system

Abstract

We provide the system. [Solution] A data processing method that receives and analyzes user requests in natural language, A data retrieval means for obtaining relevant product information from a data aggregate based on the analysis results, A product suggestion method that generates recommended products using an artificial intelligence model based on product information, A data display means for presenting generated recommended products to the user, An information acquisition means that allows the user to obtain extended detailed information using an identification code attached to the product, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] While modern consumers can access a variety of product information, it is very difficult to select the optimal household appliances from a huge number of options. As a result, a lot of time and effort are spent on purchase decisions, and there is also a risk of making wrong choices. Also, it is a great burden for sales staff to make product proposals according to the detailed needs of each customer. Therefore, there is a need for a system that enables consumers to efficiently and quickly select the optimal household appliances and reduces the burden on sales staff.

Means for Solving the Problems

[0005] This invention includes an information processing means that receives input from a user and analyzes it using natural language processing technology. Based on the analysis results, it provides an information retrieval means that quickly collects relevant product information from a database, and a product suggestion means that uses an artificial intelligence model to generate recommended products that are best suited to the user's needs. Furthermore, by using an information display means that presents the generated results to the user in a clear and easy-to-understand format, the optimal product can be selected efficiently. In addition, the invention further enhances the user experience by providing an information enhancement means that obtains and provides detailed product information via QR codes (registered trademark) in stores or online.

[0006] "User" refers to an individual or organization that uses this system to select home appliances.

[0007] "Information processing means" refers to devices or software that have the function of analyzing natural language data received from users and extracting necessary information.

[0008] "Information retrieval means" refers to devices or software that have the function of identifying relevant product information from a database based on data extracted by information processing means.

[0009] A "product suggestion tool" refers to a device or software that uses an artificial intelligence model based on acquired product information to suggest the most suitable product to meet the user's needs.

[0010] "Information display means" refers to devices or software with display functions for providing users with product suggestions generated by product suggestion means.

[0011] "Information enhancement means" refers to devices or software that have the function of providing users with further detailed information using QR codes, etc.

[0012] An "artificial intelligence model" is a learning algorithm or structured program that analyzes given data and derives the optimal solution.

[0013] A "database" is a system that systematically stores information related to products, making it searchable and retrievable. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]A sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides a method for building an interactive home appliance recommendation system. This system automatically analyzes the input by utilizing pre-prepared information processing means, based on the user's preferences and requirements entered through an interface.

[0036] First, the terminal receives input from the user and temporarily stores the data. The stored data is sent to the server, which uses natural language processing technology to understand the user's requests and preferences. The server then uses information retrieval tools to efficiently retrieve product information related to the user's preferences from the database.

[0037] Next, the server utilizes an artificial intelligence model to select recommended products that best suit the user's needs based on the acquired product information. The products selected by the product suggestion system are sent from the server to the terminal, which then presents the information to the user. This allows the user to easily choose products that are right for them.

[0038] Furthermore, users can obtain additional detailed information by using a QR code when checking products in-store or online. The terminal uses this information to expand the information provided to the user and support their product selection decision.

[0039] As a concrete example, consider a scenario where a user is looking for a new refrigerator. The user enters information such as the number of family members, budget, and desired energy consumption into a terminal. The terminal sends this information to a server, which collects information on refrigerators that match the criteria and presents the user with the most suitable product. This allows the user to find a suitable refrigerator without spending time in the store, and they can also obtain more detailed information by scanning a QR code if necessary.

[0040] Thus, this system quickly and efficiently supports the entire process from user information input to product selection and provision of detailed information.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user uses the terminal's interface to enter detailed information such as desired specifications, budget, and intended use for home appliances. The terminal temporarily stores this information.

[0044] Step 2:

[0045] The terminal sends information entered by the user to the server. This transmission is performed via a secure network protocol.

[0046] Step 3:

[0047] The server receives information from the terminal and uses a natural language processing engine to analyze the user's requests and preferences. This analysis converts the user's input into structured data.

[0048] Step 4:

[0049] The server activates an information retrieval mechanism to retrieve relevant product information from the database based on the analysis results. This identifies the product candidates that best match the user's preferences.

[0050] Step 5:

[0051] The server uses an AI model generated from acquired product information to identify the optimal recommended product that meets the user's needs. The product suggestion method prioritizes multiple items based on evaluation criteria.

[0052] Step 6:

[0053] The server sends the final selected proposal results to the terminal. The information provided by the server includes detailed product specifications and user reviews.

[0054] Step 7:

[0055] The terminal visually displays suggested products received from the server to the user. The user can check the product features, price, benefits, etc. on the screen.

[0056] Step 8:

[0057] If a user requires more detailed information, the terminal can display a QR code in-store or online, and scanning it will allow them to obtain additional information. The server will then provide additional content based on that QR code information.

[0058] Step 9:

[0059] Users make purchasing decisions based on the information provided. Optimizing the selection options enables quicker decision-making.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] It is difficult for consumers to quickly and accurately find the products that best suit their needs. This problem stems from the existence of a wide variety of options and the inability to obtain effective recommendations based on individual requirements. In particular, there is a need to improve the accuracy of recommendations by analyzing product information and considering past user preferences. Furthermore, obtaining detailed product information can be a cumbersome process, sometimes detracting from the user experience.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes data processing means, data retrieval means, product recommendation means utilizing a machine learning model, and data analysis means. This enables the rapid identification of products that match the user's needs and highly accurate recommendations that take into account past selection history and trend data. Furthermore, detailed product information can be easily obtained using general-purpose code, improving the user experience.

[0065] A "data processing tool" is a means that has the function of analyzing requests received from users in natural language and converting them into structured information.

[0066] A "data retrieval method" is a means that has the function of efficiently retrieving relevant product information from storage media based on the analyzed information.

[0067] A "machine learning model" is a mathematical model that incorporates algorithms to learn from past data and current trends, and to recommend the most suitable products to users.

[0068] A "product recommendation system" is a system that utilizes acquired product information to select and suggest products suitable for the user through a machine learning model.

[0069] An "information presentation means" is a means of displaying information about generated recommended products to the user, and provides an interface that allows the user to make intuitive selections.

[0070] "Data analysis methods" refer to techniques that take into account past selection history and market trend data to deepen our understanding of user needs and improve the accuracy of recommendations.

[0071] "Data enhancement means" refers to methods of providing users with additional information by using general-purpose codes at sales locations or in e-commerce to obtain detailed product information.

[0072] This invention provides an interactive system that enables consumers to easily find products that meet their needs. The system consistently supports users from input to the recommendation of relevant product information and the provision of detailed information.

[0073] First, the user enters the specifications of the product they wish to purchase through a terminal. This terminal can be used with general-purpose electronic devices such as tablets and smartphones, and the interface is designed to be easy for users to operate. Users can enter specific conditions such as, "I'm looking for an eco-friendly refrigerator for a family of four. My budget is under 100,000 yen, and I'd prefer an energy-efficient model."

[0074] The terminal sends the entered data to the server via a secure protocol (e.g., HTTPS). The server uses Python's NLTK library or spaCy to perform natural language processing on this data and clearly understand the user's request. Based on the information obtained through this analysis, the server accesses the database and retrieves appropriate product information. SQL is used to retrieve relevant information for data retrieval.

[0075] Once product information is retrieved, the server uses machine learning frameworks such as TENSORFLOW® to generate recommended products that best suit the user's criteria. The generating AI model makes it possible to make optimized recommendations by considering past data and trends.

[0076] Subsequently, the server transmits the selected product information to the terminal, which then presents the information to the user in a visually easy-to-understand format. Based on this information, the user can easily select the appropriate product.

[0077] Furthermore, when users check products in stores or online, they can use their devices to scan the product's QR code. The server then uses the information obtained from the QR code to provide the user with additional details. This allows users to easily access in-depth information such as specific specifications and user reviews, enabling them to make more informed purchase decisions. This entire process enhances the user's purchasing experience and speeds up the selection process.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user enters their desired product specifications using a terminal. The terminal receives the information from the user, such as a prompt like "an eco-friendly refrigerator for a family of four," and temporarily stores the data. The entered data is then structured and ready to be sent to the server.

[0081] Step 2:

[0082] The terminal sends user input data to the server. The HTTPS protocol is used for transmission, ensuring secure transfer of the input data. The data sent to the server is then placed in a receive buffer for further processing.

[0083] Step 3:

[0084] The server passes the received data to a natural language processing engine for analysis. Here, the Python NLTK library is used to convert the input language information into structured data. During this process, user preferences (e.g., budget, energy consumption) are extracted.

[0085] Step 4:

[0086] The server uses the parsed structured data to search for product information. It generates SQL queries and retrieves relevant product information from the database. Specifically, data for refrigerators that match the criteria is efficiently extracted.

[0087] Step 5:

[0088] The server inputs the acquired product information into a generating AI model to select the most suitable product for the user. This process utilizes a machine learning model based on TensorFlow, which also takes into account past user preferences and trend information to generate optimal recommendation candidates.

[0089] Step 6:

[0090] The server sends the selected recommended products to the terminal. The terminal displays this data in a user-friendly format. This makes it easier for the user to select the most suitable product based on this information.

[0091] Step 7:

[0092] When users view products in stores or online, their devices scan the product's QR code. This action allows the server to retrieve additional detailed information, which is then provided to the user. This makes it easy for users to check detailed product specifications and reviews, supporting their purchase decisions.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Modern information systems handle vast amounts of data, making it difficult for users to quickly find products that meet their needs. Furthermore, accessing product information in stores and online shopping often makes it difficult to instantly obtain more detailed information. This situation detracts from the consumer purchasing experience and hinders optimal product selection.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes data processing means for receiving and analyzing user requests in natural language, data retrieval means for obtaining relevant product information from a data aggregate, product suggestion means for generating recommended products using an artificial intelligence model based on the product information, and information acquisition means for obtaining extended detailed information using an identification code attached to a product. This makes it possible for users to easily find the optimal product and instantly obtain detailed information using the identification code.

[0098] A "data processing means" is a mechanism that receives requests in natural language from users, analyzes them, and converts them into useful information.

[0099] A "data retrieval means" is a mechanism that efficiently obtains relevant product information from a data repository based on the results of the analysis.

[0100] A "product recommendation system" is a mechanism that uses an artificial intelligence model based on acquired product information to generate recommended products that best meet the user's needs.

[0101] A "data display means" is a mechanism that presents information on generated recommended products to the user, making it visually verifiable.

[0102] "Information acquisition means" refers to a mechanism that allows users to quickly obtain extended detailed information using an identification code attached to the product.

[0103] The system implementing this invention mainly consists of a portable information terminal used by the user and a server. The terminal can receive requests and conditions from the user in natural language and temporarily store them in a storage device. The stored data is transmitted to the server via the network.

[0104] The server uses natural language processing techniques such as the BERT model to analyze incoming requests and understand user needs and conditions. Based on this analysis, it uses information retrieval methods to efficiently obtain relevant product information from the database. Subsequently, the server utilizes a generative AI model to generate recommended products that best suit the user's needs based on the retrieved product information.

[0105] The generated recommended product information is transmitted back to the terminal via the network, and the terminal presents it to the user. The user can review the presented product information and instantly obtain more detailed information by scanning the identification code (QR code) attached to the product with the terminal's camera function. This information acquisition helps users make informed choices when selecting products.

[0106] For example, if a user is looking for a new home appliance, they input their budget, desired features, design preferences, etc., into the terminal. The server then recommends the most suitable appliance based on this information, and scanning the QR code of the suggested product displays detailed product specifications and reviews. As an example of a prompt, if the user enters, "I'm looking for an energy-efficient refrigerator under 50,000 yen. What do you recommend?", the system can suggest appropriate products that meet this request.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] Users use a portable information terminal to input their preferences and requirements in natural language. The input data includes product category, price range, and desired features. The input data is temporarily stored in the terminal's internal storage.

