system

Abstract

We provide the system. [Solution] Means of collecting personal purchasing activity data, A means for analyzing collected purchasing activity data and generating personalized purchasing suggestions, A means of providing individuals with analyzed suggestions and real-time sales promotion information, A means of two-way communication with an individual using voice and text, 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]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In personal purchasing activities, it is difficult to make an optimal choice from a vast amount of product information and complex sales promotion information. Also, there is a lack of proposals according to an individual's purchasing pattern and preference, and an improvement in the purchasing experience is required. Furthermore, due to the lack of real-time information provision and two-way communication means via an interface, an efficient and individualized purchasing support system is needed.

Means for Solving the Problems

[0005] This invention provides a means for collecting individual purchasing activity data and generating optimal purchasing suggestions by analyzing that data. Furthermore, it enhances the purchasing experience by providing the analyzed suggestions and sales promotion information to individuals in real time. Additionally, by utilizing two-way communication methods using voice and text, the invention realizes a system that quickly provides the information individuals need, enabling efficient decision-making.

[0006] "Purchase activity data" refers to a series of data generated when an individual purchases a product or service, including information such as product name, price, and date and time of purchase.

[0007] "Analysis" is the process of examining collected data and deriving useful patterns and trends from it.

[0008] "Purchase suggestions" are pieces of information that present the most suitable product or service options for an individual based on the results obtained through analysis.

[0009] "Sales promotion information" refers to information such as sales, campaigns, and special discounts, and is a factor that influences when and how consumers purchase products or services.

[0010] "Real-time" refers to processing or providing information almost instantly without delay.

[0011] A "two-way communication method" is an interface that allows information to be sent and received via voice or text, enabling interactive data exchange between individuals and systems. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It 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

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0015] In the following embodiments, the labeled 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.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled 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.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The system of the present invention utilizes personal data from purchasing activities to provide personalized purchasing suggestions to each user. An embodiment of this system is described below.

[0034] First, when a user makes a purchase through their device, purchase activity data is generated. This includes information such as the purchased items, purchase price, and date and time of purchase. The device sends this information to the server in real time. The server stores the received purchase activity data in a database and updates the data profile for each individual user.

[0035] Next, the server analyzes this purchase data. Specifically, it uses machine learning algorithms to extract user purchasing patterns and preferences. Based on these analysis results, it generates suggestions for the most appropriate products and services.

[0036] Furthermore, the server combines the suggestions derived from the analysis with real-time sales promotion information and sends it to the terminal. This allows users to immediately receive information through their terminal via screen display or audio output. For example, if a product that a user has frequently purchased in the past is included in a special sale, they will be notified immediately.

[0037] Furthermore, users can make inquiries via voice or text to obtain additional information. The terminal receives the user's inquiry and sends it to the server. The server quickly searches for the information, sends it back to the terminal, and notifies the user of the details.

[0038] For example, if a user purchases the same food items every week, the server can learn this purchase cycle and provide corresponding sale and discount information, thereby helping them reduce their living expenses.

[0039] In this way, the system of the present invention aims to provide individuals with a more valuable experience in their purchasing behavior and to streamline the purchasing decision-making process.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] When a user purchases a product, purchase activity data is generated. This data includes the name of the purchased product, its price, and the date and time of purchase.

[0043] Step 2:

[0044] The terminal sends the generated purchase activity data to the server. The data is transmitted in real time, immediately after the purchase.

[0045] Step 3:

[0046] The server stores the received purchasing activity data in a database. During this process, the data is organized for each user, and individual profiles are continuously updated.

[0047] Step 4:

[0048] The server analyzes the stored data. This includes a process of applying machine learning algorithms based on the user's past purchase history and frequency to extract purchasing patterns and characteristics.

[0049] Step 5:

[0050] Based on the analysis results, the server generates a list of recommended products and services best suited to a specific user. This includes integrating relevant promotional and sales information.

[0051] Step 6:

[0052] The server sends recommended lists and promotional information to the terminal in real time. This information is displayed on the user's screen or played as audio.

[0053] Step 7:

[0054] The user receives a notification and checks its contents. If necessary, they can request additional information from their device via voice or text input.

[0055] Step 8:

[0056] The terminal receives a request from the user and sends a query to the server.

[0057] Step 9:

[0058] The server searches the database for information based on the user's request and returns the appropriate information to the terminal.

[0059] Step 10:

[0060] The device provides the user with the information it receives to help them make their next purchase decision. This information is presented visually on the screen or delivered via audio.

[0061] (Example 1)

[0062] 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."

[0063] In modern society, individual consumers are required to select products and services that are suitable for them from a vast amount of product information. However, the sheer volume of information and the lack of personalized recommendations make it difficult for consumers to make appropriate choices. Furthermore, there is a need for efficient systems that can quickly acquire real-time sales promotion information and respond to the diverse needs of consumers.

[0064] 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.

[0065] In this invention, the server includes means for collecting personal purchase-related information in real time via a terminal and transmitting it to the server; means for analyzing purchase patterns using a machine learning algorithm and automatically generating personalized purchase suggestions; and means for providing the generated suggestions to the individual in combination with sales promotion information and notifying them via screen or audio through the terminal. This makes it possible to generate and provide personalized suggestions in real time, enabling buyers to make more appropriate purchase decisions more quickly.

[0066] A "terminal" is an information processing device used by an individual when making a purchase, and it has the function of inputting and outputting data.

[0067] A "server" is a central computer system that communicates with terminals via a network and processes, stores, and analyzes data.

[0068] "Purchase-related information" refers to a series of data generated by an individual regarding their purchases, such as the name of the product, price, date and time, and location of the purchase.

[0069] A "machine learning algorithm" is an analytical method used to discover patterns and rules from data and build models that can be applied to new data.

[0070] "Purchase suggestions" are recommendations for products and services generated based on an individual's purchase history and patterns.

[0071] "Sales promotion information" refers to marketing information provided to promote the sale of products, such as special discounts, sale information, and campaign information.

[0072] A "generative AI model" is an artificial intelligence model that automatically generates responses and suggestions in natural language from given data.

[0073] A "prompt statement" is an instruction given to a generative AI model, and it functions as a guideline for deriving a specific output.

[0074] A "data profile" is a dataset that systematically aggregates information about an individual's purchasing behavior and tendencies.

[0075] "Two-way communication via voice and text" refers to the process of exchanging information between an individual and a server using voice or text data.

[0076] Embodiments of the present invention will be described below.

[0077] This system uses personal data in purchasing activities to provide personalized purchase suggestions to each user. First, users purchase goods or services via a terminal. The terminal includes a POS system and an online payment platform, and can be a general-purpose information processing device such as a smartphone or tablet. This generates purchase-related information entered by the user. This information includes the product name, price, date and time of purchase, and location of purchase.

[0078] The terminal transmits the generated purchase information to the server in real time. This transmission uses encrypted communication protocols such as HTTPS to ensure the security of the information. The server is located in a cloud computing environment, for example, and performs data storage and analysis. The received purchase information is stored in a database, and each user's data profile is updated. Database systems such as MySQL® or MongoDB may be used.

[0079] The server uses machine learning algorithms to analyze data profiles. Libraries such as Python's Scikit-learn and TENSORFLOW® are used for the analysis. The server identifies purchasing trends and patterns, and based on this, generates personalized purchase suggestions using a generative AI model.

[0080] This purchase suggestion is combined with sales promotion information acquired in real time from the server. This sales promotion information includes discounts and campaign information. The server sends the generated purchase suggestion to the terminal, and the terminal notifies the user of this through screen display or audio output.

[0081] Furthermore, users can send voice or text inquiries to the server via their devices. For example, in response to an inquiry requesting detailed information about a specific product, the server will quickly search for the information and return a response to the user.

[0082] For example, if a user regularly purchases beverages, the server can use that purchase history to suggest special offers and notify the user, thereby supporting efficient purchasing.

[0083] An example of a prompt message might be: "Analyze purchase data to generate optimal product recommendations for the user. Reference data: Real-time purchase history, individual user purchasing patterns, and the latest promotional information."

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] When a user purchases a product, the terminal collects purchase-related information. Input data includes product name, price, purchase date and time, and purchase location. This information is automatically retrieved from POS systems and online payment platforms and recorded in the terminal. Purchase-related information is then generated as output.

[0087] Step 2:

[0088] The terminal sends generated purchase-related information to the server in real time. The input is purchase information recorded on the terminal. The transmission is encrypted using the HTTPS protocol and securely transmitted to the server. The server receives the purchase information as output.

[0089] Step 3:

[0090] The server stores the received purchase information in a database and updates each user's data profile. The input consists of purchase information and the existing data profile. A database system such as MySQL or MongoDB is used. The output is the updated user data profile.

[0091] Step 4:

[0092] The server performs analysis using machine learning algorithms based on data profiles. The input is updated user data profiles. It uses Python's Scikit-learn and TensorFlow to perform data calculations to analyze purchasing patterns and trends. The output is the analysis results.

[0093] Step 5:

[0094] The server uses a generative AI model based on the analysis results to generate purchase suggestions for the user. The inputs are the analysis results and sales promotion information. The generated purchase suggestions are obtained when the generative AI model creates and outputs prompt messages.

[0095] Step 6:

[0096] The server sends the generated purchase suggestion to the terminal. This suggestion incorporates sales promotion information such as special discounts and sale information. The input is the generated purchase suggestion. The output is a suggestion displayed or notified to the terminal based on the prompt.

[0097] Step 7:

[0098] Users can make inquiries to the server via voice or text through their device. The user's inquiry is sent to the server. The server searches for relevant information and returns a response to the user. Inputs include the user's inquiry and the user's data profile. Outputs include specific purchase-related information notified to the user.

[0099] (Application Example 1)

[0100] 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."

[0101] In modern consumer activity, consumers are required to efficiently select products that suit their individual needs from a vast amount of product information. However, conventional systems have struggled to provide personalized product recommendations in real time that fully consider each user's purchasing patterns. As a result, consumers may miss out on valuable sales promotion information, making it a challenge to provide users with optimal purchasing recommendations.

[0102] 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.

[0103] In this invention, the server includes means for collecting individual purchasing activity data, means for analyzing the collected purchasing activity data and generating personalized purchase suggestions, means for providing the analyzed suggestions and real-time sales promotion information to the individual, means for two-way communication with the individual using voice and text, means for providing purchase suggestions to the user via push notifications, and means for analyzing the user's purchasing patterns based on a machine learning algorithm. This makes it possible to efficiently provide personalized purchase suggestions to the user in real time.

[0104] "Personal purchasing activity data" refers to information about products and services purchased by users, and is a collection of data that includes details such as the date and time of purchase and the purchase price.

[0105] "Analyzing and generating personalized purchase recommendations" refers to the process of analyzing collected purchasing activity data to recommend the most suitable products and services to individual users.

[0106] "Providing real-time sales promotion information" means instantly communicating ongoing sales and discount information to users.

[0107] "Two-way communication using voice and text" refers to a means of communication in which the user and the system interact using voice or text.

[0108] "Delivering via push notifications" is a method of automatically sending information to a user's device to attract their attention.

[0109] "Analyzing data based on machine learning algorithms" refers to the act of analyzing data using algorithms that identify patterns and make predictions and recommendations.

[0110] To realize this invention, the system uses multiple hardware and software components. First, the user makes a purchase via a terminal such as a smartphone or personal computer. This generates purchase activity data such as product name, purchase price, and purchase date and time. The terminal has the function of transmitting this information to the server in real time.

[0111] The server collects purchasing activity data into a database and updates the data profile for each individual user. The server then uses machine learning algorithms to analyze user purchasing patterns and generate personalized purchase recommendations. The machine learning models used here are designed for pattern recognition and user behavior prediction.

[0112] The analyzed purchase suggestions are combined with real-time sales promotion information and sent from the server to the user's device as push notifications. Users can view these on their device screen or receive them as audio output. Users can also interact with the system interactively via voice or text, asking further questions or requesting more detailed information.

[0113] The server uses a generative AI model to enhance recommendations based on the user's purchase history and sends push notifications to alert users so they don't miss anything. This process allows users to optimize their time and purchasing efficiency.

[0114] As a concrete example, the server can help users save on living expenses by providing special discount information and new product suggestions for everyday necessities they frequently purchase. Furthermore, effective notifications can be achieved by using prompts to the generative AI model, such as, "Write code to generate personalized notifications suggesting special milk sales to users who purchase milk every week."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] A user purchases a product using a terminal. The terminal generates purchase activity data, such as product name, purchase price, and purchase date and time, and sends it to the server. The input is the user's purchase action, and the output is the generated purchase activity data.

[0118] Step 2:

[0119] The server stores the received purchase activity data in a database and updates each user's data profile. The input is the purchase activity data sent from the terminal, and the output is the updated user data profile. The server then integrates the new data into the existing user profile.

[0120] Step 3:

[0121] The server applies machine learning algorithms based on data profiles to analyze user purchasing patterns and generate personalized purchase recommendations. The input is an updated user profile, and the output is personalized purchase recommendations. The analysis process involves recognizing the user's past purchasing trends and constructing new recommendations.

[0122] Step 4:

[0123] The server processes the generated purchase proposals in combination with sales promotion information collected in real time. The input consists of individualized purchase proposals and sales promotion information, while the output is integrated proposal information. The integration process optimizes the proposal information and prepares it for delivery to the user.

[0124] Step 5:

[0125] The server sends integrated suggestion information to the device via push notification. The input is the integrated suggestion information, and the output is the notification delivered to the user. Push notification operation includes methods of conveying information visually or audibly through the user interface on the device.

