may say, "Currently, most customers are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0739] The user can select an outfit based on the suggested fashion trends and emotions, and a link to an online shopping site is provided accordingly. The server retrieves the links to the online shopping sites for related fashion items and presents them to the user. At this time, the links clicked by the user are tracked and necessary data is recorded.

[0740] Stores can also continuously collect and analyze fashion data from the server, obtaining real-time data on customers' fashion trends and users' emotional status. This data is provided as weekly reports, which can be used to plan marketing strategies and promotional activities.

[0741] Specific examples

[0742] For example, when a user visits "Aoyama Cafe A," he or she inputs a prompt sentence such as, "I'm planning to go to Aoyama Cafe A. Please tell me fashion suggestions based on the current fashion trends of customers and my feelings accordingly." As a result, fashion suggestions are displayed in the form of, "Most customers currently visiting the store are wearing casual styles. Taking your mood into consideration, I recommend this casual style jacket."

[0743] This system allows users to choose clothing that matches the atmosphere of the store they are visiting in advance, resulting in a comfortable experience. It also allows stores to implement effective marketing strategies.

[0744] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0745] Step 1:

[0746] The user uses the device to search for the name and location of the store they want to visit. By inputting the user's specified location information, the device sends that location information to the server. The server then obtains basic information about the specific store based on the location information and returns it to the user. This basic information includes the address, business hours, current congestion status, etc.

[0747] Step 2:

[0748] The server acquires surveillance camera footage from the relevant store in real time. The video data obtained from the surveillance cameras is used as input and sent to the generative AI model. The generative AI model preprocesses the video data and classifies the clothing worn by customers into categories such as casual, formal, and street style. The model outputs the classified fashion trend data.

[0749] Step 3:

[0750] The device uses a built-in camera and microphone to capture the user's facial expressions and voice data. This data is sent as input to the emotion engine, which analyzes and determines the user's emotional status, such as joy, sadness, surprise, or anger, from the user's facial expressions and voice. The emotion data resulting from the analysis is output.

[0751] Step 4:

[0752] The server integrates the fashion trend data analyzed by the generative AI model with the emotion data obtained from the emotion engine. This generates personalized fashion suggestions based on the user's emotions. The generated suggestion data is output. The suggestions include specific clothing items based on each fashion style.

[0753] Step 5:

[0754] The server sends the generated personalized fashion suggestions in JSON format to the user's device. The device analyzes the received data and displays appropriate fashion suggestions to the user. For example, it displays a message like, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0755] Step 6:

[0756] The user selects a clothing item based on the suggested fashion trends. The server provides the user with a link to an online shopping site for the related clothing item. When the user clicks on the link, the user can purchase the item from the online shop. The server tracks the clicked link and records the necessary data.

[0757] Step 7:

[0758] The server continuously captures surveillance camera footage and periodically collects and analyzes customer clothing data. This data is provided to the store. The store uses this data to plan and execute marketing strategies and promotional activities tailored to specific fashion trends and time periods. For example, the store can offer special discounts during times when many customers are wearing casual clothing.

[0759] In this way, users can know the fashion trends of the store they are visiting in advance and receive personalized fashion suggestions that match their own emotions, while also enabling the store to implement effective marketing strategies.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] [Third embodiment]

[0764] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0765] 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.

[0766] 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).

[0767] 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.

[0768] 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.

[0769] 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).

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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."

[0776] The present invention is a system for providing a user with a fashion style suited to a specific store that the user visits. This system improves user convenience and also provides marketing support to the store. Specific embodiments of the present invention will be described below.

[0777] System configuration

[0778] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0779] Program processing

[0780] 1. User Request

[0781] The user opens the Yahoo! Maps app or website on their device and searches for the store they want to visit. For example, they enter keywords such as "Aoyama Cafe A" and press the search button.

[0782] The device sends this search query to the Yahoo! Maps API and sends a request to the server to obtain specific store information based on the specified location information.

[0783] 2. Obtaining store information

[0784] The server receives the user's request and retrieves the details of the relevant store from the database, including basic information such as the address, opening hours, and current occupancy status.

[0785] The server then accesses the store's security cameras and obtains real-time video data.

[0786] 3. Analysis of video data

[0787] The server sends the video data acquired from the security cameras to the generative AI model, which then preprocesses the video data and analyzes the clothing of customers.

[0788] The generative AI model classifies customers' clothing into categories such as casual, formal, and street style, and generates data on current fashion trends.

[0789] 4. Displaying the analysis results

[0790] The server sends the analysis results to the user's device, generally in JSON format.

[0791] The device analyzes the received data and displays appropriate fashion style information to the user, such as a message like, "Most of our customers are currently wearing casual styles."

[0792] 5. Online shopping support

[0793] The user chooses an outfit based on presented fashion trends, and if desired, is provided with a link to an online shopping site.

[0794] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0795] 6. Store-side data analysis

[0796] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, as well as weekly reports on specific fashion trends.

[0797] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts and promotions at times when certain styles are in high demand.

[0798] Specific examples

[0799] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0800] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0801] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0802] 3. The analysis results are sent to the user's device, and the message "Most of our current customers are dressed casually" is displayed.

[0803] 4. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0804] This allows users to choose clothes that match the atmosphere of the store they are visiting, and also allows the store to implement an effective marketing strategy.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit in the search bar, and presses the search button.

[0808] Step 2:

[0809] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0810] Step 3:

[0811] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0812] Step 4:

[0813] The server accesses the security cameras of the relevant store, sends a request to the security camera API, and obtains real-time video data.

[0814] Step 5:

[0815] The server sends the acquired security camera video data to the generative AI model, where it undergoes preprocessing and is converted into a format suitable for analysis.

[0816] Step 6:

[0817] The generative AI model analyzes the fashion trends of customers and categorizes the clothing of people in the video into categories such as casual, formal, and street style.

[0818] Step 7:

[0819] The server sends the analysis results in JSON format to the user's device, which receives the results.

[0820] Step 8:

[0821] The device parses the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Currently, most customers are wearing casual styles."

[0822] Step 9:

[0823] The user chooses an outfit based on displayed fashion trends, and if necessary, links to online shopping sites are provided.

[0824] Step 10:

[0825] The user clicks the "Shop Online" button. The device displays a page of related fashion items.

[0826] Step 11:

[0827] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[0828] Step 12:

[0829] The server periodically collects and analyzes security camera footage and stores customer fashion data in a database in real time.

[0830] Step 13:

[0831] The server provides regularly updated fashion data to the stores, who can then access real-time demographic data and weekly reports via a management screen.

[0832] Step 14:

[0833] Stores can use the data provided to plan and execute marketing strategies and promotional activities, such as holding discount events tailored to specific fashion trends.

[0834] Example 1

[0835] 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."

[0836] Conventional fashion suggestion systems did not fully satisfy user convenience, making it difficult to provide appropriate fashion styles that match the atmosphere of the store the user visits. Furthermore, stores lacked sufficient means to utilize customer fashion trends as data, making it difficult to develop effective marketing strategies.

[0837] 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.

[0838] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage of the store, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers, means for classifying the clothing of customers using the generative AI model and suggesting fashion styles, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for providing a link to an online shopping site so that the user can purchase fashion items. This enables users to select an appropriate fashion style that matches the atmosphere of the store they visit, and also enables the store to utilize the fashion trends of customers as marketing data.

[0839] "User" refers to a person who uses the system to obtain information about a specific store and receive fashion style suggestions.

[0840] A "terminal" is a device operated by a user, and includes a smartphone, a personal computer, etc.

[0841] "Server" refers to a computer system that processes and analyzes data and communicates with user terminals.

[0842] "Location information" is data indicating the geographical location of a store that a user wants to visit.

[0843] A "security camera" refers to a device installed in a specific store that captures video data of customers.

[0844] A "generative AI model" refers to a machine learning model that analyzes acquired video data and classifies and suggests fashion trends for customers.

[0845] "Analysis results" refers to data regarding the fashion trends of store customers obtained after the generative AI model analyzes the video data.

[0846] "Online shopping site" refers to a website that sells fashion items over the Internet.

[0847] "Fashion style" refers to the classification of customers' clothing characteristics into casual, formal, street style, etc.

[0848] "Fashion items" refer to products such as clothing and accessories that users can purchase.

[0849] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, improving convenience for the user and providing marketing support to the store.

[0850] System configuration

[0851] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[0852] Program processing

[0853] First, a user opens a map app or website on their device and searches for a store they want to visit. For example, they search for "Aoyama Cafe." In this case, the device sends a search query and a request to the server to obtain specific store information based on the specified location information.

[0854] Upon receiving a user request, the server retrieves detailed information about the relevant store from the database. This information includes the store's name, address, business hours, and current occupancy status. The server also accesses the store's security cameras to obtain video data in real time. This video data is obtained using RTSP (Real-Time Streaming Protocol).

[0855] The server then sends the acquired security camera footage to a generative AI model, which uses image processing libraries such as OpenCV to preprocess the video data and remove noise. The video data then classifies the customer's fashion style into categories such as casual, formal, and street style, and analyzes current fashion trends.

[0856] The server converts the analysis results received from the generative AI model into JSON format and sends it to the user's device. The user's device analyzes this data and displays appropriate fashion style information to the user. For example, a message such as "Most customers currently in the store are wearing casual styles" may be displayed.

[0857] Furthermore, the user selects an appropriate outfit based on the presented fashion trends and clicks on a link to an online shopping site if necessary. The server obtains a link to an online shopping site for related fashion items and provides it to the user. This link click event is tracked and necessary data is recorded.

