system

Abstract

We provide the system. [Solution] An input method including a terminal in which the user enters requests in natural language, A natural language processing system on a server that analyzes the input natural language, A database search means on a server for searching past proposal information and customer data, A generative model means for selecting the optimal product using the retrieved information, A display means for presenting information about the selected products to the user, 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 persona chatbot control method 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] [[ID=2l]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a corporate salesperson proposes an optimal product to a customer, it is difficult to quickly find an appropriate product from a huge number of products, and it takes a lot of time to create a proposal. In such a situation, in order to improve the efficiency of sales, there is a need to develop a system that effectively uses past proposal information and customer data and utilizes AI to quickly and accurately propose products.

Means for Solving the Problems

[0005] This invention provides a system comprising a terminal in which the user inputs requests in natural language, a natural language processing means on a server for analyzing the input natural language, a database search means for searching past proposal information and customer data, a generative model means for selecting the optimal product using the retrieved information, and a display means for presenting information about the selected product to the user. As a result, sales representatives can simply input requests in natural language, and the AI ​​will automatically propose appropriate products, thereby improving the efficiency of proposal work and increasing the success rate of closing deals.

[0006] A "user" is an entity that uses the system to input product requests in natural language.

[0007] A "terminal" is a device used by users to input requests and communicate with a server.

[0008] "Input means" refers to the part that provides the interface and functions for users to input requests in natural language.

[0009] A "server" is a computer system that analyzes user information and performs processing using database searches and generative models.

[0010] A "natural language processing tool" is a function that analyzes natural language input by a user and extracts relevant keywords and information.

[0011] The "database search method" refers to a function that searches past proposal information and customer databases to retrieve relevant information.

[0012] "Generative model means" refers to a function that includes an AI algorithm that selects the optimal product based on information obtained through search.

[0013] A "display means" is an interface for visually presenting selected product information to the user. [Brief explanation of the drawing]

[0014] [Figure 1] The figure is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] The figure is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] The figure is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] The figure 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] The figure is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] The figure 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] The figure is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] The figure 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] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] The figure is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] The figure is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] The figure is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] The figure is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the 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 tagged 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 tagged 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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[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, 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] In the system of this invention, the user begins by inputting their product request in natural language using a handheld terminal. The terminal receives this input and transmits the data to the server. The server analyzes the received data using a natural language processing engine to understand the content of the request.

[0036] The server then searches a database containing relevant past proposal information and customer data. Based on these search results, a generative model is activated to select the product best suited to the user's needs. Machine learning and AI algorithms are used for evaluation and scoring during the selection process.

[0037] The selected product information is transmitted to the user's terminal and presented to the user through the terminal's display. This allows the user to review the proposed products and make quick and accurate product recommendations in sales activities.

[0038] Specific example:

[0039] For example, a user might type "I want a new smartphone with a high-resolution camera" into their device. This input is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generation model selects the product that best fits the criteria from these candidates and sends information about "Smartphone X" to the device as a recommended product. The user can then use this information to make customer suggestions.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses a device to input product requests in natural language. The device collects and temporarily stores the entered data.

[0043] Step 2:

[0044] The terminal sends user input data to the server. During this process, the data is formatted according to communication standards and transmitted through a secure channel.

[0045] Step 3:

[0046] The server analyzes the received data. Using a natural language processing engine, it tokenizes the input text and extracts keywords and important phrases.

[0047] Step 4:

[0048] The server searches a database containing historical data and customer data related to product suggestions based on the extracted keywords. It then retrieves relevant product information.

[0049] Step 5:

[0050] The server uses a generative model to analyze product information retrieved from the database. An AI algorithm scores the suitability of each product and selects the most suitable product.

[0051] Step 6:

[0052] The server compiles information on the selected products and sends it back to the user's terminal. The transmitted data includes product suggestions that best suit the user's needs.

[0053] Step 7:

[0054] The terminal displays received product information, making it easy for the user to review. The user can then review the displayed product suggestions and make product selections and customer proposals based on them.

[0055] (Example 1)

[0056] 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."

[0057] The modern process of information acquisition and product selection presents a problem: users must independently collect and evaluate vast amounts of information, which is time-consuming and laborious. Furthermore, there is a lack of efficient methods for quickly finding the product best suited to the user's needs.

[0058] 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.

[0059] In this invention, the server includes a natural language processing means on an information processing device that analyzes input natural language, an information recording device search means that searches for past proposal content and customer information, and a generative artificial intelligence model means that selects the optimal product using the retrieved information. As a result, the optimal product can be quickly and accurately identified and presented simply by the user inputting their request using natural language.

[0060] "Input means" refers to a device that includes an information processing device for users to input requests in natural language.

[0061] "Natural language processing means" refers to a function on an information processing device that analyzes input natural language and understands the content of a request.

[0062] "Information recording device search means" refers to means on an information processing device for searching data that stores past proposals and customer information.

[0063] A "generative artificial intelligence model means" is a means that includes an algorithm for selecting the optimal product using machine learning methods.

[0064] "Display means" refers to a device or function used to present information about selected products to the user.

[0065] To implement this invention, the process begins with the user inputting their request in natural language using their handheld device. The device provides user-friendly input methods, such as voice input or text input. Next, the device receives the user's input and sends it to the server.

[0066] The server analyzes the input data using a natural language processing engine. This process can utilize natural language processing libraries such as Python's NLTK or spaCy. This allows the user's requests to be broken down into specific keywords, making it possible to understand their intent.

[0067] Next, the server searches a database containing past proposals and customer information. This is done using SQL queries to extract relevant information. Based on the extracted information, the server drives a generative artificial intelligence model. This model is built using machine learning frameworks such as TENSORFLOW® and PyTorch, and performs product evaluation and scoring.

[0068] Ultimately, the server sends back the optimal product information selected by the generation AI model to the terminal. The terminal then visually presents the selected product information to the user. This process allows the user to efficiently find products that meet their needs.

[0069] As a concrete example, a user enters "I want a new smartphone with a high-resolution camera" into their device. This information is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generative artificial intelligence model selects the product that best matches the user's criteria from the candidate products and sends information about "Smartphone X" to the device as a recommended product.

[0070] An example of a prompt message would be, "The user wants a smartphone with a high-resolution camera. Search the database for related products and recommend the best one." In this way, the user can receive product recommendations quickly and accurately.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The user enters their product request using natural language on the device. This input is converted into digital data using the device's voice recognition and text input functions. The entered data proceeds directly to the next processing step, so the process involves converting physical signals into information.

[0074] Step 2:

[0075] The terminal sends the input data received from the user to the server. The terminal uses HTTP requests to transfer the data. The transmitted data includes the user's requests, and the server receives this data and prepares it for the next processing step.

[0076] Step 3:

[0077] The server processes the received data using a natural language processing engine. Here, libraries such as Python's NLTK and spaCy are used to extract keywords from the input data and interpret their intent. Specifically, text data is tokenized, analyzed based on natural language structure, and relevant keywords are output.

[0078] Step 4:

[0079] The server searches the information storage device based on the extracted keywords. This process uses SQL queries to retrieve relevant data from past suggestions and customer information in the database. As a result of the search, information on products that match the keywords is output.

[0080] Step 5:

[0081] The server drives a generative AI model based on the search results. Here, machine learning algorithms are used to evaluate and score candidate products. Frameworks such as TensorFlow and PyTorch are used for this process, analyzing the product data received as input and selecting the most suitable product. The optimal product is then selected as the output.

[0082] Step 6:

[0083] The server sends information about the selected products back to the terminal. This information is transmitted via an API. The terminal receives this information, converts the output data into a visual format, and presents it to the user. This allows the user to confirm the selected products.

[0084] (Application Example 1)

[0085] 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."

[0086] In today's information processing environment, it is difficult for users to quickly and accurately identify the items they desire, especially when there are many options. Users need to express their needs appropriately, but even when natural language input is possible, there is insufficient support for making the best choice from the suggested products. As a result, the user experience is unsatisfactory, and further improvements are needed.

[0087] 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.

[0088] In this invention, the server includes an input means that includes an information processing device in which the user inputs requests in natural language, a natural language analysis means on an electronic processing machine that analyzes the input natural language, and an information retrieval means on an electronic processing machine that searches for past proposal information and customer information. This enables efficient information extraction based on the user's natural language input and the recommendation of appropriate items.

[0089] An "information processing device" is an electronic device that allows users to input requests in natural language and is responsible for transmitting the input information to a server.

[0090] "Natural language processing means" refers to a function or program on an electronic processing machine for analyzing input natural language, and is a means of extracting desired meanings and vocabulary from language.

[0091] "Information retrieval means" refers to a function on an electronic processing machine that searches an information repository containing past proposal information and customer information, and retrieves information related to the user's requests.

[0092] A "generative model means" is a computational program or device that uses machine learning algorithms or AI technology to select the optimal item based on information obtained from an information retrieval means.

[0093] "Display means" refers to an output device or its function for visually presenting information about selected items to the user.

[0094] "Speech recognition means" refers to an electronic function or program that converts voice input from a user into a string of characters and provides it to a natural language analysis means.

[0095] "Information provision means" refers to a program or device that provides a user with a list of items that match a user's request, based on the user's natural language request.

[0096] The system implementing this invention consists of an information processing device, a server, and related software components. The user inputs a request in natural language using the information processing device. The input can also be converted from speech to text by a speech recognition means. The converted natural language text is sent to the server.

[0097] On the server, software implemented as a natural language processing tool analyzes the text and extracts important keywords and requests. This analysis could potentially utilize the natural language processing library "Transformers." Based on the analysis results, an information retrieval tool searches a database on the electronic processing unit to obtain relevant data from past proposal information and customer information.

[0098] The acquired data is fed into a generative modeling system, where machine learning algorithms and AI technology select the most suitable items. The selected items are transmitted to an information processing device via a display system and presented to the user. The user can then use this information to select products that meet their needs.

[0099] For example, if a user enters the prompt "I'm looking for waterproof sneakers," the system analyzes and extracts keywords such as "waterproof" and "sneakers," then displays a list of related products. This allows the user to efficiently find products that meet their needs. In this way, the prompt is received by the generating AI model, and information is provided.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The user inputs their request in natural language using an information processing device. Input can be via a text form or speech recognition. In the case of speech, the speech recognition means converts the speech to text. The output of this step is text data representing the user's request.

[0103] Step 2:

[0104] The terminal sends the input text data to the server. Upon receiving this text data, the server analyzes it using natural language processing (NLP) tools. Specifically, it uses a natural language processing library to extract keywords and the meaning of requests from the text. The output of this step is the extracted keywords and semantic information.

