system

Abstract

To provide a system that enables users to avoid wasteful consumption and make better purchasing decisions. [Solution] A system including: means for receiving an operation by a user to add a product to an online shopping cart; means for prompting the user to input the reason for purchase and expected frequency of use for the product; means for transmitting the input data on the reason for purchase and expected frequency of use to a server; means on the server for referencing the user's past purchase history data and predicting the actual frequency of use of the product; means for generating a warning message urging the user to reconsider their purchase if the predicted frequency of use falls below a set threshold; means for suggesting alternative products along with the warning message; and means for displaying the warning message and information regarding the alternative products to the user.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Online shopping is very common these days, but users often make impulse purchases or purchase unnecessary items, resulting in the waste of money that could be used for savings or asset formation. This problem can lead to an increase in possessions, making it difficult to tidy up a room and cluttering living space with unnecessary items. Furthermore, there is a lack of appropriate information for users to reconsider their purchases, making it difficult to curb one-sided consumption behavior. There is a need for a system that can improve this situation and enable users to make more profitable purchases. [Means for solving the problem]

[0005] The present invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and determines the effectiveness of the purchase. Specifically, it receives an operation by the user to add the product to their cart, and provides a means for the user to input the reason for purchase and expected frequency of use at that time. This input data is sent to a server, which then references past purchase history data to predict the actual frequency of use. If the predicted frequency of use falls below a set threshold, a warning message is generated urging the user to reconsider the purchase, and alternative products such as financial products or health-related products are simultaneously suggested. This allows users to avoid wasteful consumption and make better purchasing decisions.

[0006] "Online shopping" is the act of purchasing goods and services via the Internet.

[0007] "Add to cart" is an operation in which a user places an item that they are considering purchasing on an online shopping site into a temporary shopping list.

[0008] A "reason for purchase" is a user's motivation or purpose for purchasing a particular product.

[0009] "Expected frequency of use" is a prediction that indicates how often the user plans to use the product they are planning to purchase.

[0010] A "server" is a computer system that processes and stores data on a network.

[0011] A "database" is a system for efficiently handling a collection of data, and is used in particular to manage past purchase history and user information.

[0012] "Frequency of use" is a measure of how often a particular product is used.

[0013] A "threshold" is a value for setting a specific standard, and is a reference point at which a specific process is performed depending on whether the value is exceeded or falls below the threshold.

[0014] A "warning message" is a notice that is displayed to alert the user, especially to prevent unnecessary purchases.

[0015] A "substitute product" is a product that replaces the product the user intends to purchase and primarily contributes to the user's benefit or health.

[0016] "Financial products" are various economic products offered for purposes such as investment, savings, and insurance.

[0017] "Health-related products" are products related to improving or maintaining a user's health, including fitness trackers and health foods. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[0040] Overall flow

[0041] 1. User adds product to cart

[0042] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use.

[0043] 2. Sending input data

[0044] The user enters the reason for purchase and expected frequency of use, and this data is sent to the server.

[0045] 3. Data Analysis

[0046] The server analyzes the received user data and predicts actual usage frequency by referencing the user's past purchase history data.

[0047] The server generates a warning message if the predicted usage frequency falls below a set threshold.

[0048] 4. Warnings and alternative products

[0049] It receives a response from the server and displays alternative products (financial products or health-related products) to the user along with a warning message.

[0050] Program processing steps and examples

[0051] 1. User adds product to cart

[0052] Terminal handling

[0053] When a user adds an item to their cart on an online shopping site, they are prompted with a form asking them to enter their reason for purchase and expected frequency of use.

[0054] For example, if a user adds a "camera" to their cart, they might purchase the camera "to enjoy taking photos while traveling" and enter the expected frequency of use as "once a week."

[0055] 2. Sending input data

[0056] Terminal handling

[0057] The purchase reason and expected frequency of use entered by the user are sent to the server.

[0058] 3. Data Analysis

[0059] Server Processing

[0060] The server receives the user data and stores it in a database.

[0061] The server refers to the user's past purchase history data and predicts how often similar products will be used.

[0062] For example, based on data on how often a user has used cameras they have purchased in the past, it predicts that the actual frequency of use of a new camera will be about "once a month."

[0063] If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[0064] 4. Warnings and alternative products

[0065] Terminal handling

[0066] Receives the response from the server and displays a warning message to the user.