[0110] Step 2:

[0111] The terminal transmits the stored input data to the server via the network. The server receives this natural language data and performs analysis using data processing methods that employ natural language processing technology. As a result of the analysis, the user's requests and conditions are extracted as specific data.

[0112] Step 3:

[0113] Based on the analyzed user request, the server uses information retrieval tools to obtain relevant product information from the data repository. During this process, products matching criteria such as product category and price range are searched, and a product list is generated as a result.

[0114] Step 4:

[0115] Using a generative AI model, the server selects the most suitable recommended product from the acquired product information to meet the user's needs. Product evaluation takes into account review information and specification data. Finally, the recommended product and its detailed information are finalized.

[0116] Step 5:

[0117] The server transmits confirmed recommended product information to the terminal. The terminal receives this information and presents it visually to the user using a data display device. The user can then review the presented product information.

[0118] Step 6:

[0119] The user scans the product identification code (such as a QR code) presented to them using their device's camera. The device sends the acquired code to a server, which then retrieves enhanced product information through an information acquisition system. This process displays detailed specifications, product reviews, and usage examples, allowing the user to make more informed decisions.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention provides a system that, when a user inputs information about product purchases via a terminal, integrates and analyzes the input data and the user's emotional state to provide optimal product recommendations. This system combines natural language processing technology and an emotion engine to enable product suggestions based on the user's requests, desires, and emotions.

[0122] The terminal receives information entered by the user and sends it to the server. When the server analyzes the information, it uses an emotion engine to evaluate sentiment indicators within the text. This sentiment evaluation is used to determine the user's emotional state when selecting a product. The sentiment data identified by the emotion engine is combined with request data analyzed using natural language processing.

[0123] The server processes this integrated data using information retrieval tools and retrieves relevant product information from the database. Next, an artificial intelligence model is used to generate product suggestions tailored to the user's requests and emotional state. The ranking and display method of the generated recommendations may change depending on the emotional state. In particular, it is possible to present many options to a relaxed user and narrow down the suggestions to the most effective options for a user in a hurry.

[0124] The terminal presents the user with a product list that reflects the results of the emotion engine. By viewing the product suggestions displayed through the terminal, users can more intuitively select products that suit their preferences. Furthermore, if the user needs more detailed information about a product, they can obtain it using a QR code. The server provides deeper level product information in response to that request.

[0125] For example, if a user is tired and trying to choose a home appliance, the system will prioritize presenting products that contribute to relaxation or products that quickly meet the user's needs. In this way, by utilizing emotional data, users can efficiently select the most suitable products.

[0126] Embodiments of the present invention enable product recommendations that take user emotions into consideration, thereby providing a more personalized purchasing experience.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user enters their preferences and requirements for purchasing home appliances as text through the terminal's interface. The terminal temporarily stores the entered data.

[0130] Step 2:

[0131] The terminal sends the entered information to the server. A secure protocol is used for this transmission.

[0132] Step 3:

[0133] The server uses the text data received from the terminal to pass it to a natural language processing engine, which then analyzes the user's request. The analysis results then structure the user's intent.

[0134] Step 4:

[0135] The server activates the emotion engine and extracts emotion indicators from the user's input text. This allows the user's current emotional state to be evaluated.

[0136] Step 5:

[0137] The server integrates the results of natural language processing and sentiment analysis, and uses information retrieval tools to collect relevant product information from the database.

[0138] Step 6:

[0139] The server utilizes an artificial intelligence model to select appropriate recommended products that reflect the user's requests and emotional state. During this selection process, the priority and selection criteria for products may be adjusted based on the emotional state.

[0140] Step 7:

[0141] The server sends the selected product information to the terminal.

[0142] Step 8:

[0143] The terminal displays product suggestions received from the server to the user in an easy-to-read format. The displayed content may be customized according to the user's emotional state.

[0144] Step 9:

[0145] Users review the presented product list and make selections based on their emotions and intuition. Additional detailed information can be obtained using QR codes as needed.

[0146] Step 10:

[0147] The server receives a request for detailed information via a QR code and provides the relevant detailed information to the terminal.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] In modern product purchasing systems, product recommendations based on individual user emotional states and specific needs are insufficient, resulting in users being unable to select appropriate products satisfactorily and efficiently. Solving this problem and improving the user's purchasing experience is crucial.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, integrated data generation means for evaluating the user's emotional state and integrating it with the request, and product suggestion means for generating recommended products using an artificial intelligence model based on the integrated data. This enables optimal product recommendations that take into account the user's emotional state and requests.

[0153] "Information processing means" refers to equipment or technology that has the function of analyzing requests received from users in natural language and extracting meaning.

[0154] "Information retrieval means" refers to equipment or technology used to find relevant product information from a database based on analysis results.

[0155] "Integrated data generation means" refers to equipment or technology for generating a single integrated data set by combining a user's emotional state and requests.

[0156] "Product recommendation means" refers to equipment or technology for generating appropriate recommended products using an artificial intelligence model based on integrated data.

[0157] "Information display means" refers to equipment or technology for presenting generated recommended products to users and displaying them in a format and ranking them according to their emotional state.

[0158] "Information enhancement means" refers to equipment or technology that enables users to obtain detailed product information using QR codes in stores or online.

[0159] This invention implements a system in which a user inputs information about product purchases into a terminal, and based on that information, provides optimal product recommendations. Specifically, the user's emotional state and requests are analyzed using natural language processing and artificial intelligence technology, and personalized product suggestions are made.

[0160] The server first receives information entered by the user from the terminal. This input information is then analyzed using a natural language processing engine. Natural language processing typically uses open-source libraries or custom-developed software to tokenize and semantic analyze the text. Simultaneously, a sentiment engine operates to evaluate the sentiment in the text. Sentiment evaluation is used to determine whether the user's input is classified as positive, negative, or neutral. Existing sentiment analysis libraries can be used for the sentiment engine.

[0161] The server integrates the analyzed user requests and emotional information, and performs information retrieval based on this integrated data. The server searches the database for relevant product information and generates optimal product suggestions using a generative AI model. The generative AI model employs machine learning algorithms, and in particular, optimizes suggestions based on the user's emotional state.

[0162] The suggested products are displayed to the user on their device. The user interface on the device is carefully designed, and how products are presented changes depending on the user's mood. Relaxed users are shown many options in a card format, while users in a hurry are shown a narrower, simpler selection of options.

[0163] As a concrete example, consider a scenario where a user is feeling tired but is looking for new home appliances for their living room. In this case, the system can prioritize suggesting items such as massage chairs or easy-to-use air purifiers designed to enhance relaxation. An example of a prompt to the generating AI model would be, "Please recommend products that will improve the comfort of my room when I'm feeling tired."

[0164] In this way, the system of the present invention is capable of providing personalized product recommendations that take into account the user's specific needs and emotional state.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The user enters information about their product purchase using the device. Specifically, the user enters the desired product category and any special requirements via the device's keyboard or touchscreen. The entered information is temporarily stored on the device as text data.

[0168] Step 2:

[0169] The terminal sends the information entered by the user to the server. Specifically, the terminal securely transmits the data via an internet connection. The input data arrives at the server in text format. The server receives this data and immediately prepares it for natural language processing.

[0170] Step 3:

[0171] The server analyzes the received text data using a natural language processing engine. Specifically, the server tokenizes the text and analyzes its meaning. The input is raw text data, and the output is structured data that represents the user's request. At this point, the analysis results are in a format that includes the user's purchase intent and desired conditions.

[0172] Step 4:

[0173] The server simultaneously uses an emotion engine to evaluate the user's emotional state. The input is the analyzed text data, and emotion analysis is performed. Specifically, the emotion engine calculates positive and negative emotion scores. The output generates data regarding the type and intensity of the emotion.

[0174] Step 5:

[0175] The server integrates the analyzed request data and sentiment data. This integrated data forms the basis for information retrieval. As part of the data processing, request and sentiment information are merged into a single dataset. The output is comprehensive information based on the user's wishes and emotions.

[0176] Step 6:

[0177] The server performs information retrieval based on integrated data. Specifically, the server accesses the database and searches for highly relevant product information. The input is integrated data, and the output is a list of related products. This list is used by the generative AI model to suggest products.

[0178] Step 7:

[0179] The server generates optimal product recommendations using a generative AI model. The input consists of a list of related products and integrated data. The AI ​​model uses machine learning algorithms to create personalized recommendations. The output is a list of recommended products, optimized to the emotional state of a specific user.

[0180] Step 8:

[0181] The terminal presents the user with recommended products received from the server. Specifically, the terminal displays product suggestions on the screen through a user interface. The display format and priority of products are adjusted according to the user's emotional state. The output is a visually verifiable selection of product suggestions for the user.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] Modern shopping systems offer recommendations based on user requests, but they often fail to adequately consider the user's emotional state when suggesting products. As a result, users may experience stress or struggle to select the products they want. Online stores, in particular, need flexible recommendations that can adapt to changes in user emotions.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, sentiment analysis means for comprehensively evaluating the analysis results and the user's emotional state, and information retrieval means for obtaining relevant product information from a database based on the analysis and evaluation results. This enables optimal product recommendations that take into account the user's emotional state.

[0187] "Information processing means" refers to a device or program that has the function of receiving and analyzing user requests in natural language.

[0188] "Emotional analysis means" refers to a device or program that has the function of evaluating and analyzing the emotional state of a user based on data obtained from the user.

[0189] "Information retrieval means" refers to a device or program that has the function of obtaining relevant product information from a database based on analysis results and evaluation results.

[0190] "Product suggestion means" refers to a device or program that has the function of generating recommended products suitable for the user using an artificial intelligence model based on product information.

[0191] "Information display means" refers to a device or program that has the function of presenting generated recommended products to the user.

[0192] To implement this invention, the system implements a program for collecting and analyzing user input information. First, when a user enters a shopping request using a terminal, the request is sent to the server in real time. The server uses natural language processing technology as an information processing tool to analyze the user's request. It also uses sentiment analysis tools to evaluate the user's emotional state. For this purpose, sentiment analysis software such as Microsoft® Azure® Text Analytics is useful.

[0193] The analysis results and sentiment evaluation results are integrated, and the information retrieval tool retrieves relevant product information from the database. The database contains information on a wide variety of products, allowing it to meet the specific needs of the user.

[0194] Next, an artificial intelligence model (for example, a recommendation system using TensorFlow) is used as a product suggestion tool to generate products suitable for the user's emotional state. This model uses past user data and real-time emotional data to provide personalized suggestions. Finally, an information display tool presents the generated recommended products to the user. For example, a user in a relaxed state might be shown an aroma diffuser or relaxation goods.

[0195] For example, if a user is online shopping during a busy workday, the system takes their stress level into account and recommends efficient and practical items. This aims to improve user convenience.

[0196] An example of a prompt used in a generative AI model might be: "Write code that analyzes the user's emotions from their input text and suggests the most suitable product for a relaxed user."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The user enters their shopping request using a terminal. The entered text data is collected by the terminal and sent to the server. The server receives this data and passes it to a natural language processing engine. This analyzes the input data and generates the user's specific request.

[0200] Step 2:

[0201] The server evaluates the user's emotions from the input data using emotion analysis tools. The input is the text data processed in the previous step, and a real-time emotion analysis tool (e.g., Microsoft Azure Text Analytics) is used to evaluate its emotional state. As a result, an emotion rating is generated.

[0202] Step 3:

[0203] The server integrates the analyzed request data and sentiment evaluation values, and performs database queries using information retrieval tools. The integrated data is used as input, and relevant product information is retrieved from the database. Through this process, product information that matches the user's needs is output.

[0204] Step 4:

[0205] The server generates product suggestions using an artificial intelligence model based on the acquired product information. Product information and sentiment rating values ​​are used as input, and the AI ​​model (e.g., a recommendation system using TensorFlow) generates a list of products that match the user's emotional state. This results in a personalized list of recommended products.

[0206] Step 5:

[0207] The terminal receives a list of recommended products sent from the server and displays it to the user. The recommended product list is used as input, and products are presented visually, taking into account the user's emotional state. This step allows the user to view the presented products and obtain more information if needed.