[0105] Step 3:

[0106] The server searches the database using information retrieval tools. Using the extracted keywords as clues, the server retrieves relevant data, including past proposal information and customer information. This process utilizes a database search algorithm for efficient information retrieval. The output of this step is the relevant data.

[0107] Step 4:

[0108] The server supplies relevant data to the generative model and uses a machine learning algorithm to select the optimal item. This is a process in which the AI ​​evaluation model scores each candidate item and selects the optimal item based on those scores. The output of this step is the selected item information.

[0109] Step 5:

[0110] The selected item information is transmitted to the user's information processing device via a display device. The user can view the provided list on the terminal and see detailed information about the items. In this step, it is ensured that the data is displayed accurately and quickly in the user interface. The output of this step is item information presented visually to the user.

[0111] 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.

[0112] In the emotion recognition system of the present invention, the user inputs product requests in natural language through a terminal. The terminal has an emotion engine that analyzes the user's emotions in real time from the tone of the user's voice, input speed, or facial expressions using camera images.

[0113] The device sends this emotion data and request data to the server. The server analyzes the received natural language data and extracts the necessary keywords. At this point, it also takes into account the user's emotion information received from the emotion engine to further optimize the suggested products.

[0114] The server searches past suggestion databases and customer data based on the extracted information and collects relevant products. The generative model uses AI algorithms to analyze all information, including sentiment data, and scores recommended products. Scoring using sentiment information enables product suggestions that are tailored to enhance user comfort and satisfaction.

[0115] The generated recommended product information is sent from the server to the user's terminal and presented to the user through a display device. Based on this information, the user can select the most suitable product according to their emotional state and engage in suggestion activities.

[0116] Specific example:

[0117] For example, if a user enters "I'm looking for a new laptop, but I want to stay within my budget," and the emotion engine simultaneously detects the user's anxiety, the server will use this emotional information to prioritize recommending cost-effective products. Furthermore, by offering product suggestions that focus on "ease of use," it is expected that the user's anxiety will be alleviated.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The user inputs their product requests in natural language using their device. Simultaneously, an emotion engine built into the device analyzes the user's emotions based on their voice tone and facial expression data during input.

[0121] Step 2:

[0122] The device sends analyzed natural language data and sentiment data to the server. The transmitted data includes the user's desired requirements and current sentiment state.

[0123] Step 3:

[0124] The server uses a natural language processing engine to analyze the received requests and identify key keywords. In this process, sentiment data is also considered to determine which suggestions are most effective.

[0125] Step 4:

[0126] The server searches past suggestion databases and customer databases based on extracted keywords and sentiment data. It collects highly relevant product information and creates a list of candidates.

[0127] Step 5:

[0128] The server uses a generative model to select the best product from the collected product candidates. Sentimental data influences the evaluation and scoring of recommended products, ensuring that the product best matches the user's emotions.

[0129] Step 6:

[0130] The server sends information about the selected products to the user's device. Detailed information and reasons for recommendations may be included to ensure that emotionally sensitive suggestions are conveyed to the user.

[0131] Step 7:

[0132] The device displays received product information and prompts the user to make appropriate choices. Based on these suggestions, which take into account the user's emotional state, the user can then make a product selection.

[0133] (Example 2)

[0134] 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".

[0135] Traditional product selection systems have a problem in that they do not adequately improve user satisfaction because they make suggestions without considering the user's emotions. It is necessary to make product suggestions that are more in line with user needs by incorporating user emotions into the suggestions.

[0136] 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.

[0137] In this invention, the server includes information processing means for analyzing input natural language and sentiment data, information retrieval means for searching past suggestion information and customer data, and generative modeling means for selecting the optimal product using the retrieved information and sentiment data. This makes it possible to suggest products that take the user's emotions into consideration, thereby improving user satisfaction.

[0138] "Natural language" refers to the language that humans use in their daily lives, and includes the sentences and phrases that users input to convey their intentions and requests to machines.

[0139] "Emotional state" refers to the user's inner psychological state and is derived from information analyzed from the user's tone of voice, facial expressions, and other factors.

[0140] A "terminal" is an electronic device used by users to input or receive information, and may include an emotion analysis engine.

[0141] "Information processing means" refers to server-side functions that analyze natural language and emotional data entered by users to understand their meaning and emotions.

[0142] "Information retrieval means" refers to a function that runs on a server to search past proposal information and customer data and retrieve related information.

[0143] "Generative modeling means" refers to server-side functions, including algorithms and machine learning models, for selecting the optimal product based on acquired information and sentiment data.

[0144] "Display means" refers to the means used to present information about selected products to the user, and includes the screen or interface of the user's terminal.

[0145] This invention is a product suggestion system that incorporates emotion recognition. It begins with the user inputting their product requests in natural language using a terminal. The terminal is equipped with an emotion engine that analyzes the user's voice tone, input speed, or facial expressions via camera footage, recognizing the user's emotional state in real time. This enables suggestions based on the user's psychological state.

[0146] The terminal sends the input request data and acquired sentiment data to the server. The server analyzes the input request using a dedicated natural language processing engine and extracts important keywords. At the same time, the sentiment data is also taken into consideration.

[0147] The server searches a database containing past suggestion information and customer data based on extracted keywords and sentiment data. Based on the retrieved information, a generative AI model evaluates and scores products using a machine learning algorithm. By incorporating sentiment data into the scoring, product suggestions are made that improve user comfort and satisfaction.

[0148] Ultimately, the server sends information about recommended products to the user's device and presents it to the user through the device's display. This allows the user to choose the most suitable product based on the information received and their emotional state.

[0149] Specific example:

[0150] For example, if a user types "I'm looking for a new laptop, but I want to stay within my budget," the emotion engine will sense the user's anxiety, and the server will prioritize recommending products that offer good value for money or focus on ease of use.

[0151] Example of a prompt:

[0152] "I'm looking for a new laptop, but I want to stay within my budget. I'd like something inexpensive but easy to use."

[0153] In this way, product proposals that improve the user experience are realized.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The user uses a device to input product requests in natural language. The device receives these requests as text data. In addition, an emotion engine is used to analyze the user's voice tone and facial expressions in real time and obtain emotion data. The output of this step is natural language request data and user emotion data.

[0157] Step 2:

[0158] The device sends the acquired natural language request data and sentiment data to the server. The server receives this data. The received request data is analyzed using a natural language processing engine, and important keywords are extracted. As a result, keyword data is obtained. The sentiment data is stored along with the analysis results.

[0159] Step 3:

[0160] The server uses the extracted keywords to search past suggestion information and customer data within the database. Sentiment data is also considered during this search. The search output is a list of related product candidates.

[0161] Step 4:

[0162] The generative AI model receives a list of candidates and sentiment data as input and uses a machine learning algorithm to evaluate and score the products. Here, the system is specifically processed to improve the scores of products that better match the user's needs based on the sentiment data. The output of this step is a list of scored products.

[0163] Step 5:

[0164] The server sends a scored product list to the user's device. The device receives this information and displays it to the user in real time using a display device. The user can review and select products based on the displayed information. The output is information about the recommended products presented to the user.

[0165] (Application Example 2)

[0166] 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".

[0167] Traditional online shopping product recommendation systems typically provide recommendations based on explicit user requests, making it difficult to consider user emotions and underlying anxieties. As a result, users often find the suggested product selections unsatisfactory, which can diminish their willingness to purchase. In particular, users with concerns about budget and quality require more appropriate and reassuring product recommendations.

[0168] 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.

[0169] In this invention, the server includes an emotion engine means for analyzing the user's emotions, a database search means for retrieving past suggestion information and customer information, and a generative model device for selecting the optimal product using the retrieved information and the user's emotion data. This enables appropriate product suggestions according to the user's emotional state.

[0170] A "receiving device" is a terminal that receives requests from users in natural language and retrieves that information.

[0171] An "information processing device" is a computer device that analyzes input data and performs processing based on that analysis.

[0172] A "natural language processing means" is a software function that operates on an information processing device and analyzes natural language input by a user to understand the content of their request.

[0173] An "emotional engine" is a system that analyzes a user's emotions and determines their emotional state in real time based on data such as voice and facial expressions.

[0174] The "database search method" refers to a function for searching past proposal information and customer information to obtain relevant information.

[0175] A "generative model device" is a device that selects the optimal product and generates a proposal based on acquired information and analyzed sentiment data.

[0176] A "display device" is a device used to visually present selected product information to a user.

[0177] This invention consists of a terminal used by the user and a server that processes information. First, the user uses the terminal's receiving device to input their product requests in natural language. At that time, facial expression and voice data are collected through the terminal's camera and microphone and transmitted to an emotion engine means. This emotion engine means evaluates the user's emotional state in real time and transmits that information to the server as an analysis result.

[0178] The server analyzes user requests using natural language processing on an information processing device. Based on this analysis, it uses a database search to retrieve past proposal information and customer information and collect relevant data. In parallel, it also utilizes sentiment data sent from the sentiment engine.

[0179] Furthermore, the generative modeling system within the server integrates collected information and sentiment data to select the optimal product. This selection process utilizes a generative AI model, which performs product evaluation and scoring based on machine learning algorithms.

[0180] The selected product information is transmitted via the network to the terminal's display device and presented to the user. The user can visually confirm this information and receive product suggestions that are appropriate to their emotional state.

[0181] As a concrete example, consider a scenario where a user enters into the terminal, "I'm looking for a new laptop, but I want to stay within my budget." In this case, the server analyzes the user's anxieties and, considering the emotional data, prioritizes presenting products with excellent cost performance and positive reviews. If the user then provides a prompt such as, "I'm looking for something high-performance at an affordable price," the system will suggest products best suited to that request.

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] On the device, the user inputs their requests in natural language using a receiving device. The input data is in voice or text format, and the device's camera and microphone simultaneously record the user's facial expressions and voice tone. Based on this input, data representing the user's requests and emotions is generated.

[0185] Step 2:

[0186] The terminal sends the acquired user's natural language requests and sentiment data to the server. The server first uses natural language processing to analyze the request data. As a result of the analysis, keywords of the requests are extracted. Using these keywords and sentiment data as input, data is obtained to understand the user's purchasing intent.

[0187] Step 3:

[0188] The server uses a database search mechanism to retrieve past proposal information and customer information. This retrieves relevant product information that matches the request. The search results are then filtered based on the entered keywords and output as a candidate list.

[0189] Step 4:

[0190] The generative modeling system evaluates products using a candidate list of search results and sentiment data. A generative AI model is applied, and machine learning algorithms are used to score and rank each product. The output is a list of recommended products that best suit the user's emotional state.