[0067] For example, you might see a message like, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0068] At the same time, alternative products such as "financial savings products" and "health improvement devices" are proposed.

[0069] Specific examples

[0070] User operation example

[0071] 1. A user adds a camera to their cart online.

[0072] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0073] System processing flow

[0074] 1. The device accepts user input and sends it to the server.

[0075] 2. The server analyzes the user's past purchase history to determine how frequently the user has used the camera they previously purchased.

[0076] 3. If the predicted results indicate that the actual usage frequency is low, a warning message is generated.

[0077] 4. Along with the warning, offer alternative product suggestions.

[0078] In this way, the present invention helps users avoid wasteful consumption and purchase more beneficial products. By utilizing the user's past behavior data, the server can make more accurate predictions and promote conscious consumption behavior by the user.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] A user adds a product to a cart on an online shopping site. The device receives this action and displays a form that asks the user to enter the reason for purchase and expected frequency of use. Once the user enters and confirms this information, the input data is saved on the device.

[0082] Step 2:

[0083] The terminal sends the input data of the user's reason for purchase and expected frequency of use to the server. This transmission includes all data such as product information, reason for purchase, and expected frequency of use.

[0084] Step 3:

[0085] The server analyzes the received user data. Specifically, the server accesses a database, references the user's past purchase history, and obtains usage frequency data for similar products.

[0086] Step 4:

[0087] The server compares the past purchase history data with the user's input data. Based on the actual usage frequency of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction process uses statistical analysis of the historical data.

[0088] Step 5:

[0089] The server compares the predicted usage frequency with a configured threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, the server generates a warning message, which includes a message encouraging the user to reconsider their purchase.

[0090] Step 6:

[0091] The server generates a list of alternative products along with a warning message. The alternative products are mainly financial and health-related products. This list is retrieved from a database and is selected with the user's convenience and health in mind.

[0092] Step 7:

[0093] The device receives a response from the server, which includes a warning message and information about alternative products.

[0094] Step 8:

[0095] The device displays a warning message to the user, such as "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0096] Step 9:

[0097] The device displays a list of alternative products to the user, including the name and a brief description of each alternative product, allowing the user to reconsider their purchase or switch to an alternative product.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] Conventional online shopping systems lack the means to predict the frequency of use or effectiveness of a product after the user has purchased it, which leads to problems such as increased wasteful consumption and unnecessary purchases.In addition, there is a lack of information to help users reconsider their purchases or suggestions for alternative products, which makes it difficult for them to make more beneficial product choices.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes means for referencing the user's past purchase history data and predicting the actual frequency of use of the product, means for the server to predict the frequency of use using a machine learning model, means for storing the data in a database, means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a set threshold, means for suggesting alternative products along with the warning message, and means for displaying the warning message and information about the alternative products to the user. This allows the user to obtain useful information when purchasing a product, avoid wasteful consumption, and select more beneficial products.

[0103] "User" refers to a consumer who uses the system to purchase products.

[0104] An "online shopping cart" is a virtual cart that allows users to temporarily store items they wish to purchase on an online shopping site.

[0105] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0106] "Expected frequency of use" refers to a prediction of how often a user will use the product they are about to purchase.

[0107] "Server" refers to a computer system that receives, processes, and stores data from users.

[0108] "Means of transmission" refers to the method or technology used to transfer data from the user's device to the server.

[0109] "Purchase history data" refers to information about products a user has purchased in the past and how often they have been used.

[0110] A "machine learning model" refers to an algorithm or mathematical model that allows a computer to generate patterns and make predictions based on past data.

[0111] A "database" refers to a system that organizes and stores data so that it can be searched and retrieved as needed.

[0112] A "threshold" refers to a specific numerical standard, and is a reference value for setting conditions under which judgments and processing differ depending on whether the standard is exceeded or not.

[0113] "Warning message" refers to a notification message that alerts the user to a specific action or situation.

[0114] "Substitute products" refer to products that are offered as alternatives to the product a user is considering purchasing.

[0115] "Financial product" means a product offered for investment or asset management, including, for example, savings plans and mutual funds.

[0116] "Health-related products" are products designed to promote the health of users, including, for example, fitness equipment and health supplements.