[0208] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0209] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0224] This invention provides a method for building an interactive home appliance recommendation system. This system automatically analyzes the input by utilizing pre-prepared information processing means, based on the user's preferences and requirements entered through an interface.

[0225] First, the terminal receives input from the user and temporarily stores the data. The stored data is sent to the server, which uses natural language processing technology to understand the user's requests and preferences. The server then uses information retrieval tools to efficiently retrieve product information related to the user's preferences from the database.

[0226] Next, the server utilizes an artificial intelligence model to select recommended products that best suit the user's needs based on the acquired product information. The products selected by the product suggestion system are sent from the server to the terminal, which then presents the information to the user. This allows the user to easily choose products that are right for them.

[0227] Furthermore, users can obtain additional detailed information by using a QR code when checking products in-store or online. The terminal uses this information to expand the information provided to the user and support their product selection decision.

[0228] As a concrete example, consider a scenario where a user is looking for a new refrigerator. The user enters information such as the number of family members, budget, and desired energy consumption into a terminal. The terminal sends this information to a server, which collects information on refrigerators that match the criteria and presents the user with the most suitable product. This allows the user to find a suitable refrigerator without spending time in the store, and they can also obtain more detailed information by scanning a QR code if necessary.

[0229] Thus, this system quickly and efficiently supports the entire process from user information input to product selection and provision of detailed information.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The user uses the terminal's interface to enter detailed information such as desired specifications, budget, and intended use for home appliances. The terminal temporarily stores this information.

[0233] Step 2:

[0234] The terminal sends information entered by the user to the server. This transmission is performed via a secure network protocol.

[0235] Step 3:

[0236] The server receives information from the terminal and uses a natural language processing engine to analyze the user's requests and preferences. This analysis converts the user's input into structured data.

[0237] Step 4:

[0238] The server activates an information retrieval mechanism to retrieve relevant product information from the database based on the analysis results. This identifies the product candidates that best match the user's preferences.

[0239] Step 5:

[0240] The server uses an AI model generated from acquired product information to identify the optimal recommended product that meets the user's needs. The product suggestion method prioritizes multiple items based on evaluation criteria.

[0241] Step 6:

[0242] The server sends the final selected proposal results to the terminal. The information provided by the server includes detailed product specifications and user reviews.

[0243] Step 7:

[0244] The terminal visually displays suggested products received from the server to the user. The user can check the product features, price, benefits, etc. on the screen.

[0245] Step 8:

[0246] If a user requires more detailed information, the terminal can display a QR code in-store or online, and scanning it will allow them to obtain additional information. The server will then provide additional content based on that QR code information.

[0247] Step 9:

[0248] Users make purchasing decisions based on the information provided. Optimizing the selection options enables quicker decision-making.

[0249] (Example 1)

[0250] Next, we will describe Example 1. 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."

[0251] It is difficult for consumers to quickly and accurately find the products that best suit their needs. This problem stems from the existence of a wide variety of options and the inability to obtain effective recommendations based on individual requirements. In particular, there is a need to improve the accuracy of recommendations by analyzing product information and considering past user preferences. Furthermore, obtaining detailed product information can be a cumbersome process, sometimes detracting from the user experience.

[0252] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0253] In this invention, the server includes data processing means, data retrieval means, product recommendation means utilizing a machine learning model, and data analysis means. This enables the rapid identification of products that match the user's needs and highly accurate recommendations that take into account past selection history and trend data. Furthermore, detailed product information can be easily obtained using general-purpose code, improving the user experience.

[0254] A "data processing tool" is a means that has the function of analyzing requests received from users in natural language and converting them into structured information.

[0255] A "data retrieval method" is a means that has the function of efficiently retrieving relevant product information from storage media based on the analyzed information.

[0256] A "machine learning model" is a mathematical model that incorporates algorithms to learn from past data and current trends, and to recommend the most suitable products to users.

[0257] A "product recommendation system" is a system that utilizes acquired product information to select and suggest products suitable for the user through a machine learning model.

[0258] An "information presentation means" is a means of displaying information about generated recommended products to the user, and provides an interface that allows the user to make intuitive selections.

[0259] "Data analysis methods" refer to techniques that take into account past selection history and market trend data to deepen our understanding of user needs and improve the accuracy of recommendations.

[0260] "Data enhancement means" refers to methods of providing users with additional information by using general-purpose codes at sales locations or in e-commerce to obtain detailed product information.

[0261] This invention provides an interactive system that enables consumers to easily find products that meet their needs. The system consistently supports users from input to the recommendation of relevant product information and the provision of detailed information.

[0262] First, the user enters the specifications of the product they wish to purchase through a terminal. This terminal can be used with general-purpose electronic devices such as tablets and smartphones, and the interface is designed to be easy for users to operate. Users can enter specific conditions such as, "I'm looking for an eco-friendly refrigerator for a family of four. My budget is under 100,000 yen, and I'd prefer an energy-efficient model."

[0263] The terminal sends the entered data to the server via a secure protocol (e.g., HTTPS). The server uses Python's NLTK library or spaCy to perform natural language processing on this data and clearly understand the user's request. Based on the information obtained through this analysis, the server accesses the database and retrieves appropriate product information. SQL is used to retrieve relevant information for data retrieval.

[0264] Once product information is retrieved, the server uses machine learning frameworks such as TensorFlow to generate recommended products that best suit the user's criteria. The generating AI model allows for optimized recommendations that take into account historical data and trends.

[0265] Subsequently, the server transmits the selected product information to the terminal, which then presents the information to the user in a visually easy-to-understand format. Based on this information, the user can easily select the appropriate product.

[0266] Furthermore, when users check products in stores or online, they can use their devices to scan the product's QR code. The server then uses the information obtained from the QR code to provide the user with additional details. This allows users to easily access in-depth information such as specific specifications and user reviews, enabling them to make more informed purchase decisions. This entire process enhances the user's purchasing experience and speeds up the selection process.

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The user enters their desired product specifications using a terminal. The terminal receives the information from the user, such as a prompt like "an eco-friendly refrigerator for a family of four," and temporarily stores the data. The entered data is then structured and ready to be sent to the server.

[0270] Step 2:

[0271] The terminal sends user input data to the server. The HTTPS protocol is used for transmission, ensuring secure transfer of the input data. The data sent to the server is then placed in a receive buffer for further processing.

[0272] Step 3:

[0273] The server passes the received data to a natural language processing engine for analysis. Here, the Python NLTK library is used to convert the input language information into structured data. During this process, user preferences (e.g., budget, energy consumption) are extracted.

[0274] Step 4:

[0275] The server uses the parsed structured data to search for product information. It generates SQL queries and retrieves relevant product information from the database. Specifically, data for refrigerators that match the criteria is efficiently extracted.

[0276] Step 5:

[0277] The server inputs the acquired product information into a generating AI model to select the most suitable product for the user. This process utilizes a machine learning model based on TensorFlow, which also takes into account past user preferences and trend information to generate optimal recommendation candidates.

[0278] Step 6:

[0279] The server sends the selected recommended products to the terminal. The terminal displays this data in a user-friendly format. This makes it easier for the user to select the most suitable product based on this information.

[0280] Step 7:

[0281] When a user checks a product in a store or online, the terminal scans the QR code of the product. By this operation, the server obtains additional detailed information and provides it to the user. This enables the user to easily check the detailed specifications and reviews of the product and supports the purchase decision-making.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] Modern information provision systems handle a vast amount of data, so there is a problem that it is difficult for users to quickly find products that meet their needs. Also, in accessing product information in stores or online shopping, there is a problem that it is not easy to immediately obtain further detailed information. Such a situation is causing damage to the consumer's purchase experience and hindering the optimal product selection.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0286] In this invention, the server includes data processing means for receiving and analyzing a request from a user in natural language, data search means for obtaining related product information from a data aggregate, product proposal means for generating recommended products using an artificial intelligence model based on the product information, and information acquisition means for obtaining extended detailed information using the identification code attached to the product by the user. This enables the user to easily find the optimal product and immediately obtain detailed information using the identification code.

[0287] The "data processing means" is a mechanism that receives a request in natural language input by a user, analyzes it, and converts it into useful information.

[0288] A "data retrieval means" is a mechanism that efficiently obtains relevant product information from a data repository based on the results of the analysis.

[0289] A "product recommendation system" is a mechanism that uses an artificial intelligence model based on acquired product information to generate recommended products that best meet the user's needs.

[0290] A "data display means" is a mechanism that presents information on generated recommended products to the user, making it visually verifiable.

[0291] "Information acquisition means" refers to a mechanism that allows users to quickly obtain extended detailed information using an identification code attached to the product.

[0292] The system implementing this invention mainly consists of a portable information terminal used by the user and a server. The terminal can receive requests and conditions from the user in natural language and temporarily store them in a storage device. The stored data is transmitted to the server via the network.

[0293] The server uses natural language processing techniques such as the BERT model to analyze incoming requests and understand user needs and conditions. Based on this analysis, it uses information retrieval methods to efficiently obtain relevant product information from the database. Subsequently, the server utilizes a generative AI model to generate recommended products that best suit the user's needs based on the retrieved product information.

[0294] The generated recommended product information is transmitted back to the terminal via the network, and the terminal presents it to the user. The user can review the presented product information and instantly obtain more detailed information by scanning the identification code (QR code) attached to the product with the terminal's camera function. This information acquisition helps users make informed choices when selecting products.

[0295] For example, if a user is looking for a new home appliance, they input their budget, desired features, design preferences, etc., into the terminal. The server then recommends the most suitable appliance based on this information, and scanning the QR code of the suggested product displays detailed product specifications and reviews. As an example of a prompt, if the user enters, "I'm looking for an energy-efficient refrigerator under 50,000 yen. What do you recommend?", the system can suggest appropriate products that meet this request.

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] Users use a portable information terminal to input their preferences and requirements in natural language. The input data includes product category, price range, and desired features. The input data is temporarily stored in the terminal's internal storage.

[0299] Step 2:

[0300] The terminal transmits the stored input data to the server via the network. The server receives this natural language data and performs analysis using data processing methods that employ natural language processing technology. As a result of the analysis, the user's requests and conditions are extracted as specific data.

[0301] Step 3:

[0302] Based on the analyzed user request, the server uses information retrieval tools to obtain relevant product information from the data repository. During this process, products matching criteria such as product category and price range are searched, and a product list is generated as a result.

[0303] Step 4:

[0304] Using the generated AI model, the server selects the recommended products that best suit the user's needs from the acquired product information. Review information and specification data are considered for product evaluation. Finally, the recommended products and their detailed information are determined.

[0305] Step 5:

[0306] The server sends the determined recommended product information to the terminal. The terminal receives this and visually presents it to the user using the data display means. The user can view the presented product information.

[0307] Step 6:

[0308] The user reads the identification code (such as a QR code) of the presented product using the camera function of the terminal. The terminal sends the acquired code to the server and acquires the extended product information by the information acquisition means. By this operation, detailed specifications, product reviews, and usage examples are displayed, and the user can make a more informed decision based on the information.

[0309] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0310] The present invention provides a system that integrally analyzes the input data and the user's emotional state when the user inputs information related to product purchase via a terminal, and makes an optimal product recommendation. This system combines natural language processing technology and an emotion engine to enable product proposals based on the user's requests, wishes, and emotions.

[0311] The terminal receives information entered by the user and sends it to the server. When the server analyzes the information, it uses an emotion engine to evaluate sentiment indicators within the text. This sentiment evaluation is used to determine the user's emotional state when selecting a product. The sentiment data identified by the emotion engine is combined with request data analyzed using natural language processing.

[0312] The server processes this integrated data using information retrieval tools and retrieves relevant product information from the database. Next, an artificial intelligence model is used to generate product suggestions tailored to the user's requests and emotional state. The ranking and display method of the generated recommendations may change depending on the emotional state. In particular, it is possible to present many options to a relaxed user and narrow down the suggestions to the most effective options for a user in a hurry.