[0126] Step 6:

[0127] Users can review the suggestions through their terminal and make further inquiries to the server using voice or text. Input consists of the suggestion confirmation action and additional inquiries, while output is the additional information the user receives. In the communication process, the terminal relays user input to the server, which then generates an appropriate response.

[0128] Step 7:

[0129] The server uses a generative AI model to process user inquiries and provide additional information. The input is the user's inquiry, and the output is the answer information obtained from the AI ​​model. The AI ​​model's operation includes a process of resolving the user's questions using the prediction results.

[0130] 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.

[0131] The system of the present invention collects detailed data on an individual's purchasing activities and analyzes it in combination with an emotion engine to provide users with personalized purchasing suggestions in real time. An embodiment of this system is described below.

[0132] First, the user's purchasing behavior is recorded on the device. At this time, purchasing activity data such as the name of the purchased product, price, and date and time of purchase are generated and sent from the device to the server. The server stores this data in a database and continuously updates the individual user's profile.

[0133] The server uses machine learning algorithms to analyze the accumulated data. This extracts user purchasing patterns and preferences. Based on these analysis results, a list of recommended products and services is generated.

[0134] Here, an emotion engine operates on the device, detecting the user's emotional state by analyzing their voice input and on-screen interactions. Based on the emotional state recognized by the emotion engine (e.g., joy, surprise, or dissatisfaction), the server adjusts the content and presentation of purchase suggestions. For example, if the user indicates dissatisfaction, the emotion engine will suggest more advantageous discount information.

[0135] Next, the analyzed and refined recommendations and related real-time promotional information are sent from the server to the terminal. The information is displayed on the user's screen or output as audio. This allows the user to immediately review the recommendations and, if necessary, request further information via voice or text input.

[0136] For example, if a user shows a high level of interest in a particular brand's product and adds it to their purchase list, but for some reason hesitates to buy it, the emotion engine recognizes that interest, and the server adjusts to display special offers to encourage a purchase.

[0137] In this way, the system combining the emotion engine of the present invention aims to provide optimal support to improve the individual user experience and make purchasing decisions more personalized and efficient.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] When a user purchases a product through their device, purchase activity data is generated, including the name of the purchased product, its price, and the date and time of purchase.

[0141] Step 2:

[0142] The terminal sends the generated purchase activity data to the server. This data is sent in real time immediately after the transaction is completed.

[0143] Step 3:

[0144] The server saves the received data to the database and updates each user's profile. The saved data is stored in the database along with past purchase history.

[0145] Step 4:

[0146] The server analyzes the purchase data stored in the database. This analysis uses machine learning algorithms to extract user purchasing patterns and preferences.

[0147] Step 5:

[0148] The device analyzes the user's reactions to the product using an emotion engine based on voice input and screen interactions. The emotion engine detects the user's emotional state in real time.

[0149] Step 6:

[0150] The server adjusts the content and presentation method of generated purchase suggestions based on the emotional state obtained from the emotion engine. For example, if a customer expresses dissatisfaction, it will create suggestions that emphasize more favorable discount information.

[0151] Step 7:

[0152] The server sends customized purchase suggestions and real-time sales promotion information to the terminal.

[0153] Step 8:

[0154] The device notifies the user of received purchase suggestions. Notifications are provided to the user via screen display, audio output, and push notifications.

[0155] Step 9:

[0156] Users consider purchasing based on the information provided. If they need more detailed information, they can request additional information via voice or text on their device.

[0157] Step 10:

[0158] The terminal receives a user request and sends a query to the server.

[0159] Step 11:

[0160] The server quickly extracts information from the database in response to additional queries and sends it back to the terminal.

[0161] Step 12:

[0162] The device provides the user with further information to support their final purchasing decision. The information is presented in an optimal format, taking into account the user's emotional state.

[0163] (Example 2)

[0164] 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".

[0165] There is a need to streamline purchasing decision-making and improve the user experience by more accurately analyzing individual purchasing behavior and providing personalized purchase suggestions in real time that are tailored to the user's emotional state. Current systems have difficulty capturing the emotions of individual users, therefore, new technologies are needed to effectively facilitate purchasing activities.

[0166] 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.

[0167] In this invention, the server includes means for aggregating individual purchase behavior records and transmitting data, means for analyzing preferences using machine learning and adjusting and generating purchase suggestions, and means for detecting emotional states from voice and interactions using emotion analysis technology. This makes it possible to create and provide highly accurate suggestions based on the user's purchase behavior and emotional state.

[0168] "Collecting individual purchase behavior records and transmitting the data" refers to the process of recording a series of purchasing actions performed by individual users and sending them together to a server.

[0169] "Using machine learning to analyze preferences and adjust and generate purchase suggestions" refers to a method of analyzing user preferences and patterns using algorithms based on collected data, and then generating purchase suggestions that reflect the results.

[0170] "Detecting emotional states from voice and interaction using emotion analysis technology" refers to a process that accurately discerns a user's current emotional state by utilizing technology that identifies a user's emotions from voice data and user interactions.

[0171] "Providing real-time optimized sales promotion information" means a function that immediately presents users with the most effective sales information at the moment, based on analysis results.

[0172] "Enabling the request for additional information through two-way information communication" means a method that enables interaction between the user and the system by providing a mechanism that allows the user to request additional information as needed and provides the information accordingly.

[0173] A description of embodiments for carrying out the present invention will be provided.

[0174] This system analyzes the purchasing behavior and emotional state of individual users and provides personalized purchase recommendations in real time. The system consists of three main components: users, terminals, and servers.

[0175] First, the user views product information and proceeds with the purchase through a specific interface. The device utilizes a mobile application or web browser, and these interfaces begin recording the purchase behavior. Upon completion of the purchase, data such as product name, price, and purchase date and time are generated.

[0176] Next, the device sends this purchase data to the server using a secure protocol (e.g., HTTPS). The device has a built-in script that sends the data to the server in real time and possesses processing power capable of handling large-scale data communication.

[0177] The server stores and continuously updates purchase data using a database management system (e.g., MySQL, PostgreSQL). Machine learning algorithms also run on the server, analyzing the collected data to extract user preferences. Software tools such as Python, TensorFlow, and scikit-learn are used in this process. Based on the machine learning results, the most suitable purchase suggestions for the user are generated.

[0178] Furthermore, an emotion engine operates on the device, analyzing the user's emotional state from their voice input and on-screen interactions. This emotion analysis utilizes a voice recognition API and emotion analysis software. The device sends emotion analysis information to the server each time the user speaks or interacts with the screen.

[0179] The server receives sentiment analysis results, adjusts the generated purchase suggestions, and provides optimized sales promotion information in real time. Suggestions are presented via audio output or on-screen display through the terminal, allowing users to review them and request further information as needed.

[0180] As a concrete example, consider a scenario where a user is considering purchasing a new smartphone, but the price is a barrier. When the emotion engine detects the user's hesitation or anxiety, the server adjusts the suggestions to include special discount offers related to the price and displays them on the device.

[0181] Examples of prompts for generative AI models:

[0182] "Users are hesitant to make a purchase. Please generate effective sales promotion proposals that take their emotional state into consideration."

[0183] In this way, the system aims to improve the user's purchasing experience and support more efficient decision-making.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1: Recording and Data Generation

[0186] The user selects products and completes the purchase process through the application. As input, product information, product name, price, and purchase date and time are automatically generated based on the user's actions. As output, purchase behavior data is recorded on the device. During this process, the application displays a confirmation message through the user interface.

[0187] Step 2: Data transmission

[0188] The terminal sends recorded purchase data to the server via a secure communication protocol. The input is the generated purchase data, which is sent using HTTPS. The output is the data arriving at the server. Specifically, the terminal attempts to send data to the server at regular intervals and retries until successful completion is confirmed.

[0189] Step 3: Storing and updating data

[0190] The server stores the received purchase data in the database. The input is the purchase data sent from the terminal, and the output is the updated state of the database. The database system maintains and updates the purchase history as needed. If the data is stored successfully, a confirmation message is logged.

[0191] Step 4: Preference analysis using machine learning

[0192] The server uses a machine learning model to analyze user preferences from accumulated purchase data. The input is purchase history in a database, and the output is a list of recommended products. A specific algorithm is applied to analyze user trends. This process utilizes Python and machine learning libraries.

[0193] Step 5: Emotion Analysis

[0194] On the device, an emotion engine analyzes the user's voice input and on-screen interactions to detect their emotional state. The input consists of user voice data and interaction data, while the output is the determined emotional state. Voice input is captured from the microphone, and an analysis API infers the emotional state.

[0195] Step 6: Adjusting the purchase proposal

[0196] The server adjusts pre-generated purchase suggestions based on the sentiment analysis results. The input is the emotional state identified by sentiment analysis and a list of recommended products generated by machine learning; the output is the adjusted purchase suggestion. Depending on a specific emotional state (e.g., surprise), the server performs processing to include special offers or recommended product information.

[0197] Step 7: Providing Proposal Information

[0198] The server sends the adjusted information to the terminal and provides it to the user. The input is the adjusted purchase suggestion, and the output is a notification to the user. The terminal presents the information to the user via voice and display, and offers the option to request additional information.

[0199] (Application Example 2)

[0200] 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 device 14 will be referred to as the "terminal."

[0201] Modern consumers find it difficult to make the best purchase choices from a vast amount of information and products. Furthermore, standard product recommendations fail to consider individual preferences and emotional states, resulting in ineffective sales promotion. This challenge needs to be addressed.

[0202] 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.

[0203] In this invention, the server includes means for collecting personal purchasing activity information, means for detecting the personal emotional state and optimizing purchase suggestions based on it, and means for generating prompt sentences based on emotion analysis and inputting them into a generation AI model. This makes it possible to provide each consumer with personalized purchase suggestions in real time that best match their emotions and preferences at that time.

[0204] "Means for collecting personal purchasing activity information" refers to a system that collects data on product purchases and browsing behaviors performed by users through their devices.

[0205] "A means of analyzing collected purchasing activity information and generating personalized purchase suggestions" refers to a process that uses machine learning algorithms to analyze acquired data and create suggestions tailored to the individual user's preferences and past behavior.

[0206] "A means of providing analyzed purchase suggestions and real-time sales promotion information to individuals" refers to a function that optimizes and delivers suggestion content in order to present users with immediately useful information on products and services.

[0207] "Means of two-way communication with individuals using voice and text" refers to an interface in which users interact with a system in voice or text format and exchange information and instructions.

[0208] "Methods for detecting an individual's emotional state and optimizing purchase suggestions based on it" refers to a system that analyzes voice and on-screen user actions to read changes in emotion and adjust the content of purchase suggestions accordingly.

[0209] "A means of generating prompt sentences based on sentiment analysis and inputting them into a generative AI model" refers to a process that generates text based on sentiment analysis results and uses that as input data for the AI ​​model to consider appropriate responses and suggestions.

[0210] To implement this invention, a system is required in which a user's terminal, a server, and an emotion engine work in coordination. The user's terminal consists of an electronic device such as a smartphone or tablet. When a user purchases a product, this terminal collects detailed product information and purchase history and transmits it to the server. The collected data is stored on the server as personal purchasing activity information.

[0211] The server analyzes this information using machine learning algorithms. Data science tools using Python or R, such as TensorFlow and Sci-kit Learn, are used for the analysis. This extracts user preferences and purchasing patterns, generating personalized purchase recommendations.

[0212] Furthermore, the user's device incorporates an emotion engine that analyzes voice input and on-screen interactions to detect the user's emotional state in real time. This emotion engine utilizes natural language processing technologies such as Google's Dialogflow and IBM Watson. Based on the emotional state, the server optimizes purchase suggestions. For example, if the user is feeling anxious, it emphasizes reassuring product reviews and special offers.

[0213] The analyzed and optimized suggestion information is sent back to the user's device in real time. Users can review the suggestions on the screen or request further information via voice. This allows users to receive suggestions that best match their emotions and purchasing needs at that moment.

[0214] For example, if a user is considering purchasing an expensive item, the system can analyze their past emotions when purchasing similar items to help them make a decision. If the emotion engine detects anxiety about the purchase, the server provides reassurance by showing compelling reasons to buy and positive reviews from other users. The prompt for the generating AI model would look like this: "Generate a way to provide additional product information to encourage purchase when the user's emotional state is anxious."

[0215] Thus, the system of the present invention is designed to personalize the user experience and support purchasing decisions.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The terminal records the user's purchasing actions. It collects data such as details of purchased items, purchase date, and price, and sends it to the server. The input is the user's purchasing action, and the output is purchase data that can be processed on the server side. The data is transmitted in real time.

[0219] Step 2:

[0220] The server stores the received purchase data in a database. A database management system is used to continuously update user-specific data profiles. The input is newly acquired purchase data, and the output is the updated user data profile.

[0221] Step 3:

[0222] The server analyzes purchase data using machine learning algorithms. It utilizes Python and R libraries to extract user preferences and patterns. The input is user history data, and the output is predictive data based on the analyzed patterns and preferences.

[0223] Step 4:

[0224] The server generates personalized purchase suggestions based on the analysis results and adjusts the suggestions by incorporating data from the emotion engine. The emotion analysis results are generated as prompts and input into the generating AI model. The input consists of analysis results and emotion data, and the output is an optimized purchase suggestion.

[0225] Step 5:

[0226] The device uses an emotion engine to detect the user's emotional state. It performs real-time speech recognition and text analysis, and sends the results to the server. The input is real-time interaction with the user, and the output is emotion analysis data.

[0227] Step 6:

[0228] The server uses sentiment analysis data to finalize purchase recommendations and sends them to the user's terminal. It presents information that provides specific purchase motivations. The input is optimized recommendation data, and the output is a presentation of recommended information to the user.