[0117] "Means for displaying" refers to the method or technology for visually displaying information sent from the server on the user's device.

[0118] The present invention provides a system for predicting the frequency and duration of a user's purchase of a product through online shopping, and determining the effectiveness of the purchase. This system is implemented through the following steps.

[0119] User adds product to cart

[0120] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter their reason for purchase and expected frequency of use. The device generates the input form using HTML and JavaScript (registered trademark) and provides the user interface. In this example, a user adds a "camera" to their cart and enters their reason for purchase as "to enjoy taking photos on trips" and their expected frequency of use as "once a week."

[0121] Sending input data

[0122] The device sends the purchase reason and expected usage frequency entered by the user to the server via an HTTP POST request, and the data is sent securely.

[0123] Data analysis

[0124] The server stores the received data in a database (e.g., MySQL (registered trademark) or PostgreSQL) and references the user's past purchase history. Next, the server uses a machine learning model (e.g., scikit-learn or TENSORFLOW (registered trademark)) to predict the actual usage frequency of the product. If the prediction result falls below a set threshold (e.g., threshold 0.5), the server generates a warning message.

[0125] Warnings and alternative products

[0126] The response from the server is sent to the device, which then displays a warning message and alternative products to the user. For example, the warning message might say, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase." At the same time, alternative products such as "financial savings products" and "health improvement devices" are suggested.

[0127] Specific examples

[0128] A specific example of a user's actions might be adding a camera to their cart online, inputting the reason for the purchase as "to enjoy taking photos while traveling" and the expected frequency of use as "once a week."

[0129] Prompt Sentence Examples

[0130] Examples of prompts to input to a generative AI model include:

[0131] "A user adds a camera to their cart and enters the reason for the purchase, "to enjoy taking photos while traveling," and the expected frequency of use, "once a week." The server receives this information, predicts that the user will use the camera infrequently based on their past purchase history, and displays a warning message and alternative products."

[0132] This invention allows users to avoid wasteful consumption and receive assistance in selecting beneficial products. The server utilizes the user's past behavioral data to make highly accurate predictions, enabling the user to promote conscious consumption behavior.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1: User adds product to cart

[0135] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and expected frequency of use. The input here is the product name added to the cart by the user, the reason for purchase, and expected frequency of use. The device generates the input form using HTML and JavaScript and displays it to the user.

[0136] Specific behavior:

[0137] A user adds an item to their cart.

[0138] The terminal generates and displays an input form using HTML and JavaScript.

[0139] The user enters the reason for purchase and frequency of use.

[0140] Step 2: Submitting input data

[0141] The device sends the data entered by the user, including the reason for purchase and expected frequency of use, to the server. This is done using an HTTP POST request. The input data includes the product name, reason for purchase, and expected frequency of use. This data is then passed to the server as output.

[0142] Specific behavior:

[0143] The user clicks the submit button.

[0144] The device generates an HTTP POST request.

[0145] Data on purchase reason and frequency of use is sent to the server.

[0146] Step 3: Save your data

[0147] The server stores the received data in a database. The input is the user's reason for purchasing and expected frequency of use, and the output is the data stored in the database. Databases such as MySQL or PostgreSQL are often used here.

[0148] Specific behavior:

[0149] The server receives the data.

[0150] The server establishes a database connection.

[0151] Execute an INSERT query on the database to save the data.

[0152] Step 4: Get your past purchase history

[0153] The server retrieves the user's past purchase history data from the database. The input is the user ID, and the output is the past purchase history data.

[0154] Specific behavior:

[0155] The server queries the database for past purchase history based on the user ID.

[0156] The database returns historical purchase data.

[0157] Step 5: Predicting usage frequency

[0158] The server uses a machine learning model to predict the frequency of new product purchases based on the acquired past purchase history. The input is past purchase history data and new product data, and the output is the predicted frequency of use. Machine learning libraries such as scikit-learn and TensorFlow are used here.

[0159] Specific behavior:

[0160] The server inputs past purchase history data into the machine learning model.

[0161] Machine learning models predict the frequency of new product use.

[0162] The predicted usage frequency is returned to the server.

[0163] Step 6: Generate a warning message

[0164] If the predicted usage frequency is below a set threshold, the server generates a warning message. The inputs are the predicted usage frequency and the threshold, and the output is the warning message.