[0191] Step 5:

[0192] The server transmits scored product information to the terminal via the network. The terminal's display shows recommended products to the user in real time. The user can make product selections based on the visualized information. This process provides the user with personalized product recommendations.

[0193] 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.

[0194] Data generation model 58 is a 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.

[0195] 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.

[0196] [Second Embodiment]

[0197] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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".

[0209] In the system of this invention, the user begins by inputting their product request in natural language using a handheld terminal. The terminal receives this input and transmits the data to the server. The server analyzes the received data using a natural language processing engine to understand the content of the request.

[0210] The server then searches a database containing relevant past proposal information and customer data. Based on these search results, a generative model is activated to select the product best suited to the user's needs. Machine learning and AI algorithms are used for evaluation and scoring during the selection process.

[0211] The selected product information is transmitted to the user's terminal and presented to the user through the terminal's display. This allows the user to review the proposed products and make quick and accurate product recommendations in sales activities.

[0212] Specific example:

[0213] For example, a user might type "I want a new smartphone with a high-resolution camera" into their device. This input is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generation model selects the product that best fits the criteria from these candidates and sends information about "Smartphone X" to the device as a recommended product. The user can then use this information to make customer suggestions.

[0214] The following describes the processing flow.

[0215] Step 1:

[0216] The user uses a device to input product requests in natural language. The device collects and temporarily stores the entered data.

[0217] Step 2:

[0218] The terminal sends user input data to the server. During this process, the data is formatted according to communication standards and transmitted through a secure channel.

[0219] Step 3:

[0220] The server analyzes the received data. Using a natural language processing engine, it tokenizes the input text and extracts keywords and important phrases.

[0221] Step 4:

[0222] The server searches a database containing historical data and customer data related to product suggestions based on the extracted keywords. It then retrieves relevant product information.

[0223] Step 5:

[0224] The server uses a generative model to analyze product information retrieved from the database. An AI algorithm scores the suitability of each product and selects the most suitable product.

[0225] Step 6:

[0226] The server compiles information on the selected products and sends it back to the user's terminal. The transmitted data includes product suggestions that best suit the user's needs.

[0227] Step 7:

[0228] The terminal displays received product information, making it easy for the user to review. The user can then review the displayed product suggestions and make product selections and customer proposals based on them.

[0229] (Example 1)

[0230] 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."

[0231] The modern process of information acquisition and product selection presents a problem: users must independently collect and evaluate vast amounts of information, which is time-consuming and laborious. Furthermore, there is a lack of efficient methods for quickly finding the product best suited to the user's needs.

[0232] 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.

[0233] In this invention, the server includes a natural language processing means on an information processing device that analyzes input natural language, an information recording device search means that searches for past proposal content and customer information, and a generative artificial intelligence model means that selects the optimal product using the retrieved information. As a result, the optimal product can be quickly and accurately identified and presented simply by the user inputting their request using natural language.

[0234] "Input means" refers to a device that includes an information processing device for users to input requests in natural language.

[0235] "Natural language processing means" refers to a function on an information processing device that analyzes input natural language and understands the content of a request.

[0236] "Information recording device search means" refers to means on an information processing device for searching data that stores past proposals and customer information.

[0237] A "generative artificial intelligence model means" is a means that includes an algorithm for selecting the optimal product using machine learning methods.

[0238] "Display means" refers to a device or function used to present information about selected products to the user.

[0239] To implement this invention, the process begins with the user inputting their request in natural language using their handheld device. The device provides user-friendly input methods, such as voice input or text input. Next, the device receives the user's input and sends it to the server.

[0240] The server analyzes the input data using a natural language processing engine. This process can utilize natural language processing libraries such as Python's NLTK or spaCy. This allows the user's requests to be broken down into specific keywords, making it possible to understand their intent.

[0241] Next, the server searches a database containing past proposals and customer information. This is done using SQL queries to extract relevant information. Based on the extracted information, the server drives a generative artificial intelligence model. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and performs product evaluation and scoring.

[0242] Ultimately, the server sends back the optimal product information selected by the generation AI model to the terminal. The terminal then visually presents the selected product information to the user. This process allows the user to efficiently find products that meet their needs.

[0243] As a concrete example, a user enters "I want a new smartphone with a high-resolution camera" into their device. This information is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generative artificial intelligence model selects the product that best matches the user's criteria from the candidate products and sends information about "Smartphone X" to the device as a recommended product.

[0244] An example of a prompt message would be, "The user wants a smartphone with a high-resolution camera. Search the database for related products and recommend the best one." In this way, the user can receive product recommendations quickly and accurately.

[0245] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0246] Step 1:

[0247] The user enters their product request using natural language on the device. This input is converted into digital data using the device's voice recognition and text input functions. The entered data proceeds directly to the next processing step, so the process involves converting physical signals into information.

[0248] Step 2:

[0249] The terminal sends the input data received from the user to the server. The terminal uses HTTP requests to transfer the data. The transmitted data includes the user's requests, and the server receives this data and prepares it for the next processing step.

[0250] Step 3:

[0251] The server processes the received data using a natural language processing engine. Here, libraries such as Python's NLTK and spaCy are used to extract keywords from the input data and interpret their intent. Specifically, text data is tokenized, analyzed based on natural language structure, and relevant keywords are output.

[0252] Step 4:

[0253] The server searches the information storage device based on the extracted keywords. This process uses SQL queries to retrieve relevant data from past suggestions and customer information in the database. As a result of the search, information on products that match the keywords is output.

[0254] Step 5:

[0255] The server drives a generative AI model based on the search results. Here, machine learning algorithms are used to evaluate and score candidate products. Frameworks such as TensorFlow and PyTorch are used for this process, analyzing the product data received as input and selecting the most suitable product. The optimal product is then selected as the output.

[0256] Step 6:

[0257] The server sends information about the selected products back to the terminal. This information is transmitted via an API. The terminal receives this information, converts the output data into a visual format, and presents it to the user. This allows the user to confirm the selected products.

[0258] (Application Example 1)

[0259] 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 glasses 214 will be referred to as the "terminal."

[0260] In today's information processing environment, it is difficult for users to quickly and accurately identify the items they desire, especially when there are many options. Users need to express their needs appropriately, but even when natural language input is possible, there is insufficient support for making the best choice from the suggested products. As a result, the user experience is unsatisfactory, and further improvements are needed.

[0261] 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.

[0262] In this invention, the server includes an input means that includes an information processing device in which the user inputs requests in natural language, a natural language analysis means on an electronic processing machine that analyzes the input natural language, and an information retrieval means on an electronic processing machine that searches for past proposal information and customer information. This enables efficient information extraction based on the user's natural language input and the recommendation of appropriate items.

[0263] An "information processing device" is an electronic device that allows users to input requests in natural language and is responsible for transmitting the input information to a server.

[0264] "Natural language processing means" refers to a function or program on an electronic processing machine for analyzing input natural language, and is a means of extracting desired meanings and vocabulary from language.

[0265] "Information retrieval means" refers to a function on an electronic processing machine that searches an information repository containing past proposal information and customer information, and retrieves information related to the user's requests.

[0266] A "generative model means" is a computational program or device that uses machine learning algorithms or AI technology to select the optimal item based on information obtained from an information retrieval means.

[0267] "Display means" refers to an output device or its function for visually presenting information about selected items to the user.

[0268] "Speech recognition means" refers to an electronic function or program that converts voice input from a user into a string of characters and provides it to a natural language analysis means.

[0269] "Information provision means" refers to a program or device that provides a user with a list of items that match a user's request, based on the user's natural language request.

[0270] The system implementing this invention consists of an information processing device, a server, and related software components. The user inputs a request in natural language using the information processing device. The input can also be converted from speech to text by a speech recognition means. The converted natural language text is sent to the server.

[0271] On the server, software implemented as a natural language processing tool analyzes the text and extracts important keywords and requests. This analysis could potentially utilize the natural language processing library "Transformers." Based on the analysis results, an information retrieval tool searches a database on the electronic processing unit to obtain relevant data from past proposal information and customer information.

[0272] The acquired data is fed into a generative modeling system, where machine learning algorithms and AI technology select the most suitable items. The selected items are transmitted to an information processing device via a display system and presented to the user. The user can then use this information to select products that meet their needs.

[0273] For example, if a user enters the prompt "I'm looking for waterproof sneakers," the system analyzes and extracts keywords such as "waterproof" and "sneakers," then displays a list of related products. This allows the user to efficiently find products that meet their needs. In this way, the prompt is received by the generating AI model, and information is provided.

[0274] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0275] Step 1:

[0276] The user inputs their request in natural language using an information processing device. Input can be via a text form or speech recognition. In the case of speech, the speech recognition means converts the speech to text. The output of this step is text data representing the user's request.

[0277] Step 2:

[0278] The terminal sends the input text data to the server. Upon receiving this text data, the server analyzes it using natural language processing (NLP) tools. Specifically, it uses a natural language processing library to extract keywords and the meaning of requests from the text. The output of this step is the extracted keywords and semantic information.

[0279] Step 3:

[0280] The server searches the database using information retrieval means. Using the extracted keywords as clues, the server obtains related data including past proposal information and customer information. In this process, an efficient information search is performed using a database search algorithm. The output of this step is the corresponding related data.

[0281] Step 4:

[0282] The server supplies the related data to the generation model means and selects the optimal item using a machine learning algorithm. This is a process in which the AI evaluation model scores each candidate item and selects the optimal item based on it. The output of this step is the selected item information.

[0283] Step 5:

[0284] The selected item information is transmitted to the user's information processing device through the display means. The user can view the list provided on the terminal and see the detailed information of the item. In this step, it is ensured that the data is displayed accurately and quickly on the interface for the user. The output of this step is the item information visually presented to the user.

[0285] 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.

[0286] In the system combined with the emotion recognition of the present invention, the user inputs a request regarding a product in natural language through the terminal. The terminal incorporates an emotion engine and has a function of analyzing the user's emotion in real time using the tone of the user's voice, input speed, or facial expressions from camera images.

[0287] The device sends this emotion data and request data to the server. The server analyzes the received natural language data and extracts the necessary keywords. At this point, it also takes into account the user's emotion information received from the emotion engine to further optimize the suggested products.

[0288] The server searches past suggestion databases and customer data based on the extracted information and collects relevant products. The generative model uses AI algorithms to analyze all information, including sentiment data, and scores recommended products. Scoring using sentiment information enables product suggestions that are tailored to enhance user comfort and satisfaction.