[0858] Finally, the server analyzes the continuously collected fashion data and displays demographic information in real time on a dashboard for store managers. Store managers can use this data to plan marketing strategies and promotional activities, making it possible to effectively run promotions tailored to times when certain styles are popular.

[0859] Specific examples

[0860] For example, for a user visiting "Aoyama Cafe," the system works as follows: The user searches for "Aoyama Cafe," and the search results are sent from the device to the server. The server obtains store information and security camera footage, and analyzes fashion trends using a generative AI model. The analysis results are then sent to the user's device, displaying a message saying, "Most customers currently visiting the store are wearing casual styles." The user references this information, purchases appropriate clothing on an online shopping site, and visits the store with peace of mind.

[0861] Examples of prompt statements

[0862] "What is the recommended fashion style for visiting Aoyama Cafe?"

[0863] As described above, the system of the present invention suggests fashion styles that match the atmosphere of a store before the user visits, and also supports online shopping. This allows users to choose appropriate clothing for the store they are visiting, and stores can also use real-time data to conduct effective marketing.

[0864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] User Request

[0867] A user opens a map app or website on their device and searches for a store they want to visit. For example, they enter a keyword such as "Aoyama Cafe A." The device then sends this search query to the server. Specifically, the device sends an HTTP GET request to the specified URI, sending the search query. The input data is the keyword entered by the user, and the output is the request data sent to the server.

[0868] Step 2:

[0869] Obtaining store information

[0870] The server receives the user's request and retrieves detailed information about the corresponding store from a database. The server executes an SQL query on the database to retrieve information such as the store's address, business hours, and current occupancy status. The server then accesses the store's security cameras to obtain real-time video data. This video data is processed using RTSP (Real-Time Streaming Protocol). The input data is the user's request, and the output data is store information and security camera video data.

[0871] Step 3:

[0872] Video data preprocessing

[0873] The server receives the video data acquired from the security camera and performs preprocessing. This processing uses image processing libraries such as OpenCV to remove noise and normalize the image. The input is the security camera video data, and the output is the preprocessed, clean video data.

[0874] Step 4:

[0875] Video data analysis

[0876] The server inputs the preprocessed video data into a generative AI model to analyze the fashion trends of customers. The generative AI model uses frameworks such as TensorFlow and PyTorch to classify the video data into categories such as casual, formal, and street style. The input is the preprocessed video data, and the output is the analysis results, which are fashion trend data.

[0877] Step 5:

[0878] Sending analysis results

[0879] The server receives the analysis results returned by the generative AI model, converts them into JSON format, and then sends the analysis results to the user's device. The input is the analysis results of the generative AI model, and the output is JSON format data sent to the user's device.

[0880] Step 6:

[0881] Displaying analysis results

[0882] The user device parses the JSON format analysis results received from the server and displays them visually in the user interface. For example, a message or icon such as "Most of our current customers are dressed casually" is displayed. The input is JSON format data, and the output is visual information displayed to the user.

[0883] Step 7:

[0884] Online shopping support

[0885] The user clicks on a link to an online shopping site based on the presented fashion trend. The server tracks the click event, obtains links to online shopping sites for related fashion items, and provides them to the user. The input is the user's click event, and the output is the link to the online shopping site.

[0886] Step 8:

[0887] Store-side data analysis

[0888] The server analyzes continuously collected fashion data and displays demographic information in real time on the store management screen. Store managers use this data to plan marketing strategies and promotional activities. The input is continuously collected fashion data, and the output is real-time data and analysis results provided to the store managers.

[0889] (Application example 1)

[0890] 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."

[0891] Conventionally, there have been limited ways to know what kind of clothing is appropriate when visiting a particular store, making it difficult to grasp the store's atmosphere and the fashion trends of customers in advance. As a result, users were unable to choose appropriate clothing and were likely to have an unpleasant experience. It was also difficult for stores to develop marketing strategies that effectively utilized customer fashion data. The present invention aims to solve these problems.

[0892] 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.

[0893] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for suggesting a fashion style suitable for the user based on the fashion trends. This enables users to choose clothes that match the atmosphere of the store they visit, and also enables stores to implement effective marketing strategies based on the fashion data of customers visiting the store.

[0894] A "user terminal" is a device used to input and display location information and analysis results specified by the user, such as a smartphone or personal computer.

[0895] "Security camera footage" refers to video data captured in real time by security cameras installed within a specific store.

[0896] A "generative AI model" is an artificial intelligence algorithm used to analyze captured video data and classify the fashion trends of customers.

[0897] "Analysis results" refers to the fashion trend data of customers analyzed by the generative AI model, and includes classification results such as casual, formal, and street style.

[0898] The "fashion style suggestion means" refers to a function for recommending a fashion style suitable for the user based on the analysis results.

[0899] "Online shopping means" refers to a means by which a user purchases related fashion items based on the analysis results from a shopping site on the Internet.

[0900] "Customer fashion data" refers to information about the clothing worn by customers at stores that is regularly collected and analyzed from security camera footage, and is data that stores can use in their marketing strategies.

[0901] This invention is a system for providing fashion styles suited to specific stores. This system analyzes the fashion trends of stores that users want to visit in real time and suggests fashion styles suited to the user based on the results. The system is mainly composed of a user terminal, a server, and security cameras.

[0902] System configuration

[0903] 1. User Device

[0904] The user terminal can be a smartphone or a personal computer. The user inputs the location information specified by the user and displays the analysis results sent from the server. The user then uses the terminal to search for the store they want to visit.

[0905] 2. Server

[0906] The server receives requests from users, obtains store information, and collects security camera footage. The acquired video data is then input into a generative AI model to analyze the fashion trends of customers. The analysis results are sent to the user's device, and appropriate styles are suggested to the user based on their fashion trends.

[0907] 3. Security cameras

[0908] Security cameras are installed inside the store and capture real-time video data of customers, which is then sent to a server and analyzed by a generative AI model.

[0909] Program processing explanation

[0910] 1. User Request Processing

[0911] A user searches for a store they want to visit using a smartphone app. The app uses the Yahoo! Maps API to retrieve store information based on the specified location.

[0912] 2. Obtaining store information and security camera footage

[0913] The server receives the store information and obtains the URL of the security camera footage. The video data is captured from the security camera in real time.

[0914] 3. Analysis of video data

[0915] The server inputs the acquired video data into a generative AI model, which is built using TensorFlow, and analyzes the video data to classify the customer's outfit (e.g., casual, formal, street style, etc.).

[0916] 4. Displaying the analysis results

[0917] The server sends the analysis results in JSON format to the user's device, which receives the results and displays suggestions for suitable fashion styles for the user.

[0918] Specific examples

[0919] For example, if a user wants to visit a cafe, the system works as follows: When the user searches for "cafe" in the app, the app retrieves real-time security camera footage and analyzes it using an AI model. As a result, it displays a message saying, "Most customers currently visiting are dressed casually," and also provides a link to a related online shopping site. This allows the user to choose an appropriate outfit with peace of mind.

[0920] Prompt Sentence Examples

[0921] "Please analyze the fashion styles of current cafe customers."

[0922] This makes it easier for users to choose clothing that matches the atmosphere of the store they visit, and real-time analysis using security cameras and generative AI models is possible. Furthermore, the analysis results can be used to support online shopping, improving the user experience.

[0923] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0924] Step 1:

[0925] The user's device searches for the store they want to visit based on the location information specified by the user. The input includes location information and search keywords. The output is basic information about the store (address, business hours, etc.). The user's device uses the Yahoo! Maps API to obtain store information based on the specified location information.

[0926] Step 2:

[0927] The server gets the URL of the security camera footage. In this step, the server receives the store information and gets the URL of the security camera footage. The input contains the store information and the output is the URL of the security camera.

[0928] Step 3:

[0929] The server retrieves real-time video data from security cameras. The server captures real-time video data based on the camera's URL. The input contains the camera's URL, and the output is real-time video data. This data is used for downstream analysis.

[0930] Step 4:

[0931] The server inputs the acquired video data into the generative AI model. The server preprocesses the video data and analyzes it using the TensorFlow model. The video data is included as input, and the customer's clothing data (casual, formal, street style, etc.) is obtained as output.

[0932] Step 5:

[0933] The server sends the analysis results to the user's device. The server structures the analysis results in JSON format and sends it to the user's device. The analysis results are included as input, and the structured data is sent in JSON format as output.

[0934] Step 6:

[0935] The user's device will suggest a fashion style based on the analysis results. The user's device will display the received analysis results and suggest a fashion style that suits the user. The input contains JSON format data, and the output is fashion style suggestion information that is displayed to the user.

[0936] Step 7:

[0937] The user then performs online shopping as needed. The user's device provides links to fashion items based on the analysis results, which the user then uses to shop. The input includes links to suggested items, and the output is access to online shopping sites.

[0938] Step 8:

[0939] The store utilizes customer fashion data. The server periodically collects and analyzes the fashion data of customers visiting the store and provides it to the store. The input includes security camera footage and analysis data, and the output is data that is provided to the store in the form of a weekly report or similar.

[0940] This allows users to choose clothing that matches the atmosphere of the store they are visiting, and stores can implement effective marketing strategies based on customer fashion data.

[0941] 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.

[0942] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, and further provides more personalized fashion suggestions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention will be described below.

[0943] System configuration

[0944] The system consists of a user's device, a server, security cameras, a generative AI model, and an emotion engine. The user's device refers to a device such as a smartphone or PC, and the server processes and analyzes the data. Security cameras are installed inside the store and capture video data of customers. The generative AI model is an algorithm that analyzes the fashion trends of customers, and the emotion engine has the function of recognizing user emotions and reflecting them in the system.