[0165] Specific behavior:

[0166] The server compares the predicted usage frequency with a threshold.

[0167] If the usage rate falls below a threshold, the server generates a warning message.

[0168] Step 7: Suggest alternative products

[0169] The server suggests alternative products along with a warning message, such as financial products or health-related products. The input is the warning message, and the output is a list of alternative products.

[0170] Specific behavior:

[0171] The server generates a list of alternative products.

[0172] The server includes a warning message and information about alternative products in an HTTP response and sends it to the terminal.

[0173] Step 8: Display warning messages and alternative products

[0174] The terminal receives the response from the server and displays a warning message and alternative products to the user. The input is the response data from the server, and the output is the displayed message and product list.

[0175] Specific behavior:

[0176] The terminal receives an HTTP response from the server.

[0177] The device generates a warning message and a list of alternative products using HTML and JavaScript.

[0178] The user is presented with a warning message and alternative products.

[0179] (Application example 1)

[0180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] When shopping online, it is common for users to fail to use purchased products appropriately, resulting in wasteful consumption. This not only reduces user satisfaction, but can also be a factor in increasing the burden on the environment. In particular, it is difficult to predict how much a user will actually use a product, making it difficult to make purchases based on that judgment. Therefore, there is a need for methods to support efficient consumption behavior. In addition, there is a lack of methods to suggest appropriate alternative products to encourage users to reconsider their purchase.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0183] In this invention, the server includes: means for receiving a user's operation to add a product to an online shopping cart; means for prompting the user to input a reason for purchase and an expected frequency of use for the product; means for transmitting the input data on the reason for purchase and expected frequency of use to the server; means for referencing the user's past purchase history data and predicting the actual frequency of use of the product; means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a preset threshold; means for suggesting alternative products along with the warning message; means for displaying the warning message and information about the alternative products to the user; means for generating alternative products using an artificial intelligence model if the expected frequency of use and the actual frequency of use do not match; and means for inputting the warning message and the content of the suggested alternative products as prompts to the artificial intelligence model. This allows users to avoid wasteful consumption and purchase products that are more effective and meet their needs. Furthermore, supporting efficient consumption behavior is expected to reduce environmental impact.

[0184] "User" refers to a consumer who purchases or uses a product.

[0185] An "online shopping cart" refers to a virtual shopping basket on an online shopping site that has the function of temporarily storing items that users intend to purchase.

[0186] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0187] "Expected frequency of use" refers to how often a user plans to use the product they have purchased.

[0188] "Server" refers to a computer system for processing and managing data.

[0189] "Purchase history data" refers to data regarding information about products purchased by a user in the past and their usage status.

[0190] "Actual frequency of use" refers to how often a user has used a product they have purchased in the past.

[0191] "Threshold" refers to a set reference value below which specific action is taken.

[0192] "Warning message" refers to a notification displayed to the user to encourage caution or reconsideration.

[0193] "Substitute products" are products that are suggested to replace the product a user is considering purchasing with other suitable products.

[0194] An "artificial intelligence model" refers to a type of computer program that processes large amounts of data, learns, and makes predictions and suggestions.

[0195] A "prompt sentence" is an instruction sentence input to an artificial intelligence model, and includes conditions and questions for obtaining a specific output.

[0196] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[0197] Overall flow

[0198] 1. User adds product to cart

[0199] When a user adds an item to their cart on an online shopping site, they are prompted to enter the reason for the purchase and the expected frequency of use. For example, if a user adds a "camera" to their cart, they will purchase the camera "to enjoy taking photos on trips" and enter the expected frequency of use as "once a week."

[0200] 2. Sending input data

[0201] The reason for purchase and expected frequency of use entered by the user are sent to the server. Data can be easily sent to the server using a device such as a smartphone.

[0202] 3. Data Analysis

[0203] The server analyzes the user's past purchase history data to predict actual usage frequency. This analysis is performed using a server system using Python and the Django framework. For example, based on the usage frequency data of a user's previously purchased camera, it predicts that the actual usage frequency of a new camera will be about "once a month."

[0204] 4. Warnings and alternative products

[0205] If the predicted usage frequency falls below a set threshold, the server generates a warning message for the user. At the same time, it uses an artificial intelligence model (generative AI model) to suggest alternative products to the user. For example, the server might suggest "savings products" or "health improvement equipment" along with a message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase."