[0313] The terminal presents the user with a product list that reflects the results of the emotion engine. By viewing the product suggestions displayed through the terminal, users can more intuitively select products that suit their preferences. Furthermore, if the user needs more detailed information about a product, they can obtain it using a QR code. The server provides deeper level product information in response to that request.

[0314] For example, if a user is tired and trying to choose a home appliance, the system will prioritize presenting products that contribute to relaxation or products that quickly meet the user's needs. In this way, by utilizing emotional data, users can efficiently select the most suitable products.

[0315] Embodiments of the present invention enable product recommendations that take user emotions into consideration, thereby providing a more personalized purchasing experience.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The user enters their preferences and requirements for purchasing home appliances as text through the terminal's interface. The terminal temporarily stores the entered data.

[0319] Step 2:

[0320] The terminal sends the entered information to the server. A secure protocol is used for this transmission.

[0321] Step 3:

[0322] The server uses the text data received from the terminal to pass it to a natural language processing engine, which then analyzes the user's request. The analysis results then structure the user's intent.

[0323] Step 4:

[0324] The server activates the emotion engine and extracts emotion indicators from the user's input text. This allows the user's current emotional state to be evaluated.

[0325] Step 5:

[0326] The server integrates the results of natural language processing and sentiment analysis, and uses information retrieval tools to collect relevant product information from the database.

[0327] Step 6:

[0328] The server utilizes an artificial intelligence model to select appropriate recommended products that reflect the user's requests and emotional state. During this selection process, the priority and selection criteria for products may be adjusted based on the emotional state.

[0329] Step 7:

[0330] The server sends the selected product information to the terminal.

[0331] Step 8:

[0332] The terminal displays product suggestions received from the server to the user in an easy-to-read format. The displayed content may be customized according to the user's emotional state.

[0333] Step 9:

[0334] Users review the presented product list and make selections based on their emotions and intuition. Additional detailed information can be obtained using QR codes as needed.

[0335] Step 10:

[0336] The server receives a request for detailed information via a QR code and provides the relevant detailed information to the terminal.

[0337] (Example 2)

[0338] Next, we will describe Example 2. 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".

[0339] In modern product purchasing systems, product recommendations based on individual user emotional states and specific needs are insufficient, resulting in users being unable to select appropriate products satisfactorily and efficiently. Solving this problem and improving the user's purchasing experience is crucial.

[0340] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0341] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, integrated data generation means for evaluating the user's emotional state and integrating it with the request, and product suggestion means for generating recommended products using an artificial intelligence model based on the integrated data. This enables optimal product recommendations that take into account the user's emotional state and requests.

[0342] "Information processing means" refers to equipment or technology that has the function of analyzing requests received from users in natural language and extracting meaning.

[0343] "Information retrieval means" refers to equipment or technology used to find relevant product information from a database based on analysis results.

[0344] "Integrated data generation means" refers to equipment or technology for generating a single integrated data set by combining a user's emotional state and requests.

[0345] "Product recommendation means" refers to equipment or technology for generating appropriate recommended products using an artificial intelligence model based on integrated data.

[0346] "Information display means" refers to equipment or technology for presenting generated recommended products to users and displaying them in a format and ranking them according to their emotional state.

[0347] "Information enhancement means" refers to equipment or technology that enables users to obtain detailed product information using QR codes in stores or online.

[0348] This invention implements a system in which a user inputs information about product purchases into a terminal, and based on that information, provides optimal product recommendations. Specifically, the user's emotional state and requests are analyzed using natural language processing and artificial intelligence technology, and personalized product suggestions are made.

[0349] The server first receives information entered by the user from the terminal. This input information is then analyzed using a natural language processing engine. Natural language processing typically uses open-source libraries or custom-developed software to tokenize and semantic analyze the text. Simultaneously, a sentiment engine operates to evaluate the sentiment in the text. Sentiment evaluation is used to determine whether the user's input is classified as positive, negative, or neutral. Existing sentiment analysis libraries can be used for the sentiment engine.

[0350] The server integrates the analyzed user requests and emotional information, and performs information retrieval based on this integrated data. The server searches the database for relevant product information and generates optimal product suggestions using a generative AI model. The generative AI model employs machine learning algorithms, and in particular, optimizes suggestions based on the user's emotional state.

[0351] The suggested products are displayed to the user on their device. The user interface on the device is carefully designed, and how products are presented changes depending on the user's mood. Relaxed users are shown many options in a card format, while users in a hurry are shown a narrower, simpler selection of options.

[0352] As a concrete example, consider a scenario where a user is feeling tired but is looking for new home appliances for their living room. In this case, the system can prioritize suggesting items such as massage chairs or easy-to-use air purifiers designed to enhance relaxation. An example of a prompt to the generating AI model would be, "Please recommend products that will improve the comfort of my room when I'm feeling tired."

[0353] In this way, the system of the present invention is capable of providing personalized product recommendations that take into account the user's specific needs and emotional state.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The user enters information about their product purchase using the device. Specifically, the user enters the desired product category and any special requirements via the device's keyboard or touchscreen. The entered information is temporarily stored on the device as text data.

[0357] Step 2:

[0358] The terminal sends the information entered by the user to the server. Specifically, the terminal securely transmits the data via an internet connection. The input data arrives at the server in text format. The server receives this data and immediately prepares it for natural language processing.

[0359] Step 3:

[0360] The server analyzes the received text data using a natural language processing engine. Specifically, the server tokenizes the text and analyzes its meaning. The input is raw text data, and the output is structured data that represents the user's request. At this point, the analysis results are in a format that includes the user's purchase intent and desired conditions.

[0361] Step 4:

[0362] The server simultaneously uses an emotion engine to evaluate the user's emotional state. The input is the analyzed text data, and emotion analysis is performed. Specifically, the emotion engine calculates positive and negative emotion scores. The output generates data regarding the type and intensity of the emotion.

[0363] Step 5:

[0364] The server integrates the analyzed request data and sentiment data. This integrated data forms the basis for information retrieval. As part of the data processing, request and sentiment information are merged into a single dataset. The output is comprehensive information based on the user's wishes and emotions.

[0365] Step 6:

[0366] The server performs information retrieval based on integrated data. Specifically, the server accesses the database and searches for highly relevant product information. The input is integrated data, and the output is a list of related products. This list is used by the generative AI model to suggest products.

[0367] Step 7:

[0368] The server generates optimal product recommendations using a generative AI model. The input consists of a list of related products and integrated data. The AI ​​model uses machine learning algorithms to create personalized recommendations. The output is a list of recommended products, optimized to the emotional state of a specific user.

[0369] Step 8:

[0370] The terminal presents the user with recommended products received from the server. Specifically, the terminal displays product suggestions on the screen through a user interface. The display format and priority of products are adjusted according to the user's emotional state. The output is a visually verifiable selection of product suggestions for the user.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] Modern shopping systems offer recommendations based on user requests, but they often fail to adequately consider the user's emotional state when suggesting products. As a result, users may experience stress or struggle to select the products they want. Online stores, in particular, need flexible recommendations that can adapt to changes in user emotions.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, sentiment analysis means for comprehensively evaluating the analysis results and the user's emotional state, and information retrieval means for obtaining relevant product information from a database based on the analysis and evaluation results. This enables optimal product recommendations that take into account the user's emotional state.

[0376] "Information processing means" refers to a device or program that has the function of receiving and analyzing user requests in natural language.

[0377] "Emotional analysis means" refers to a device or program that has the function of evaluating and analyzing the emotional state of a user based on data obtained from the user.

[0378] "Information retrieval means" refers to a device or program that has the function of obtaining relevant product information from a database based on analysis results and evaluation results.

[0379] "Product suggestion means" refers to a device or program that has the function of generating recommended products suitable for the user using an artificial intelligence model based on product information.

[0380] "Information display means" refers to a device or program that has the function of presenting generated recommended products to the user.

[0381] To implement this invention, the system implements a program for collecting and analyzing user input information. First, when a user enters a shopping request using a terminal, the request is sent to the server in real time. The server uses natural language processing technology as an information processing tool to analyze the user's request. It also uses sentiment analysis tools to evaluate the user's emotional state. For this purpose, sentiment analysis software such as Microsoft Azure Text Analytics is useful.

[0382] The analysis results and sentiment evaluation results are integrated, and the information retrieval tool retrieves relevant product information from the database. The database contains information on a wide variety of products, allowing it to meet the specific needs of the user.

[0383] Next, an artificial intelligence model (for example, a recommendation system using TensorFlow) is used as a product suggestion tool to generate products suitable for the user's emotional state. This model uses past user data and real-time emotional data to provide personalized suggestions. Finally, an information display tool presents the generated recommended products to the user. For example, a user in a relaxed state might be shown an aroma diffuser or relaxation goods.

[0384] For example, if a user is online shopping during a busy workday, the system takes their stress level into account and recommends efficient and practical items. This aims to improve user convenience.

[0385] An example of a prompt used in a generative AI model might be: "Write code that analyzes the user's emotions from their input text and suggests the most suitable product for a relaxed user."

[0386] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0387] Step 1:

[0388] The user enters their shopping request using a terminal. The entered text data is collected by the terminal and sent to the server. The server receives this data and passes it to a natural language processing engine. This analyzes the input data and generates the user's specific request.

[0389] Step 2:

[0390] The server evaluates the user's emotions from the input data using emotion analysis tools. The input is the text data processed in the previous step, and a real-time emotion analysis tool (e.g., Microsoft Azure Text Analytics) is used to evaluate its emotional state. As a result, an emotion rating is generated.

[0391] Step 3:

[0392] The server integrates the analyzed request data and sentiment evaluation values, and performs database queries using information retrieval tools. The integrated data is used as input, and relevant product information is retrieved from the database. Through this process, product information that matches the user's needs is output.

[0393] Step 4:

[0394] The server generates product suggestions using an artificial intelligence model based on the acquired product information. Product information and sentiment rating values ​​are used as input, and the AI ​​model (e.g., a recommendation system using TensorFlow) generates a list of products that match the user's emotional state. This results in a personalized list of recommended products.

[0395] Step 5:

[0396] The terminal receives a list of recommended products sent from the server and displays it to the user. The recommended product list is used as input, and products are presented visually, taking into account the user's emotional state. This step allows the user to view the presented products and obtain more information if needed.

[0397] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0398] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0403] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0405] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0407] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0408] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0409] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0410] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0411] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0412] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0413] This invention provides a method for building an interactive home appliance recommendation system. This system automatically analyzes the input by utilizing pre-prepared information processing means, based on the user's preferences and requirements entered through an interface.

[0414] First, the terminal receives input from the user and temporarily stores the data. The stored data is sent to the server, which uses natural language processing technology to understand the user's requests and preferences. The server then uses information retrieval tools to efficiently retrieve product information related to the user's preferences from the database.

[0415] Next, the server utilizes an artificial intelligence model to select recommended products that best suit the user's needs based on the acquired product information. The products selected by the product suggestion system are sent from the server to the terminal, which then presents the information to the user. This allows the user to easily choose products that are right for them.

[0416] Furthermore, users can obtain additional detailed information by using a QR code when checking products in-store or online. The terminal uses this information to expand the information provided to the user and support their product selection decision.

[0417] As a concrete example, consider a scenario where a user is looking for a new refrigerator. The user enters information such as the number of family members, budget, and desired energy consumption into a terminal. The terminal sends this information to a server, which collects information on refrigerators that match the criteria and presents the user with the most suitable product. This allows the user to find a suitable refrigerator without spending time in the store, and they can also obtain more detailed information by scanning a QR code if necessary.

[0418] Thus, this system quickly and efficiently supports the entire process from user information input to product selection and provision of detailed information.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The user uses the terminal's interface to enter detailed information such as desired specifications, budget, and intended use for home appliances. The terminal temporarily stores this information.

[0422] Step 2:

[0423] The terminal sends information entered by the user to the server. This transmission is performed via a secure network protocol.