[0945] Program processing

[0946] 1. User Request

[0947] Users can open the Yahoo! Maps app or website and search for the name or location of the store they want to visit. For example, they can enter "Aoyama Cafe A" in the search bar and press the search button.

[0948] The device sends the user's search query to the Yahoo! Maps API and sends a request to the server to retrieve specific store information based on the specified location information.

[0949] 2. Obtaining store information

[0950] The server receives the user's request and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[0951] The server then accesses the store's security cameras and obtains real-time video data.

[0952] 3. Analysis of video data

[0953] The server sends the video data acquired from the security camera to the generative AI model.

[0954] The generative AI model preprocesses the video data, classifies customers' clothing into categories such as casual, formal, and street style, and generates data representing current fashion trends.

[0955] 4. User Emotion Recognition

[0956] The device captures the user's facial expressions and voice using a built-in camera and microphone.

[0957] The acquired data is sent to the emotion engine to analyze the user's emotions, which determine the user's emotional status (e.g., joy, sadness, surprise, anger) based on their facial expressions and tone of voice.

[0958] 5. Integration and display of analysis results

[0959] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine.

[0960] More personalized fashion style suggestions based on the user's emotions are sent to the user's device in JSON format.

[0961] The device analyzes the received data and displays appropriate fashion style information to the user. For example, it might say, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0962] 6. Online shopping support

[0963] The user chooses an outfit based on presented fashion trends and emotions, and if desired, is provided with a link to an online shopping site.

[0964] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[0965] 7. Store-side data analysis

[0966] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, which is also provided as a weekly report on specific fashion trends and customer sentiment.

[0967] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts or promotions tailored to specific styles or times of day when certain emotions are more prevalent.

[0968] Specific examples

[0969] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[0970] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[0971] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[0972] 3. The emotion engine recognizes the user's emotion and the result is sent to the server.

[0973] 4. The analysis results are sent to the user's device, and a message is displayed saying, "Most of our customers are currently wearing casual clothing. Taking your mood into consideration, we recommend this casual jacket."

[0974] 5. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[0975] This allows users to choose clothes that match the atmosphere of the store they are visiting, and allows stores to implement effective marketing strategies. The introduction of an emotion engine will enable even more personalized fashion suggestions, improving the user experience.

[0976] The processing flow will be explained below.

[0977] Step 1:

[0978] A user opens the Yahoo! Maps app or website and searches for the name or location of the store they want to visit. For example, they enter "Aoyama Cafe A" in the search bar and press the search button.

[0979] Step 2:

[0980] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[0981] Step 3:

[0982] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current occupancy status, etc.) from the database. The server queries the database and retrieves the corresponding information.

[0983] Step 4:

[0984] The server accesses the security cameras at the relevant store and sends a request to the security camera API to obtain real-time video data.

[0985] Step 5:

[0986] The server sends the acquired security camera video data to the generative AI model, which then preprocesses the video data and converts it into a format suitable for analysis.

[0987] Step 6:

[0988] A generative AI model analyzes customers' fashion trends and categorizes their outfits into categories such as casual, formal, and street style based on video data.

[0989] Step 7:

[0990] The device captures the user's facial expressions and voice using the built-in camera and microphone. The user selects to use the emotion recognition function, and facial expressions and voice are collected.

[0991] Step 8:

[0992] The device sends the acquired facial and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the facial expressions and tone of voice.

[0993] Step 9:

[0994] The server combines the fashion trend analysis results from the generated AI model with the emotion recognition results from the emotion engine, and generates data to provide optimal fashion suggestions to users.

[0995] Step 10:

[0996] The server sends the integrated analysis results in JSON format to the user's device, which receives the analysis results.

[0997] Step 11:

[0998] The device analyzes the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[0999] Step 12:

[1000] The user chooses an outfit based on the displayed fashion suggestions, and if desired, is provided with a link to an online shopping site.

[1001] Step 13:

[1002] The user clicks the "Shop Online" button. The device displays a page with related fashion items.

[1003] Step 14:

[1004] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[1005] Step 15:

[1006] The server periodically collects and analyzes security camera footage and stores customer clothing data in a database in real time. The server periodically acquires security camera footage and analyzes it using a generative AI model.

[1007] Step 16:

[1008] The server provides regularly updated fashion data to the store, as well as real-time demographic data and weekly reports to the store.

[1009] Step 17:

[1010] Based on the data provided by the store, we plan and execute marketing strategies and promotional activities, and develop promotional activities based on specific fashion trends and emotions.

[1011] This makes it easier for users to choose clothes that match the atmosphere of the store they are visiting, and allows them to receive personalized fashion suggestions based on their emotions.It also enables stores to plan and implement effective marketing strategies.

[1012] Example 2

[1013] 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."

[1014] Conventional fashion suggestion systems often end up making uniform suggestions because they are unable to fully reflect the user's preferences and emotions. Furthermore, it is difficult to analyze the fashion trends of customers in real time and, based on the results, suggest fashion styles that fit the store's atmosphere. This makes it difficult to improve the user experience and reduces the desire to purchase fashion items.

[1015] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1016] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring surveillance footage, means for inputting the acquired surveillance footage into a generative AI model and analyzing the fashion trends of customers, means for acquiring user emotion data using a camera or microphone on the user terminal and analyzing it with an emotion engine, and means for integrating the analysis results and displaying personalized fashion style suggestions on the user terminal. This enables personalized fashion suggestions in real time based on the user's emotions and the fashion trends of customers.

[1017] "User terminal" refers to an electronic device operated by a user, such as a smartphone, personal computer, or tablet.

[1018] "Server" refers to a computer system on a network that processes and analyzes data.

[1019] "Monitoring footage" refers to real-time video data captured by cameras installed within the store.

[1020] A "generative AI model" refers to an artificial intelligence model that has an algorithm that analyzes video data obtained from security cameras and other sources, and classifies and analyzes the fashion trends of customers.

[1021] "Emotion engine" refers to software or hardware functionality that determines a user's emotional status by analyzing their facial expressions and tone of voice.

[1022] "Real-time" means that data is collected, processed, analyzed, and results are output almost instantly.

[1023] "Individualized fashion style suggestions" refers to recommending the most suitable fashion items and styles to each individual user based on the user's emotions and the fashion trends of customers.

[1024] "Location Information" means information about a location, such as geographic coordinates or an address.

[1025] "Online shopping system" refers to an e-commerce platform that allows customers to purchase fashion items via the Internet.

[1026] "Analysis Results" refers to the output of data processed and analyzed by the Generative AI Model and Emotion Engine.

[1027] This invention is a system that provides a user with a fashion style suited to the specific store they visit, and by combining it with an emotion engine that recognizes the user's emotions, it makes more personalized fashion suggestions. The system consists of a user terminal, a server, a monitoring device, a generative AI model, and an emotion engine.

[1028] The user terminal refers to a device such as a smartphone or PC, and provides an interface for users to input search queries. The server processes and analyzes data. Upon receiving a request from the user terminal, it retrieves the specified store information from a database. The server also inputs surveillance footage into a generative AI model to analyze the fashion trends of customers.

[1029] The generative AI model preprocesses the video data, classifies the clothing of customers into categories such as casual, formal, and street style, and generates data on current fashion trends. The analysis results are sent to a server and integrated.

[1030] The user device captures the user's facial expressions and voice using a built-in camera and microphone, and transmits them to the emotion engine, which then determines the user's emotional status from the user's facial expressions and tone of voice.

[1031] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine, and sends personalized fashion style suggestions in JSON format to the user's device. The user's device analyzes the received data and displays appropriate fashion style information to the user.

[1032] For example, when a user visits "XX Cafe A," the user's device requests information about "XX Cafe A" from the server. The server obtains the store information and sends the surveillance footage to the generative AI model. The generative AI model analyzes the video data and determines fashion trends. The user's device obtains emotion data and analyzes it with an emotion engine. The server then integrates the analysis results and displays personalized fashion style suggestions on the user's device.

[1033] An example of a prompt is as follows:

[1034] "What fashion style would be appropriate for Cafe A?"

[1035] "Please suggest some fashion items that suit my current mood."

[1036] "Analyze real-time footage from surveillance equipment to tell us the fashion trends in the store."

[1037] This embodiment allows users to choose clothes that match the atmosphere of the store they are visiting and receive fashion style suggestions that match their individual emotions and preferences, which is expected to improve the user experience and increase purchasing motivation.

[1038] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1039] Step 1:

[1040] Users search for stores using devices such as smartphones or PCs.

[1041] Specific operation: A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit, for example, "XX Cafe A" in the search bar, and presses the search button.

[1042] Input: User's search query (e.g. "XX Cafe A").

[1043] Output: The search query is sent from the device to the server.

[1044] Step 2:

[1045] The server receives the user's request and obtains store information.

[1046] Specific operation: The server uses the Yahoo! Maps API to obtain basic information about the relevant store (e.g., address, business hours, congestion status, etc.) based on the specified location information.

[1047] Input: The user's search query.

[1048] Output: Basic store information.

[1049] Step 3:

[1050] The server acquires the video from the surveillance device of the store.

[1051] Specific operation: The server accesses the surveillance equipment of the relevant store, acquires real-time video data, and streams it.

[1052] Input: Basic store information.

[1053] Output: Surveillance video data.

[1054] Step 4:

[1055] The server sends the surveillance footage to a generative AI model that analyzes fashion trends.

[1056] How it works: The server inputs surveillance footage into a generative AI model and applies an algorithm to classify customers' clothing into categories such as casual, formal, and street style.