[0289] The generated recommended product information is sent from the server to the user's terminal and presented to the user through a display device. Based on this information, the user can select the most suitable product according to their emotional state and engage in suggestion activities.

[0290] Specific example:

[0291] For example, if a user enters "I'm looking for a new laptop, but I want to stay within my budget," and the emotion engine simultaneously detects the user's anxiety, the server will use this emotional information to prioritize recommending cost-effective products. Furthermore, by offering product suggestions that focus on "ease of use," it is expected that the user's anxiety will be alleviated.

[0292] The following describes the processing flow.

[0293] Step 1:

[0294] The user inputs their product requests in natural language using their device. Simultaneously, an emotion engine built into the device analyzes the user's emotions based on their voice tone and facial expression data during input.

[0295] Step 2:

[0296] The terminal sends the analyzed natural language data and sentiment data to the server. The transmitted data includes the user's desired requirements and the current sentiment state.

[0297] Step 3:

[0298] The server uses a natural language processing engine to analyze the received requests and identify important keywords. In this process, sentiment data is also considered to determine which proposals are the most effective.

[0299] Step 4:

[0300] Based on the extracted keywords and sentiment data, the server searches the past proposal database and customer database. It collects highly relevant product information to create a candidate list.

[0301] Step 5:

[0302] The server uses a generation model to select the optimal product from the collected product candidates. Sentiment data affects the evaluation and scoring of the recommended products, and the product that best suits the user's sentiment is selected.

[0303] Step 6:

[0304] The server sends the information of the selected product to the user's terminal. Detailed information and recommended reasons may be attached so that the sentiment - considered proposal can be conveyed to the user.

[0305] Step 7:

[0306] The terminal displays the received product information and prompts the user to make an appropriate selection. Based on these proposals considered in the user's sentiment state, the user can make a product selection.

[0307] (Example 2)

[0308] 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".

[0309] Traditional product selection systems have a problem in that they do not adequately improve user satisfaction because they make suggestions without considering the user's emotions. It is necessary to make product suggestions that are more in line with user needs by incorporating user emotions into the suggestions.

[0310] 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.

[0311] In this invention, the server includes information processing means for analyzing input natural language and sentiment data, information retrieval means for searching past suggestion information and customer data, and generative modeling means for selecting the optimal product using the retrieved information and sentiment data. This makes it possible to suggest products that take the user's emotions into consideration, thereby improving user satisfaction.

[0312] "Natural language" refers to the language that humans use in their daily lives, and includes the sentences and phrases that users input to convey their intentions and requests to machines.

[0313] "Emotional state" refers to the user's inner psychological state and is derived from information analyzed from the user's tone of voice, facial expressions, and other factors.

[0314] A "terminal" is an electronic device used by users to input or receive information, and may include an emotion analysis engine.

[0315] "Information processing means" refers to server-side functions that analyze natural language and emotional data entered by users to understand their meaning and emotions.

[0316] "Information retrieval means" refers to a function that runs on a server to search past proposal information and customer data and retrieve related information.

[0317] "Generative modeling means" refers to server-side functions, including algorithms and machine learning models, for selecting the optimal product based on acquired information and sentiment data.

[0318] "Display means" refers to the means used to present information about selected products to the user, and includes the screen or interface of the user's terminal.

[0319] This invention is a product suggestion system that incorporates emotion recognition. It begins with the user inputting their product requests in natural language using a terminal. The terminal is equipped with an emotion engine that analyzes the user's voice tone, input speed, or facial expressions via camera footage, recognizing the user's emotional state in real time. This enables suggestions based on the user's psychological state.

[0320] The terminal sends the input request data and acquired sentiment data to the server. The server analyzes the input request using a dedicated natural language processing engine and extracts important keywords. At the same time, the sentiment data is also taken into consideration.

[0321] The server searches a database containing past suggestion information and customer data based on extracted keywords and sentiment data. Based on the retrieved information, a generative AI model evaluates and scores products using a machine learning algorithm. By incorporating sentiment data into the scoring, product suggestions are made that improve user comfort and satisfaction.

[0322] Ultimately, the server sends information about recommended products to the user's device and presents it to the user through the device's display. This allows the user to choose the most suitable product based on the information received and their emotional state.

[0323] Specific example:

[0324] For example, if a user types "I'm looking for a new laptop, but I want to stay within my budget," the emotion engine will sense the user's anxiety, and the server will prioritize recommending products that offer good value for money or focus on ease of use.

[0325] Example of a prompt:

[0326] "I'm looking for a new laptop, but I want to stay within my budget. I'd like something inexpensive but easy to use."

[0327] In this way, product proposals that improve the user experience are realized.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1:

[0330] The user uses a device to input product requests in natural language. The device receives these requests as text data. In addition, an emotion engine is used to analyze the user's voice tone and facial expressions in real time and obtain emotion data. The output of this step is natural language request data and user emotion data.

[0331] Step 2:

[0332] The device sends the acquired natural language request data and sentiment data to the server. The server receives this data. The received request data is analyzed using a natural language processing engine, and important keywords are extracted. As a result, keyword data is obtained. The sentiment data is stored along with the analysis results.

[0333] Step 3:

[0334] The server uses the extracted keywords to search past suggestion information and customer data within the database. Sentiment data is also considered during this search. The search output is a list of related product candidates.

[0335] Step 4:

[0336] The generative AI model receives a list of candidates and sentiment data as input and uses a machine learning algorithm to evaluate and score the products. Here, the system is specifically processed to improve the scores of products that better match the user's needs based on the sentiment data. The output of this step is a list of scored products.

[0337] Step 5:

[0338] The server sends a scored product list to the user's device. The device receives this information and displays it to the user in real time using a display device. The user can review and select products based on the displayed information. The output is information about the recommended products presented to the user.

[0339] (Application Example 2)

[0340] 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."

[0341] Traditional online shopping product recommendation systems typically provide recommendations based on explicit user requests, making it difficult to consider user emotions and underlying anxieties. As a result, users often find the suggested product selections unsatisfactory, which can diminish their willingness to purchase. In particular, users with concerns about budget and quality require more appropriate and reassuring product recommendations.

[0342] 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.

[0343] In this invention, the server includes an emotion engine means for analyzing the user's emotions, a database search means for retrieving past suggestion information and customer information, and a generative model device for selecting the optimal product using the retrieved information and the user's emotion data. This enables appropriate product suggestions according to the user's emotional state.

[0344] A "receiving device" is a terminal that receives requests from users in natural language and retrieves that information.

[0345] An "information processing device" is a computer device that analyzes input data and performs processing based on that analysis.

[0346] A "natural language processing means" is a software function that operates on an information processing device and analyzes natural language input by a user to understand the content of their request.

[0347] An "emotional engine" is a system that analyzes a user's emotions and determines their emotional state in real time based on data such as voice and facial expressions.

[0348] The "database search method" refers to a function for searching past proposal information and customer information to obtain relevant information.

[0349] A "generative model device" is a device that selects the optimal product and generates a proposal based on acquired information and analyzed sentiment data.

[0350] A "display device" is a device used to visually present selected product information to a user.

[0351] This invention consists of a terminal used by the user and a server that processes information. First, the user uses the terminal's receiving device to input their product requests in natural language. At that time, facial expression and voice data are collected through the terminal's camera and microphone and transmitted to an emotion engine means. This emotion engine means evaluates the user's emotional state in real time and transmits that information to the server as an analysis result.

[0352] The server analyzes user requests using natural language processing on an information processing device. Based on this analysis, it uses a database search to retrieve past proposal information and customer information and collect relevant data. In parallel, it also utilizes sentiment data sent from the sentiment engine.

[0353] Furthermore, the generative modeling system within the server integrates collected information and sentiment data to select the optimal product. This selection process utilizes a generative AI model, which performs product evaluation and scoring based on machine learning algorithms.

[0354] The selected product information is transmitted via the network to the terminal's display device and presented to the user. The user can visually confirm this information and receive product suggestions that are appropriate to their emotional state.

[0355] As a concrete example, consider a scenario where a user enters into the terminal, "I'm looking for a new laptop, but I want to stay within my budget." In this case, the server analyzes the user's anxieties and, considering the emotional data, prioritizes presenting products with excellent cost performance and positive reviews. If the user then provides a prompt such as, "I'm looking for something high-performance at an affordable price," the system will suggest products best suited to that request.

[0356] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0357] Step 1:

[0358] On the device, the user inputs their requests in natural language using a receiving device. The input data is in voice or text format, and the device's camera and microphone simultaneously record the user's facial expressions and voice tone. Based on this input, data representing the user's requests and emotions is generated.

[0359] Step 2:

[0360] The terminal sends the acquired user's natural language requests and sentiment data to the server. The server first uses natural language processing to analyze the request data. As a result of the analysis, keywords of the requests are extracted. Using these keywords and sentiment data as input, data is obtained to understand the user's purchasing intent.

[0361] Step 3:

[0362] The server uses a database search mechanism to retrieve past proposal information and customer information. This retrieves relevant product information that matches the request. The search results are then filtered based on the entered keywords and output as a candidate list.

[0363] Step 4:

[0364] The generative modeling system evaluates products using a candidate list of search results and sentiment data. A generative AI model is applied, and machine learning algorithms are used to score and rank each product. The output is a list of recommended products that best suit the user's emotional state.

[0365] Step 5:

[0366] The server transmits scored product information to the terminal via the network. The terminal's display shows recommended products to the user in real time. The user can make product selections based on the visualized information. This process provides the user with personalized product recommendations.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] [Third Embodiment]

[0371] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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".

[0383] In the system of this invention, the user begins by inputting their product request in natural language using a handheld terminal. The terminal receives this input and transmits the data to the server. The server analyzes the received data using a natural language processing engine to understand the content of the request.

[0384] The server then searches a database containing relevant past proposal information and customer data. Based on these search results, a generative model is activated to select the product best suited to the user's needs. Machine learning and AI algorithms are used for evaluation and scoring during the selection process.

[0385] The selected product information is transmitted to the user's terminal and presented to the user through the terminal's display. This allows the user to review the proposed products and make quick and accurate product recommendations in sales activities.

[0386] Specific example:

[0387] For example, a user might type "I want a new smartphone with a high-resolution camera" into their device. This input is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generation model selects the product that best fits the criteria from these candidates and sends information about "Smartphone X" to the device as a recommended product. The user can then use this information to make customer suggestions.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] The user uses a device to input product requests in natural language. The device collects and temporarily stores the entered data.

[0391] Step 2:

[0392] The terminal sends user input data to the server. During this process, the data is formatted according to communication standards and transmitted through a secure channel.