[0229] Step 7:

[0230] The user reviews the proposal and requests the necessary information via voice or text. The terminal sends the request to the server and retrieves the requested information. The input is the user's request operation, and the output is the provision of additional information.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] [Second Embodiment]

[0235] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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).

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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".

[0247] The system of the present invention utilizes personal data from purchasing activities to provide personalized purchasing suggestions to each user. An embodiment of this system is described below.

[0248] First, when a user makes a purchase through their device, purchase activity data is generated. This includes information such as the purchased items, purchase price, and date and time of purchase. The device sends this information to the server in real time. The server stores the received purchase activity data in a database and updates the data profile for each individual user.

[0249] Next, the server analyzes this purchase data. Specifically, it uses machine learning algorithms to extract user purchasing patterns and preferences. Based on these analysis results, it generates suggestions for the most appropriate products and services.

[0250] Furthermore, the server combines the suggestions derived from the analysis with real-time sales promotion information and sends it to the terminal. This allows users to immediately receive information through their terminal via screen display or audio output. For example, if a product that a user has frequently purchased in the past is included in a special sale, they will be notified immediately.

[0251] Furthermore, users can make inquiries via voice or text to obtain additional information. The terminal receives the user's inquiry and sends it to the server. The server quickly searches for the information, sends it back to the terminal, and notifies the user of the details.

[0252] For example, if a user purchases the same food items every week, the server can learn this purchase cycle and provide corresponding sale and discount information, thereby helping them reduce their living expenses.

[0253] In this way, the system of the present invention aims to provide individuals with a more valuable experience in their purchasing behavior and to streamline the purchasing decision-making process.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] When a user purchases a product, purchase activity data is generated. This data includes the name of the purchased product, its price, and the date and time of purchase.

[0257] Step 2:

[0258] The terminal sends the generated purchase activity data to the server. The data is transmitted in real time, immediately after the purchase.

[0259] Step 3:

[0260] The server stores the received purchasing activity data in a database. During this process, the data is organized for each user, and individual profiles are continuously updated.

[0261] Step 4:

[0262] The server analyzes the stored data. This includes a process of applying machine learning algorithms based on the user's past purchase history and frequency to extract purchasing patterns and characteristics.

[0263] Step 5:

[0264] Based on the analysis results, the server generates a list of recommended products and services best suited to a specific user. This includes integrating relevant promotional and sales information.

[0265] Step 6:

[0266] The server sends recommended lists and promotional information to the terminal in real time. This information is displayed on the user's screen or played as audio.

[0267] Step 7:

[0268] The user receives a notification and checks its contents. If necessary, they can request additional information from their device via voice or text input.

[0269] Step 8:

[0270] The terminal receives a request from the user and sends a query to the server.

[0271] Step 9:

[0272] The server searches the database for information based on the user's request and returns the appropriate information to the terminal.

[0273] Step 10:

[0274] The device provides the user with the information it receives to help them make their next purchase decision. This information is presented visually on the screen or delivered via audio.

[0275] (Example 1)

[0276] 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."

[0277] In modern society, individual consumers are required to select products and services that are suitable for them from a vast amount of product information. However, the sheer volume of information and the lack of personalized recommendations make it difficult for consumers to make appropriate choices. Furthermore, there is a need for efficient systems that can quickly acquire real-time sales promotion information and respond to the diverse needs of consumers.

[0278] 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.

[0279] In this invention, the server includes means for collecting personal purchase-related information in real time via a terminal and transmitting it to the server; means for analyzing purchase patterns using a machine learning algorithm and automatically generating personalized purchase suggestions; and means for providing the generated suggestions to the individual in combination with sales promotion information and notifying them via screen or audio through the terminal. This makes it possible to generate and provide personalized suggestions in real time, enabling buyers to make more appropriate purchase decisions more quickly.

[0280] The "terminal" refers to an information processing device used by an individual when making a purchase, which has the function of inputting and outputting data.

[0281] The "server" is a central computer system that communicates with terminals via a network and processes, stores, and analyzes data.

[0282] The "purchase-related information" refers to a series of data generated by an individual regarding a purchase, such as the name of the purchased product, price, date and time, location, etc.

[0283] The "machine learning algorithm" is an analysis method for discovering patterns and rules from data and constructing a model applicable to new data.

[0284] The "purchase recommendation" is recommendation information on products and services generated based on an individual's purchase history and patterns.

[0285] The "sales promotion information" is marketing information provided to promote the sales of products, such as special discounts, sale information, campaign information, etc.

[0286] The "generative AI model" is an artificial intelligence model for automatically generating responses and proposals in natural language from given data.

[0287] The "prompt text" is an instruction text input to the generative AI model and functions as a guideline for deriving a specific output.

[0288] The "data profile" is a dataset that systematically aggregates information on an individual's purchase behavior and tendencies.

[0289] The "two-way communication in voice and text" is a process of information exchange using voice or text information between an individual and a server.

[0290] Embodiments of the present invention will be described.

[0291] This system uses personal data in purchasing activities to provide personalized purchase suggestions to each user. First, users purchase goods or services via a terminal. The terminal includes a POS system and an online payment platform, and can be a general-purpose information processing device such as a smartphone or tablet. This generates purchase-related information entered by the user. This information includes the product name, price, date and time of purchase, and location of purchase.

[0292] The terminal sends the generated purchase information to the server in real time. This transmission uses encrypted communication protocols such as HTTPS to ensure the security of the information. The server is located in a cloud computing environment, for example, and stores and analyzes the data. The received purchase information is stored in a database, and each user's data profile is updated. Database systems such as MySQL or MongoDB may be used.

[0293] The server uses machine learning algorithms to analyze data profiles. Libraries such as Python's Scikit-learn and TensorFlow are used for the analysis. The server identifies purchasing trends and patterns, and based on this, generates personalized purchase suggestions using a generative AI model.

[0294] This purchase suggestion is combined with sales promotion information acquired in real time from the server. This sales promotion information includes discounts and campaign information. The server sends the generated purchase suggestion to the terminal, and the terminal notifies the user of this through screen display or audio output.

[0295] Furthermore, users can send voice or text inquiries to the server via their devices. For example, in response to an inquiry requesting detailed information about a specific product, the server will quickly search for the information and return a response to the user.

[0296] For example, if a user regularly purchases beverages, the server can use that purchase history to suggest special offers and notify the user, thereby supporting efficient purchasing.

[0297] An example of a prompt message might be: "Analyze purchase data to generate optimal product recommendations for the user. Reference data: Real-time purchase history, individual user purchasing patterns, and the latest promotional information."

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] When a user purchases a product, the terminal collects purchase-related information. Input data includes product name, price, purchase date and time, and purchase location. This information is automatically retrieved from POS systems and online payment platforms and recorded in the terminal. Purchase-related information is then generated as output.

[0301] Step 2:

[0302] The terminal sends generated purchase-related information to the server in real time. The input is purchase information recorded on the terminal. The transmission is encrypted using the HTTPS protocol and securely transmitted to the server. The server receives the purchase information as output.

[0303] Step 3:

[0304] The server stores the received purchase information in a database and updates each user's data profile. The input consists of purchase information and the existing data profile. A database system such as MySQL or MongoDB is used. The output is the updated user data profile.

[0305] Step 4:

[0306] The server performs analysis using a machine learning algorithm based on the data profile. As input, there is an updated user data profile. Using Python's Scikit - learn or TensorFlow, data operations are performed to analyze purchase patterns and trends. As output, analysis results are generated.

[0307] Step 5:

[0308] The server uses the generated AI model based on the analysis results to generate purchase proposals for users. As input, there are the analysis results and sales promotion information. The generated purchase proposals are obtained by the generated AI model creating and outputting a prompt text.

[0309] Step 6:

[0310] The server sends the generated purchase proposals to the terminal. These proposals are combined with sales promotion information such as special discounts or sale information. As input, there is the generated purchase proposal. As output, a prompt - based proposal is displayed or notified to the terminal.

[0311] Step 7:

[0312] The user can query the server via the terminal in voice or text. The query content entered by the user is sent to the server. The server searches for relevant information and returns a response to the user. As input, there are the user's query and the user's data profile. As output, specific purchase - related information is notified to the user.

[0313] (Application Example 1)

[0314] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] In modern consumer activity, consumers are required to efficiently select products that suit their individual needs from a vast amount of product information. However, conventional systems have struggled to provide personalized product recommendations in real time that fully consider each user's purchasing patterns. As a result, consumers may miss out on valuable sales promotion information, making it a challenge to provide users with optimal purchasing recommendations.

[0316] 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.

[0317] In this invention, the server includes means for collecting individual purchasing activity data, means for analyzing the collected purchasing activity data and generating personalized purchase suggestions, means for providing the analyzed suggestions and real-time sales promotion information to the individual, means for two-way communication with the individual using voice and text, means for providing purchase suggestions to the user via push notifications, and means for analyzing the user's purchasing patterns based on a machine learning algorithm. This makes it possible to efficiently provide personalized purchase suggestions to the user in real time.

[0318] "Personal purchasing activity data" refers to information about products and services purchased by users, and is a collection of data that includes details such as the date and time of purchase and the purchase price.

[0319] "Analyzing and generating personalized purchase recommendations" refers to the process of analyzing collected purchasing activity data to recommend the most suitable products and services to individual users.

[0320] "Providing real-time sales promotion information" means instantly communicating ongoing sales and discount information to users.

[0321] "Two-way communication using voice and text" refers to a means of communication in which the user and the system interact using voice or text.

[0322] "Delivering via push notifications" is a method of automatically sending information to a user's device to attract their attention.

[0323] "Analyzing data based on machine learning algorithms" refers to the act of analyzing data using algorithms that identify patterns and make predictions and recommendations.

[0324] To realize this invention, the system uses multiple hardware and software components. First, the user makes a purchase via a terminal such as a smartphone or personal computer. This generates purchase activity data such as product name, purchase price, and purchase date and time. The terminal has the function of transmitting this information to the server in real time.

[0325] The server collects purchasing activity data into a database and updates the data profile for each individual user. The server then uses machine learning algorithms to analyze user purchasing patterns and generate personalized purchase recommendations. The machine learning models used here are designed for pattern recognition and user behavior prediction.

[0326] The analyzed purchase suggestions are combined with real-time sales promotion information and sent from the server to the user's device as push notifications. Users can view these on their device screen or receive them as audio output. Users can also interact with the system interactively via voice or text, asking further questions or requesting more detailed information.

[0327] The server uses a generative AI model to enhance recommendations based on the user's purchase history and sends push notifications to alert users so they don't miss anything. This process allows users to optimize their time and purchasing efficiency.

[0328] As a concrete example, the server can help users save on living expenses by providing special discount information and new product suggestions for everyday necessities they frequently purchase. Furthermore, effective notifications can be achieved by using prompts to the generative AI model, such as, "Write code to generate personalized notifications suggesting special milk sales to users who purchase milk every week."

[0329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0330] Step 1:

[0331] A user purchases a product using a terminal. The terminal generates purchase activity data, such as product name, purchase price, and purchase date and time, and sends it to the server. The input is the user's purchase action, and the output is the generated purchase activity data.

[0332] Step 2:

[0333] The server stores the received purchase activity data in a database and updates each user's data profile. The input is the purchase activity data sent from the terminal, and the output is the updated user data profile. The server then integrates the new data into the existing user profile.

[0334] Step 3:

[0335] The server applies machine learning algorithms based on data profiles to analyze user purchasing patterns and generate personalized purchase recommendations. The input is an updated user profile, and the output is personalized purchase recommendations. The analysis process involves recognizing the user's past purchasing trends and constructing new recommendations.

[0336] Step 4:

[0337] The server processes the generated purchase proposals in combination with sales promotion information collected in real time. The input consists of individualized purchase proposals and sales promotion information, while the output is integrated proposal information. The integration process optimizes the proposal information and prepares it for delivery to the user.

[0338] Step 5:

[0339] The server sends integrated suggestion information to the device via push notification. The input is the integrated suggestion information, and the output is the notification delivered to the user. Push notification operation includes methods of conveying information visually or audibly through the user interface on the device.

[0340] Step 6:

[0341] Users can review the suggestions through their terminal and make further inquiries to the server using voice or text. Input consists of the suggestion confirmation action and additional inquiries, while output is the additional information the user receives. In the communication process, the terminal relays user input to the server, which then generates an appropriate response.

[0342] Step 7:

[0343] The server uses a generative AI model to process user inquiries and provide additional information. The input is the user's inquiry, and the output is the answer information obtained from the AI ​​model. The AI ​​model's operation includes a process of resolving the user's questions using the prediction results.

[0344] 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.

[0345] The system of the present invention collects detailed data on an individual's purchasing activities and analyzes it in combination with an emotion engine to provide users with personalized purchasing suggestions in real time. An embodiment of this system is described below.

[0346] First, the user's purchasing behavior is recorded on the device. At this time, purchasing activity data such as the name of the purchased product, price, and date and time of purchase are generated and sent from the device to the server. The server stores this data in a database and continuously updates the individual user's profile.

[0347] The server uses machine learning algorithms to analyze the accumulated data. This extracts user purchasing patterns and preferences. Based on these analysis results, a list of recommended products and services is generated.

[0348] Here, an emotion engine operates on the device, detecting the user's emotional state by analyzing their voice input and on-screen interactions. Based on the emotional state recognized by the emotion engine (e.g., joy, surprise, or dissatisfaction), the server adjusts the content and presentation of purchase suggestions. For example, if the user indicates dissatisfaction, the emotion engine will suggest more advantageous discount information.

[0349] Next, the analyzed and refined recommendations and related real-time promotional information are sent from the server to the terminal. The information is displayed on the user's screen or output as audio. This allows the user to immediately review the recommendations and, if necessary, request further information via voice or text input.