[1057] Input: Surveillance video data.

[1058] Output: Analysis of customer fashion trends.

[1059] Step 5:

[1060] The device acquires the user's facial expressions and voice and sends them to the emotion engine.

[1061] Specific operation: Uses the device's camera and microphone to collect the user's facial expressions and voice in real time.

[1062] Input: User's facial expression data and voice data.

[1063] Output: Emotion data sent to the emotion engine.

[1064] Step 6:

[1065] The emotion engine analyzes the user's emotions.

[1066] Specific operation: The emotion engine applies algorithms to determine the user's emotional status (happiness, sadness, surprise, anger, etc.) from their facial expressions and tone of voice.

[1067] Input: Emotion data.

[1068] Output: The user's emotional status.

[1069] Step 7:

[1070] The server integrates the fashion trend analysis result and the user emotion recognition result.

[1071] Specific operation: The server combines the analysis results from the generative AI model with the emotional status from the emotion engine to generate personalized fashion style suggestions.

[1072] Input: Fashion trend analysis results and sentiment status.

[1073] Output: personalized fashion style suggestions.

[1074] Step 8:

[1075] The server transmits the personalized fashion style suggestions to the user terminal.

[1076] Specific operation: The server sends fashion style suggestions in JSON format to the user's device.

[1077] Enter: personalized fashion style suggestions.

[1078] Output: Fashion style information displayed on the user's device.

[1079] Step 9:

[1080] The user terminal displays the fashion style information.

[1081] Specific operation: The user device analyzes the received data and displays appropriate fashion style information to the user. For example, it displays, "Most customers currently in the store are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1082] Input: Fashion style information sent from the server.

[1083] Output: Visual and textual suggestions displayed to the user.

[1084] (Application example 2)

[1085] 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."

[1086] In conventional store visits, users have limited means of knowing the fashion trends and atmosphere of the store they are visiting in advance, making it difficult to choose appropriate clothing.In addition, personalized fashion suggestions based on the user's emotions are not provided, which hinders the user experience.

[1087] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring information about a specific store based on location information specified by the user, means for acquiring surveillance camera footage of the store, means for inputting the acquired surveillance camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for recognizing the user's emotions using the camera and microphone of the user's terminal, means for integrating the analyzed fashion trends with emotion data and generating fashion suggestions personalized for the user, and means for transmitting the suggestion results to the user terminal and displaying them on the user terminal. This allows the user to know in advance the fashion trends of the store they will visit and to receive personalized fashion suggestions tailored to their emotions.

[1088] A "user" is an individual who uses the system to obtain information about a specific store and receive fashion suggestions.

[1089] "Location information" is data that indicates the address and coordinates of a specific location or store that a user specifies they want to visit.

[1090] A "specific store" refers to an individual commercial facility, restaurant, etc. that the user is interested in based on location information.

[1091] "Information" refers to basic data about a specific store, such as its address, opening hours, and how busy it is.

[1092] "Monitoring camera footage" refers to video data captured in real time by cameras installed inside a store.

[1093] A "generative AI model" refers to an artificial intelligence algorithm that analyzes captured surveillance camera footage and automatically classifies and recognizes the fashion trends of customers.

[1094] "Fashion trends" refers to the styles and categories of clothing and accessories worn by customers.

[1095] "Emotion" refers to an emotional status such as joy, sadness, surprise, or anger that is analyzed from the user's facial expression and tone of voice.

[1096] "Means for recognizing emotions" refers to software or hardware that uses the camera or microphone installed on the user's device to acquire and analyze emotional data.

[1097] "Terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1098] "Personalized fashion suggestions" are recommendations of specific clothing and accessories that are best suited to a user, generated by integrating analyzed fashion trends with the user's emotional data.

[1099] An "online shopping site" is a website where you can purchase products over the Internet.

[1100] This invention relates to a system for providing a user with a fashion style suited to the store they plan to visit. The system is composed of a user terminal, a server, a surveillance camera, a generative AI model, and an emotion engine.

[1101] First, a user uses a device such as a smartphone or PC to search for the name and location of the store they want to visit and obtain that information. At this time, the device sends location information to the server. Based on this location information, the server obtains basic information about the specific store and obtains surveillance camera footage of the store in real time.

[1102] The server then inputs the captured surveillance camera footage into a generative AI model, which preprocesses the video data, classifies the customers' clothing, and generates data to analyze current fashion trends. Based on its algorithm, the generative AI model classifies the clothing into categories such as casual, formal, and street style.

[1103] Furthermore, the user device uses a built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine, which determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the user's facial expressions and tone of voice.

[1104] The server integrates these analysis results and generates more personalized fashion style suggestions based on the user's emotions. These suggestions are sent to the user's device in JSON format. The user's device analyzes the received data and displays appropriate fashion style information to the user. For example, it may say, "Currently, most customers are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1105] The user can select an outfit based on the suggested fashion trends and emotions, and a link to an online shopping site is provided accordingly. The server retrieves the links to the online shopping sites for related fashion items and presents them to the user. At this time, the links clicked by the user are tracked and necessary data is recorded.

[1106] Stores can also continuously collect and analyze fashion data from the server, obtaining real-time data on customers' fashion trends and users' emotional status. This data is provided as weekly reports, which can be used to plan marketing strategies and promotional activities.

[1107] Specific examples

[1108] For example, when a user visits "Aoyama Cafe A," he or she inputs a prompt sentence such as, "I'm planning to go to Aoyama Cafe A. Please tell me fashion suggestions based on the current fashion trends of customers and my feelings accordingly." As a result, fashion suggestions are displayed in the form of, "Most customers currently visiting the store are wearing casual styles. Taking your mood into consideration, I recommend this casual style jacket."

[1109] This system allows users to choose clothing that matches the atmosphere of the store they are visiting in advance, resulting in a comfortable experience. It also allows stores to implement effective marketing strategies.

[1110] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1111] Step 1:

[1112] The user uses the device to search for the name and location of the store they want to visit. By inputting the user's specified location information, the device sends that location information to the server. The server then obtains basic information about the specific store based on the location information and returns it to the user. This basic information includes the address, business hours, current congestion status, etc.

[1113] Step 2:

[1114] The server acquires surveillance camera footage from the relevant store in real time. The video data obtained from the surveillance cameras is used as input and sent to the generative AI model. The generative AI model preprocesses the video data and classifies the clothing worn by customers into categories such as casual, formal, and street style. The model outputs the classified fashion trend data.

[1115] Step 3:

[1116] The device uses a built-in camera and microphone to capture the user's facial expressions and voice data. This data is sent as input to the emotion engine, which analyzes and determines the user's emotional status, such as joy, sadness, surprise, or anger, from the user's facial expressions and voice. The emotion data resulting from the analysis is output.

[1117] Step 4:

[1118] The server integrates the fashion trend data analyzed by the generative AI model with the emotion data obtained from the emotion engine. This generates personalized fashion suggestions based on the user's emotions. The generated suggestion data is output. The suggestions include specific clothing items based on each fashion style.

[1119] Step 5:

[1120] The server sends the generated personalized fashion suggestions in JSON format to the user's device. The device analyzes the received data and displays appropriate fashion suggestions to the user. For example, it displays a message like, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1121] Step 6:

[1122] The user selects a clothing item based on the suggested fashion trends. The server provides the user with a link to an online shopping site for the related clothing item. When the user clicks on the link, the user can purchase the item from the online shop. The server tracks the clicked link and records the necessary data.

[1123] Step 7:

[1124] The server continuously captures surveillance camera footage and periodically collects and analyzes customer clothing data. This data is provided to the store. The store uses this data to plan and execute marketing strategies and promotional activities tailored to specific fashion trends and time periods. For example, the store can offer special discounts during times when many customers are wearing casual clothing.

[1125] In this way, users can know the fashion trends of the store they are visiting in advance and receive personalized fashion suggestions that match their own emotions, while also enabling the store to implement effective marketing strategies.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] [Fourth embodiment]

[1130] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1131] 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.

[1132] 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).

[1133] 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.

[1134] 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.

[1135] 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).

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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."

[1143] The present invention is a system for providing a user with a fashion style suited to a specific store that the user visits. This system improves user convenience and also provides marketing support to the store. Specific embodiments of the present invention will be described below.

[1144] System configuration

[1145] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[1146] Program processing

[1147] 1. User Request

[1148] The user opens the Yahoo! Maps app or website on their device and searches for the store they want to visit. For example, they enter keywords such as "Aoyama Cafe A" and press the search button.

[1149] The device sends this search query to the Yahoo! Maps API and sends a request to the server to obtain specific store information based on the specified location information.

[1150] 2. Obtaining store information

[1151] The server receives the user's request and retrieves the details of the relevant store from the database, including basic information such as the address, opening hours, and current occupancy status.

[1152] The server then accesses the store's security cameras and obtains real-time video data.

[1153] 3. Analysis of video data

[1154] The server sends the video data acquired from the security cameras to the generative AI model, which then preprocesses the video data and analyzes the clothing of customers.

[1155] The generative AI model classifies customers' clothing into categories such as casual, formal, and street style, and generates data on current fashion trends.

[1156] 4. Displaying the analysis results

[1157] The server sends the analysis results to the user's device, generally in JSON format.

[1158] The device analyzes the received data and displays appropriate fashion style information to the user, such as a message like, "Most of our customers are currently wearing casual styles."

[1159] 5. Online shopping support

[1160] The user chooses an outfit based on presented fashion trends, and if desired, is provided with a link to an online shopping site.

[1161] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[1162] 6. Store-side data analysis

[1163] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, as well as weekly reports on specific fashion trends.