[0393] Step 3:

[0394] The server analyzes the received data. Using a natural language processing engine, it tokenizes the input text and extracts keywords and important phrases.

[0395] Step 4:

[0396] The server searches a database containing historical data and customer data related to product suggestions based on the extracted keywords. It then retrieves relevant product information.

[0397] Step 5:

[0398] The server uses a generative model to analyze product information retrieved from the database. An AI algorithm scores the suitability of each product and selects the most suitable product.

[0399] Step 6:

[0400] The server compiles information on the selected products and sends it back to the user's terminal. The transmitted data includes product suggestions that best suit the user's needs.

[0401] Step 7:

[0402] The terminal displays received product information, making it easy for the user to review. The user can then review the displayed product suggestions and make product selections and customer proposals based on them.

[0403] (Example 1)

[0404] 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."

[0405] The modern process of information acquisition and product selection presents a problem: users must independently collect and evaluate vast amounts of information, which is time-consuming and laborious. Furthermore, there is a lack of efficient methods for quickly finding the product best suited to the user's needs.

[0406] 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.

[0407] In this invention, the server includes a natural language processing means on an information processing device that analyzes input natural language, an information recording device search means that searches for past proposal content and customer information, and a generative artificial intelligence model means that selects the optimal product using the retrieved information. As a result, the optimal product can be quickly and accurately identified and presented simply by the user inputting their request using natural language.

[0408] "Input means" refers to a device that includes an information processing device for users to input requests in natural language.

[0409] "Natural language processing means" refers to a function on an information processing device that analyzes input natural language and understands the content of a request.

[0410] "Information recording device search means" refers to means on an information processing device for searching data that stores past proposals and customer information.

[0411] A "generative artificial intelligence model means" is a means that includes an algorithm for selecting the optimal product using machine learning methods.

[0412] "Display means" refers to a device or function used to present information about selected products to the user.

[0413] To implement this invention, the process begins with the user inputting their request in natural language using their handheld device. The device provides user-friendly input methods, such as voice input or text input. Next, the device receives the user's input and sends it to the server.

[0414] The server analyzes the input data using a natural language processing engine. This process can utilize natural language processing libraries such as Python's NLTK or spaCy. This allows the user's requests to be broken down into specific keywords, making it possible to understand their intent.

[0415] Next, the server searches a database containing past proposals and customer information. This is done using SQL queries to extract relevant information. Based on the extracted information, the server drives a generative artificial intelligence model. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and performs product evaluation and scoring.

[0416] Ultimately, the server sends back the optimal product information selected by the generation AI model to the terminal. The terminal then visually presents the selected product information to the user. This process allows the user to efficiently find products that meet their needs.

[0417] As a concrete example, a user enters "I want a new smartphone with a high-resolution camera" into their device. This information is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generative artificial intelligence model selects the product that best matches the user's criteria from the candidate products and sends information about "Smartphone X" to the device as a recommended product.

[0418] An example of a prompt message would be, "The user wants a smartphone with a high-resolution camera. Search the database for related products and recommend the best one." In this way, the user can receive product recommendations quickly and accurately.

[0419] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0420] Step 1:

[0421] The user enters their product request using natural language on the device. This input is converted into digital data using the device's voice recognition and text input functions. The entered data proceeds directly to the next processing step, so the process involves converting physical signals into information.

[0422] Step 2:

[0423] The terminal sends the input data received from the user to the server. The terminal uses HTTP requests to transfer the data. The transmitted data includes the user's requests, and the server receives this data and prepares it for the next processing step.

[0424] Step 3:

[0425] The server processes the received data using a natural language processing engine. Here, libraries such as Python's NLTK and spaCy are used to extract keywords from the input data and interpret their intent. Specifically, text data is tokenized, analyzed based on natural language structure, and relevant keywords are output.

[0426] Step 4:

[0427] The server searches the information storage device based on the extracted keywords. This process uses SQL queries to retrieve relevant data from past suggestions and customer information in the database. As a result of the search, information on products that match the keywords is output.

[0428] Step 5:

[0429] The server drives a generative AI model based on the search results. Here, machine learning algorithms are used to evaluate and score candidate products. Frameworks such as TensorFlow and PyTorch are used for this process, analyzing the product data received as input and selecting the most suitable product. The optimal product is then selected as the output.

[0430] Step 6:

[0431] The server sends information about the selected products back to the terminal. This information is transmitted via an API. The terminal receives this information, converts the output data into a visual format, and presents it to the user. This allows the user to confirm the selected products.

[0432] (Application Example 1)

[0433] 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."

[0434] In today's information processing environment, it is difficult for users to quickly and accurately identify the items they desire, especially when there are many options. Users need to express their needs appropriately, but even when natural language input is possible, there is insufficient support for making the best choice from the suggested products. As a result, the user experience is unsatisfactory, and further improvements are needed.

[0435] 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.

[0436] In this invention, the server includes an input means that includes an information processing device in which the user inputs requests in natural language, a natural language analysis means on an electronic processing machine that analyzes the input natural language, and an information retrieval means on an electronic processing machine that searches for past proposal information and customer information. This enables efficient information extraction based on the user's natural language input and the recommendation of appropriate items.

[0437] An "information processing device" is an electronic device that allows users to input requests in natural language and is responsible for transmitting the input information to a server.

[0438] "Natural language processing means" refers to a function or program on an electronic processing machine for analyzing input natural language, and is a means of extracting desired meanings and vocabulary from language.

[0439] "Information retrieval means" refers to a function on an electronic processing machine that searches an information repository containing past proposal information and customer information, and retrieves information related to the user's requests.

[0440] A "generative model means" is a computational program or device that uses machine learning algorithms or AI technology to select the optimal item based on information obtained from an information retrieval means.

[0441] "Display means" refers to an output device or its function for visually presenting information about selected items to the user.

[0442] "Speech recognition means" refers to an electronic function or program that converts voice input from a user into a string of characters and provides it to a natural language analysis means.

[0443] "Information provision means" refers to a program or device that provides a user with a list of items that match a user's request, based on the user's natural language request.

[0444] The system implementing this invention consists of an information processing device, a server, and related software components. The user inputs a request in natural language using the information processing device. The input can also be converted from speech to text by a speech recognition means. The converted natural language text is sent to the server.

[0445] On the server, software implemented as a natural language processing tool analyzes the text and extracts important keywords and requests. This analysis could potentially utilize the natural language processing library "Transformers." Based on the analysis results, an information retrieval tool searches a database on the electronic processing unit to obtain relevant data from past proposal information and customer information.

[0446] The acquired data is fed into a generative modeling system, where machine learning algorithms and AI technology select the most suitable items. The selected items are transmitted to an information processing device via a display system and presented to the user. The user can then use this information to select products that meet their needs.

[0447] For example, if a user enters the prompt "I'm looking for waterproof sneakers," the system analyzes and extracts keywords such as "waterproof" and "sneakers," then displays a list of related products. This allows the user to efficiently find products that meet their needs. In this way, the prompt is received by the generating AI model, and information is provided.

[0448] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0449] Step 1:

[0450] The user inputs their request in natural language using an information processing device. Input can be via a text form or speech recognition. In the case of speech, the speech recognition means converts the speech to text. The output of this step is text data representing the user's request.

[0451] Step 2:

[0452] The terminal sends the input text data to the server. Upon receiving this text data, the server analyzes it using natural language processing (NLP) tools. Specifically, it uses a natural language processing library to extract keywords and the meaning of requests from the text. The output of this step is the extracted keywords and semantic information.

[0453] Step 3:

[0454] The server searches the database using information retrieval tools. Using the extracted keywords as clues, the server retrieves relevant data, including past proposal information and customer information. This process utilizes a database search algorithm for efficient information retrieval. The output of this step is the relevant data.

[0455] Step 4:

[0456] The server supplies relevant data to the generative model and uses a machine learning algorithm to select the optimal item. This is a process in which the AI ​​evaluation model scores each candidate item and selects the best item based on those scores. The output of this step is the selected item information.

[0457] Step 5:

[0458] The selected item information is transmitted to the user's information processing device via a display device. The user can view the provided list on the terminal and see detailed information about the items. In this step, it is ensured that the data is displayed accurately and quickly in the user interface. The output of this step is item information presented visually to the user.

[0459] 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.

[0460] In the emotion recognition system of the present invention, the user inputs product requests in natural language through a terminal. The terminal has an emotion engine that analyzes the user's emotions in real time from the tone of the user's voice, input speed, or facial expressions using camera images.

[0461] The device sends this emotion data and request data to the server. The server analyzes the received natural language data and extracts the necessary keywords. At this point, it also takes into account the user's emotion information received from the emotion engine to further optimize the suggested products.

[0462] The server searches past suggestion databases and customer data based on the extracted information and collects relevant products. The generative model uses AI algorithms to analyze all information, including sentiment data, and scores recommended products. Scoring using sentiment information enables product suggestions that are tailored to enhance user comfort and satisfaction.

[0463] The generated recommended product information is sent from the server to the user's terminal and presented to the user through a display device. Based on this information, the user can select the most suitable product according to their emotional state and engage in suggestion activities.

[0464] Specific example:

[0465] For example, if a user enters "I'm looking for a new laptop, but I want to stay within my budget," and the emotion engine simultaneously detects the user's anxiety, the server will use this emotional information to prioritize recommending cost-effective products. Furthermore, by offering product suggestions that focus on "ease of use," it is expected that the user's anxiety will be alleviated.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] The user inputs their product requests in natural language using their device. Simultaneously, an emotion engine built into the device analyzes the user's emotions based on their voice tone and facial expression data during input.

[0469] Step 2:

[0470] The device sends analyzed natural language data and sentiment data to the server. The transmitted data includes the user's desired requirements and current sentiment state.

[0471] Step 3:

[0472] The server uses a natural language processing engine to analyze the received requests and identify key keywords. In this process, sentiment data is also considered to determine which suggestions are most effective.

[0473] Step 4:

[0474] The server searches past suggestion databases and customer databases based on extracted keywords and sentiment data. It collects highly relevant product information and creates a list of candidates.

[0475] Step 5:

[0476] The server uses a generative model to select the best product from the collected product candidates. Sentimental data influences the evaluation and scoring of recommended products, ensuring that the product best matches the user's emotions.

[0477] Step 6:

[0478] The server sends information about the selected products to the user's device. Detailed information and reasons for recommendations may be included to ensure that emotionally sensitive suggestions are conveyed to the user.

[0479] Step 7:

[0480] The device displays received product information and prompts the user to make appropriate choices. Based on these suggestions, which take into account the user's emotional state, the user can then make a product selection.