[0424] Step 3:

[0425] The server receives information from the terminal and uses a natural language processing engine to analyze the user's requests and preferences. This analysis converts the user's input into structured data.

[0426] Step 4:

[0427] The server activates an information retrieval mechanism to retrieve relevant product information from the database based on the analysis results. This identifies the product candidates that best match the user's preferences.

[0428] Step 5:

[0429] The server uses an AI model generated from acquired product information to identify the optimal recommended product that meets the user's needs. The product suggestion method prioritizes multiple items based on evaluation criteria.

[0430] Step 6:

[0431] The server sends the final selected proposal results to the terminal. The information provided by the server includes detailed product specifications and user reviews.

[0432] Step 7:

[0433] The terminal visually displays suggested products received from the server to the user. The user can check the product features, price, benefits, etc. on the screen.

[0434] Step 8:

[0435] If a user requires more detailed information, the terminal can display a QR code in-store or online, and scanning it will allow them to obtain additional information. The server will then provide additional content based on that QR code information.

[0436] Step 9:

[0437] Users make purchasing decisions based on the information provided. Optimizing the selection options enables quicker decision-making.

[0438] (Example 1)

[0439] Next, we will describe Example 1. 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."

[0440] It is difficult for consumers to quickly and accurately find the products that best suit their needs. This problem stems from the existence of a wide variety of options and the inability to obtain effective recommendations based on individual requirements. In particular, there is a need to improve the accuracy of recommendations by analyzing product information and considering past user preferences. Furthermore, obtaining detailed product information can be a cumbersome process, sometimes detracting from the user experience.

[0441] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0442] In this invention, the server includes data processing means, data retrieval means, product recommendation means utilizing a machine learning model, and data analysis means. This enables the rapid identification of products that match the user's needs and highly accurate recommendations that take into account past selection history and trend data. Furthermore, detailed product information can be easily obtained using general-purpose code, improving the user experience.

[0443] A "data processing tool" is a means that has the function of analyzing requests received from users in natural language and converting them into structured information.

[0444] A "data retrieval method" is a means that has the function of efficiently retrieving relevant product information from storage media based on the analyzed information.

[0445] A "machine learning model" is a mathematical model that incorporates algorithms to learn from past data and current trends, and to recommend the most suitable products to users.

[0446] A "product recommendation system" is a system that utilizes acquired product information to select and suggest products suitable for the user through a machine learning model.

[0447] An "information presentation means" is a means of displaying information about generated recommended products to the user, and provides an interface that allows the user to make intuitive selections.

[0448] "Data analysis methods" refer to techniques that take into account past selection history and market trend data to deepen our understanding of user needs and improve the accuracy of recommendations.

[0449] "Data enhancement means" refers to methods of providing users with additional information by using general-purpose codes at sales locations or in e-commerce to obtain detailed product information.

[0450] This invention provides an interactive system that enables consumers to easily find products that meet their needs. The system consistently supports users from input to the recommendation of relevant product information and the provision of detailed information.

[0451] First, the user enters the specifications of the product they wish to purchase through a terminal. This terminal can be used with general-purpose electronic devices such as tablets and smartphones, and the interface is designed to be easy for users to operate. Users can enter specific conditions such as, "I'm looking for an eco-friendly refrigerator for a family of four. My budget is under 100,000 yen, and I'd prefer an energy-efficient model."

[0452] The terminal sends the entered data to the server via a secure protocol (e.g., HTTPS). The server uses Python's NLTK library or spaCy to perform natural language processing on this data and clearly understand the user's request. Based on the information obtained through this analysis, the server accesses the database and retrieves appropriate product information. SQL is used to retrieve relevant information for data retrieval.

[0453] Once product information is retrieved, the server uses machine learning frameworks such as TensorFlow to generate recommended products that best suit the user's criteria. The generating AI model allows for optimized recommendations that take into account historical data and trends.

[0454] Subsequently, the server transmits the selected product information to the terminal, which then presents the information to the user in a visually easy-to-understand format. Based on this information, the user can easily select the appropriate product.

[0455] Furthermore, when users check products in stores or online, they can use their devices to scan the product's QR code. The server then uses the information obtained from the QR code to provide the user with additional details. This allows users to easily access in-depth information such as specific specifications and user reviews, enabling them to make more informed purchase decisions. This entire process enhances the user's purchasing experience and speeds up the selection process.

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1:

[0458] The user enters their desired product specifications using a terminal. The terminal receives the information from the user, such as a prompt like "an eco-friendly refrigerator for a family of four," and temporarily stores the data. The entered data is then structured and ready to be sent to the server.

[0459] Step 2:

[0460] The terminal sends user input data to the server. The HTTPS protocol is used for transmission, ensuring secure transfer of the input data. The data sent to the server is then placed in a receive buffer for further processing.

[0461] Step 3:

[0462] The server passes the received data to a natural language processing engine for analysis. Here, the Python NLTK library is used to convert the input language information into structured data. During this process, user preferences (e.g., budget, energy consumption) are extracted.

[0463] Step 4:

[0464] The server uses the parsed structured data to search for product information. It generates SQL queries and retrieves relevant product information from the database. Specifically, data for refrigerators that match the criteria is efficiently extracted.

[0465] Step 5:

[0466] The server inputs the acquired product information into a generating AI model to select the most suitable product for the user. This process utilizes a machine learning model based on TensorFlow, which also takes into account past user preferences and trend information to generate optimal recommendation candidates.

[0467] Step 6:

[0468] The server sends the selected recommended products to the terminal. The terminal displays this data in a user-friendly format. This makes it easier for the user to select the most suitable product based on this information.

[0469] Step 7:

[0470] When users view products in stores or online, their devices scan the product's QR code. This action allows the server to retrieve additional detailed information, which is then provided to the user. This makes it easy for users to check detailed product specifications and reviews, supporting their purchase decisions.

[0471] (Application Example 1)

[0472] Next, we will explain Application Example 1. In the following explanation, 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."

[0473] Modern information systems handle vast amounts of data, making it difficult for users to quickly find products that meet their needs. Furthermore, accessing product information in stores and online shopping often makes it difficult to instantly obtain more detailed information. This situation detracts from the consumer purchasing experience and hinders optimal product selection.

[0474] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0475] In this invention, the server includes data processing means for receiving and analyzing user requests in natural language, data retrieval means for obtaining relevant product information from a data aggregate, product suggestion means for generating recommended products using an artificial intelligence model based on the product information, and information acquisition means for obtaining extended detailed information using an identification code attached to a product. This makes it possible for users to easily find the optimal product and instantly obtain detailed information using the identification code.

[0476] A "data processing means" is a mechanism that receives requests in natural language from users, analyzes them, and converts them into useful information.

[0477] A "data retrieval means" is a mechanism that efficiently obtains relevant product information from a data repository based on the results of the analysis.

[0478] A "product recommendation system" is a mechanism that uses an artificial intelligence model based on acquired product information to generate recommended products that best meet the user's needs.

[0479] A "data display means" is a mechanism that presents information on generated recommended products to the user, making it visually verifiable.

[0480] "Information acquisition means" refers to a mechanism that allows users to quickly obtain extended detailed information using an identification code attached to the product.

[0481] The system implementing this invention mainly consists of a portable information terminal used by the user and a server. The terminal can receive requests and conditions from the user in natural language and temporarily store them in a storage device. The stored data is transmitted to the server via the network.

[0482] The server uses natural language processing techniques such as the BERT model to analyze incoming requests and understand user needs and conditions. Based on this analysis, it uses information retrieval methods to efficiently obtain relevant product information from the database. Subsequently, the server utilizes a generative AI model to generate recommended products that best suit the user's needs based on the retrieved product information.

[0483] The generated recommended product information is transmitted back to the terminal via the network, and the terminal presents it to the user. The user can review the presented product information and instantly obtain more detailed information by scanning the identification code (QR code) attached to the product with the terminal's camera function. This information acquisition helps users make informed choices when selecting products.

[0484] For example, if a user is looking for a new home appliance, they input their budget, desired features, design preferences, etc., into the terminal. The server then recommends the most suitable appliance based on this information, and scanning the QR code of the suggested product displays detailed product specifications and reviews. As an example of a prompt, if the user enters, "I'm looking for an energy-efficient refrigerator under 50,000 yen. What do you recommend?", the system can suggest appropriate products that meet this request.

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] Users use a portable information terminal to input their preferences and requirements in natural language. The input data includes product category, price range, and desired features. The input data is temporarily stored in the terminal's internal storage.

[0488] Step 2:

[0489] The terminal transmits the stored input data to the server via the network. The server receives this natural language data and performs analysis using data processing methods that employ natural language processing technology. As a result of the analysis, the user's requests and conditions are extracted as specific data.

[0490] Step 3:

[0491] Based on the analyzed user request, the server uses information retrieval tools to obtain relevant product information from the data repository. During this process, products matching criteria such as product category and price range are searched, and a product list is generated as a result.

[0492] Step 4:

[0493] Using a generative AI model, the server selects the most suitable recommended product from the acquired product information to meet the user's needs. Product evaluation takes into account review information and specification data. Finally, the recommended product and its detailed information are finalized.

[0494] Step 5:

[0495] The server transmits confirmed recommended product information to the terminal. The terminal receives this information and presents it visually to the user using a data display device. The user can then review the presented product information.

[0496] Step 6:

[0497] The user scans the product identification code (such as a QR code) presented to them using their device's camera. The device sends the acquired code to a server, which then retrieves enhanced product information through an information acquisition system. This process displays detailed specifications, product reviews, and usage examples, allowing the user to make more informed decisions.

[0498] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0499] This invention provides a system that, when a user inputs information about product purchases via a terminal, integrates and analyzes the input data and the user's emotional state to provide optimal product recommendations. This system combines natural language processing technology and an emotion engine to enable product suggestions based on the user's requests, desires, and emotions.

[0500] The terminal receives information entered by the user and sends it to the server. When the server analyzes the information, it uses an emotion engine to evaluate sentiment indicators within the text. This sentiment evaluation is used to determine the user's emotional state when selecting a product. The sentiment data identified by the emotion engine is combined with request data analyzed using natural language processing.

[0501] The server processes this integrated data using information retrieval tools and retrieves relevant product information from the database. Next, an artificial intelligence model is used to generate product suggestions tailored to the user's requests and emotional state. The ranking and display method of the generated recommendations may change depending on the emotional state. In particular, it is possible to present many options to a relaxed user and narrow down the suggestions to the most effective options for a user in a hurry.

[0502] The terminal presents the user with a product list that reflects the results of the emotion engine. By viewing the product suggestions displayed through the terminal, users can more intuitively select products that suit their preferences. Furthermore, if the user needs more detailed information about a product, they can obtain it using a QR code. The server provides deeper level product information in response to that request.

[0503] For example, if a user is tired and trying to choose a home appliance, the system will prioritize presenting products that contribute to relaxation or products that quickly meet the user's needs. In this way, by utilizing emotional data, users can efficiently select the most suitable products.

[0504] Embodiments of the present invention enable product recommendations that take user emotions into consideration, thereby providing a more personalized purchasing experience.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The user enters their preferences and requirements for purchasing home appliances as text through the terminal's interface. The terminal temporarily stores the entered data.

[0508] Step 2:

[0509] The terminal sends the entered information to the server. A secure protocol is used for this transmission.

[0510] Step 3:

[0511] The server uses the text data received from the terminal to pass it to a natural language processing engine, which then analyzes the user's request. The analysis results then structure the user's intent.

[0512] Step 4:

[0513] The server activates the emotion engine and extracts emotion indicators from the user's input text. This allows the user's current emotional state to be evaluated.

[0514] Step 5:

[0515] The server integrates the results of natural language processing and sentiment analysis, and uses information retrieval tools to collect relevant product information from the database.

[0516] Step 6:

[0517] The server utilizes an artificial intelligence model to select appropriate recommended products that reflect the user's requests and emotional state. During this selection process, the priority and selection criteria for products may be adjusted based on the emotional state.