[0350] For example, if a user shows a high level of interest in a particular brand's product and adds it to their purchase list, but for some reason hesitates to buy it, the emotion engine recognizes that interest, and the server adjusts to display special offers to encourage a purchase.

[0351] In this way, the system combining the emotion engine of the present invention aims to provide optimal support to improve the individual user experience and make purchasing decisions more personalized and efficient.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] When a user purchases a product through their device, purchase activity data is generated, including the name of the purchased product, its price, and the date and time of purchase.

[0355] Step 2:

[0356] The terminal sends the generated purchase activity data to the server. This data is sent in real time immediately after the transaction is completed.

[0357] Step 3:

[0358] The server saves the received data to the database and updates each user's profile. The saved data is stored in the database along with past purchase history.

[0359] Step 4:

[0360] The server analyzes the purchase data stored in the database. This analysis uses machine learning algorithms to extract user purchasing patterns and preferences.

[0361] Step 5:

[0362] The device analyzes the user's reactions to the product using an emotion engine based on voice input and screen interactions. The emotion engine detects the user's emotional state in real time.

[0363] Step 6:

[0364] The server adjusts the content and presentation method of generated purchase suggestions based on the emotional state obtained from the emotion engine. For example, if a customer expresses dissatisfaction, it will create suggestions that emphasize more favorable discount information.

[0365] Step 7:

[0366] The server sends customized purchase suggestions and real-time sales promotion information to the terminal.

[0367] Step 8:

[0368] The device notifies the user of received purchase suggestions. Notifications are provided to the user via screen display, audio output, and push notifications.

[0369] Step 9:

[0370] Users consider purchasing based on the information provided. If they need more detailed information, they can request additional information via voice or text on their device.

[0371] Step 10:

[0372] The terminal receives a user request and sends a query to the server.

[0373] Step 11:

[0374] The server quickly extracts information from the database in response to additional queries and sends it back to the terminal.

[0375] Step 12:

[0376] The device provides the user with further information to support their final purchasing decision. The information is presented in an optimal format, taking into account the user's emotional state.

[0377] (Example 2)

[0378] 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".

[0379] There is a need to streamline purchasing decision-making and improve the user experience by more accurately analyzing individual purchasing behavior and providing personalized purchase suggestions in real time that are tailored to the user's emotional state. Current systems have difficulty capturing the emotions of individual users, therefore, new technologies are needed to effectively facilitate purchasing activities.

[0380] 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.

[0381] In this invention, the server includes means for aggregating individual purchase behavior records and transmitting data, means for analyzing preferences using machine learning and adjusting and generating purchase suggestions, and means for detecting emotional states from voice and interactions using emotion analysis technology. This makes it possible to create and provide highly accurate suggestions based on the user's purchase behavior and emotional state.

[0382] "Collecting individual purchase behavior records and transmitting the data" refers to the process of recording a series of purchasing actions performed by individual users and sending them together to a server.

[0383] "Using machine learning to analyze preferences and adjust and generate purchase suggestions" refers to a method of analyzing user preferences and patterns using algorithms based on collected data, and then generating purchase suggestions that reflect the results.

[0384] "Detecting emotional states from voice and interaction using emotion analysis technology" refers to a process that accurately discerns a user's current emotional state by utilizing technology that identifies a user's emotions from voice data and user interactions.

[0385] "Providing real-time optimized sales promotion information" means a function that immediately presents users with the most effective sales information at the moment, based on analysis results.

[0386] "Enabling the request for additional information through two-way information communication" means a method that enables interaction between the user and the system by providing a mechanism that allows the user to request additional information as needed and provides the information accordingly.

[0387] A description of embodiments for carrying out the present invention will be provided.

[0388] This system analyzes the purchasing behavior and emotional state of individual users and provides personalized purchase recommendations in real time. The system consists of three main components: users, terminals, and servers.

[0389] First, the user views product information and proceeds with the purchase through a specific interface. The device utilizes a mobile application or web browser, and these interfaces begin recording the purchase behavior. Upon completion of the purchase, data such as product name, price, and purchase date and time are generated.

[0390] Next, the device sends this purchase data to the server using a secure protocol (e.g., HTTPS). The device has a built-in script that sends the data to the server in real time and possesses processing power capable of handling large-scale data communication.

[0391] The server stores and continuously updates purchase data using a database management system (e.g., MySQL, PostgreSQL). Machine learning algorithms also run on the server, analyzing the collected data to extract user preferences. Software tools such as Python, TensorFlow, and scikit-learn are used in this process. Based on the machine learning results, the most suitable purchase suggestions for the user are generated.

[0392] Furthermore, an emotion engine operates on the device, analyzing the user's emotional state from their voice input and on-screen interactions. This emotion analysis utilizes a voice recognition API and emotion analysis software. The device sends emotion analysis information to the server each time the user speaks or interacts with the screen.

[0393] The server receives sentiment analysis results, adjusts the generated purchase suggestions, and provides optimized sales promotion information in real time. Suggestions are presented via audio output or on-screen display through the terminal, allowing users to review them and request further information as needed.

[0394] As a concrete example, consider a scenario where a user is considering purchasing a new smartphone, but the price is a barrier. When the emotion engine detects the user's hesitation or anxiety, the server adjusts the suggestions to include special discount offers related to the price and displays them on the device.

[0395] Examples of prompts for generative AI models:

[0396] "Users are hesitant to make a purchase. Please generate effective sales promotion proposals that take their emotional state into consideration."

[0397] In this way, the system aims to improve the user's purchasing experience and support more efficient decision-making.

[0398] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0399] Step 1: Recording and Data Generation

[0400] The user selects products and completes the purchase process through the application. As input, product information, product name, price, and purchase date and time are automatically generated based on the user's actions. As output, purchase behavior data is recorded on the device. During this process, the application displays a confirmation message through the user interface.

[0401] Step 2: Data transmission

[0402] The terminal sends recorded purchase data to the server via a secure communication protocol. The input is the generated purchase data, which is sent using HTTPS. The output is the data arriving at the server. Specifically, the terminal attempts to send data to the server at regular intervals and retries until successful completion is confirmed.

[0403] Step 3: Storing and updating data

[0404] The server stores the received purchase data in the database. The input is the purchase data sent from the terminal, and the output is the updated state of the database. The database system maintains and updates the purchase history as needed. If the data is stored successfully, a confirmation message is logged.

[0405] Step 4: Preference analysis using machine learning

[0406] The server uses a machine learning model to analyze user preferences from accumulated purchase data. The input is purchase history in a database, and the output is a list of recommended products. A specific algorithm is applied to analyze user trends. This process utilizes Python and machine learning libraries.

[0407] Step 5: Emotion Analysis

[0408] On the device, an emotion engine analyzes the user's voice input and on-screen interactions to detect their emotional state. The input consists of user voice data and interaction data, while the output is the determined emotional state. Voice input is captured from the microphone, and an analysis API infers the emotional state.

[0409] Step 6: Adjusting the purchase proposal

[0410] The server adjusts pre-generated purchase suggestions based on the sentiment analysis results. The input is the emotional state identified by sentiment analysis and a list of recommended products generated by machine learning; the output is the adjusted purchase suggestion. Depending on a specific emotional state (e.g., surprise), the server performs processing to include special offers or recommended product information.

[0411] Step 7: Providing Proposal Information

[0412] The server sends the adjusted information to the terminal and provides it to the user. The input is the adjusted purchase suggestion, and the output is a notification to the user. The terminal presents the information to the user via voice and display, and offers the option to request additional information.

[0413] (Application Example 2)

[0414] 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 as the "terminal".

[0415] Modern consumers find it difficult to make the best purchase choices from a vast amount of information and products. Furthermore, standard product recommendations fail to consider individual preferences and emotional states, resulting in ineffective sales promotion. This challenge needs to be addressed.

[0416] 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.

[0417] In this invention, the server includes means for collecting personal purchasing activity information, means for detecting the personal emotional state and optimizing purchase suggestions based on it, and means for generating prompt sentences based on emotion analysis and inputting them into a generation AI model. This makes it possible to provide each consumer with personalized purchase suggestions in real time that best match their emotions and preferences at that time.

[0418] "Means for collecting personal purchasing activity information" refers to a system that collects data on product purchases and browsing behaviors performed by users through their devices.

[0419] "A means of analyzing collected purchasing activity information and generating personalized purchase suggestions" refers to a process that uses machine learning algorithms to analyze acquired data and create suggestions tailored to the individual user's preferences and past behavior.

[0420] "A means of providing analyzed purchase suggestions and real-time sales promotion information to individuals" refers to a function that optimizes and delivers suggestion content in order to present users with immediately useful information on products and services.

[0421] "Means of two-way communication with individuals using voice and text" refers to an interface in which users interact with a system in voice or text format and exchange information and instructions.

[0422] "Methods for detecting an individual's emotional state and optimizing purchase suggestions based on it" refers to a system that analyzes voice and on-screen user actions to read changes in emotion and adjust the content of purchase suggestions accordingly.

[0423] "A means of generating prompt sentences based on sentiment analysis and inputting them into a generative AI model" refers to a process that generates text based on sentiment analysis results and uses that as input data for the AI ​​model to consider appropriate responses and suggestions.

[0424] To implement this invention, a system is required in which a user's terminal, a server, and an emotion engine work in coordination. The user's terminal consists of an electronic device such as a smartphone or tablet. When a user purchases a product, this terminal collects detailed product information and purchase history and transmits it to the server. The collected data is stored on the server as personal purchasing activity information.

[0425] The server analyzes this information using machine learning algorithms. Data science tools using Python or R, such as TensorFlow and Sci-kit Learn, are used for the analysis. This extracts user preferences and purchasing patterns, generating personalized purchase recommendations.

[0426] Furthermore, the user's device has a built-in emotion engine that analyzes voice input and on-screen interactions to detect the user's emotional state in real time. This emotion engine uses natural language processing technologies such as Google's Dialogflow and IBM Watson. Based on the emotional state, the server optimizes purchase suggestions. For example, if the user is feeling anxious, it will emphasize reassuring product reviews and special offers.

[0427] The analyzed and optimized suggestion information is sent back to the user's device in real time. Users can review the suggestions on the screen or request further information via voice. This allows users to receive suggestions that best match their emotions and purchasing needs at that moment.

[0428] For example, if a user is considering purchasing an expensive item, the system can analyze their past emotions when purchasing similar items to help them make a decision. If the emotion engine detects anxiety about the purchase, the server provides reassurance by showing compelling reasons to buy and positive reviews from other users. The prompt for the generating AI model would look like this: "Generate a way to provide additional product information to encourage purchase when the user's emotional state is anxious."

[0429] Thus, the system of the present invention is designed to personalize the user experience and support purchasing decisions.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The terminal records the user's purchasing actions. It collects data such as details of purchased items, purchase date, and price, and sends it to the server. The input is the user's purchasing action, and the output is purchase data that can be processed on the server side. The data is transmitted in real time.

[0433] Step 2:

[0434] The server stores the received purchase data in a database. A database management system is used to continuously update user-specific data profiles. The input is newly acquired purchase data, and the output is the updated user data profile.

[0435] Step 3:

[0436] The server analyzes purchase data using machine learning algorithms. It utilizes Python and R libraries to extract user preferences and patterns. The input is user history data, and the output is predictive data based on the analyzed patterns and preferences.

[0437] Step 4:

[0438] The server generates personalized purchase suggestions based on the analysis results and adjusts the suggestions by incorporating data from the emotion engine. The emotion analysis results are generated as prompts and input into the generating AI model. The input consists of analysis results and emotion data, and the output is an optimized purchase suggestion.

[0439] Step 5:

[0440] The device uses an emotion engine to detect the user's emotional state. It performs real-time speech recognition and text analysis, and sends the results to the server. The input is real-time interaction with the user, and the output is emotion analysis data.

[0441] Step 6:

[0442] The server uses sentiment analysis data to finalize purchase recommendations and sends them to the user's terminal. It presents information that provides specific purchase motivations. The input is optimized recommendation data, and the output is a presentation of recommended information to the user.

[0443] Step 7:

[0444] The user reviews the proposal and requests the necessary information via voice or text. The terminal sends the request to the server and retrieves the requested information. The input is the user's request operation, and the output is the provision of additional information.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] [Third Embodiment]

[0449] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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".

[0461] The system of the present invention utilizes personal data from purchasing activities to provide personalized purchasing suggestions to each user. An embodiment of this system is described below.

[0462] First, when a user makes a purchase through their device, purchase activity data is generated. This includes information such as the purchased items, purchase price, and date and time of purchase. The device sends this information to the server in real time. The server stores the received purchase activity data in a database and updates the data profile for each individual user.

[0463] Next, the server analyzes this purchase data. Specifically, it uses machine learning algorithms to extract user purchasing patterns and preferences. Based on these analysis results, it generates suggestions for the most appropriate products and services.

[0464] Furthermore, the server combines the suggestions derived from the analysis with real-time sales promotion information and sends it to the terminal. This allows users to immediately receive information through their terminal via screen display or audio output. For example, if a product that a user has frequently purchased in the past is included in a special sale, they will be notified immediately.

[0465] Furthermore, users can make inquiries via voice or text to obtain additional information. The terminal receives the user's inquiry and sends it to the server. The server quickly searches for the information, sends it back to the terminal, and notifies the user of the details.

[0466] For example, if a user purchases the same food items every week, the server can learn this purchase cycle and provide corresponding sale and discount information, thereby helping them reduce their living expenses.

[0467] In this way, the system of the present invention aims to provide individuals with a more valuable experience in their purchasing behavior and to streamline the purchasing decision-making process.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] When a user purchases a product, purchase activity data is generated. This data includes the name of the purchased product, its price, and the date and time of purchase.