[0481] (Example 2)

[0482] 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."

[0483] Traditional product selection systems have a problem in that they do not adequately improve user satisfaction because they make suggestions without considering the user's emotions. It is necessary to make product suggestions that are more in line with user needs by incorporating user emotions into the suggestions.

[0484] 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.

[0485] In this invention, the server includes information processing means for analyzing input natural language and sentiment data, information retrieval means for searching past suggestion information and customer data, and generative modeling means for selecting the optimal product using the retrieved information and sentiment data. This makes it possible to suggest products that take the user's emotions into consideration, thereby improving user satisfaction.

[0486] "Natural language" refers to the language that humans use in their daily lives, and includes the sentences and phrases that users input to convey their intentions and requests to machines.

[0487] "Emotional state" refers to the user's inner psychological state and is derived from information analyzed from the user's tone of voice, facial expressions, and other factors.

[0488] A "terminal" is an electronic device used by users to input or receive information, and may include an emotion analysis engine.

[0489] "Information processing means" refers to server-side functions that analyze natural language and emotional data entered by users to understand their meaning and emotions.

[0490] "Information retrieval means" refers to a function that runs on a server to search past proposal information and customer data and retrieve related information.

[0491] "Generative modeling means" refers to server-side functions, including algorithms and machine learning models, for selecting the optimal product based on acquired information and sentiment data.

[0492] "Display means" refers to the means used to present information about selected products to the user, and includes the screen or interface of the user's terminal.

[0493] This invention is a product suggestion system that incorporates emotion recognition. It begins with the user inputting their product requests in natural language using a terminal. The terminal is equipped with an emotion engine that analyzes the user's voice tone, input speed, or facial expressions via camera footage, recognizing the user's emotional state in real time. This enables suggestions based on the user's psychological state.

[0494] The terminal sends the input request data and acquired sentiment data to the server. The server analyzes the input request using a dedicated natural language processing engine and extracts important keywords. At the same time, the sentiment data is also taken into consideration.

[0495] The server searches a database containing past suggestion information and customer data based on extracted keywords and sentiment data. Based on the retrieved information, a generative AI model evaluates and scores products using a machine learning algorithm. By incorporating sentiment data into the scoring, product suggestions are made that improve user comfort and satisfaction.

[0496] Ultimately, the server sends information about recommended products to the user's device and presents it to the user through the device's display. This allows the user to choose the most suitable product based on the information received and their emotional state.

[0497] Specific example:

[0498] For example, if a user types "I'm looking for a new laptop, but I want to stay within my budget," the emotion engine will sense the user's anxiety, and the server will prioritize recommending products that offer good value for money or focus on ease of use.

[0499] Example of a prompt:

[0500] "I'm looking for a new laptop, but I want to stay within my budget. I'd like something inexpensive but easy to use."

[0501] In this way, product proposals that improve the user experience are realized.

[0502] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0503] Step 1:

[0504] The user uses a device to input product requests in natural language. The device receives these requests as text data. In addition, an emotion engine is used to analyze the user's voice tone and facial expressions in real time and obtain emotion data. The output of this step is natural language request data and user emotion data.

[0505] Step 2:

[0506] The device sends the acquired natural language request data and sentiment data to the server. The server receives this data. The received request data is analyzed using a natural language processing engine, and important keywords are extracted. As a result, keyword data is obtained. The sentiment data is stored along with the analysis results.

[0507] Step 3:

[0508] The server uses the extracted keywords to search past suggestion information and customer data within the database. Sentiment data is also considered during this search. The search output is a list of related product candidates.

[0509] Step 4:

[0510] The generative AI model receives a list of candidates and sentiment data as input and uses a machine learning algorithm to evaluate and score the products. Here, the system is specifically processed to improve the scores of products that better match the user's needs based on the sentiment data. The output of this step is a list of scored products.

[0511] Step 5:

[0512] The server sends a scored product list to the user's device. The device receives this information and displays it to the user in real time using a display device. The user can review and select products based on the displayed information. The output is information about the recommended products presented to the user.

[0513] (Application Example 2)

[0514] 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."

[0515] Traditional online shopping product recommendation systems typically provide recommendations based on explicit user requests, making it difficult to consider user emotions and underlying anxieties. As a result, users often find the suggested product selections unsatisfactory, which can diminish their willingness to purchase. In particular, users with concerns about budget and quality require more appropriate and reassuring product recommendations.

[0516] 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.

[0517] In this invention, the server includes an emotion engine means for analyzing the user's emotions, a database search means for searching past suggestion information and customer information, and a generative model device for selecting the optimal product using the retrieved information and the user's emotion data. This enables appropriate product suggestions according to the user's emotional state.

[0518] A "receiving device" is a terminal that receives requests from users in natural language and retrieves that information.

[0519] An "information processing device" is a computer device that analyzes input data and performs processing based on that analysis.

[0520] A "natural language processing means" is a software function that operates on an information processing device and analyzes natural language input by a user to understand the content of their request.

[0521] An "emotional engine" is a system that analyzes a user's emotions and determines their emotional state in real time based on data such as voice and facial expressions.

[0522] The "database search method" refers to a function for searching past proposal information and customer information to obtain relevant information.

[0523] A "generative model device" is a device that selects the optimal product and generates a proposal based on acquired information and analyzed sentiment data.

[0524] A "display device" is a device used to visually present selected product information to a user.

[0525] This invention consists of a terminal used by the user and a server that processes information. First, the user uses the terminal's receiving device to input their product requests in natural language. At that time, facial expression and voice data are collected through the terminal's camera and microphone and transmitted to an emotion engine means. This emotion engine means evaluates the user's emotional state in real time and transmits that information to the server as an analysis result.

[0526] The server analyzes user requests using natural language processing on an information processing device. Based on this analysis, it uses a database search to retrieve past proposal information and customer information and collect relevant data. In parallel, it also utilizes sentiment data sent from the sentiment engine.

[0527] Furthermore, the generative modeling system within the server integrates collected information and sentiment data to select the optimal product. This selection process utilizes a generative AI model, which performs product evaluation and scoring based on machine learning algorithms.

[0528] The selected product information is transmitted via the network to the terminal's display device and presented to the user. The user can visually confirm this information and receive product suggestions that are appropriate to their emotional state.

[0529] As a concrete example, consider a scenario where a user enters into the terminal, "I'm looking for a new laptop, but I want to stay within my budget." In this case, the server analyzes the user's anxieties and, considering the emotional data, prioritizes presenting products with excellent cost performance and positive reviews. If the user then provides a prompt such as, "I'm looking for something high-performance at an affordable price," the system will suggest products best suited to that request.

[0530] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0531] Step 1:

[0532] On the device, the user inputs their requests in natural language using a receiving device. The input data is in voice or text format, and the device's camera and microphone simultaneously record the user's facial expressions and voice tone. Based on this input, data representing the user's requests and emotions is generated.

[0533] Step 2:

[0534] The terminal sends the acquired user's natural language requests and sentiment data to the server. The server first uses natural language processing to analyze the request data. As a result of the analysis, keywords of the requests are extracted. Using these keywords and sentiment data as input, data is obtained to understand the user's purchasing intent.

[0535] Step 3:

[0536] The server uses a database search mechanism to retrieve past proposal information and customer information. This retrieves relevant product information that matches the request. The search results are then filtered based on the entered keywords and output as a candidate list.

[0537] Step 4:

[0538] The generative modeling system evaluates products using a candidate list of search results and sentiment data. A generative AI model is applied, and machine learning algorithms are used to score and rank each product. The output is a list of recommended products that best suit the user's emotional state.

[0539] Step 5:

[0540] The server transmits scored product information to the terminal via the network. The terminal's display shows recommended products to the user in real time. The user can make product selections based on the visualized information. This process provides the user with personalized product recommendations.

[0541] 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.

[0542] 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.

[0543] 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.

[0544] [Fourth Embodiment]

[0545] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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.

[0557] 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".

[0558] In the system of this invention, the user begins by inputting their product request in natural language using a handheld terminal. The terminal receives this input and transmits the data to the server. The server analyzes the received data using a natural language processing engine to understand the content of the request.

[0559] The server then searches a database containing relevant past proposal information and customer data. Based on these search results, a generative model is activated to select the product best suited to the user's needs. Machine learning and AI algorithms are used for evaluation and scoring during the selection process.

[0560] The selected product information is transmitted to the user's terminal and presented to the user through the terminal's display. This allows the user to review the proposed products and make quick and accurate product recommendations in sales activities.

[0561] Specific example:

[0562] For example, a user might type "I want a new smartphone with a high-resolution camera" into their device. This input is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generation model selects the product that best fits the criteria from these candidates and sends information about "Smartphone X" to the device as a recommended product. The user can then use this information to make customer suggestions.

[0563] The following describes the processing flow.

[0564] Step 1:

[0565] The user uses a device to input product requests in natural language. The device collects and temporarily stores the entered data.

[0566] Step 2:

[0567] The terminal sends user input data to the server. During this process, the data is formatted according to communication standards and transmitted through a secure channel.

[0568] Step 3:

[0569] The server analyzes the received data. Using a natural language processing engine, it tokenizes the input text and extracts keywords and important phrases.

[0570] Step 4:

[0571] The server searches a database containing historical data and customer data related to product suggestions based on the extracted keywords. It then retrieves relevant product information.

[0572] Step 5:

[0573] The server uses a generative model to analyze product information retrieved from the database. An AI algorithm scores the suitability of each product and selects the most suitable product.

[0574] Step 6:

[0575] The server compiles information on the selected products and sends it back to the user's terminal. The transmitted data includes product suggestions that best suit the user's needs.

[0576] Step 7:

[0577] The terminal displays received product information, making it easy for the user to review. The user can then review the displayed product suggestions and make product selections and customer proposals based on them.

[0578] (Example 1)

[0579] 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".

[0580] The modern process of information acquisition and product selection presents a problem: users must independently collect and evaluate vast amounts of information, which is time-consuming and laborious. Furthermore, there is a lack of efficient methods for quickly finding the product best suited to the user's needs.

[0581] 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.

[0582] In this invention, the server includes a natural language processing means on an information processing device that analyzes input natural language, an information recording device search means that searches for past proposal content and customer information, and a generative artificial intelligence model means that selects the optimal product using the retrieved information. As a result, the optimal product can be quickly and accurately identified and presented simply by the user inputting their request using natural language.

[0583] "Input means" refers to a device that includes an information processing device for users to input requests in natural language.

[0584] "Natural language processing means" refers to a function on an information processing device that analyzes input natural language and understands the content of a request.