[0518] Step 7:

[0519] The server sends the selected product information to the terminal.

[0520] Step 8:

[0521] The terminal displays product suggestions received from the server to the user in an easy-to-read format. The displayed content may be customized according to the user's emotional state.

[0522] Step 9:

[0523] Users review the presented product list and make selections based on their emotions and intuition. Additional detailed information can be obtained using QR codes as needed.

[0524] Step 10:

[0525] The server receives a request for detailed information via a QR code and provides the relevant detailed information to the terminal.

[0526] (Example 2)

[0527] Next, we will describe Example 2. 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."

[0528] In modern product purchasing systems, product recommendations based on individual user emotional states and specific needs are insufficient, resulting in users being unable to select appropriate products satisfactorily and efficiently. Solving this problem and improving the user's purchasing experience is crucial.

[0529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0530] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, integrated data generation means for evaluating the user's emotional state and integrating it with the request, and product suggestion means for generating recommended products using an artificial intelligence model based on the integrated data. This enables optimal product recommendations that take into account the user's emotional state and requests.

[0531] "Information processing means" refers to equipment or technology that has the function of analyzing requests received from users in natural language and extracting meaning.

[0532] "Information retrieval means" refers to equipment or technology used to find relevant product information from a database based on analysis results.

[0533] "Integrated data generation means" refers to equipment or technology for generating a single integrated data set by combining a user's emotional state and requests.

[0534] "Product recommendation means" refers to equipment or technology for generating appropriate recommended products using an artificial intelligence model based on integrated data.

[0535] "Information display means" refers to equipment or technology for presenting generated recommended products to users and displaying them in a format and ranking them according to their emotional state.

[0536] "Information enhancement means" refers to equipment or technology that enables users to obtain detailed product information using QR codes in stores or online.

[0537] This invention implements a system in which a user inputs information about product purchases into a terminal, and based on that information, provides optimal product recommendations. Specifically, the user's emotional state and requests are analyzed using natural language processing and artificial intelligence technology, and personalized product suggestions are made.

[0538] The server first receives information entered by the user from the terminal. This input information is then analyzed using a natural language processing engine. Natural language processing typically uses open-source libraries or custom-developed software to tokenize and semantic analyze the text. Simultaneously, a sentiment engine operates to evaluate the sentiment in the text. Sentiment evaluation is used to determine whether the user's input is classified as positive, negative, or neutral. Existing sentiment analysis libraries can be used for the sentiment engine.

[0539] The server integrates the analyzed user requests and emotional information, and performs information retrieval based on this integrated data. The server searches the database for relevant product information and generates optimal product suggestions using a generative AI model. The generative AI model employs machine learning algorithms, and in particular, optimizes suggestions based on the user's emotional state.

[0540] The suggested products are displayed to the user on their device. The user interface on the device is carefully designed, and how products are presented changes depending on the user's mood. Relaxed users are shown many options in a card format, while users in a hurry are shown a narrower, simpler selection of options.

[0541] As a concrete example, consider a scenario where a user is feeling tired but is looking for new home appliances for their living room. In this case, the system can prioritize suggesting items such as massage chairs or easy-to-use air purifiers designed to enhance relaxation. An example of a prompt to the generating AI model would be, "Please recommend products that will improve the comfort of my room when I'm feeling tired."

[0542] In this way, the system of the present invention is capable of providing personalized product recommendations that take into account the user's specific needs and emotional state.

[0543] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0544] Step 1:

[0545] The user enters information about their product purchase using the device. Specifically, the user enters the desired product category and any special requirements via the device's keyboard or touchscreen. The entered information is temporarily stored on the device as text data.

[0546] Step 2:

[0547] The terminal sends the information entered by the user to the server. Specifically, the terminal securely transmits the data via an internet connection. The input data arrives at the server in text format. The server receives this data and immediately prepares it for natural language processing.

[0548] Step 3:

[0549] The server analyzes the received text data using a natural language processing engine. Specifically, the server tokenizes the text and analyzes its meaning. The input is raw text data, and the output is structured data that represents the user's request. At this point, the analysis results are in a format that includes the user's purchase intent and desired conditions.

[0550] Step 4:

[0551] The server simultaneously uses an emotion engine to evaluate the user's emotional state. The input is the analyzed text data, and emotion analysis is performed. Specifically, the emotion engine calculates positive and negative emotion scores. The output generates data regarding the type and intensity of the emotion.

[0552] Step 5:

[0553] The server integrates the analyzed request data and sentiment data. This integrated data forms the basis for information retrieval. As part of the data processing, request and sentiment information are merged into a single dataset. The output is comprehensive information based on the user's wishes and emotions.

[0554] Step 6:

[0555] The server performs information retrieval based on integrated data. Specifically, the server accesses the database and searches for highly relevant product information. The input is integrated data, and the output is a list of related products. This list is used by the generative AI model to suggest products.

[0556] Step 7:

[0557] The server generates optimal product recommendations using a generative AI model. The input consists of a list of related products and integrated data. The AI ​​model uses machine learning algorithms to create personalized recommendations. The output is a list of recommended products, optimized to the emotional state of a specific user.

[0558] Step 8:

[0559] The terminal presents the user with recommended products received from the server. Specifically, the terminal displays product suggestions on the screen through a user interface. The display format and priority of products are adjusted according to the user's emotional state. The output is a visually verifiable selection of product suggestions for the user.

[0560] (Application Example 2)

[0561] Next, we will explain application example 2. In the following explanation, 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."

[0562] Modern shopping systems offer recommendations based on user requests, but they often fail to adequately consider the user's emotional state when suggesting products. As a result, users may experience stress or struggle to select the products they want. Online stores, in particular, need flexible recommendations that can adapt to changes in user emotions.

[0563] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0564] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, sentiment analysis means for comprehensively evaluating the analysis results and the user's emotional state, and information retrieval means for obtaining relevant product information from a database based on the analysis and evaluation results. This enables optimal product recommendations that take into account the user's emotional state.

[0565] "Information processing means" refers to a device or program that has the function of receiving and analyzing user requests in natural language.

[0566] "Emotional analysis means" refers to a device or program that has the function of evaluating and analyzing the emotional state of a user based on data obtained from the user.

[0567] "Information retrieval means" refers to a device or program that has the function of obtaining relevant product information from a database based on analysis results and evaluation results.

[0568] "Product suggestion means" refers to a device or program that has the function of generating recommended products suitable for the user using an artificial intelligence model based on product information.

[0569] "Information display means" refers to a device or program that has the function of presenting generated recommended products to the user.

[0570] To implement this invention, the system implements a program for collecting and analyzing user input information. First, when a user enters a shopping request using a terminal, the request is sent to the server in real time. The server uses natural language processing technology as an information processing tool to analyze the user's request. It also uses sentiment analysis tools to evaluate the user's emotional state. For this purpose, sentiment analysis software such as Microsoft Azure Text Analytics is useful.

[0571] The analysis results and sentiment evaluation results are integrated, and the information retrieval tool retrieves relevant product information from the database. The database contains information on a wide variety of products, allowing it to meet the specific needs of the user.

[0572] Next, an artificial intelligence model (for example, a recommendation system using TensorFlow) is used as a product suggestion tool to generate products suitable for the user's emotional state. This model uses past user data and real-time emotional data to provide personalized suggestions. Finally, an information display tool presents the generated recommended products to the user. For example, a user in a relaxed state might be shown an aroma diffuser or relaxation goods.

[0573] For example, if a user is online shopping during a busy workday, the system takes their stress level into account and recommends efficient and practical items. This aims to improve user convenience.

[0574] An example of a prompt used in a generative AI model might be: "Write code that analyzes the user's emotions from their input text and suggests the most suitable product for a relaxed user."

[0575] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0576] Step 1:

[0577] The user enters their shopping request using a terminal. The entered text data is collected by the terminal and sent to the server. The server receives this data and passes it to a natural language processing engine. This analyzes the input data and generates the user's specific request.

[0578] Step 2:

[0579] The server evaluates the user's emotions from the input data using emotion analysis tools. The input is the text data processed in the previous step, and a real-time emotion analysis tool (e.g., Microsoft Azure Text Analytics) is used to evaluate its emotional state. As a result, an emotion rating is generated.

[0580] Step 3:

[0581] The server integrates the analyzed request data and sentiment evaluation values, and performs database queries using information retrieval tools. The integrated data is used as input, and relevant product information is retrieved from the database. Through this process, product information that matches the user's needs is output.

[0582] Step 4:

[0583] The server generates product suggestions using an artificial intelligence model based on the acquired product information. Product information and sentiment rating values ​​are used as input, and the AI ​​model (e.g., a recommendation system using TensorFlow) generates a list of products that match the user's emotional state. This results in a personalized list of recommended products.

[0584] Step 5:

[0585] The terminal receives a list of recommended products sent from the server and displays it to the user. The recommended product list is used as input, and products are presented visually, taking into account the user's emotional state. This step allows the user to view the presented products and obtain more information if needed.

[0586] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0588] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] As shown in Figure 7, the 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.

[0592] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0593] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0594] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0595] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0596] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0597] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0598] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0599] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0600] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0601] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0602] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0603] This invention provides a method for building an interactive home appliance recommendation system. This system automatically analyzes the input by utilizing pre-prepared information processing means, based on the user's preferences and requirements entered through an interface.

[0604] First, the terminal receives input from the user and temporarily stores the data. The stored data is sent to the server, which uses natural language processing technology to understand the user's requests and preferences. The server then uses information retrieval tools to efficiently retrieve product information related to the user's preferences from the database.

[0605] Next, the server utilizes an artificial intelligence model to select recommended products that best suit the user's needs based on the acquired product information. The products selected by the product suggestion system are sent from the server to the terminal, which then presents the information to the user. This allows the user to easily choose products that are right for them.

[0606] Furthermore, users can obtain additional detailed information by using a QR code when checking products in-store or online. The terminal uses this information to expand the information provided to the user and support their product selection decision.

[0607] As a concrete example, consider a scenario where a user is looking for a new refrigerator. The user enters information such as the number of family members, budget, and desired energy consumption into a terminal. The terminal sends this information to a server, which collects information on refrigerators that match the criteria and presents the user with the most suitable product. This allows the user to find a suitable refrigerator without spending time in the store, and they can also obtain more detailed information by scanning a QR code if necessary.

[0608] Thus, this system quickly and efficiently supports the entire process from user information input to product selection and provision of detailed information.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] The user uses the terminal's interface to enter detailed information such as desired specifications, budget, and intended use for home appliances. The terminal temporarily stores this information.

[0612] Step 2:

[0613] The terminal sends information entered by the user to the server. This transmission is performed via a secure network protocol.

[0614] Step 3:

[0615] The server receives information from the terminal and uses a natural language processing engine to analyze the user's requests and preferences. This analysis converts the user's input into structured data.

[0616] Step 4:

[0617] The server activates an information retrieval mechanism to retrieve relevant product information from the database based on the analysis results. This identifies the product candidates that best match the user's preferences.

[0618] Step 5:

[0619] The server uses an AI model generated from acquired product information to identify the optimal recommended product that meets the user's needs. The product suggestion method prioritizes multiple items based on evaluation criteria.

[0620] Step 6:

[0621] The server sends the final selected proposal results to the terminal. The information provided by the server includes detailed product specifications and user reviews.

[0622] Step 7:

[0623] The terminal visually displays suggested products received from the server to the user. The user can check the product features, price, benefits, etc. on the screen.

[0624] Step 8:

[0625] If a user requires more detailed information, the terminal can display a QR code in-store or online, and scanning it will allow them to obtain additional information. The server will then provide additional content based on that QR code information.

[0626] Step 9:

[0627] Users make purchasing decisions based on the information provided. Optimizing the selection options enables quicker decision-making.