[0471] Step 2:

[0472] The terminal sends the generated purchase activity data to the server. The data is transmitted in real time, immediately after the purchase.

[0473] Step 3:

[0474] The server stores the received purchasing activity data in a database. During this process, the data is organized for each user, and individual profiles are continuously updated.

[0475] Step 4:

[0476] The server analyzes the stored data. This includes a process of applying machine learning algorithms based on the user's past purchase history and frequency to extract purchasing patterns and characteristics.

[0477] Step 5:

[0478] Based on the analysis results, the server generates a list of recommended products and services best suited to a specific user. This includes integrating relevant promotional and sales information.

[0479] Step 6:

[0480] The server sends recommended lists and promotional information to the terminal in real time. This information is displayed on the user's screen or played as audio.

[0481] Step 7:

[0482] The user receives a notification and checks its contents. If necessary, they can request additional information from their device via voice or text input.

[0483] Step 8:

[0484] The terminal receives a request from the user and sends a query to the server.

[0485] Step 9:

[0486] The server searches the database for information based on the user's request and returns the appropriate information to the terminal.

[0487] Step 10:

[0488] The device provides the user with the information it receives to help them make their next purchase decision. This information is presented visually on the screen or delivered via audio.

[0489] (Example 1)

[0490] 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."

[0491] In modern society, individual consumers are required to select products and services that are suitable for them from a vast amount of product information. However, the sheer volume of information and the lack of personalized recommendations make it difficult for consumers to make appropriate choices. Furthermore, there is a need for efficient systems that can quickly acquire real-time sales promotion information and respond to the diverse needs of consumers.

[0492] 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.

[0493] In this invention, the server includes means for collecting personal purchase-related information in real time via a terminal and transmitting it to the server; means for analyzing purchase patterns using a machine learning algorithm and automatically generating personalized purchase suggestions; and means for providing the generated suggestions to the individual in combination with sales promotion information and notifying them via screen or audio through the terminal. This makes it possible to generate and provide personalized suggestions in real time, enabling buyers to make more appropriate purchase decisions more quickly.

[0494] A "terminal" is an information processing device used by an individual when making a purchase, and it has the function of inputting and outputting data.

[0495] A "server" is a central computer system that communicates with terminals via a network and processes, stores, and analyzes data.

[0496] "Purchase-related information" refers to a series of data generated by an individual regarding their purchases, such as the name of the product, price, date and time, and location of the purchase.

[0497] A "machine learning algorithm" is an analytical method used to discover patterns and rules from data and build models that can be applied to new data.

[0498] "Purchase suggestions" are recommendations for products and services generated based on an individual's purchase history and patterns.

[0499] "Sales promotion information" refers to marketing information provided to promote the sale of products, such as special discounts, sale information, and campaign information.

[0500] A "generative AI model" is an artificial intelligence model that automatically generates responses and suggestions in natural language from given data.

[0501] A "prompt statement" is an instruction given to a generative AI model, and it functions as a guideline for deriving a specific output.

[0502] A "data profile" is a dataset that systematically aggregates information about an individual's purchasing behavior and tendencies.

[0503] "Two-way communication via voice and text" refers to the process of exchanging information between an individual and a server using voice or text data.

[0504] Embodiments of the present invention will be described below.

[0505] This system uses personal data in purchasing activities to provide personalized purchase suggestions to each user. First, users purchase goods or services via a terminal. The terminal includes a POS system and an online payment platform, and can be a general-purpose information processing device such as a smartphone or tablet. This generates purchase-related information entered by the user. This information includes the product name, price, date and time of purchase, and location of purchase.

[0506] The terminal sends the generated purchase information to the server in real time. This transmission uses encrypted communication protocols such as HTTPS to ensure the security of the information. The server is located in a cloud computing environment, for example, and stores and analyzes the data. The received purchase information is stored in a database, and each user's data profile is updated. Database systems such as MySQL or MongoDB may be used.

[0507] The server uses machine learning algorithms to analyze data profiles. Libraries such as Python's Scikit-learn and TensorFlow are used for the analysis. The server identifies purchasing trends and patterns, and based on this, generates personalized purchase suggestions using a generative AI model.

[0508] This purchase suggestion is combined with sales promotion information acquired in real time from the server. This sales promotion information includes discounts and campaign information. The server sends the generated purchase suggestion to the terminal, and the terminal notifies the user of this through screen display or audio output.

[0509] Furthermore, users can send voice or text inquiries to the server via their devices. For example, in response to an inquiry requesting detailed information about a specific product, the server will quickly search for the information and return a response to the user.

[0510] For example, if a user regularly purchases beverages, the server can use that purchase history to suggest special offers and notify the user, thereby supporting efficient purchasing.

[0511] An example of a prompt message might be: "Analyze purchase data to generate optimal product recommendations for the user. Reference data: Real-time purchase history, individual user purchasing patterns, and the latest promotional information."

[0512] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0513] Step 1:

[0514] When a user purchases a product, the terminal collects purchase-related information. Input data includes product name, price, purchase date and time, and purchase location. This information is automatically retrieved from POS systems and online payment platforms and recorded in the terminal. Purchase-related information is then generated as output.

[0515] Step 2:

[0516] The terminal sends generated purchase-related information to the server in real time. The input is purchase information recorded on the terminal. The transmission is encrypted using the HTTPS protocol and securely transmitted to the server. The server receives the purchase information as output.

[0517] Step 3:

[0518] The server stores the received purchase information in a database and updates each user's data profile. The input consists of purchase information and the existing data profile. A database system such as MySQL or MongoDB is used. The output is the updated user data profile.

[0519] Step 4:

[0520] The server performs analysis using machine learning algorithms based on data profiles. The input is updated user data profiles. It uses Python's Scikit-learn and TensorFlow to perform data calculations to analyze purchasing patterns and trends. The output is the analysis results.

[0521] Step 5:

[0522] The server uses a generative AI model based on the analysis results to generate purchase suggestions for the user. The inputs are the analysis results and sales promotion information. The generated purchase suggestions are obtained when the generative AI model creates and outputs prompt messages.

[0523] Step 6:

[0524] The server sends the generated purchase suggestion to the terminal. This suggestion incorporates sales promotion information such as special discounts and sale information. The input is the generated purchase suggestion. The output is a suggestion displayed or notified to the terminal based on the prompt.

[0525] Step 7:

[0526] Users can make inquiries to the server via voice or text through their device. The user's inquiry is sent to the server. The server searches for relevant information and returns a response to the user. Inputs include the user's inquiry and the user's data profile. Outputs include specific purchase-related information notified to the user.

[0527] (Application Example 1)

[0528] 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."

[0529] In modern consumer activity, consumers are required to efficiently select products that suit their individual needs from a vast amount of product information. However, conventional systems have struggled to provide personalized product recommendations in real time that fully consider each user's purchasing patterns. As a result, consumers may miss out on valuable sales promotion information, making it a challenge to provide users with optimal purchasing recommendations.

[0530] 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.

[0531] In this invention, the server includes means for collecting individual purchasing activity data, means for analyzing the collected purchasing activity data and generating personalized purchase suggestions, means for providing the analyzed suggestions and real-time sales promotion information to the individual, means for two-way communication with the individual using voice and text, means for providing purchase suggestions to the user via push notifications, and means for analyzing the user's purchasing patterns based on a machine learning algorithm. This makes it possible to efficiently provide personalized purchase suggestions to the user in real time.

[0532] "Personal purchasing activity data" refers to information about products and services purchased by users, and is a collection of data that includes details such as the date and time of purchase and the purchase price.

[0533] "Analyzing and generating personalized purchase recommendations" refers to the process of analyzing collected purchasing activity data to recommend the most suitable products and services to individual users.

[0534] "Providing real-time sales promotion information" means instantly communicating ongoing sales and discount information to users.

[0535] "Two-way communication using voice and text" refers to a means of communication in which the user and the system interact using voice or text.

[0536] "Delivering via push notifications" is a method of automatically sending information to a user's device to attract their attention.

[0537] "Analyzing data based on machine learning algorithms" refers to the act of analyzing data using algorithms that identify patterns and make predictions and recommendations.

[0538] To realize this invention, the system uses multiple hardware and software components. First, the user makes a purchase via a terminal such as a smartphone or personal computer. This generates purchase activity data such as product name, purchase price, and purchase date and time. The terminal has the function of transmitting this information to the server in real time.

[0539] The server collects purchasing activity data into a database and updates the data profile for each individual user. The server then uses machine learning algorithms to analyze user purchasing patterns and generate personalized purchase recommendations. The machine learning models used here are designed for pattern recognition and user behavior prediction.

[0540] The analyzed purchase suggestions are combined with real-time sales promotion information and sent from the server to the user's device as push notifications. Users can view these on their device screen or receive them as audio output. Users can also interact with the system interactively via voice or text, asking further questions or requesting more detailed information.

[0541] The server uses a generative AI model to enhance recommendations based on the user's purchase history and sends push notifications to alert users so they don't miss anything. This process allows users to optimize their time and purchasing efficiency.

[0542] As a concrete example, the server can help users save on living expenses by providing special discount information and new product suggestions for everyday necessities they frequently purchase. Furthermore, effective notifications can be achieved by using prompts to the generative AI model, such as, "Write code to generate personalized notifications suggesting special milk sales to users who purchase milk every week."

[0543] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0544] Step 1:

[0545] A user purchases a product using a terminal. The terminal generates purchase activity data, such as product name, purchase price, and purchase date and time, and sends it to the server. The input is the user's purchase action, and the output is the generated purchase activity data.

[0546] Step 2:

[0547] The server stores the received purchase activity data in a database and updates each user's data profile. The input is the purchase activity data sent from the terminal, and the output is the updated user data profile. The server then integrates the new data into the existing user profile.

[0548] Step 3:

[0549] The server applies machine learning algorithms based on data profiles to analyze user purchasing patterns and generate personalized purchase recommendations. The input is an updated user profile, and the output is personalized purchase recommendations. The analysis process involves recognizing the user's past purchasing trends and constructing new recommendations.

[0550] Step 4:

[0551] The server processes the generated purchase proposals in combination with sales promotion information collected in real time. The input consists of individualized purchase proposals and sales promotion information, while the output is integrated proposal information. The integration process optimizes the proposal information and prepares it for delivery to the user.

[0552] Step 5:

[0553] The server sends integrated suggestion information to the device via push notification. The input is the integrated suggestion information, and the output is the notification delivered to the user. Push notification operation includes methods of conveying information visually or audibly through the user interface on the device.

[0554] Step 6:

[0555] Users can review the suggestions through their terminal and make further inquiries to the server using voice or text. Input consists of the suggestion confirmation action and additional inquiries, while output is the additional information the user receives. In the communication process, the terminal relays user input to the server, which then generates an appropriate response.

[0556] Step 7:

[0557] The server uses a generative AI model to process user inquiries and provide additional information. The input is the user's inquiry, and the output is the answer information obtained from the AI ​​model. The AI ​​model's operation includes a process of resolving the user's questions using the prediction results.

[0558] 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.

[0559] The system of the present invention collects detailed data on an individual's purchasing activities and analyzes it in combination with an emotion engine to provide users with personalized purchasing suggestions in real time. An embodiment of this system is described below.

[0560] First, the user's purchasing behavior is recorded on the device. At this time, purchasing activity data such as the name of the purchased product, price, and date and time of purchase are generated and sent from the device to the server. The server stores this data in a database and continuously updates the individual user's profile.

[0561] The server uses machine learning algorithms to analyze the accumulated data. This extracts user purchasing patterns and preferences. Based on these analysis results, a list of recommended products and services is generated.

[0562] Here, an emotion engine operates on the device, detecting the user's emotional state by analyzing their voice input and on-screen interactions. Based on the emotional state recognized by the emotion engine (e.g., joy, surprise, or dissatisfaction), the server adjusts the content and presentation of purchase suggestions. For example, if the user indicates dissatisfaction, the emotion engine will suggest more advantageous discount information.

[0563] Next, the analyzed and refined recommendations and related real-time promotional information are sent from the server to the terminal. The information is displayed on the user's screen or output as audio. This allows the user to immediately review the recommendations and, if necessary, request further information via voice or text input.

[0564] For example, if a user shows a high level of interest in a particular brand's product and adds it to their purchase list, but for some reason hesitates to buy it, the emotion engine recognizes that interest, and the server adjusts to display special offers to encourage a purchase.

[0565] In this way, the system combining the emotion engine of the present invention aims to provide optimal support to improve the individual user experience and make purchasing decisions more personalized and efficient.

[0566] The following describes the processing flow.

[0567] Step 1:

[0568] When a user purchases a product through their device, purchase activity data is generated, including the name of the purchased product, its price, and the date and time of purchase.

[0569] Step 2:

[0570] The terminal sends the generated purchase activity data to the server. This data is sent in real time immediately after the transaction is completed.

[0571] Step 3:

[0572] The server saves the received data to the database and updates each user's profile. The saved data is stored in the database along with past purchase history.

[0573] Step 4:

[0574] The server analyzes the purchase data stored in the database. This analysis uses machine learning algorithms to extract user purchasing patterns and preferences.

[0575] Step 5:

[0576] The device analyzes the user's reactions to the product using an emotion engine based on voice input and screen interactions. The emotion engine detects the user's emotional state in real time.

[0577] Step 6:

[0578] The server adjusts the content and presentation method of generated purchase suggestions based on the emotional state obtained from the emotion engine. For example, if a customer expresses dissatisfaction, it will create suggestions that emphasize more favorable discount information.

[0579] Step 7:

[0580] The server sends customized purchase suggestions and real-time sales promotion information to the terminal.