[1164] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts and promotions at times when certain styles are in high demand.

[1165] Specific examples

[1166] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[1167] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[1168] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[1169] 3. The analysis results are sent to the user's device, and the message "Most of our current customers are dressed casually" is displayed.

[1170] 4. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[1171] This allows users to choose clothes that match the atmosphere of the store they are visiting, and also allows the store to implement an effective marketing strategy.

[1172] The processing flow will be explained below.

[1173] Step 1:

[1174] A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit in the search bar, and presses the search button.

[1175] Step 2:

[1176] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[1177] Step 3:

[1178] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[1179] Step 4:

[1180] The server accesses the security cameras of the relevant store, sends a request to the security camera API, and obtains real-time video data.

[1181] Step 5:

[1182] The server sends the acquired security camera video data to the generative AI model, where it undergoes preprocessing and is converted into a format suitable for analysis.

[1183] Step 6:

[1184] The generative AI model analyzes the fashion trends of customers and categorizes the clothing of people in the video into categories such as casual, formal, and street style.

[1185] Step 7:

[1186] The server sends the analysis results in JSON format to the user's device, which receives the results.

[1187] Step 8:

[1188] The device parses the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Currently, most customers are wearing casual styles."

[1189] Step 9:

[1190] The user chooses an outfit based on displayed fashion trends, and if necessary, links to online shopping sites are provided.

[1191] Step 10:

[1192] The user clicks the "Shop Online" button. The device displays a page of related fashion items.

[1193] Step 11:

[1194] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[1195] Step 12:

[1196] The server periodically collects and analyzes security camera footage and stores customer fashion data in a database in real time.

[1197] Step 13:

[1198] The server provides regularly updated fashion data to the stores, who can then access real-time demographic data and weekly reports via a management screen.

[1199] Step 14:

[1200] Stores can use the data provided to plan and execute marketing strategies and promotional activities, such as holding discount events tailored to specific fashion trends.

[1201] Example 1

[1202] 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."

[1203] Conventional fashion suggestion systems did not fully satisfy user convenience, making it difficult to provide appropriate fashion styles that match the atmosphere of the store the user visits. Furthermore, stores lacked sufficient means to utilize customer fashion trends as data, making it difficult to develop effective marketing strategies.

[1204] 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.

[1205] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage of the store, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers, means for classifying the clothing of customers using the generative AI model and suggesting fashion styles, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for providing a link to an online shopping site so that the user can purchase fashion items. This enables users to select an appropriate fashion style that matches the atmosphere of the store they visit, and also enables the store to utilize the fashion trends of customers as marketing data.

[1206] "User" refers to a person who uses the system to obtain information about a specific store and receive fashion style suggestions.

[1207] A "terminal" is a device operated by a user, and includes a smartphone, a personal computer, etc.

[1208] "Server" refers to a computer system that processes and analyzes data and communicates with user terminals.

[1209] "Location information" is data indicating the geographical location of a store that a user wants to visit.

[1210] A "security camera" refers to a device installed in a specific store that captures video data of customers.

[1211] A "generative AI model" refers to a machine learning model that analyzes acquired video data and classifies and suggests fashion trends for customers.

[1212] "Analysis results" refers to data regarding the fashion trends of store customers obtained after the generative AI model analyzes the video data.

[1213] "Online shopping site" refers to a website that sells fashion items over the Internet.

[1214] "Fashion style" refers to the classification of customers' clothing characteristics into casual, formal, street style, etc.

[1215] "Fashion items" refer to products such as clothing and accessories that users can purchase.

[1216] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, improving convenience for the user and providing marketing support to the store.

[1217] System configuration

[1218] The system consists of three main parts: the user's device, the server, and the security camera. The user's device includes a smartphone or PC, and the server processes and analyzes the data. The security camera is installed inside the store and captures video data of customers.

[1219] Program processing

[1220] First, a user opens a map app or website on their device and searches for a store they want to visit. For example, they search for "Aoyama Cafe." In this case, the device sends a search query and a request to the server to obtain specific store information based on the specified location information.

[1221] Upon receiving a user request, the server retrieves detailed information about the relevant store from the database. This information includes the store's name, address, business hours, and current occupancy status. The server also accesses the store's security cameras to obtain video data in real time. This video data is obtained using RTSP (Real-Time Streaming Protocol).

[1222] The server then sends the acquired security camera footage to a generative AI model, which uses image processing libraries such as OpenCV to preprocess the video data and remove noise. The video data then classifies the customer's fashion style into categories such as casual, formal, and street style, and analyzes current fashion trends.

[1223] The server converts the analysis results received from the generative AI model into JSON format and sends it to the user's device. The user's device analyzes this data and displays appropriate fashion style information to the user. For example, a message such as "Most customers currently in the store are wearing casual styles" may be displayed.

[1224] Furthermore, the user selects an appropriate outfit based on the presented fashion trends and clicks on a link to an online shopping site if necessary. The server obtains a link to an online shopping site for related fashion items and provides it to the user. This link click event is tracked and necessary data is recorded.

[1225] Finally, the server analyzes the continuously collected fashion data and displays demographic information in real time on a dashboard for store managers. Store managers can use this data to plan marketing strategies and promotional activities, making it possible to effectively run promotions tailored to times when certain styles are popular.

[1226] Specific examples

[1227] For example, for a user visiting "Aoyama Cafe," the system works as follows: The user searches for "Aoyama Cafe," and the search results are sent from the device to the server. The server obtains store information and security camera footage, and analyzes fashion trends using a generative AI model. The analysis results are then sent to the user's device, displaying a message saying, "Most customers currently visiting the store are wearing casual styles." The user references this information, purchases appropriate clothing on an online shopping site, and visits the store with peace of mind.

[1228] Examples of prompt statements

[1229] "What is the recommended fashion style for visiting Aoyama Cafe?"

[1230] As described above, the system of the present invention suggests fashion styles that match the atmosphere of a store before the user visits, and also supports online shopping. This allows users to choose appropriate clothing for the store they are visiting, and stores can also use real-time data to conduct effective marketing.

[1231] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1232] Step 1:

[1233] User Request

[1234] A user opens a map app or website on their device and searches for a store they want to visit. For example, they enter a keyword such as "Aoyama Cafe A." The device then sends this search query to the server. Specifically, the device sends an HTTP GET request to the specified URI, sending the search query. The input data is the keyword entered by the user, and the output is the request data sent to the server.

[1235] Step 2:

[1236] Obtaining store information

[1237] The server receives the user's request and retrieves detailed information about the corresponding store from a database. The server executes an SQL query on the database to retrieve information such as the store's address, business hours, and current occupancy status. The server then accesses the store's security cameras to obtain real-time video data. This video data is processed using RTSP (Real-Time Streaming Protocol). The input data is the user's request, and the output data is store information and security camera video data.

[1238] Step 3:

[1239] Video data preprocessing

[1240] The server receives the video data acquired from the security camera and performs preprocessing. This processing uses image processing libraries such as OpenCV to remove noise and normalize the image. The input is the security camera video data, and the output is the preprocessed, clean video data.

[1241] Step 4:

[1242] Video data analysis

[1243] The server inputs the preprocessed video data into a generative AI model to analyze the fashion trends of customers. The generative AI model uses frameworks such as TensorFlow and PyTorch to classify the video data into categories such as casual, formal, and street style. The input is the preprocessed video data, and the output is the analysis results, which are fashion trend data.

[1244] Step 5:

[1245] Sending analysis results

[1246] The server receives the analysis results returned by the generative AI model, converts them into JSON format, and then sends the analysis results to the user's device. The input is the analysis results of the generative AI model, and the output is JSON format data sent to the user's device.

[1247] Step 6:

[1248] Displaying analysis results

[1249] The user device parses the JSON format analysis results received from the server and displays them visually in the user interface. For example, a message or icon such as "Most of our current customers are dressed casually" is displayed. The input is JSON format data, and the output is visual information displayed to the user.

[1250] Step 7:

[1251] Online shopping support

[1252] The user clicks on a link to an online shopping site based on the presented fashion trend. The server tracks the click event, obtains links to online shopping sites for related fashion items, and provides them to the user. The input is the user's click event, and the output is the link to the online shopping site.

[1253] Step 8:

[1254] Store-side data analysis

[1255] The server analyzes continuously collected fashion data and displays demographic information in real time on the store management screen. Store managers use this data to plan marketing strategies and promotional activities. The input is continuously collected fashion data, and the output is real-time data and analysis results provided to the store managers.

[1256] (Application example 1)

[1257] 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."

[1258] Conventionally, there have been limited ways to know what kind of clothing is appropriate when visiting a particular store, making it difficult to grasp the store's atmosphere and the fashion trends of customers in advance. As a result, users were unable to choose appropriate clothing and were likely to have an unpleasant experience. It was also difficult for stores to develop marketing strategies that effectively utilized customer fashion data. The present invention aims to solve these problems.

[1259] 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.

[1260] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring security camera footage, means for inputting the acquired security camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for transmitting the analysis results to a user terminal and displaying the analysis results on the user terminal, and means for suggesting a fashion style suitable for the user based on the fashion trends. This enables users to choose clothes that match the atmosphere of the store they visit, and also enables stores to implement effective marketing strategies based on the fashion data of customers visiting the store.

[1261] A "user terminal" is a device used to input and display location information and analysis results specified by the user, such as a smartphone or personal computer.

[1262] "Security camera footage" refers to video data captured in real time by security cameras installed within a specific store.

[1263] A "generative AI model" is an artificial intelligence algorithm used to analyze captured video data and classify the fashion trends of customers.