[0628] (Example 1)

[0629] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] It is difficult for consumers to quickly and accurately find the products that best suit their needs. This problem stems from the existence of a wide variety of options and the inability to obtain effective recommendations based on individual requirements. In particular, there is a need to improve the accuracy of recommendations by analyzing product information and considering past user preferences. Furthermore, obtaining detailed product information can be a cumbersome process, sometimes detracting from the user experience.

[0631] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0632] In this invention, the server includes data processing means, data retrieval means, product recommendation means utilizing a machine learning model, and data analysis means. This enables the rapid identification of products that match the user's needs and highly accurate recommendations that take into account past selection history and trend data. Furthermore, detailed product information can be easily obtained using general-purpose code, improving the user experience.

[0633] A "data processing tool" is a means that has the function of analyzing requests received from users in natural language and converting them into structured information.

[0634] A "data retrieval method" is a means that has the function of efficiently retrieving relevant product information from storage media based on the analyzed information.

[0635] A "machine learning model" is a mathematical model that incorporates algorithms to learn from past data and current trends, and to recommend the most suitable products to users.

[0636] A "product recommendation system" is a system that utilizes acquired product information to select and suggest products suitable for the user through a machine learning model.

[0637] An "information presentation means" is a means of displaying information about generated recommended products to the user, and provides an interface that allows the user to make intuitive selections.

[0638] "Data analysis methods" refer to techniques that take into account past selection history and market trend data to deepen our understanding of user needs and improve the accuracy of recommendations.

[0639] "Data enhancement means" refers to methods of providing users with additional information by using general-purpose codes at sales locations or in e-commerce to obtain detailed product information.

[0640] This invention provides an interactive system that enables consumers to easily find products that meet their needs. The system consistently supports users from input to the recommendation of relevant product information and the provision of detailed information.

[0641] First, the user enters the specifications of the product they wish to purchase through a terminal. This terminal can be used with general-purpose electronic devices such as tablets and smartphones, and the interface is designed to be easy for users to operate. Users can enter specific conditions such as, "I'm looking for an eco-friendly refrigerator for a family of four. My budget is under 100,000 yen, and I'd prefer an energy-efficient model."

[0642] The terminal sends the entered data to the server via a secure protocol (e.g., HTTPS). The server uses Python's NLTK library or spaCy to perform natural language processing on this data and clearly understand the user's request. Based on the information obtained through this analysis, the server accesses the database and retrieves appropriate product information. SQL is used to retrieve relevant information for data retrieval.

[0643] Once product information is retrieved, the server uses machine learning frameworks such as TensorFlow to generate recommended products that best suit the user's criteria. The generating AI model allows for optimized recommendations that take into account historical data and trends.

[0644] Subsequently, the server transmits the selected product information to the terminal, which then presents the information to the user in a visually easy-to-understand format. Based on this information, the user can easily select the appropriate product.

[0645] Furthermore, when users check products in stores or online, they can use their devices to scan the product's QR code. The server then uses the information obtained from the QR code to provide the user with additional details. This allows users to easily access in-depth information such as specific specifications and user reviews, enabling them to make more informed purchase decisions. This entire process enhances the user's purchasing experience and speeds up the selection process.

[0646] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0647] Step 1:

[0648] The user enters their desired product specifications using a terminal. The terminal receives the information from the user, such as a prompt like "an eco-friendly refrigerator for a family of four," and temporarily stores the data. The entered data is then structured and ready to be sent to the server.

[0649] Step 2:

[0650] The terminal sends user input data to the server. The HTTPS protocol is used for transmission, ensuring secure transfer of the input data. The data sent to the server is then placed in a receive buffer for further processing.

[0651] Step 3:

[0652] The server passes the received data to a natural language processing engine for analysis. Here, the Python NLTK library is used to convert the input language information into structured data. During this process, user preferences (e.g., budget, energy consumption) are extracted.

[0653] Step 4:

[0654] The server uses the parsed structured data to search for product information. It generates SQL queries and retrieves relevant product information from the database. Specifically, data for refrigerators that match the criteria is efficiently extracted.

[0655] Step 5:

[0656] The server inputs the acquired product information into a generating AI model to select the most suitable product for the user. This process utilizes a machine learning model based on TensorFlow, which also takes into account past user preferences and trend information to generate optimal recommendation candidates.

[0657] Step 6:

[0658] The server sends the selected recommended products to the terminal. The terminal displays this data in a user-friendly format. This makes it easier for the user to select the most suitable product based on this information.

[0659] Step 7:

[0660] When users view products in stores or online, their devices scan the product's QR code. This action allows the server to retrieve additional detailed information, which is then provided to the user. This makes it easy for users to check detailed product specifications and reviews, supporting their purchase decisions.

[0661] (Application Example 1)

[0662] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] Modern information systems handle vast amounts of data, making it difficult for users to quickly find products that meet their needs. Furthermore, accessing product information in stores and online shopping often makes it difficult to instantly obtain more detailed information. This situation detracts from the consumer purchasing experience and hinders optimal product selection.

[0664] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0665] In this invention, the server includes data processing means for receiving and analyzing user requests in natural language, data retrieval means for obtaining relevant product information from a data aggregate, product suggestion means for generating recommended products using an artificial intelligence model based on the product information, and information acquisition means for obtaining extended detailed information using an identification code attached to a product. This makes it possible for users to easily find the optimal product and instantly obtain detailed information using the identification code.

[0666] A "data processing means" is a mechanism that receives requests in natural language from users, analyzes them, and converts them into useful information.

[0667] A "data retrieval means" is a mechanism that efficiently obtains relevant product information from a data repository based on the results of the analysis.

[0668] A "product recommendation system" is a mechanism that uses an artificial intelligence model based on acquired product information to generate recommended products that best meet the user's needs.

[0669] A "data display means" is a mechanism that presents information on generated recommended products to the user, making it visually verifiable.

[0670] "Information acquisition means" refers to a mechanism that allows users to quickly obtain extended detailed information using an identification code attached to the product.

[0671] The system implementing this invention mainly consists of a portable information terminal used by the user and a server. The terminal can receive requests and conditions from the user in natural language and temporarily store them in a storage device. The stored data is transmitted to the server via the network.

[0672] The server uses natural language processing techniques such as the BERT model to analyze incoming requests and understand user needs and conditions. Based on this analysis, it uses information retrieval methods to efficiently obtain relevant product information from the database. Subsequently, the server utilizes a generative AI model to generate recommended products that best suit the user's needs based on the retrieved product information.

[0673] The generated recommended product information is transmitted back to the terminal via the network, and the terminal presents it to the user. The user can review the presented product information and instantly obtain more detailed information by scanning the identification code (QR code) attached to the product with the terminal's camera function. This information acquisition helps users make informed choices when selecting products.

[0674] For example, if a user is looking for a new home appliance, they input their budget, desired features, design preferences, etc., into the terminal. The server then recommends the most suitable appliance based on this information, and scanning the QR code of the suggested product displays detailed product specifications and reviews. As an example of a prompt, if the user enters, "I'm looking for an energy-efficient refrigerator under 50,000 yen. What do you recommend?", the system can suggest appropriate products that meet this request.

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] Users use a portable information terminal to input their preferences and requirements in natural language. The input data includes product category, price range, and desired features. The input data is temporarily stored in the terminal's internal storage.

[0678] Step 2:

[0679] The terminal transmits the stored input data to the server via the network. The server receives this natural language data and performs analysis using data processing methods that employ natural language processing technology. As a result of the analysis, the user's requests and conditions are extracted as specific data.

[0680] Step 3:

[0681] Based on the analyzed user request, the server uses information retrieval tools to obtain relevant product information from the data repository. During this process, products matching criteria such as product category and price range are searched, and a product list is generated as a result.

[0682] Step 4:

[0683] Using a generative AI model, the server selects the most suitable recommended product from the acquired product information to meet the user's needs. Product evaluation takes into account review information and specification data. Finally, the recommended product and its detailed information are finalized.

[0684] Step 5:

[0685] The server transmits confirmed recommended product information to the terminal. The terminal receives this information and presents it visually to the user using a data display device. The user can then review the presented product information.

[0686] Step 6:

[0687] The user scans the product identification code (such as a QR code) presented to them using their device's camera. The device sends the acquired code to a server, which then retrieves enhanced product information through an information acquisition system. This process displays detailed specifications, product reviews, and usage examples, allowing the user to make more informed decisions.

[0688] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0689] This invention provides a system that, when a user inputs information about product purchases via a terminal, integrates and analyzes the input data and the user's emotional state to provide optimal product recommendations. This system combines natural language processing technology and an emotion engine to enable product suggestions based on the user's requests, desires, and emotions.

[0690] The terminal receives information entered by the user and sends it to the server. When the server analyzes the information, it uses an emotion engine to evaluate sentiment indicators within the text. This sentiment evaluation is used to determine the user's emotional state when selecting a product. The sentiment data identified by the emotion engine is combined with request data analyzed using natural language processing.

[0691] The server processes this integrated data using information retrieval tools and retrieves relevant product information from the database. Next, an artificial intelligence model is used to generate product suggestions tailored to the user's requests and emotional state. The ranking and display method of the generated recommendations may change depending on the emotional state. In particular, it is possible to present many options to a relaxed user and narrow down the suggestions to the most effective options for a user in a hurry.

[0692] The terminal presents the user with a product list that reflects the results of the emotion engine. By viewing the product suggestions displayed through the terminal, users can more intuitively select products that suit their preferences. Furthermore, if the user needs more detailed information about a product, they can obtain it using a QR code. The server provides deeper level product information in response to that request.

[0693] For example, if a user is tired and trying to choose a home appliance, the system will prioritize presenting products that contribute to relaxation or products that quickly meet the user's needs. In this way, by utilizing emotional data, users can efficiently select the most suitable products.

[0694] Embodiments of the present invention enable product recommendations that take user emotions into consideration, thereby providing a more personalized purchasing experience.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The user enters their preferences and requirements for purchasing home appliances as text through the terminal's interface. The terminal temporarily stores the entered data.

[0698] Step 2:

[0699] The terminal sends the entered information to the server. A secure protocol is used for this transmission.

[0700] Step 3:

[0701] The server uses the text data received from the terminal to pass it to a natural language processing engine, which then analyzes the user's request. The analysis results then structure the user's intent.

[0702] Step 4:

[0703] The server activates the emotion engine and extracts emotion indicators from the user's input text. This allows the user's current emotional state to be evaluated.

[0704] Step 5:

[0705] The server integrates the results of natural language processing and sentiment analysis, and uses information retrieval tools to collect relevant product information from the database.

[0706] Step 6:

[0707] The server utilizes an artificial intelligence model to select appropriate recommended products that reflect the user's requests and emotional state. During this selection process, the priority and selection criteria for products may be adjusted based on the emotional state.

[0708] Step 7:

[0709] The server sends the selected product information to the terminal.

[0710] Step 8:

[0711] The terminal displays product suggestions received from the server to the user in an easy-to-read format. The displayed content may be customized according to the user's emotional state.

[0712] Step 9:

[0713] Users review the presented product list and make selections based on their emotions and intuition. Additional detailed information can be obtained using QR codes as needed.

[0714] Step 10:

[0715] The server receives a request for detailed information via a QR code and provides the relevant detailed information to the terminal.

[0716] (Example 2)

[0717] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0718] In modern product purchasing systems, product recommendations based on individual user emotional states and specific needs are insufficient, resulting in users being unable to select appropriate products satisfactorily and efficiently. Solving this problem and improving the user's purchasing experience is crucial.

[0719] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0720] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, integrated data generation means for evaluating the user's emotional state and integrating it with the request, and product suggestion means for generating recommended products using an artificial intelligence model based on the integrated data. This enables optimal product recommendations that take into account the user's emotional state and requests.

[0721] "Information processing means" refers to equipment or technology that has the function of analyzing requests received from users in natural language and extracting meaning.

[0722] "Information retrieval means" refers to equipment or technology used to find relevant product information from a database based on analysis results.

[0723] "Integrated data generation means" refers to equipment or technology for generating a single integrated data set by combining a user's emotional state and requests.