[0206] Hardware and software used

[0207] Hardware: User's smartphone, server computer

[0208] Software: Python, Django framework, generative AI models

[0209] Specific examples of processing and prompts

[0210] For example, if a user adds a camera to their cart using the "Shopping Advisor" app on their smartphone and enters "to enjoy taking photos while traveling" and "to use once a week," the process proceeds as follows: The server receives the input data, predicts the actual frequency of use based on past purchase history data, and if the predicted value falls below a threshold, generates a warning message and suggests alternative products.

[0211] Example prompt sentence:

[0212] When a user purchases a product, the system asks them to input their expected usage frequency and reason for purchase. Predict the actual usage frequency from the user's past purchase history, and if the predicted usage frequency is below a threshold, display a warning message and suggest alternative products.

[0213] This allows users to avoid wasteful consumption and support efficient and beneficial consumption behavior. Furthermore, by using a generative AI model, more accurate alternative product suggestions can be realized.

[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0215] Step 1:

[0216] The user adds an item to the cart.

[0217] Input: The user selects the product they want to purchase and adds it to their cart.

[0218] Output: The product to be purchased is added to the cart, and a form is displayed to enter the reason for purchase and expected frequency of use.

[0219] Step 2:

[0220] The device prompts the user to enter the reason for purchase and expected frequency of use.

[0221] Input: Product information added to cart. Enter the reason for purchase (e.g., to enjoy taking photos while traveling) and expected frequency of use (e.g., once a week).

[0222] Output: Data on purchase reasons and expected frequency of use.

[0223] Step 3:

[0224] The terminal transmits the input data on the reason for purchase and the expected frequency of use to the server.

[0225] Input: Purchasing reason and expected frequency of use data.

[0226] Output: This data is sent to the server.

[0227] Step 4:

[0228] Based on the data received by the server, the server refers to the user's past purchase history data and predicts the actual frequency of use of the product.

[0229] Inputs: Purchasing reason, expected frequency of use, and the user's past purchasing history data.

[0230] Output: The predicted usage frequency of the product.

[0231] How it works: The server retrieves past purchase history from the database, analyzes usage frequency data for similar products, and uses an AI model to calculate the predicted usage frequency of newly added products.

[0232] Step 5:

[0233] If the server predicts that the frequency of use will fall below a set threshold, it generates a warning message encouraging users to reconsider their purchase.

[0234] Input: The expected frequency of use of the product. Threshold (e.g., 0.5).

[0235] Output: A warning message.

[0236] How it works: The server compares the predicted usage frequency to a threshold and generates a warning message if it falls below the threshold. The message might include, "This product is unlikely to be used as frequently as expected. Please reconsider your purchase."

[0237] Step 6:

[0238] The server inputs a prompt sentence into the generative AI model to suggest alternative products along with a warning message.

[0239] Input: Warning message, suggested alternative products, prompt (e.g., prompting the user to input their expected usage frequency and reason for purchasing the product, and suggesting alternative products).

[0240] Output: A list of suggested alternative products.

[0241] How it works: The server inputs a prompt into the generative AI model, which then generates appropriate alternative products (e.g., financial products for savings, health improvement devices, etc.).

[0242] Step 7:

[0243] The device will display a warning message and information about alternative products to the user.

[0244] Input: Warning message, list of suggested alternative products.

[0245] Output: A warning message and a list of alternative products that are displayed to the user.

[0246] Behavior: The device displays a warning message received from the server and a list of alternative products to the user, encouraging them to reconsider. For example, a message like "The camera is unlikely to be used as frequently as expected. Consider purchasing the following product instead" is displayed along with a list of alternative products.

[0247] This allows users to avoid wasteful consumption and purchase products efficiently and appropriately. Furthermore, by using generative AI models, more accurate alternative product suggestions can be realized.

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] The present invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[0250] Overall system overview

[0251] 1. User adds product to cart

[0252] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use, and an interface is also displayed to recognize the user's emotional state.

[0253] 2. Sending input data

[0254] The user inputs the reason for purchase and the expected frequency of use, and emotional data is also acquired. This data is sent to the server.

[0255] 3. Data Analysis

[0256] The server analyzes the received user data and emotion data, accesses a database to reference past purchase history data, and predicts the actual frequency of use for each product.