[0585] "Information recording device search means" refers to means on an information processing device for searching data that stores past proposals and customer information.

[0586] A "generative artificial intelligence model means" is a means that includes an algorithm for selecting the optimal product using machine learning methods.

[0587] "Display means" refers to a device or function used to present information about selected products to the user.

[0588] To implement this invention, the process begins with the user inputting their request in natural language using their handheld device. The device provides user-friendly input methods, such as voice input or text input. Next, the device receives the user's input and sends it to the server.

[0589] The server analyzes the input data using a natural language processing engine. This process can utilize natural language processing libraries such as Python's NLTK or spaCy. This allows the user's requests to be broken down into specific keywords, making it possible to understand their intent.

[0590] Next, the server searches a database containing past proposals and customer information. This is done using SQL queries to extract relevant information. Based on the extracted information, the server drives a generative artificial intelligence model. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and performs product evaluation and scoring.

[0591] Ultimately, the server sends back the optimal product information selected by the generation AI model to the terminal. The terminal then visually presents the selected product information to the user. This process allows the user to efficiently find products that meet their needs.

[0592] As a concrete example, a user enters "I want a new smartphone with a high-resolution camera" into their device. This information is sent to a server, where a natural language processing engine extracts the keywords "high-resolution camera" and "new smartphone." The server then searches its database to identify relevant products. The generative artificial intelligence model selects the product that best matches the user's criteria from the candidate products and sends information about "Smartphone X" to the device as a recommended product.

[0593] An example of a prompt message would be, "The user wants a smartphone with a high-resolution camera. Search the database for related products and recommend the best one." In this way, the user can receive product recommendations quickly and accurately.

[0594] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0595] Step 1:

[0596] The user enters their product request using natural language on the device. This input is converted into digital data using the device's voice recognition and text input functions. The entered data proceeds directly to the next processing step, so the process involves converting physical signals into information.

[0597] Step 2:

[0598] The terminal sends the input data received from the user to the server. The terminal uses HTTP requests to transfer the data. The transmitted data includes the user's requests, and the server receives this data and prepares it for the next processing step.

[0599] Step 3:

[0600] The server processes the received data using a natural language processing engine. Here, libraries such as Python's NLTK and spaCy are used to extract keywords from the input data and interpret their intent. Specifically, text data is tokenized, analyzed based on natural language structure, and relevant keywords are output.

[0601] Step 4:

[0602] The server searches the information storage device based on the extracted keywords. This process uses SQL queries to retrieve relevant data from past suggestions and customer information in the database. As a result of the search, information on products that match the keywords is output.

[0603] Step 5:

[0604] The server drives a generative AI model based on the search results. Here, machine learning algorithms are used to evaluate and score candidate products. Frameworks such as TensorFlow and PyTorch are used for this process, analyzing the product data received as input and selecting the most suitable product. The optimal product is then selected as the output.

[0605] Step 6:

[0606] The server sends information about the selected products back to the terminal. This information is transmitted via an API. The terminal receives this information, converts the output data into a visual format, and presents it to the user. This allows the user to confirm the selected products.

[0607] (Application Example 1)

[0608] 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".

[0609] In today's information processing environment, it is difficult for users to quickly and accurately identify the items they desire, especially when there are many options. Users need to express their needs appropriately, but even when natural language input is possible, there is insufficient support for making the best choice from the suggested products. As a result, the user experience is unsatisfactory, and further improvements are needed.

[0610] 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.

[0611] In this invention, the server includes an input means that includes an information processing device in which the user inputs requests in natural language, a natural language analysis means on an electronic processing machine that analyzes the input natural language, and an information retrieval means on an electronic processing machine that searches for past proposal information and customer information. This enables efficient information extraction based on the user's natural language input and the recommendation of appropriate items.

[0612] An "information processing device" is an electronic device that allows users to input requests in natural language and is responsible for transmitting the input information to a server.

[0613] "Natural language processing means" refers to a function or program on an electronic processing machine for analyzing input natural language, and is a means of extracting desired meanings and vocabulary from language.

[0614] "Information retrieval means" refers to a function on an electronic processing machine that searches an information repository containing past proposal information and customer information, and retrieves information related to the user's requests.

[0615] A "generative model means" is a computational program or device that uses machine learning algorithms or AI technology to select the optimal item based on information obtained from an information retrieval means.

[0616] "Display means" refers to an output device or its function for visually presenting information about selected items to the user.

[0617] "Speech recognition means" refers to an electronic function or program that converts voice input from a user into a string of characters and provides it to a natural language analysis means.

[0618] "Information provision means" refers to a program or device that provides a user with a list of items that match a user's request, based on the user's natural language request.

[0619] The system implementing this invention consists of an information processing device, a server, and related software components. The user inputs a request in natural language using the information processing device. The input can also be converted from speech to text by a speech recognition means. The converted natural language text is sent to the server.

[0620] On the server, software implemented as a natural language processing tool analyzes the text and extracts important keywords and requests. This analysis could potentially utilize the natural language processing library "Transformers." Based on the analysis results, an information retrieval tool searches a database on the electronic processing unit to obtain relevant data from past proposal information and customer information.

[0621] The acquired data is fed into a generative modeling system, where machine learning algorithms and AI technology select the most suitable items. The selected items are transmitted to an information processing device via a display system and presented to the user. The user can then use this information to select products that meet their needs.

[0622] For example, if a user enters the prompt "I'm looking for waterproof sneakers," the system analyzes and extracts keywords such as "waterproof" and "sneakers," then displays a list of related products. This allows the user to efficiently find products that meet their needs. In this way, the prompt is received by the generating AI model, and information is provided.

[0623] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0624] Step 1:

[0625] The user inputs their request in natural language using an information processing device. Input can be via a text form or speech recognition. In the case of speech, the speech recognition means converts the speech to text. The output of this step is text data representing the user's request.

[0626] Step 2:

[0627] The terminal sends the input text data to the server. Upon receiving this text data, the server analyzes it using natural language processing (NLP) tools. Specifically, it uses a natural language processing library to extract keywords and the meaning of requests from the text. The output of this step is the extracted keywords and semantic information.

[0628] Step 3:

[0629] The server searches the database using information retrieval tools. Using the extracted keywords as clues, the server retrieves relevant data, including past proposal information and customer information. This process utilizes a database search algorithm for efficient information retrieval. The output of this step is the relevant data.

[0630] Step 4:

[0631] The server supplies relevant data to the generative model and uses a machine learning algorithm to select the optimal item. This is a process in which the AI ​​evaluation model scores each candidate item and selects the optimal item based on those scores. The output of this step is the selected item information.

[0632] Step 5:

[0633] The selected item information is transmitted to the user's information processing device via a display device. The user can view the provided list on the terminal and see detailed information about the items. In this step, it is ensured that the data is displayed accurately and quickly in the user interface. The output of this step is item information presented visually to the user.

[0634] 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.

[0635] In the emotion recognition system of the present invention, the user inputs product requests in natural language through a terminal. The terminal has an emotion engine that analyzes the user's emotions in real time from the tone of the user's voice, input speed, or facial expressions using camera images.

[0636] The device sends this emotion data and request data to the server. The server analyzes the received natural language data and extracts the necessary keywords. At this point, it also takes into account the user's emotion information received from the emotion engine to further optimize the suggested products.

[0637] The server searches past suggestion databases and customer data based on the extracted information and collects relevant products. The generative model uses AI algorithms to analyze all information, including sentiment data, and scores recommended products. Scoring using sentiment information enables product suggestions that are tailored to enhance user comfort and satisfaction.

[0638] The generated recommended product information is sent from the server to the user's terminal and presented to the user through a display device. Based on this information, the user can select the most suitable product according to their emotional state and engage in suggestion activities.

[0639] Specific example:

[0640] For example, if a user enters "I'm looking for a new laptop, but I want to stay within my budget," and the emotion engine simultaneously detects the user's anxiety, the server will use this emotional information to prioritize recommending cost-effective products. Furthermore, by offering product suggestions that focus on "ease of use," it is expected that the user's anxiety will be alleviated.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The user inputs their product requests in natural language using their device. Simultaneously, an emotion engine built into the device analyzes the user's emotions based on their voice tone and facial expression data during input.

[0644] Step 2:

[0645] The device sends analyzed natural language data and sentiment data to the server. The transmitted data includes the user's desired requirements and current sentiment state.

[0646] Step 3:

[0647] The server uses a natural language processing engine to analyze the received requests and identify key keywords. In this process, sentiment data is also considered to determine which suggestions are most effective.

[0648] Step 4:

[0649] The server searches past suggestion databases and customer databases based on extracted keywords and sentiment data. It collects highly relevant product information and creates a list of candidates.

[0650] Step 5:

[0651] The server uses a generative model to select the best product from the collected product candidates. Sentimental data influences the evaluation and scoring of recommended products, ensuring that the product best matches the user's emotions.

[0652] Step 6:

[0653] The server sends information about the selected products to the user's device. Detailed information and reasons for recommendations may be included to ensure that emotionally sensitive suggestions are conveyed to the user.

[0654] Step 7:

[0655] The device displays received product information and prompts the user to make appropriate choices. Based on these suggestions, which take into account the user's emotional state, the user can then make a product selection.

[0656] (Example 2)

[0657] 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".

[0658] Traditional product selection systems have a problem in that they do not adequately improve user satisfaction because they make suggestions without considering the user's emotions. It is necessary to make product suggestions that are more in line with user needs by incorporating user emotions into the suggestions.

[0659] 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.

[0660] In this invention, the server includes information processing means for analyzing input natural language and sentiment data, information retrieval means for searching past suggestion information and customer data, and generative modeling means for selecting the optimal product using the retrieved information and sentiment data. This makes it possible to suggest products that take the user's emotions into consideration, thereby improving user satisfaction.

[0661] "Natural language" refers to the language that humans use in their daily lives, and includes the sentences and phrases that users input to convey their intentions and requests to machines.

[0662] "Emotional state" refers to the user's inner psychological state and is derived from information analyzed from the user's tone of voice, facial expressions, and other factors.

[0663] A "terminal" is an electronic device used by users to input or receive information, and may include an emotion analysis engine.

[0664] "Information processing means" refers to server-side functions that analyze natural language and emotional data entered by users to understand their meaning and emotions.

[0665] "Information retrieval means" refers to a function that runs on a server to search past proposal information and customer data and retrieve related information.

[0666] "Generative modeling means" refers to server-side functions, including algorithms and machine learning models, for selecting the optimal product based on acquired information and sentiment data.

[0667] "Display means" refers to the means used to present information about selected products to the user, and includes the screen or interface of the user's terminal.