[0581] Step 8:

[0582] The device notifies the user of received purchase suggestions. Notifications are provided to the user via screen display, audio output, and push notifications.

[0583] Step 9:

[0584] Users consider purchasing based on the information provided. If they need more detailed information, they can request additional information via voice or text on their device.

[0585] Step 10:

[0586] The terminal receives a user request and sends a query to the server.

[0587] Step 11:

[0588] The server quickly extracts information from the database in response to additional queries and sends it back to the terminal.

[0589] Step 12:

[0590] The device provides the user with further information to support their final purchasing decision. The information is presented in an optimal format, taking into account the user's emotional state.

[0591] (Example 2)

[0592] 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."

[0593] There is a need to streamline purchasing decision-making and improve the user experience by more accurately analyzing individual purchasing behavior and providing personalized purchase suggestions in real time that are tailored to the user's emotional state. Current systems have difficulty capturing the emotions of individual users, therefore, new technologies are needed to effectively facilitate purchasing activities.

[0594] 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.

[0595] In this invention, the server includes means for aggregating individual purchase behavior records and transmitting data, means for analyzing preferences using machine learning and adjusting and generating purchase suggestions, and means for detecting emotional states from voice and interactions using emotion analysis technology. This makes it possible to create and provide highly accurate suggestions based on the user's purchase behavior and emotional state.

[0596] "Collecting individual purchase behavior records and transmitting the data" refers to the process of recording a series of purchasing actions performed by individual users and sending them together to a server.

[0597] "Using machine learning to analyze preferences and adjust and generate purchase suggestions" refers to a method of analyzing user preferences and patterns using algorithms based on collected data, and then generating purchase suggestions that reflect the results.

[0598] "Detecting emotional states from voice and interaction using emotion analysis technology" refers to a process that accurately discerns a user's current emotional state by utilizing technology that identifies a user's emotions from voice data and user interactions.

[0599] "Providing real-time optimized sales promotion information" means a function that immediately presents users with the most effective sales information at the moment, based on analysis results.

[0600] "Enabling the request for additional information through two-way information communication" means a method that enables interaction between the user and the system by providing a mechanism that allows the user to request additional information as needed and provides the information accordingly.

[0601] A description of embodiments for carrying out the present invention will be provided.

[0602] This system analyzes the purchasing behavior and emotional state of individual users and provides personalized purchase recommendations in real time. The system consists of three main components: users, terminals, and servers.

[0603] First, the user views product information and proceeds with the purchase through a specific interface. The device utilizes a mobile application or web browser, and these interfaces begin recording the purchase behavior. Upon completion of the purchase, data such as product name, price, and purchase date and time are generated.

[0604] Next, the device sends this purchase data to the server using a secure protocol (e.g., HTTPS). The device has a built-in script that sends the data to the server in real time and possesses processing power capable of handling large-scale data communication.

[0605] The server stores and continuously updates purchase data using a database management system (e.g., MySQL, PostgreSQL). Machine learning algorithms also run on the server, analyzing the collected data to extract user preferences. Software tools such as Python, TensorFlow, and scikit-learn are used in this process. Based on the machine learning results, the most suitable purchase suggestions for the user are generated.

[0606] Furthermore, an emotion engine operates on the device, analyzing the user's emotional state from their voice input and on-screen interactions. This emotion analysis utilizes a voice recognition API and emotion analysis software. The device sends emotion analysis information to the server each time the user speaks or interacts with the screen.

[0607] The server receives sentiment analysis results, adjusts the generated purchase suggestions, and provides optimized sales promotion information in real time. Suggestions are presented via audio output or on-screen display through the terminal, allowing users to review them and request further information as needed.

[0608] As a concrete example, consider a scenario where a user is considering purchasing a new smartphone, but the price is a barrier. When the emotion engine detects the user's hesitation or anxiety, the server adjusts the suggestions to include special discount offers related to the price and displays them on the device.

[0609] Examples of prompts for generative AI models:

[0610] "Users are hesitant to make a purchase. Please generate effective sales promotion proposals that take their emotional state into consideration."

[0611] In this way, the system aims to improve the user's purchasing experience and support more efficient decision-making.

[0612] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0613] Step 1: Recording and Data Generation

[0614] The user selects products and completes the purchase process through the application. As input, product information, product name, price, and purchase date and time are automatically generated based on the user's actions. As output, purchase behavior data is recorded on the device. During this process, the application displays a confirmation message through the user interface.

[0615] Step 2: Data transmission

[0616] The terminal sends recorded purchase data to the server via a secure communication protocol. The input is the generated purchase data, which is sent using HTTPS. The output is the data arriving at the server. Specifically, the terminal attempts to send data to the server at regular intervals and retries until successful completion is confirmed.

[0617] Step 3: Storing and updating data

[0618] The server stores the received purchase data in the database. The input is the purchase data sent from the terminal, and the output is the updated state of the database. The database system maintains and updates the purchase history as needed. If the data is stored successfully, a confirmation message is logged.

[0619] Step 4: Preference analysis using machine learning

[0620] The server uses a machine learning model to analyze user preferences from accumulated purchase data. The input is purchase history in a database, and the output is a list of recommended products. A specific algorithm is applied to analyze user trends. This process utilizes Python and machine learning libraries.

[0621] Step 5: Emotion Analysis

[0622] On the device, an emotion engine analyzes the user's voice input and on-screen interactions to detect their emotional state. The input consists of user voice data and interaction data, while the output is the determined emotional state. Voice input is captured from the microphone, and an analysis API infers the emotional state.

[0623] Step 6: Adjusting the purchase proposal

[0624] The server adjusts pre-generated purchase suggestions based on the sentiment analysis results. The input is the emotional state identified by sentiment analysis and a list of recommended products generated by machine learning; the output is the adjusted purchase suggestion. Depending on a specific emotional state (e.g., surprise), the server performs processing to include special offers or recommended product information.

[0625] Step 7: Providing Proposal Information

[0626] The server sends the adjusted information to the terminal and provides it to the user. The input is the adjusted purchase suggestion, and the output is a notification to the user. The terminal presents the information to the user via voice and display, and offers the option to request additional information.

[0627] (Application Example 2)

[0628] 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."

[0629] Modern consumers find it difficult to make the best purchase choices from a vast amount of information and products. Furthermore, standard product recommendations fail to consider individual preferences and emotional states, resulting in ineffective sales promotion. This challenge needs to be addressed.

[0630] 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.

[0631] In this invention, the server includes means for collecting personal purchasing activity information, means for detecting the personal emotional state and optimizing purchase suggestions based on it, and means for generating prompt sentences based on emotion analysis and inputting them into a generation AI model. This makes it possible to provide each consumer with personalized purchase suggestions in real time that best match their emotions and preferences at that time.

[0632] "Means for collecting personal purchasing activity information" refers to a system that collects data on product purchases and browsing behaviors performed by users through their devices.

[0633] "A means of analyzing collected purchasing activity information and generating personalized purchase suggestions" refers to a process that uses machine learning algorithms to analyze acquired data and create suggestions tailored to the individual user's preferences and past behavior.

[0634] "A means of providing analyzed purchase suggestions and real-time sales promotion information to individuals" refers to a function that optimizes and delivers suggestion content in order to present users with immediately useful information on products and services.

[0635] "Means of two-way communication with individuals using voice and text" refers to an interface in which users interact with a system in voice or text format and exchange information and instructions.

[0636] "Methods for detecting an individual's emotional state and optimizing purchase suggestions based on it" refers to a system that analyzes voice and on-screen user actions to read changes in emotion and adjust the content of purchase suggestions accordingly.

[0637] "A means of generating prompt sentences based on sentiment analysis and inputting them into a generative AI model" refers to a process that generates text based on sentiment analysis results and uses that as input data for the AI ​​model to consider appropriate responses and suggestions.

[0638] To implement this invention, a system is required in which a user's terminal, a server, and an emotion engine work in coordination. The user's terminal consists of an electronic device such as a smartphone or tablet. When a user purchases a product, this terminal collects detailed product information and purchase history and transmits it to the server. The collected data is stored on the server as personal purchasing activity information.

[0639] The server analyzes this information using machine learning algorithms. Data science tools using Python or R, such as TensorFlow and Sci-kit Learn, are used for the analysis. This extracts user preferences and purchasing patterns, generating personalized purchase recommendations.

[0640] Furthermore, the user's device has a built-in emotion engine that analyzes voice input and on-screen interactions to detect the user's emotional state in real time. This emotion engine uses natural language processing technologies such as Google's Dialogflow and IBM Watson. Based on the emotional state, the server optimizes purchase suggestions. For example, if the user is feeling anxious, it will emphasize reassuring product reviews and special offers.

[0641] The analyzed and optimized suggestion information is sent back to the user's device in real time. Users can review the suggestions on the screen or request further information via voice. This allows users to receive suggestions that best match their emotions and purchasing needs at that moment.

[0642] For example, if a user is considering purchasing an expensive item, the system can analyze their past emotions when purchasing similar items to help them make a decision. If the emotion engine detects anxiety about the purchase, the server provides reassurance by showing compelling reasons to buy and positive reviews from other users. The prompt for the generating AI model would look like this: "Generate a way to provide additional product information to encourage purchase when the user's emotional state is anxious."

[0643] Thus, the system of the present invention is designed to personalize the user experience and support purchasing decisions.

[0644] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0645] Step 1:

[0646] The terminal records the user's purchasing actions. It collects data such as details of purchased items, purchase date, and price, and sends it to the server. The input is the user's purchasing action, and the output is purchase data that can be processed on the server side. The data is transmitted in real time.

[0647] Step 2:

[0648] The server stores the received purchase data in a database. A database management system is used to continuously update user-specific data profiles. The input is newly acquired purchase data, and the output is the updated user data profile.

[0649] Step 3:

[0650] The server analyzes purchase data using machine learning algorithms. It utilizes Python and R libraries to extract user preferences and patterns. The input is user history data, and the output is predictive data based on the analyzed patterns and preferences.

[0651] Step 4:

[0652] The server generates personalized purchase suggestions based on the analysis results and adjusts the suggestions by incorporating data from the emotion engine. The emotion analysis results are generated as prompts and input into the generating AI model. The input consists of analysis results and emotion data, and the output is an optimized purchase suggestion.

[0653] Step 5:

[0654] The device uses an emotion engine to detect the user's emotional state. It performs real-time speech recognition and text analysis, and sends the results to the server. The input is real-time interaction with the user, and the output is emotion analysis data.

[0655] Step 6:

[0656] The server uses sentiment analysis data to finalize purchase recommendations and sends them to the user's terminal. It presents information that provides specific purchase motivations. The input is optimized recommendation data, and the output is a presentation of recommended information to the user.

[0657] Step 7:

[0658] The user reviews the proposal and requests the necessary information via voice or text. The terminal sends the request to the server and retrieves the requested information. The input is the user's request operation, and the output is the provision of additional information.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] [Fourth Embodiment]

[0663] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0664] 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.

[0665] 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).

[0666] 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.

[0667] 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.

[0668] 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).

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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.

[0674] 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.

[0675] 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".

[0676] The system of the present invention utilizes personal data from purchasing activities to provide personalized purchasing suggestions to each user. An embodiment of this system is described below.

[0677] First, when a user makes a purchase through their device, purchase activity data is generated. This includes information such as the purchased items, purchase price, and date and time of purchase. The device sends this information to the server in real time. The server stores the received purchase activity data in a database and updates the data profile for each individual user.

[0678] Next, the server analyzes this purchase data. Specifically, it uses machine learning algorithms to extract user purchasing patterns and preferences. Based on these analysis results, it generates suggestions for the most appropriate products and services.

[0679] Furthermore, the server combines the suggestions derived from the analysis with real-time sales promotion information and sends it to the terminal. This allows users to immediately receive information through their terminal via screen display or audio output. For example, if a product that a user has frequently purchased in the past is included in a special sale, they will be notified immediately.

[0680] Furthermore, users can make inquiries via voice or text to obtain additional information. The terminal receives the user's inquiry and sends it to the server. The server quickly searches for the information, sends it back to the terminal, and notifies the user of the details.

[0681] For example, if a user purchases the same food items every week, the server can learn this purchase cycle and provide corresponding sale and discount information, thereby helping them reduce their living expenses.

[0682] In this way, the system of the present invention aims to provide individuals with a more valuable experience in their purchasing behavior and to streamline the purchasing decision-making process.

[0683] The following describes the processing flow.

[0684] Step 1:

[0685] When a user purchases a product, purchase activity data is generated. This data includes the name of the purchased product, its price, and the date and time of purchase.

[0686] Step 2:

[0687] The terminal sends the generated purchase activity data to the server. The data is transmitted in real time, immediately after the purchase.

[0688] Step 3:

[0689] The server stores the received purchasing activity data in a database. During this process, the data is organized for each user, and individual profiles are continuously updated.

[0690] Step 4:

[0691] The server analyzes the stored data. This includes a process of applying machine learning algorithms based on the user's past purchase history and frequency to extract purchasing patterns and characteristics.

[0692] Step 5:

[0693] Based on the analysis results, the server generates a list of recommended products and services best suited to a specific user. This includes integrating relevant promotional and sales information.

[0694] Step 6:

[0695] The server sends recommended lists and promotional information to the terminal in real time. This information is displayed on the user's screen or played as audio.

[0696] Step 7:

[0697] The user receives a notification and checks its contents. If necessary, they can request additional information from their device via voice or text input.

[0698] Step 8:

[0699] The terminal receives a request from the user and sends a query to the server.

[0700] Step 9:

[0701] The server searches the database for information based on the user's request and returns the appropriate information to the terminal.

[0702] Step 10:

[0703] The device provides the user with the information it receives to help them make their next purchase decision. This information is presented visually on the screen or delivered via audio.