[1264] "Analysis results" refers to the fashion trend data of customers analyzed by the generative AI model, and includes classification results such as casual, formal, and street style.

[1265] The "fashion style suggestion means" refers to a function for recommending a fashion style suitable for the user based on the analysis results.

[1266] "Online shopping means" refers to a means by which a user purchases related fashion items based on the analysis results from a shopping site on the Internet.

[1267] "Customer fashion data" refers to information about the clothing worn by customers at stores that is regularly collected and analyzed from security camera footage, and is data that stores can use in their marketing strategies.

[1268] This invention is a system for providing fashion styles suited to specific stores. This system analyzes the fashion trends of stores that users want to visit in real time and suggests fashion styles suited to the user based on the results. The system is mainly composed of a user terminal, a server, and security cameras.

[1269] System configuration

[1270] 1. User Device

[1271] The user terminal can be a smartphone or a personal computer. The user inputs the location information specified by the user and displays the analysis results sent from the server. The user then uses the terminal to search for the store they want to visit.

[1272] 2. Server

[1273] The server receives requests from users, obtains store information, and collects security camera footage. The acquired video data is then input into a generative AI model to analyze the fashion trends of customers. The analysis results are sent to the user's device, and appropriate styles are suggested to the user based on their fashion trends.

[1274] 3. Security cameras

[1275] Security cameras are installed inside the store and capture real-time video data of customers, which is then sent to a server and analyzed by a generative AI model.

[1276] Program processing explanation

[1277] 1. User Request Processing

[1278] A user searches for a store they want to visit using a smartphone app. The app uses the Yahoo! Maps API to retrieve store information based on the specified location.

[1279] 2. Obtaining store information and security camera footage

[1280] The server receives the store information and obtains the URL of the security camera footage. The video data is captured from the security camera in real time.

[1281] 3. Analysis of video data

[1282] The server inputs the acquired video data into a generative AI model, which is built using TensorFlow, and analyzes the video data to classify the customer's outfit (e.g., casual, formal, street style, etc.).

[1283] 4. Displaying the analysis results

[1284] The server sends the analysis results in JSON format to the user's device, which receives the results and displays suggestions for suitable fashion styles for the user.

[1285] Specific examples

[1286] For example, if a user wants to visit a cafe, the system works as follows: When the user searches for "cafe" in the app, the app retrieves real-time security camera footage and analyzes it using an AI model. As a result, it displays a message saying, "Most customers currently visiting are dressed casually," and also provides a link to a related online shopping site. This allows the user to choose an appropriate outfit with peace of mind.

[1287] Prompt Sentence Examples

[1288] "Please analyze the fashion styles of current cafe customers."

[1289] This makes it easier for users to choose clothing that matches the atmosphere of the store they visit, and real-time analysis using security cameras and generative AI models is possible. Furthermore, the analysis results can be used to support online shopping, improving the user experience.

[1290] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1291] Step 1:

[1292] The user's device searches for the store they want to visit based on the location information specified by the user. The input includes location information and search keywords. The output is basic information about the store (address, business hours, etc.). The user's device uses the Yahoo! Maps API to obtain store information based on the specified location information.

[1293] Step 2:

[1294] The server gets the URL of the security camera footage. In this step, the server receives the store information and gets the URL of the security camera footage. The input contains the store information and the output is the URL of the security camera.

[1295] Step 3:

[1296] The server retrieves real-time video data from security cameras. The server captures real-time video data based on the camera's URL. The input contains the camera's URL, and the output is real-time video data. This data is used for downstream analysis.

[1297] Step 4:

[1298] The server inputs the acquired video data into the generative AI model. The server preprocesses the video data and analyzes it using the TensorFlow model. The video data is included as input, and the customer's clothing data (casual, formal, street style, etc.) is obtained as output.

[1299] Step 5:

[1300] The server sends the analysis results to the user's device. The server structures the analysis results in JSON format and sends it to the user's device. The analysis results are included as input, and the structured data is sent in JSON format as output.

[1301] Step 6:

[1302] The user's device will suggest a fashion style based on the analysis results. The user's device will display the received analysis results and suggest a fashion style that suits the user. The input contains JSON format data, and the output is fashion style suggestion information that is displayed to the user.

[1303] Step 7:

[1304] The user then performs online shopping as needed. The user's device provides links to fashion items based on the analysis results, which the user then uses to shop. The input includes links to suggested items, and the output is access to online shopping sites.

[1305] Step 8:

[1306] The store utilizes customer fashion data. The server periodically collects and analyzes the fashion data of customers visiting the store and provides it to the store. The input includes security camera footage and analysis data, and the output is data that is provided to the store in the form of a weekly report or similar.

[1307] This allows users to choose clothing that matches the atmosphere of the store they are visiting, and stores can implement effective marketing strategies based on customer fashion data.

[1308] 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.

[1309] The present invention is a system that provides a user with a fashion style suited to a specific store that the user visits, and further provides more personalized fashion suggestions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention will be described below.

[1310] System configuration

[1311] The system consists of a user's device, a server, security cameras, a generative AI model, and an emotion engine. The user's device refers to a device such as a smartphone or PC, and the server processes and analyzes the data. Security cameras are installed inside the store and capture video data of customers. The generative AI model is an algorithm that analyzes the fashion trends of customers, and the emotion engine has the function of recognizing user emotions and reflecting them in the system.

[1312] Program processing

[1313] 1. User Request

[1314] Users can open the Yahoo! Maps app or website and search for the name or location of the store they want to visit. For example, they can enter "Aoyama Cafe A" in the search bar and press the search button.

[1315] The device sends the user's search query to the Yahoo! Maps API and sends a request to the server to retrieve specific store information based on the specified location information.

[1316] 2. Obtaining store information

[1317] The server receives the user's request and retrieves basic information about the relevant store (address, business hours, current congestion status, etc.) from the database.

[1318] The server then accesses the store's security cameras and obtains real-time video data.

[1319] 3. Analysis of video data

[1320] The server sends the video data acquired from the security camera to the generative AI model.

[1321] The generative AI model preprocesses the video data, classifies customers' clothing into categories such as casual, formal, and street style, and generates data representing current fashion trends.

[1322] 4. User Emotion Recognition

[1323] The device captures the user's facial expressions and voice using a built-in camera and microphone.

[1324] The acquired data is sent to the emotion engine to analyze the user's emotions, which determine the user's emotional status (e.g., joy, sadness, surprise, anger) based on their facial expressions and tone of voice.

[1325] 5. Integration and display of analysis results

[1326] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine.

[1327] More personalized fashion style suggestions based on the user's emotions are sent to the user's device in JSON format.

[1328] The device analyzes the received data and displays appropriate fashion style information to the user. For example, it might say, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1329] 6. Online shopping support

[1330] The user chooses an outfit based on presented fashion trends and emotions, and if desired, is provided with a link to an online shopping site.

[1331] The server retrieves links to online shopping sites for related fashion items and presents them to the user, tracking the links clicked by the user and recording necessary data.

[1332] 7. Store-side data analysis

[1333] The server continuously collects and analyzes fashion data, providing real-time demographic data to the store's management screen, which is also provided as a weekly report on specific fashion trends and customer sentiment.

[1334] Stores can use this data to plan their marketing strategies and promotions, for example by offering special discounts or promotions tailored to specific styles or times of day when certain emotions are more prevalent.

[1335] Specific examples

[1336] For example, for a user visiting "Aoyama Cafe A," the system functions as follows:

[1337] 1. The user searches for "Aoyama Cafe A" using the Yahoo! Maps app, and the device sends a request to the server.

[1338] 2. The server obtains store information and security camera footage and analyzes fashion trends using an AI model.

[1339] 3. The emotion engine recognizes the user's emotion and the result is sent to the server.

[1340] 4. The analysis results are sent to the user's device, and a message is displayed saying, "Most of our customers are currently wearing casual clothing. Taking your mood into consideration, we recommend this casual jacket."

[1341] 5. Users can purchase casual clothes from online shopping sites as needed and visit stores with peace of mind.

[1342] This allows users to choose clothes that match the atmosphere of the store they are visiting, and allows stores to implement effective marketing strategies. The introduction of an emotion engine will enable even more personalized fashion suggestions, improving the user experience.

[1343] The processing flow will be explained below.

[1344] Step 1:

[1345] A user opens the Yahoo! Maps app or website and searches for the name or location of the store they want to visit. For example, they enter "Aoyama Cafe A" in the search bar and press the search button.

[1346] Step 2:

[1347] The device sends the user's search query to the Yahoo! Maps API. The search query is sent as a request to the specified endpoint.

[1348] Step 3:

[1349] The server receives the search query and retrieves basic information about the relevant store (address, business hours, current occupancy status, etc.) from the database. The server queries the database and retrieves the corresponding information.

[1350] Step 4:

[1351] The server accesses the security cameras at the relevant store and sends a request to the security camera API to obtain real-time video data.

[1352] Step 5:

[1353] The server sends the acquired security camera video data to the generative AI model, which then preprocesses the video data and converts it into a format suitable for analysis.

[1354] Step 6:

[1355] A generative AI model analyzes customers' fashion trends and categorizes their outfits into categories such as casual, formal, and street style based on video data.

[1356] Step 7:

[1357] The device captures the user's facial expressions and voice using the built-in camera and microphone. The user selects to use the emotion recognition function, and facial expressions and voice are collected.

[1358] Step 8:

[1359] The device sends the acquired facial and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the facial expressions and tone of voice.

[1360] Step 9:

[1361] The server combines the fashion trend analysis results from the generated AI model with the emotion recognition results from the emotion engine, and generates data to provide optimal fashion suggestions to users.