[0668] This invention is a product suggestion system that incorporates emotion recognition. It begins with the user inputting their product requests in natural language using a terminal. The terminal is equipped with an emotion engine that analyzes the user's voice tone, input speed, or facial expressions via camera footage, recognizing the user's emotional state in real time. This enables suggestions based on the user's psychological state.

[0669] The terminal sends the input request data and acquired sentiment data to the server. The server analyzes the input request using a dedicated natural language processing engine and extracts important keywords. At the same time, the sentiment data is also taken into consideration.

[0670] The server searches a database containing past suggestion information and customer data based on extracted keywords and sentiment data. Based on the retrieved information, a generative AI model evaluates and scores products using a machine learning algorithm. By incorporating sentiment data into the scoring, product suggestions are made that improve user comfort and satisfaction.

[0671] Ultimately, the server sends information about recommended products to the user's device and presents it to the user through the device's display. This allows the user to choose the most suitable product based on the information received and their emotional state.

[0672] Specific example:

[0673] For example, if a user types "I'm looking for a new laptop, but I want to stay within my budget," the emotion engine will sense the user's anxiety, and the server will prioritize recommending products that offer good value for money or focus on ease of use.

[0674] Example of a prompt:

[0675] "I'm looking for a new laptop, but I want to stay within my budget. I'd like something inexpensive but easy to use."

[0676] In this way, product proposals that improve the user experience are realized.

[0677] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0678] Step 1:

[0679] The user uses a device to input product requests in natural language. The device receives these requests as text data. In addition, an emotion engine is used to analyze the user's voice tone and facial expressions in real time and obtain emotion data. The output of this step is natural language request data and user emotion data.

[0680] Step 2:

[0681] The device sends the acquired natural language request data and sentiment data to the server. The server receives this data. The received request data is analyzed using a natural language processing engine, and important keywords are extracted. As a result, keyword data is obtained. The sentiment data is stored along with the analysis results.

[0682] Step 3:

[0683] The server uses the extracted keywords to search past suggestion information and customer data within the database. Sentiment data is also considered during this search. The search output is a list of related product candidates.

[0684] Step 4:

[0685] The generative AI model receives a list of candidates and sentiment data as input and uses a machine learning algorithm to evaluate and score the products. Here, the system is specifically processed to improve the scores of products that better match the user's needs based on the sentiment data. The output of this step is a list of scored products.

[0686] Step 5:

[0687] The server sends a scored product list to the user's device. The device receives this information and displays it to the user in real time using a display device. The user can review and select products based on the displayed information. The output is information about the recommended products presented to the user.

[0688] (Application Example 2)

[0689] 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".

[0690] Traditional online shopping product recommendation systems typically provide recommendations based on explicit user requests, making it difficult to consider user emotions and underlying anxieties. As a result, users often find the suggested product selections unsatisfactory, which can diminish their willingness to purchase. In particular, users with concerns about budget and quality require more appropriate and reassuring product recommendations.

[0691] 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.

[0692] In this invention, the server includes an emotion engine means for analyzing the user's emotions, a database search means for retrieving past suggestion information and customer information, and a generative model device for selecting the optimal product using the retrieved information and the user's emotion data. This enables appropriate product suggestions according to the user's emotional state.

[0693] A "receiving device" is a terminal that receives requests from users in natural language and retrieves that information.

[0694] An "information processing device" is a computer device that analyzes input data and performs processing based on that analysis.

[0695] A "natural language processing means" is a software function that operates on an information processing device and analyzes natural language input by a user to understand the content of their request.

[0696] An "emotional engine" is a system that analyzes a user's emotions and determines their emotional state in real time based on data such as voice and facial expressions.

[0697] The "database search method" refers to a function for searching past proposal information and customer information to obtain relevant information.

[0698] A "generative model device" is a device that selects the optimal product and generates a proposal based on acquired information and analyzed sentiment data.

[0699] A "display device" is a device used to visually present selected product information to a user.

[0700] This invention consists of a terminal used by the user and a server that processes information. First, the user uses the terminal's receiving device to input their product requests in natural language. At that time, facial expression and voice data are collected through the terminal's camera and microphone and transmitted to an emotion engine means. This emotion engine means evaluates the user's emotional state in real time and transmits that information to the server as an analysis result.

[0701] The server analyzes user requests using natural language processing on an information processing device. Based on this analysis, it uses a database search to retrieve past proposal information and customer information and collect relevant data. In parallel, it also utilizes sentiment data sent from the sentiment engine.

[0702] Furthermore, the generative modeling system within the server integrates collected information and sentiment data to select the optimal product. This selection process utilizes a generative AI model, which performs product evaluation and scoring based on machine learning algorithms.

[0703] The selected product information is transmitted via the network to the terminal's display device and presented to the user. The user can visually confirm this information and receive product suggestions that are appropriate to their emotional state.

[0704] As a concrete example, consider a scenario where a user enters into the terminal, "I'm looking for a new laptop, but I want to stay within my budget." In this case, the server analyzes the user's anxieties and, considering the emotional data, prioritizes presenting products with excellent cost performance and positive reviews. If the user then provides a prompt such as, "I'm looking for something high-performance at an affordable price," the system will suggest products best suited to that request.

[0705] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0706] Step 1:

[0707] On the device, the user inputs their requests in natural language using a receiving device. The input data is in voice or text format, and the device's camera and microphone simultaneously record the user's facial expressions and voice tone. Based on this input, data representing the user's requests and emotions is generated.

[0708] Step 2:

[0709] The terminal sends the acquired user's natural language requests and sentiment data to the server. The server first uses natural language processing to analyze the request data. As a result of the analysis, keywords of the requests are extracted. Using these keywords and sentiment data as input, data is obtained to understand the user's purchasing intent.

[0710] Step 3:

[0711] The server uses a database search mechanism to retrieve past proposal information and customer information. This retrieves relevant product information that matches the request. The search results are then filtered based on the entered keywords and output as a candidate list.

[0712] Step 4:

[0713] The generative modeling system evaluates products using a candidate list of search results and sentiment data. A generative AI model is applied, and machine learning algorithms are used to score and rank each product. The output is a list of recommended products that best suit the user's emotional state.

[0714] Step 5:

[0715] The server transmits scored product information to the terminal via the network. The terminal's display shows recommended products to the user in real time. The user can make product selections based on the visualized information. This process provides the user with personalized product recommendations.

[0716] 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.

[0717] 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.

[0718] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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."

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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 as being incorporated by reference.

[0737] The following is further disclosed regarding the embodiments described above.

[0738] (Claim 1)

[0739] An input method including a terminal in which the user enters requests in natural language,

[0740] A natural language processing system on a server that analyzes the input natural language,

[0741] A database search means on a server for searching past proposal information and customer data,

[0742] A generative model means for selecting the optimal product using the retrieved information,

[0743] A display means for presenting information about the selected products to the user,

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, characterized in that the generative model means performs product evaluation and scoring based on a machine learning algorithm.

[0747] (Claim 3)

[0748] The system according to claim 1, characterized in that the display means displays recommended products in real time on the user's terminal.

[0749] "Example 1"

[0750] (Claim 1)

[0751] An input means including an information processing device in which the user inputs requests in natural language,

[0752] A natural language processing means on an information processing device that analyzes input natural language,

[0753] Information recording device search means on an information processing device for searching past proposals and customer information,

[0754] A generative artificial intelligence model means for selecting the optimal product using the retrieved information,

[0755] A display means for presenting information about the selected products to the user,

[0756] A system that includes this.

[0757] (Claim 2)

[0758] The system according to claim 1, characterized in that the generative artificial intelligence model means performs evaluation and quantification of items based on a machine learning method.

[0759] (Claim 3)

[0760] The system according to claim 1, characterized in that the display means immediately displays recommended products on the user's information processing device.

[0761] "Application Example 1"

[0762] (Claim 1)

[0763] An input means including an information processing device in which the user inputs requests in natural language,

[0764] A natural language analysis means on an electronic processing machine that analyzes input natural language,

[0765] Information retrieval means on an electronic processing machine for searching past proposal information and customer information,

[0766] A generative model means for selecting the optimal item using the retrieved information,

[0767] A display means for presenting information about the selected items to the user,

[0768] Furthermore, a speech recognition means that enables voice input for natural language requests entered by the user,

[0769] An information provision means that provides a list of items that match a user's request based on that request in natural language,

[0770] A system that includes this.

[0771] (Claim 2)

[0772] The system according to claim 1, characterized in that the generation model means evaluates and scores items based on a machine learning algorithm.

[0773] (Claim 3)

[0774] The system according to claim 1, characterized in that the display means displays recommended items in real time on the user's information processing device.

[0775] "Example 2 of combining an emotion engine"

[0776] (Claim 1)

[0777] An input means including a terminal that allows the user to input requests in natural language and analyzes their emotional state,

[0778] A server-based information processing system that analyzes input natural language and sentiment data,

[0779] A server-based information retrieval method for searching past proposal information and customer data,

[0780] A generative model means for selecting the optimal product using retrieved information and sentiment data,

[0781] A display means for presenting information about the selected products to the user,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, characterized in that the generative model means evaluates and scores products based on a machine learning algorithm and takes sentiment data into consideration.

[0785] (Claim 3)

[0786] The system according to claim 1, characterized in that the display means displays recommended products in real time on the user's terminal and makes recommendations generated based on sentiment information.

[0787] "Application example 2 when combining with an emotional engine"

[0788] (Claim 1)

[0789] A receiving device in which the user inputs requests in natural language,

[0790] A natural language analysis means on an information processing device that analyzes input natural language,

[0791] An emotion engine that analyzes user emotions,

[0792] A database search means on an information processing device for searching past proposal information and customer information,

[0793] A generative model device that selects the optimal product using searched information and user sentiment data,

[0794] A display device that presents information about the selected product to the user,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, characterized in that the generative model device evaluates and scores products including sentiment data based on a machine learning algorithm.

[0798] (Claim 3)

[0799] The system according to claim 1, characterized in that the display device presents recommended products appropriate to the user's emotional state in real time on the user's terminal. [Explanation of Symbols]

[0800] 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. An input method including a terminal in which the user enters requests in natural language, A natural language processing system on a server that analyzes the input natural language, A database search means on a server for searching past proposal information and customer data, A generative model means for selecting the optimal product using the retrieved information, A display means for presenting information about the selected products to the user, A system that includes this.

2. The system according to claim 1, characterized in that the generative model means performs product evaluation and scoring based on a machine learning algorithm.

3. The system according to claim 1, characterized in that the display means displays recommended products in real time on the user's terminal.

Images