[0704] (Example 1)

[0705] 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".

[0706] In modern society, individual consumers are required to select products and services that are suitable for them from a vast amount of product information. However, the sheer volume of information and the lack of personalized recommendations make it difficult for consumers to make appropriate choices. Furthermore, there is a need for efficient systems that can quickly acquire real-time sales promotion information and respond to the diverse needs of consumers.

[0707] 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.

[0708] In this invention, the server includes means for collecting personal purchase-related information in real time via a terminal and transmitting it to the server; means for analyzing purchase patterns using a machine learning algorithm and automatically generating personalized purchase suggestions; and means for providing the generated suggestions to the individual in combination with sales promotion information and notifying them via screen or audio through the terminal. This makes it possible to generate and provide personalized suggestions in real time, enabling buyers to make more appropriate purchase decisions more quickly.

[0709] A "terminal" is an information processing device used by an individual when making a purchase, and it has the function of inputting and outputting data.

[0710] A "server" is a central computer system that communicates with terminals via a network and processes, stores, and analyzes data.

[0711] "Purchase-related information" refers to a series of data generated by an individual regarding their purchases, such as the name of the product, price, date and time, and location of the purchase.

[0712] A "machine learning algorithm" is an analytical method used to discover patterns and rules from data and build models that can be applied to new data.

[0713] "Purchase suggestions" are recommendations for products and services generated based on an individual's purchase history and patterns.

[0714] "Sales promotion information" refers to marketing information provided to promote the sale of products, such as special discounts, sale information, and campaign information.

[0715] A "generative AI model" is an artificial intelligence model that automatically generates responses and suggestions in natural language from given data.

[0716] A "prompt statement" is an instruction given to a generative AI model, and it functions as a guideline for deriving a specific output.

[0717] A "data profile" is a dataset that systematically aggregates information about an individual's purchasing behavior and tendencies.

[0718] "Two-way communication via voice and text" refers to the process of exchanging information between an individual and a server using voice or text data.

[0719] Embodiments of the present invention will be described below.

[0720] This system uses personal data in purchasing activities to provide personalized purchase suggestions to each user. First, users purchase goods or services via a terminal. The terminal includes a POS system and an online payment platform, and can be a general-purpose information processing device such as a smartphone or tablet. This generates purchase-related information entered by the user. This information includes the product name, price, date and time of purchase, and location of purchase.

[0721] The terminal sends the generated purchase information to the server in real time. This transmission uses encrypted communication protocols such as HTTPS to ensure the security of the information. The server is located in a cloud computing environment, for example, and stores and analyzes the data. The received purchase information is stored in a database, and each user's data profile is updated. Database systems such as MySQL or MongoDB may be used.

[0722] The server uses machine learning algorithms to analyze data profiles. Libraries such as Python's Scikit-learn and TensorFlow are used for the analysis. The server identifies purchasing trends and patterns, and based on this, generates personalized purchase suggestions using a generative AI model.

[0723] This purchase suggestion is combined with sales promotion information acquired in real time from the server. This sales promotion information includes discounts and campaign information. The server sends the generated purchase suggestion to the terminal, and the terminal notifies the user of this through screen display or audio output.

[0724] Furthermore, users can send voice or text inquiries to the server via their devices. For example, in response to an inquiry requesting detailed information about a specific product, the server will quickly search for the information and return a response to the user.

[0725] For example, if a user regularly purchases beverages, the server can use that purchase history to suggest special offers and notify the user, thereby supporting efficient purchasing.

[0726] An example of a prompt message might be: "Analyze purchase data to generate optimal product recommendations for the user. Reference data: Real-time purchase history, individual user purchasing patterns, and the latest promotional information."

[0727] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0728] Step 1:

[0729] When a user purchases a product, the terminal collects purchase-related information. Input data includes product name, price, purchase date and time, and purchase location. This information is automatically retrieved from POS systems and online payment platforms and recorded in the terminal. Purchase-related information is then generated as output.

[0730] Step 2:

[0731] The terminal sends generated purchase-related information to the server in real time. The input is purchase information recorded on the terminal. The transmission is encrypted using the HTTPS protocol and securely transmitted to the server. The server receives the purchase information as output.

[0732] Step 3:

[0733] The server stores the received purchase information in a database and updates each user's data profile. The input consists of purchase information and the existing data profile. A database system such as MySQL or MongoDB is used. The output is the updated user data profile.

[0734] Step 4:

[0735] The server performs analysis using machine learning algorithms based on data profiles. The input is updated user data profiles. It uses Python's Scikit-learn and TensorFlow to perform data calculations to analyze purchasing patterns and trends. The output is the analysis results.

[0736] Step 5:

[0737] The server uses a generative AI model based on the analysis results to generate purchase suggestions for the user. The inputs are the analysis results and sales promotion information. The generated purchase suggestions are obtained when the generative AI model creates and outputs prompt messages.

[0738] Step 6:

[0739] The server sends the generated purchase suggestion to the terminal. This suggestion incorporates sales promotion information such as special discounts and sale information. The input is the generated purchase suggestion. The output is a suggestion displayed or notified to the terminal based on the prompt.

[0740] Step 7:

[0741] Users can make inquiries to the server via voice or text through their device. The user's inquiry is sent to the server. The server searches for relevant information and returns a response to the user. Inputs include the user's inquiry and the user's data profile. Outputs include specific purchase-related information notified to the user.

[0742] (Application Example 1)

[0743] 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".

[0744] In modern consumer activity, consumers are required to efficiently select products that suit their individual needs from a vast amount of product information. However, conventional systems have struggled to provide personalized product recommendations in real time that fully consider each user's purchasing patterns. As a result, consumers may miss out on valuable sales promotion information, making it a challenge to provide users with optimal purchasing recommendations.

[0745] 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.

[0746] In this invention, the server includes means for collecting individual purchasing activity data, means for analyzing the collected purchasing activity data and generating personalized purchase suggestions, means for providing the analyzed suggestions and real-time sales promotion information to the individual, means for two-way communication with the individual using voice and text, means for providing purchase suggestions to the user via push notifications, and means for analyzing the user's purchasing patterns based on a machine learning algorithm. This makes it possible to efficiently provide personalized purchase suggestions to the user in real time.

[0747] "Personal purchasing activity data" refers to information about products and services purchased by users, and is a collection of data that includes details such as the date and time of purchase and the purchase price.

[0748] "Analyzing and generating personalized purchase recommendations" refers to the process of analyzing collected purchasing activity data to recommend the most suitable products and services to individual users.

[0749] "Providing real-time sales promotion information" means instantly communicating ongoing sales and discount information to users.

[0750] "Two-way communication using voice and text" refers to a means of communication in which the user and the system interact using voice or text.

[0751] "Delivering via push notifications" is a method of automatically sending information to a user's device to attract their attention.

[0752] "Analyzing data based on machine learning algorithms" refers to the act of analyzing data using algorithms that identify patterns and make predictions and recommendations.

[0753] To realize this invention, the system uses multiple hardware and software components. First, the user makes a purchase via a terminal such as a smartphone or personal computer. This generates purchase activity data such as product name, purchase price, and purchase date and time. The terminal has the function of transmitting this information to the server in real time.

[0754] The server collects purchasing activity data into a database and updates the data profile for each individual user. The server then uses machine learning algorithms to analyze user purchasing patterns and generate personalized purchase recommendations. The machine learning models used here are designed for pattern recognition and user behavior prediction.

[0755] The analyzed purchase suggestions are combined with real-time sales promotion information and sent from the server to the user's device as push notifications. Users can view these on their device screen or receive them as audio output. Users can also interact with the system interactively via voice or text, asking further questions or requesting more detailed information.

[0756] The server uses a generative AI model to enhance recommendations based on the user's purchase history and sends push notifications to alert users so they don't miss anything. This process allows users to optimize their time and purchasing efficiency.

[0757] As a concrete example, the server can help users save on living expenses by providing special discount information and new product suggestions for everyday necessities they frequently purchase. Furthermore, effective notifications can be achieved by using prompts to the generative AI model, such as, "Write code to generate personalized notifications suggesting special milk sales to users who purchase milk every week."

[0758] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0759] Step 1:

[0760] A user purchases a product using a terminal. The terminal generates purchase activity data, such as product name, purchase price, and purchase date and time, and sends it to the server. The input is the user's purchase action, and the output is the generated purchase activity data.

[0761] Step 2:

[0762] The server stores the received purchase activity data in a database and updates each user's data profile. The input is the purchase activity data sent from the terminal, and the output is the updated user data profile. The server then integrates the new data into the existing user profile.

[0763] Step 3:

[0764] The server applies machine learning algorithms based on data profiles to analyze user purchasing patterns and generate personalized purchase recommendations. The input is an updated user profile, and the output is personalized purchase recommendations. The analysis process involves recognizing the user's past purchasing trends and constructing new recommendations.

[0765] Step 4:

[0766] The server processes the generated purchase proposals in combination with sales promotion information collected in real time. The input consists of individualized purchase proposals and sales promotion information, while the output is integrated proposal information. The integration process optimizes the proposal information and prepares it for delivery to the user.

[0767] Step 5:

[0768] The server sends integrated suggestion information to the device via push notification. The input is the integrated suggestion information, and the output is the notification delivered to the user. Push notification operation includes methods of conveying information visually or audibly through the user interface on the device.

[0769] Step 6:

[0770] Users can review the suggestions through their terminal and make further inquiries to the server using voice or text. Input consists of the suggestion confirmation action and additional inquiries, while output is the additional information the user receives. In the communication process, the terminal relays user input to the server, which then generates an appropriate response.

[0771] Step 7:

[0772] The server uses a generative AI model to process user inquiries and provide additional information. The input is the user's inquiry, and the output is the answer information obtained from the AI ​​model. The AI ​​model's operation includes a process of resolving the user's questions using the prediction results.

[0773] 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.

[0774] The system of the present invention collects detailed data on an individual's purchasing activities and analyzes it in combination with an emotion engine to provide users with personalized purchasing suggestions in real time. An embodiment of this system is described below.

[0775] First, the user's purchasing behavior is recorded on the device. At this time, purchasing activity data such as the name of the purchased product, price, and date and time of purchase are generated and sent from the device to the server. The server stores this data in a database and continuously updates the individual user's profile.

[0776] The server uses machine learning algorithms to analyze the accumulated data. This extracts user purchasing patterns and preferences. Based on these analysis results, a list of recommended products and services is generated.

[0777] Here, an emotion engine operates on the device, detecting the user's emotional state by analyzing their voice input and on-screen interactions. Based on the emotional state recognized by the emotion engine (e.g., joy, surprise, or dissatisfaction), the server adjusts the content and presentation of purchase suggestions. For example, if the user indicates dissatisfaction, the emotion engine will suggest more advantageous discount information.

[0778] Next, the analyzed and refined recommendations and related real-time promotional information are sent from the server to the terminal. The information is displayed on the user's screen or output as audio. This allows the user to immediately review the recommendations and, if necessary, request further information via voice or text input.

[0779] For example, if a user shows a high level of interest in a particular brand's product and adds it to their purchase list, but for some reason hesitates to buy it, the emotion engine recognizes that interest, and the server adjusts to display special offers to encourage a purchase.

[0780] In this way, the system combining the emotion engine of the present invention aims to provide optimal support to improve the individual user experience and make purchasing decisions more personalized and efficient.

[0781] The following describes the processing flow.

[0782] Step 1:

[0783] When a user purchases a product through their device, purchase activity data is generated, including the name of the purchased product, its price, and the date and time of purchase.

[0784] Step 2:

[0785] The terminal sends the generated purchase activity data to the server. This data is sent in real time immediately after the transaction is completed.

[0786] Step 3:

[0787] The server saves the received data to the database and updates each user's profile. The saved data is stored in the database along with past purchase history.

[0788] Step 4:

[0789] The server analyzes the purchase data stored in the database. This analysis uses machine learning algorithms to extract user purchasing patterns and preferences.

[0790] Step 5:

[0791] The device analyzes the user's reactions to the product using an emotion engine based on voice input and screen interactions. The emotion engine detects the user's emotional state in real time.

[0792] Step 6:

[0793] The server adjusts the content and presentation method of generated purchase suggestions based on the emotional state obtained from the emotion engine. For example, if a customer expresses dissatisfaction, it will create suggestions that emphasize more favorable discount information.

[0794] Step 7:

[0795] The server sends customized purchase suggestions and real-time sales promotion information to the terminal.

[0796] Step 8:

[0797] The device notifies the user of received purchase suggestions. Notifications are provided to the user via screen display, audio output, and push notifications.

[0798] Step 9:

[0799] Users consider purchasing based on the information provided. If they need more detailed information, they can request additional information via voice or text on their device.

[0800] Step 10:

[0801] The terminal receives a user request and sends a query to the server.

[0802] Step 11:

[0803] The server quickly extracts information from the database in response to additional queries and sends it back to the terminal.

[0804] Step 12:

[0805] The device provides the user with further information to support their final purchasing decision. The information is presented in an optimal format, taking into account the user's emotional state.

[0806] (Example 2)

[0807] 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".

[0808] There is a need to streamline purchasing decision-making and improve the user experience by more accurately analyzing individual purchasing behavior and providing personalized purchase suggestions in real time that are tailored to the user's emotional state. Current systems have difficulty capturing the emotions of individual users, therefore, new technologies are needed to effectively facilitate purchasing activities.

[0809] 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.

[0810] In this invention, the server includes means for aggregating individual purchase behavior records and transmitting data, means for analyzing preferences using machine learning and adjusting and generating purchase suggestions, and means for detecting emotional states from voice and interactions using emotion analysis technology. This makes it possible to create and provide highly accurate suggestions based on the user's purchase behavior and emotional state.