[1362] Step 10:

[1363] The server sends the integrated analysis results in JSON format to the user's device, which receives the analysis results.

[1364] Step 11:

[1365] The device analyzes the analysis results received and displays appropriate fashion style information to the user. For example, it displays, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1366] Step 12:

[1367] The user chooses an outfit based on the displayed fashion suggestions, and if desired, is provided with a link to an online shopping site.

[1368] Step 13:

[1369] The user clicks the "Shop Online" button. The device displays a page with related fashion items.

[1370] Step 14:

[1371] The server provides a link to an online shopping site for related fashion items, and the link is displayed on the user's device.

[1372] Step 15:

[1373] The server periodically collects and analyzes security camera footage and stores customer clothing data in a database in real time. The server periodically acquires security camera footage and analyzes it using a generative AI model.

[1374] Step 16:

[1375] The server provides regularly updated fashion data to the store, as well as real-time demographic data and weekly reports to the store.

[1376] Step 17:

[1377] Based on the data provided by the store, we plan and execute marketing strategies and promotional activities, and develop promotional activities based on specific fashion trends and emotions.

[1378] This makes it easier for users to choose clothes that match the atmosphere of the store they are visiting, and allows them to receive personalized fashion suggestions based on their emotions.It also enables stores to plan and implement effective marketing strategies.

[1379] Example 2

[1380] 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."

[1381] Conventional fashion suggestion systems often end up making uniform suggestions because they are unable to fully reflect the user's preferences and emotions. Furthermore, it is difficult to analyze the fashion trends of customers in real time and, based on the results, suggest fashion styles that fit the store's atmosphere. This makes it difficult to improve the user experience and reduces the desire to purchase fashion items.

[1382] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1383] In this invention, the server includes means for acquiring information about a specific store based on location information specified by a user, means for acquiring surveillance footage, means for inputting the acquired surveillance footage into a generative AI model and analyzing the fashion trends of customers, means for acquiring user emotion data using a camera or microphone on the user terminal and analyzing it with an emotion engine, and means for integrating the analysis results and displaying personalized fashion style suggestions on the user terminal. This enables personalized fashion suggestions in real time based on the user's emotions and the fashion trends of customers.

[1384] "User terminal" refers to an electronic device operated by a user, such as a smartphone, personal computer, or tablet.

[1385] "Server" refers to a computer system on a network that processes and analyzes data.

[1386] "Monitoring footage" refers to real-time video data captured by cameras installed within the store.

[1387] A "generative AI model" refers to an artificial intelligence model that has an algorithm that analyzes video data obtained from security cameras and other sources, and classifies and analyzes the fashion trends of customers.

[1388] "Emotion engine" refers to software or hardware functionality that determines a user's emotional status by analyzing their facial expressions and tone of voice.

[1389] "Real-time" means that data is collected, processed, analyzed, and results are output almost instantly.

[1390] "Individualized fashion style suggestions" refers to recommending the most suitable fashion items and styles to each individual user based on the user's emotions and the fashion trends of customers.

[1391] "Location Information" means information about a location, such as geographic coordinates or an address.

[1392] "Online shopping system" refers to an e-commerce platform that allows customers to purchase fashion items via the Internet.

[1393] "Analysis Results" refers to the output of data processed and analyzed by the Generative AI Model and Emotion Engine.

[1394] This invention is a system that provides a user with a fashion style suited to the specific store they visit, and by combining it with an emotion engine that recognizes the user's emotions, it makes more personalized fashion suggestions. The system consists of a user terminal, a server, a monitoring device, a generative AI model, and an emotion engine.

[1395] The user terminal refers to a device such as a smartphone or PC, and provides an interface for users to input search queries. The server processes and analyzes data. Upon receiving a request from the user terminal, it retrieves the specified store information from a database. The server also inputs surveillance footage into a generative AI model to analyze the fashion trends of customers.

[1396] The generative AI model preprocesses the video data, classifies the clothing of customers into categories such as casual, formal, and street style, and generates data on current fashion trends. The analysis results are sent to a server and integrated.

[1397] The user device captures the user's facial expressions and voice using a built-in camera and microphone, and transmits them to the emotion engine, which then determines the user's emotional status from the user's facial expressions and tone of voice.

[1398] The server integrates the fashion trend analysis results from the generative AI model and the emotion recognition results from the emotion engine, and sends personalized fashion style suggestions in JSON format to the user's device. The user's device analyzes the received data and displays appropriate fashion style information to the user.

[1399] For example, when a user visits "XX Cafe A," the user's device requests information about "XX Cafe A" from the server. The server obtains the store information and sends the surveillance footage to the generative AI model. The generative AI model analyzes the video data and determines fashion trends. The user's device obtains emotion data and analyzes it with an emotion engine. The server then integrates the analysis results and displays personalized fashion style suggestions on the user's device.

[1400] An example of a prompt is as follows:

[1401] "What fashion style would be appropriate for Cafe A?"

[1402] "Please suggest some fashion items that suit my current mood."

[1403] "Analyze real-time footage from surveillance equipment to tell us the fashion trends in the store."

[1404] This embodiment allows users to choose clothes that match the atmosphere of the store they are visiting and receive fashion style suggestions that match their individual emotions and preferences, which is expected to improve the user experience and increase purchasing motivation.

[1405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1406] Step 1:

[1407] Users search for stores using devices such as smartphones or PCs.

[1408] Specific operation: A user opens the Yahoo! Maps app or website, enters the name or location of the store they want to visit, for example, "XX Cafe A" in the search bar, and presses the search button.

[1409] Input: User's search query (e.g. "XX Cafe A").

[1410] Output: The search query is sent from the device to the server.

[1411] Step 2:

[1412] The server receives the user's request and obtains store information.

[1413] Specific operation: The server uses the Yahoo! Maps API to obtain basic information about the relevant store (e.g., address, business hours, congestion status, etc.) based on the specified location information.

[1414] Input: The user's search query.

[1415] Output: Basic store information.

[1416] Step 3:

[1417] The server acquires the video from the surveillance device of the store.

[1418] Specific operation: The server accesses the surveillance equipment of the relevant store, acquires real-time video data, and streams it.

[1419] Input: Basic store information.

[1420] Output: Surveillance video data.

[1421] Step 4:

[1422] The server sends the surveillance footage to a generative AI model that analyzes fashion trends.

[1423] How it works: The server inputs surveillance footage into a generative AI model and applies an algorithm to classify customers' clothing into categories such as casual, formal, and street style.

[1424] Input: Surveillance video data.

[1425] Output: Analysis of customer fashion trends.

[1426] Step 5:

[1427] The device acquires the user's facial expressions and voice and sends them to the emotion engine.

[1428] Specific operation: Uses the device's camera and microphone to collect the user's facial expressions and voice in real time.

[1429] Input: User's facial expression data and voice data.

[1430] Output: Emotion data sent to the emotion engine.

[1431] Step 6:

[1432] The emotion engine analyzes the user's emotions.

[1433] Specific operation: The emotion engine applies algorithms to determine the user's emotional status (happiness, sadness, surprise, anger, etc.) from their facial expressions and tone of voice.

[1434] Input: Emotion data.

[1435] Output: The user's emotional status.

[1436] Step 7:

[1437] The server integrates the fashion trend analysis result and the user emotion recognition result.

[1438] Specific operation: The server combines the analysis results from the generative AI model with the emotional status from the emotion engine to generate personalized fashion style suggestions.

[1439] Input: Fashion trend analysis results and sentiment status.

[1440] Output: personalized fashion style suggestions.

[1441] Step 8:

[1442] The server transmits the personalized fashion style suggestions to the user terminal.

[1443] Specific operation: The server sends fashion style suggestions in JSON format to the user's device.

[1444] Enter: personalized fashion style suggestions.

[1445] Output: Fashion style information displayed on the user's device.

[1446] Step 9:

[1447] The user terminal displays the fashion style information.

[1448] Specific operation: The user device analyzes the received data and displays appropriate fashion style information to the user. For example, it displays, "Most customers currently in the store are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1449] Input: Fashion style information sent from the server.

[1450] Output: Visual and textual suggestions displayed to the user.

[1451] (Application example 2)

[1452] 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."

[1453] In conventional store visits, users have limited means of knowing the fashion trends and atmosphere of the store they are visiting in advance, making it difficult to choose appropriate clothing.In addition, personalized fashion suggestions based on the user's emotions are not provided, which hinders the user experience.

[1454] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring information about a specific store based on location information specified by the user, means for acquiring surveillance camera footage of the store, means for inputting the acquired surveillance camera footage into a generative AI model and analyzing the fashion trends of customers visiting the store, means for recognizing the user's emotions using the camera and microphone of the user's terminal, means for integrating the analyzed fashion trends with emotion data and generating fashion suggestions personalized for the user, and means for transmitting the suggestion results to the user terminal and displaying them on the user terminal. This allows the user to know in advance the fashion trends of the store they will visit and to receive personalized fashion suggestions tailored to their emotions.

[1455] A "user" is an individual who uses the system to obtain information about a specific store and receive fashion suggestions.

[1456] "Location information" is data that indicates the address and coordinates of a specific location or store that a user specifies they want to visit.

[1457] A "specific store" refers to an individual commercial facility, restaurant, etc. that the user is interested in based on location information.

[1458] "Information" refers to basic data about a specific store, such as its address, opening hours, and how busy it is.

[1459] "Monitoring camera footage" refers to video data captured in real time by cameras installed inside a store.