[0724] "Product recommendation means" refers to equipment or technology for generating appropriate recommended products using an artificial intelligence model based on integrated data.

[0725] "Information display means" refers to equipment or technology for presenting generated recommended products to users and displaying them in a format and ranking them according to their emotional state.

[0726] "Information enhancement means" refers to equipment or technology that enables users to obtain detailed product information using QR codes in stores or online.

[0727] This invention implements a system in which a user inputs information about product purchases into a terminal, and based on that information, provides optimal product recommendations. Specifically, the user's emotional state and requests are analyzed using natural language processing and artificial intelligence technology, and personalized product suggestions are made.

[0728] The server first receives information entered by the user from the terminal. This input information is then analyzed using a natural language processing engine. Natural language processing typically uses open-source libraries or custom-developed software to tokenize and semantic analyze the text. Simultaneously, a sentiment engine operates to evaluate the sentiment in the text. Sentiment evaluation is used to determine whether the user's input is classified as positive, negative, or neutral. Existing sentiment analysis libraries can be used for the sentiment engine.

[0729] The server integrates the analyzed user requests and emotional information, and performs information retrieval based on this integrated data. The server searches the database for relevant product information and generates optimal product suggestions using a generative AI model. The generative AI model employs machine learning algorithms, and in particular, optimizes suggestions based on the user's emotional state.

[0730] The suggested products are displayed to the user on their device. The user interface on the device is carefully designed, and how products are presented changes depending on the user's mood. Relaxed users are shown many options in a card format, while users in a hurry are shown a narrower, simpler selection of options.

[0731] As a concrete example, consider a scenario where a user is feeling tired but is looking for new home appliances for their living room. In this case, the system can prioritize suggesting items such as massage chairs or easy-to-use air purifiers designed to enhance relaxation. An example of a prompt to the generating AI model would be, "Please recommend products that will improve the comfort of my room when I'm feeling tired."

[0732] In this way, the system of the present invention is capable of providing personalized product recommendations that take into account the user's specific needs and emotional state.

[0733] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0734] Step 1:

[0735] The user enters information about their product purchase using the device. Specifically, the user enters the desired product category and any special requirements via the device's keyboard or touchscreen. The entered information is temporarily stored on the device as text data.

[0736] Step 2:

[0737] The terminal sends the information entered by the user to the server. Specifically, the terminal securely transmits the data via an internet connection. The input data arrives at the server in text format. The server receives this data and immediately prepares it for natural language processing.

[0738] Step 3:

[0739] The server analyzes the received text data using a natural language processing engine. Specifically, the server tokenizes the text and analyzes its meaning. The input is raw text data, and the output is structured data that represents the user's request. At this point, the analysis results are in a format that includes the user's purchase intent and desired conditions.

[0740] Step 4:

[0741] The server simultaneously uses an emotion engine to evaluate the user's emotional state. The input is the analyzed text data, and emotion analysis is performed. Specifically, the emotion engine calculates positive and negative emotion scores. The output generates data regarding the type and intensity of the emotion.

[0742] Step 5:

[0743] The server integrates the analyzed request data and sentiment data. This integrated data forms the basis for information retrieval. As part of the data processing, request and sentiment information are merged into a single dataset. The output is comprehensive information based on the user's wishes and emotions.

[0744] Step 6:

[0745] The server performs information retrieval based on integrated data. Specifically, the server accesses the database and searches for highly relevant product information. The input is integrated data, and the output is a list of related products. This list is used by the generative AI model to suggest products.

[0746] Step 7:

[0747] The server generates optimal product recommendations using a generative AI model. The input consists of a list of related products and integrated data. The AI ​​model uses machine learning algorithms to create personalized recommendations. The output is a list of recommended products, optimized to the emotional state of a specific user.

[0748] Step 8:

[0749] The terminal presents the user with recommended products received from the server. Specifically, the terminal displays product suggestions on the screen through a user interface. The display format and priority of products are adjusted according to the user's emotional state. The output is a visually verifiable selection of product suggestions for the user.

[0750] (Application Example 2)

[0751] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0752] Modern shopping systems offer recommendations based on user requests, but they often fail to adequately consider the user's emotional state when suggesting products. As a result, users may experience stress or struggle to select the products they want. Online stores, in particular, need flexible recommendations that can adapt to changes in user emotions.

[0753] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0754] In this invention, the server includes information processing means for receiving and analyzing user requests in natural language, sentiment analysis means for comprehensively evaluating the analysis results and the user's emotional state, and information retrieval means for obtaining relevant product information from a database based on the analysis and evaluation results. This enables optimal product recommendations that take into account the user's emotional state.

[0755] "Information processing means" refers to a device or program that has the function of receiving and analyzing user requests in natural language.

[0756] "Emotional analysis means" refers to a device or program that has the function of evaluating and analyzing the emotional state of a user based on data obtained from the user.

[0757] "Information retrieval means" refers to a device or program that has the function of obtaining relevant product information from a database based on analysis results and evaluation results.

[0758] "Product suggestion means" refers to a device or program that has the function of generating recommended products suitable for the user using an artificial intelligence model based on product information.

[0759] "Information display means" refers to a device or program that has the function of presenting generated recommended products to the user.

[0760] To implement this invention, the system implements a program for collecting and analyzing user input information. First, when a user enters a shopping request using a terminal, the request is sent to the server in real time. The server uses natural language processing technology as an information processing tool to analyze the user's request. It also uses sentiment analysis tools to evaluate the user's emotional state. For this purpose, sentiment analysis software such as Microsoft Azure Text Analytics is useful.

[0761] The analysis results and sentiment evaluation results are integrated, and the information retrieval tool retrieves relevant product information from the database. The database contains information on a wide variety of products, allowing it to meet the specific needs of the user.

[0762] Next, an artificial intelligence model (for example, a recommendation system using TensorFlow) is used as a product suggestion tool to generate products suitable for the user's emotional state. This model uses past user data and real-time emotional data to provide personalized suggestions. Finally, an information display tool presents the generated recommended products to the user. For example, a user in a relaxed state might be shown an aroma diffuser or relaxation goods.

[0763] For example, if a user is online shopping during a busy workday, the system takes their stress level into account and recommends efficient and practical items. This aims to improve user convenience.

[0764] An example of a prompt used in a generative AI model might be: "Write code that analyzes the user's emotions from their input text and suggests the most suitable product for a relaxed user."

[0765] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0766] Step 1:

[0767] The user enters their shopping request using a terminal. The entered text data is collected by the terminal and sent to the server. The server receives this data and passes it to a natural language processing engine. This analyzes the input data and generates the user's specific request.

[0768] Step 2:

[0769] The server evaluates the user's emotions from the input data using emotion analysis tools. The input is the text data processed in the previous step, and a real-time emotion analysis tool (e.g., Microsoft Azure Text Analytics) is used to evaluate its emotional state. As a result, an emotion rating is generated.

[0770] Step 3:

[0771] The server integrates the analyzed request data and sentiment evaluation values, and performs database queries using information retrieval tools. The integrated data is used as input, and relevant product information is retrieved from the database. Through this process, product information that matches the user's needs is output.

[0772] Step 4:

[0773] The server generates product suggestions using an artificial intelligence model based on the acquired product information. Product information and sentiment rating values ​​are used as input, and the AI ​​model (e.g., a recommendation system using TensorFlow) generates a list of products that match the user's emotional state. This results in a personalized list of recommended products.

[0774] Step 5:

[0775] The terminal receives a list of recommended products sent from the server and displays it to the user. The recommended product list is used as input, and products are presented visually, taking into account the user's emotional state. This step allows the user to view the presented products and obtain more information if needed.

[0776] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0777] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0778] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0779] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0780] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0781] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0782] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0783] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0784] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0785] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0786] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0787] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0788] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0789] 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.

[0790] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0791] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0792] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0793] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0794] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0795] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0796] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0797] The following is further disclosed regarding the embodiments described above.

[0798] (Claim 1)

[0799] An information processing means that receives and analyzes user requests in natural language,

[0800] An information retrieval means for obtaining relevant product information from a database based on the analysis results,

[0801] A product suggestion method that generates recommended products using an artificial intelligence model based on product information,

[0802] Information display means for presenting generated recommended products to the user,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, further comprising an information enhancement means for expanding user input information via a QR code in-store or online to provide detailed product information.

[0806] (Claim 3)

[0807] The system according to claim 1, wherein the product suggestion means further includes an evaluation means that analyzes multiple review pieces of information and evaluates the quality of the recommended product.

[0808] "Example 1"

[0809] (Claim 1)

[0810] A data processing method that receives and analyzes user requests in natural language,

[0811] A data retrieval means for obtaining relevant product information from a storage medium based on the analysis results,

[0812] A product recommendation method that generates recommended products using a machine learning model based on product information,

[0813] An information presentation means that presents generated recommended products to the user,

[0814] When analyzing user requirements, a data analysis method is provided to consider past selection history and trend data.

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, further comprising a data enhancement means for extending user input information by a general-purpose code at a sales location or in e-commerce to provide detailed product information.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the product recommendation means further includes an evaluation means that analyzes multiple evaluation pieces of information and evaluates the quality of the recommended product.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] A data processing method that receives and analyzes user requests in natural language,

[0823] A data retrieval means for obtaining relevant product information from a data aggregate based on the analysis results,

[0824] A product suggestion method that generates recommended products using an artificial intelligence model based on product information,

[0825] A data display means for presenting generated recommended products to the user,

[0826] An information acquisition means that allows the user to obtain extended detailed information using an identification code attached to the product,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, in which a portable information terminal is used to input user preferences and conditions based on user input information, and information processing is performed in real time.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the product suggestion means further includes an evaluation means that analyzes multiple review pieces of information and evaluates the quality of the recommended product.

[0832] "Example 2 of combining an emotion engine"

[0833] (Claim 1)

[0834] An information processing means that receives and analyzes user requests in natural language,

[0835] An information retrieval means for obtaining relevant product information from a database based on the analysis results,

[0836] An integrated data generation means that evaluates the user's emotional state and integrates it with requests,

[0837] A product suggestion method that generates recommended products using an artificial intelligence model based on integrated data,

[0838] An information display means that presents generated recommended products to the user and adjusts the ranking and display format according to the user's emotional state,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, further comprising an information enhancement means for expanding user input information via a QR code in-store or online to provide detailed product information.

[0842] (Claim 3)

[0843] The system according to claim 1, further comprising means for adjusting the options of recommended products based on the user's emotional state and providing a presentation optimized for a specific emotional state.

[0844] "Application example 2 when combining with an emotional engine"

[0845] (Claim 1)

[0846] An information processing means that receives and analyzes user requests in natural language,

[0847] An emotion analysis method that comprehensively evaluates the analysis results and the user's emotional state,

[0848] An information retrieval means for obtaining relevant product information from a database based on analysis and evaluation results,

[0849] A product suggestion method that uses an artificial intelligence model based on product information to generate recommended products that are suitable for the user's emotional state,

[0850] Information display means for presenting generated recommended products to the user,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, further comprising an information provision means that evaluates the user's emotions in real time via a terminal based on user input information and suggests products suitable for a relaxed or stressed state.

[0854] (Claim 3)

[0855] The system according to claim 1, further comprising an adjustment means for dynamically adjusting the method of presenting products and their priority according to the user's emotional state. [Explanation of Symbols]

[0856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data processing method that receives and analyzes user requests in natural language, A data retrieval means for obtaining relevant product information from a data aggregate based on the analysis results, A product suggestion method that generates recommended products using an artificial intelligence model based on product information, A data display means for presenting generated recommended products to the user, An information acquisition means that allows the user to obtain extended detailed information using an identification code attached to the product, A system that includes this.

2. The system according to claim 1, in which a portable information terminal is used to input user-generated information, such as preferences and conditions, and information processing is performed in real time.

3. The system according to claim 1, wherein the product suggestion means further includes an evaluation means that analyzes multiple review pieces of information and evaluates the quality of the recommended product.

Images