[0811] "Collecting individual purchase behavior records and transmitting the data" refers to the process of recording a series of purchasing actions performed by individual users and sending them together to a server.

[0812] "Using machine learning to analyze preferences and adjust and generate purchase suggestions" refers to a method of analyzing user preferences and patterns using algorithms based on collected data, and then generating purchase suggestions that reflect the results.

[0813] "Detecting emotional states from voice and interaction using emotion analysis technology" refers to a process that accurately discerns a user's current emotional state by utilizing technology that identifies a user's emotions from voice data and user interactions.

[0814] "Providing real-time optimized sales promotion information" means a function that immediately presents users with the most effective sales information at the moment, based on analysis results.

[0815] "Enabling the request for additional information through two-way information communication" means a method that enables interaction between the user and the system by providing a mechanism that allows the user to request additional information as needed and provides the information accordingly.

[0816] A description of embodiments for carrying out the present invention will be provided.

[0817] This system analyzes the purchasing behavior and emotional state of individual users and provides personalized purchase recommendations in real time. The system consists of three main components: users, terminals, and servers.

[0818] First, the user views product information and proceeds with the purchase through a specific interface. The device utilizes a mobile application or web browser, and these interfaces begin recording the purchase behavior. Upon completion of the purchase, data such as product name, price, and purchase date and time are generated.

[0819] Next, the device sends this purchase data to the server using a secure protocol (e.g., HTTPS). The device has a built-in script that sends the data to the server in real time and possesses processing power capable of handling large-scale data communication.

[0820] The server stores and continuously updates purchase data using a database management system (e.g., MySQL, PostgreSQL). Machine learning algorithms also run on the server, analyzing the collected data to extract user preferences. Software tools such as Python, TensorFlow, and scikit-learn are used in this process. Based on the machine learning results, the most suitable purchase suggestions for the user are generated.

[0821] Furthermore, an emotion engine operates on the device, analyzing the user's emotional state from their voice input and on-screen interactions. This emotion analysis utilizes a voice recognition API and emotion analysis software. The device sends emotion analysis information to the server each time the user speaks or interacts with the screen.

[0822] The server receives sentiment analysis results, adjusts the generated purchase suggestions, and provides optimized sales promotion information in real time. Suggestions are presented via audio output or on-screen display through the terminal, allowing users to review them and request further information as needed.

[0823] As a concrete example, consider a scenario where a user is considering purchasing a new smartphone, but the price is a barrier. When the emotion engine detects the user's hesitation or anxiety, the server adjusts the suggestions to include special discount offers related to the price and displays them on the device.

[0824] Examples of prompts for generative AI models:

[0825] "Users are hesitant to make a purchase. Please generate effective sales promotion proposals that take their emotional state into consideration."

[0826] In this way, the system aims to improve the user's purchasing experience and support more efficient decision-making.

[0827] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0828] Step 1: Recording and Data Generation

[0829] The user selects products and completes the purchase process through the application. As input, product information, product name, price, and purchase date and time are automatically generated based on the user's actions. As output, purchase behavior data is recorded on the device. During this process, the application displays a confirmation message through the user interface.

[0830] Step 2: Data transmission

[0831] The terminal sends recorded purchase data to the server via a secure communication protocol. The input is the generated purchase data, which is sent using HTTPS. The output is the data arriving at the server. Specifically, the terminal attempts to send data to the server at regular intervals and retries until successful completion is confirmed.

[0832] Step 3: Storing and updating data

[0833] The server stores the received purchase data in the database. The input is the purchase data sent from the terminal, and the output is the updated state of the database. The database system maintains and updates the purchase history as needed. If the data is stored successfully, a confirmation message is logged.

[0834] Step 4: Preference analysis using machine learning

[0835] The server uses a machine learning model to analyze user preferences from accumulated purchase data. The input is purchase history in a database, and the output is a list of recommended products. A specific algorithm is applied to analyze user trends. This process utilizes Python and machine learning libraries.

[0836] Step 5: Emotion Analysis

[0837] On the device, an emotion engine analyzes the user's voice input and on-screen interactions to detect their emotional state. The input consists of user voice data and interaction data, while the output is the determined emotional state. Voice input is captured from the microphone, and an analysis API infers the emotional state.

[0838] Step 6: Adjusting the purchase proposal

[0839] The server adjusts pre-generated purchase suggestions based on the sentiment analysis results. The input is the emotional state identified by sentiment analysis and a list of recommended products generated by machine learning; the output is the adjusted purchase suggestion. Depending on a specific emotional state (e.g., surprise), the server performs processing to include special offers or recommended product information.

[0840] Step 7: Providing Proposal Information

[0841] The server sends the adjusted information to the terminal and provides it to the user. The input is the adjusted purchase suggestion, and the output is a notification to the user. The terminal presents the information to the user via voice and display, and offers the option to request additional information.

[0842] (Application Example 2)

[0843] 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".

[0844] Modern consumers find it difficult to make the best purchase choices from a vast amount of information and products. Furthermore, standard product recommendations fail to consider individual preferences and emotional states, resulting in ineffective sales promotion. This challenge needs to be addressed.

[0845] 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.

[0846] In this invention, the server includes means for collecting personal purchasing activity information, means for detecting the personal emotional state and optimizing purchase suggestions based on it, and means for generating prompt sentences based on emotion analysis and inputting them into a generation AI model. This makes it possible to provide each consumer with personalized purchase suggestions in real time that best match their emotions and preferences at that time.

[0847] "Means for collecting personal purchasing activity information" refers to a system that collects data on product purchases and browsing behaviors performed by users through their devices.

[0848] "A means of analyzing collected purchasing activity information and generating personalized purchase suggestions" refers to a process that uses machine learning algorithms to analyze acquired data and create suggestions tailored to the individual user's preferences and past behavior.

[0849] "A means of providing analyzed purchase suggestions and real-time sales promotion information to individuals" refers to a function that optimizes and delivers suggestion content in order to present users with immediately useful information on products and services.

[0850] "Means of two-way communication with individuals using voice and text" refers to an interface in which users interact with a system in voice or text format and exchange information and instructions.

[0851] "Methods for detecting an individual's emotional state and optimizing purchase suggestions based on it" refers to a system that analyzes voice and on-screen user actions to read changes in emotion and adjust the content of purchase suggestions accordingly.

[0852] "A means of generating prompt sentences based on sentiment analysis and inputting them into a generative AI model" refers to a process that generates text based on sentiment analysis results and uses that as input data for the AI ​​model to consider appropriate responses and suggestions.

[0853] To implement this invention, a system is required in which a user's terminal, a server, and an emotion engine work in coordination. The user's terminal consists of an electronic device such as a smartphone or tablet. When a user purchases a product, this terminal collects detailed product information and purchase history and transmits it to the server. The collected data is stored on the server as personal purchasing activity information.

[0854] The server analyzes this information using machine learning algorithms. Data science tools using Python or R, such as TensorFlow and Sci-kit Learn, are used for the analysis. This extracts user preferences and purchasing patterns, generating personalized purchase recommendations.

[0855] Furthermore, the user's device has a built-in emotion engine that analyzes voice input and on-screen interactions to detect the user's emotional state in real time. This emotion engine uses natural language processing technologies such as Google's Dialogflow and IBM Watson. Based on the emotional state, the server optimizes purchase suggestions. For example, if the user is feeling anxious, it will emphasize reassuring product reviews and special offers.

[0856] The analyzed and optimized suggestion information is sent back to the user's device in real time. Users can review the suggestions on the screen or request further information via voice. This allows users to receive suggestions that best match their emotions and purchasing needs at that moment.

[0857] For example, if a user is considering purchasing an expensive item, the system can analyze their past emotions when purchasing similar items to help them make a decision. If the emotion engine detects anxiety about the purchase, the server provides reassurance by showing compelling reasons to buy and positive reviews from other users. The prompt for the generating AI model would look like this: "Generate a way to provide additional product information to encourage purchase when the user's emotional state is anxious."

[0858] Thus, the system of the present invention is designed to personalize the user experience and support purchasing decisions.

[0859] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0860] Step 1:

[0861] The terminal records the user's purchasing actions. It collects data such as details of purchased items, purchase date, and price, and sends it to the server. The input is the user's purchasing action, and the output is purchase data that can be processed on the server side. The data is transmitted in real time.

[0862] Step 2:

[0863] The server stores the received purchase data in a database. A database management system is used to continuously update user-specific data profiles. The input is newly acquired purchase data, and the output is the updated user data profile.

[0864] Step 3:

[0865] The server analyzes purchase data using machine learning algorithms. It utilizes Python and R libraries to extract user preferences and patterns. The input is user history data, and the output is predictive data based on the analyzed patterns and preferences.

[0866] Step 4:

[0867] The server generates personalized purchase suggestions based on the analysis results and adjusts the suggestions by incorporating data from the emotion engine. The emotion analysis results are generated as prompts and input into the generating AI model. The input consists of analysis results and emotion data, and the output is an optimized purchase suggestion.

[0868] Step 5:

[0869] The device uses an emotion engine to detect the user's emotional state. It performs real-time speech recognition and text analysis, and sends the results to the server. The input is real-time interaction with the user, and the output is emotion analysis data.

[0870] Step 6:

[0871] The server uses sentiment analysis data to finalize purchase recommendations and sends them to the user's terminal. It presents information that provides specific purchase motivations. The input is optimized recommendation data, and the output is a presentation of recommended information to the user.

[0872] Step 7:

[0873] The user reviews the proposal and requests the necessary information via voice or text. The terminal sends the request to the server and retrieves the requested information. The input is the user's request operation, and the output is the provision of additional information.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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."

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0895] The following is further disclosed regarding the embodiments described above.

[0896] (Claim 1)

[0897] Means of collecting personal purchasing activity data,

[0898] A means for analyzing collected purchasing activity data and generating personalized purchasing suggestions,

[0899] A means of providing individuals with analyzed suggestions and real-time sales promotion information,

[0900] A means of two-way communication with an individual using voice and text,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, which uses a machine learning algorithm to generate purchase suggestions.

[0904] (Claim 3)

[0905] The system according to claim 1, which notifies an individual of a proposal offered to them by screen display or audio output.

[0906] "Example 1"

[0907] (Claim 1)

[0908] A means of collecting personal purchase-related information in real time via a terminal and transmitting it to a server,

[0909] A means of storing collected purchase information in a database and updating individual data profiles,

[0910] A means for analyzing purchasing patterns using machine learning algorithms and automatically generating personalized purchase suggestions,

[0911] A means of providing the generated proposals to individuals in combination with sales promotion information, and notifying them via screen or audio through their devices,

[0912] A means of conducting two-way communication with individuals via voice or text and responding quickly to inquiries,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, which generates prompt sentences using a generation AI model in the generation of purchase proposals.

[0916] (Claim 3)

[0917] The system according to claim 1, which searches for relevant information based on an individual's inquiry and automatically generates and provides a response.

[0918] "Application Example 1"

[0919] (Claim 1)

[0920] Means of collecting personal purchasing activity data,

[0921] A means for analyzing collected purchasing activity data and generating personalized purchasing suggestions,

[0922] A means of providing individuals with analyzed suggestions and real-time sales promotion information,

[0923] A means of two-way communication with an individual using voice and text,

[0924] A means of providing purchase suggestions to users via push notifications,

[0925] A system that includes means for analyzing user purchasing patterns based on machine learning algorithms.

[0926] (Claim 2)

[0927] The system according to claim 1, which uses a machine learning algorithm to generate purchase suggestions.

[0928] (Claim 3)

[0929] The system according to claim 1, which notifies an individual of a proposal offered to them by screen display or audio output.

[0930] "Example 2 of combining an emotion engine"

[0931] (Claim 1)

[0932] A means of aggregating individual purchase behavior records and transmitting the data,

[0933] A means for storing aggregated purchase data and continuously updating the information,

[0934] A method for analyzing preferences using machine learning and adjusting and generating purchase suggestions,

[0935] A means for detecting emotional states from voice and interaction using emotion analysis technology,

[0936] A means for optimizing purchase suggestions based on detected emotions,

[0937] A means of providing optimized sales promotion information in real time,

[0938] A means that enables the request for additional information through two-way information communication,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, which incorporates an emotion analysis algorithm for optimizing purchase suggestions.

[0942] (Claim 3)

[0943] The system according to claim 1, which performs voice recognition and information output via digital display.

[0944] "Application example 2 when combining with an emotional engine"

[0945] (Claim 1)

[0946] Means of collecting information on individual purchasing activities,

[0947] A means for analyzing collected purchasing activity information and generating personalized purchase suggestions,

[0948] A means of providing individuals with analyzed purchase recommendations and real-time sales promotion information,

[0949] A means of two-way communication with an individual using voice and text,

[0950] A means for detecting an individual's emotional state and optimizing purchase suggestions based on it,

[0951] A means of generating prompt sentences based on sentiment analysis and inputting them into a generative AI model,

[0952] A system that includes this.

[0953] (Claim 2)

[0954] The system according to claim 1, which uses a machine learning algorithm to generate purchase suggestions.

[0955] (Claim 3)

[0956] The system according to claim 1, which notifies an individual of a proposal offered to them by screen display or audio output. [Explanation of symbols]

[0957] 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. Means of collecting personal purchasing activity data, A means for analyzing collected purchasing activity data and generating personalized purchasing suggestions, A means of providing individuals with analyzed suggestions and real-time sales promotion information, A means of two-way communication with an individual using voice and text, A system that includes this.

2. The system according to claim 1, which uses a machine learning algorithm to generate purchase suggestions.

3. The system according to claim 1, which notifies an individual of a proposal offered to them by displaying it on a screen or outputting it with sound.

Images