[1460] A "generative AI model" refers to an artificial intelligence algorithm that analyzes captured surveillance camera footage and automatically classifies and recognizes the fashion trends of customers.

[1461] "Fashion trends" refers to the styles and categories of clothing and accessories worn by customers.

[1462] "Emotion" refers to an emotional status such as joy, sadness, surprise, or anger that is analyzed from the user's facial expression and tone of voice.

[1463] "Means for recognizing emotions" refers to software or hardware that uses the camera or microphone installed on the user's device to acquire and analyze emotional data.

[1464] "Terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1465] "Personalized fashion suggestions" are recommendations of specific clothing and accessories that are best suited to a user, generated by integrating analyzed fashion trends with the user's emotional data.

[1466] An "online shopping site" is a website where you can purchase products over the Internet.

[1467] This invention relates to a system for providing a user with a fashion style suited to the store they plan to visit. The system is composed of a user terminal, a server, a surveillance camera, a generative AI model, and an emotion engine.

[1468] First, a user uses a device such as a smartphone or PC to search for the name and location of the store they want to visit and obtain that information. At this time, the device sends location information to the server. Based on this location information, the server obtains basic information about the specific store and obtains surveillance camera footage of the store in real time.

[1469] The server then inputs the captured surveillance camera footage into a generative AI model, which preprocesses the video data, classifies the customers' clothing, and generates data to analyze current fashion trends. Based on its algorithm, the generative AI model classifies the clothing into categories such as casual, formal, and street style.

[1470] Furthermore, the user device uses a built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine, which determines the user's emotional status, such as joy, sadness, surprise, or anger, based on the user's facial expressions and tone of voice.

[1471] The server integrates these analysis results and generates more personalized fashion style suggestions based on the user's emotions. These suggestions are sent to the user's device in JSON format. The user's device analyzes the received data and displays appropriate fashion style information to the user. For example, it may say, "Currently, most customers are wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1472] The user can select an outfit based on the suggested fashion trends and emotions, and a link to an online shopping site is provided accordingly. The server retrieves the links to the online shopping sites for related fashion items and presents them to the user. At this time, the links clicked by the user are tracked and necessary data is recorded.

[1473] Stores can also continuously collect and analyze fashion data from the server, obtaining real-time data on customers' fashion trends and users' emotional status. This data is provided as weekly reports, which can be used to plan marketing strategies and promotional activities.

[1474] Specific examples

[1475] For example, when a user visits "Aoyama Cafe A," he or she inputs a prompt sentence such as, "I'm planning to go to Aoyama Cafe A. Please tell me fashion suggestions based on the current fashion trends of customers and my feelings accordingly." As a result, fashion suggestions are displayed in the form of, "Most customers currently visiting the store are wearing casual styles. Taking your mood into consideration, I recommend this casual style jacket."

[1476] This system allows users to choose clothing that matches the atmosphere of the store they are visiting in advance, resulting in a comfortable experience. It also allows stores to implement effective marketing strategies.

[1477] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1478] Step 1:

[1479] The user uses the device to search for the name and location of the store they want to visit. By inputting the user's specified location information, the device sends that location information to the server. The server then obtains basic information about the specific store based on the location information and returns it to the user. This basic information includes the address, business hours, current congestion status, etc.

[1480] Step 2:

[1481] The server acquires surveillance camera footage from the relevant store in real time. The video data obtained from the surveillance cameras is used as input and sent to the generative AI model. The generative AI model preprocesses the video data and classifies the clothing worn by customers into categories such as casual, formal, and street style. The model outputs the classified fashion trend data.

[1482] Step 3:

[1483] The device uses a built-in camera and microphone to capture the user's facial expressions and voice data. This data is sent as input to the emotion engine, which analyzes and determines the user's emotional status, such as joy, sadness, surprise, or anger, from the user's facial expressions and voice. The emotion data resulting from the analysis is output.

[1484] Step 4:

[1485] The server integrates the fashion trend data analyzed by the generative AI model with the emotion data obtained from the emotion engine. This generates personalized fashion suggestions based on the user's emotions. The generated suggestion data is output. The suggestions include specific clothing items based on each fashion style.

[1486] Step 5:

[1487] The server sends the generated personalized fashion suggestions in JSON format to the user's device. The device analyzes the received data and displays appropriate fashion suggestions to the user. For example, it displays a message like, "Most of our customers are currently wearing casual styles. Taking your mood into consideration, we recommend this casual style jacket."

[1488] Step 6:

[1489] The user selects a clothing item based on the suggested fashion trends. The server provides the user with a link to an online shopping site for the related clothing item. When the user clicks on the link, the user can purchase the item from the online shop. The server tracks the clicked link and records the necessary data.

[1490] Step 7:

[1491] The server continuously captures surveillance camera footage and periodically collects and analyzes customer clothing data. This data is provided to the store. The store uses this data to plan and execute marketing strategies and promotional activities tailored to specific fashion trends and time periods. For example, the store can offer special discounts during times when many customers are wearing casual clothing.

[1492] In this way, users can know the fashion trends of the store they are visiting in advance and receive personalized fashion suggestions that match their own emotions, while also enabling the store to implement effective marketing strategies.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] FIG. 9 illustrates 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 behaviors 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.

[1498] 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.

[1499] 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).

[1500] 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.

[1501] 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."

[1502] 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.

[1503] 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).

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] The following is further disclosed regarding the above embodiment.

[1515] (Claim 1)

[1516] A means for acquiring information about a specific store based on location information specified by a user;

[1517] A means for obtaining security camera footage of the relevant store;

[1518] The acquired security camera footage is input into a generative AI model to analyze the fashion trends of customers.

[1519] means for transmitting the analysis result to a user terminal and displaying the analysis result on the user terminal;

[1520] A system including:

[1521] (Claim 2)

[1522] 10. The system of claim 1, further comprising means for a user to purchase related fashion items from an online shopping site based on the analysis results.

[1523] (Claim 3)

[1524] 2. The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers from security camera footage and providing the store with customer fashion data.

[1525] "Example 1"

[1526] (Claim 1)

[1527] A means for acquiring information about a specific store based on location information specified by a user;

[1528] A means for obtaining security camera footage of the relevant store;

[1529] The acquired security camera footage is input into a generative AI model to analyze the fashion trends of customers.

[1530] A method to classify customers' clothing and suggest fashion styles using a generative AI model;

[1531] means for transmitting the analysis result to a user terminal and displaying the analysis result on the user terminal;

[1532] providing a link to an online shopping site for users to purchase fashion items;

[1533] A system including:

[1534] (Claim 2)

[1535] 10. The system of claim 1, further comprising means for a user to purchase related fashion items from an online shopping site based on the analysis results.

[1536] (Claim 3)

[1537] 2. The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers from security camera footage and providing the store with customer fashion data.

[1538] "Application Example 1"

[1539] (Claim 1)

[1540] A means for acquiring information about a specific store based on location information specified by a user;

[1541] A means for obtaining security camera footage of the relevant store;

[1542] The acquired security camera footage is input into a generative AI model to analyze the fashion trends of customers.

[1543] means for transmitting the analysis result to a user terminal and displaying the analysis result on the user terminal;

[1544] A means for proposing a fashion style suitable for a user based on fashion trends;

[1545] A system including:

[1546] (Claim 2)

[1547] 2. The system according to claim 1, further comprising means for allowing a user to purchase related fashion items from an online shopping site based on the analysis results.

[1548] (Claim 3)

[1549] 2. The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers from security camera footage and providing the store with customer fashion data.

[1550] "Example 2: Combining Emotion Engines"

[1551] (Claim 1)

[1552] A means for acquiring information about a specific store based on location information specified by a user;

[1553] A means for acquiring surveillance video of the store;

[1554] A means of inputting the acquired surveillance footage into a generative AI model to analyze the fashion trends of customers visiting the store;

[1555] A means for acquiring user emotion data using a camera or microphone on the user device and analyzing the data with an emotion engine;

[1556] means for integrating the analysis results and displaying personalized fashion style suggestions on a user device;

[1557] A system including:

[1558] (Claim 2)

[1559] 10. The system of claim 1, further comprising means for a user to purchase related fashion items from an online shopping system based on the analysis results.

[1560] (Claim 3)

[1561] 2. The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers visiting the store from surveillance images and providing the store with customer fashion data.

[1562] "Application example 2 when combining emotion engines"

[1563] (Claim 1)

[1564] A means for acquiring information about a specific store based on location information specified by a user;

[1565] A means for obtaining surveillance camera footage of the store in question;

[1566] The acquired surveillance camera footage is input into a generative AI model to analyze the fashion trends of customers.

[1567] A means for recognizing a user's emotion using a camera or microphone of the user's device;

[1568] means for integrating the analyzed fashion trends and emotion data to generate personalized fashion suggestions for the user;

[1569] means for transmitting the proposal result to a user terminal and displaying it on the user terminal;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, further comprising means for a user to purchase related clothing items from an online shopping site based on the analysis results.

[1573] (Claim 3)

[1574] The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers from surveillance camera footage and providing the store with customer fashion data. [Explanation of symbols]

[1575] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring information about a specific store based on location information specified by a user; A means for obtaining security camera footage of the relevant store; The acquired security camera footage is input into a generative AI model to analyze the fashion trends of customers. means for transmitting the analysis result to a user terminal and displaying the analysis result on the user terminal; A system including:

2. The system according to claim 1 , further comprising means for allowing a user to purchase related fashion items from an online shopping site based on the analysis results.

3. 2. The system according to claim 1, further comprising means for periodically collecting and analyzing clothing data of customers from security camera footage and providing the store with customer fashion data.

Images