[0257] 4. Warnings and alternative products

[0258] Based on the user's emotional state, the server adjusts the tone and content of warning messages to encourage reconsideration of the purchase and suggests alternative financial or health products.

[0259] Program processing explanation

[0260] 1. User adds product to cart

[0261] Terminal handling

[0262] When a user adds an item to their cart on an online shopping site, they are prompted to enter their reason for purchase and expected frequency of use. An interface for emotion recognition is also displayed. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the system uses facial recognition and text input to recognize the user's emotional state.

[0263] 2. Sending input data

[0264] Terminal handling

[0265] The purchase reason, expected frequency of use, and emotional data entered by the user are sent to the server.

[0266] 3. Data Analysis

[0267] Server Processing

[0268] The server receives user data and emotion data and stores them in a database.

[0269] The server references the user's past purchase history data to obtain usage frequency data for similar products, and analyzes the user's emotional data to understand their current emotional state.

[0270] The server predicts the frequency of use of newly added items based on past purchase history data and user emotional data. This prediction process combines statistical analysis of historical data and analysis of emotional data.

[0271] 4. Warnings and alternative products

[0272] Server Processing

[0273] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, a warning message is generated based on the user's emotional state. For example, if emotion analysis determines that the user is in an impulsive state, a more emphatic warning message is sent.

[0274] The server will then provide a warning message along with alternative product suggestions (such as financial products or health improvement tools), which will be explained in a tone appropriate to the user's emotional state.

[0275] Specific examples

[0276] User operation example

[0277] 1. A user goes online and adds a camera (ID: 123) to their cart.

[0278] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0279] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[0280] System processing flow

[0281] 1. The device accepts user input and emotion data and sends it to the server.

[0282] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[0283] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0284] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0285] In this way, the present invention can guide users' consumption behavior in a healthier and more efficient direction by avoiding wasteful consumption and suggesting more beneficial products while taking into account their emotional state.

[0286] The processing flow will be explained below.

[0287] The present invention provides a system that, when a user purchases a product through online shopping, predicts the frequency and duration of use of the product, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase.

[0288] Step 1:

[0289] A user adds an item to their cart on an online shopping site. The device receives this action and displays a form that prompts the user to enter the reason for purchase and expected frequency of use. It also displays an interface for emotion recognition. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the device will use facial recognition and text input to identify the user's emotional state.

[0290] Step 2:

[0291] When the user inputs the reason for purchase, expected frequency of use, and emotional data and presses the confirm button, this data is saved on the device, which then sends it to the server.

[0292] Step 3:

[0293] The server analyzes the received user data, expected usage frequency, and emotion data. Specifically, the server accesses a database, references the user's past purchase history, and extracts usage frequency data for similar products.

[0294] Step 4:

[0295] The server compares past purchase history data with the user's input data. Based on the actual usage frequency data of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction reflects not only the historical data but also the user's emotional data.

[0296] Step 5:

[0297] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency is below this threshold, the emotion engine analyzes the user's emotional state and determines the appropriate tone and content of the warning message. For example, if the user's emotional state is "excited," a stronger warning message is generated.

[0298] Step 6:

[0299] The server generates a warning message along with a list of alternative products, including financial and health-related products, with descriptions that reflect the emotion data.

[0300] Step 7:

[0301] The device receives the response from the server and displays a warning message to the user, for example, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0302] Step 8:

[0303] The device presents the user with a list of alternative products, including the name and a brief description of each alternative, presented in a tone that reflects the user's emotional state—for example, a more gentle suggestion would be used if the user returned to a calm state.

[0304] As a specific example, consider the case where a user is trying to purchase a camera. The user adds a "camera" to their cart, enters the reason for the purchase as "to enjoy taking photos while traveling," and enters the expected frequency of use as "once a week." The emotion recognition interface recognizes that the user is in an "excited" state. The server analyzes past purchase data and determines that the actual predicted frequency of use is about "once a month." Therefore, the server generates a strong warning message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase," and suggests alternative products such as a "savings product" or a "health improvement device."

[0305] As described above, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding users' consumption behavior in a healthy and efficient direction.

[0306] Example 2

[0307] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] In conventional online shopping systems, users often make impulse purchases based on their emotions, and there is a lack of means to evaluate the validity of their purchases. This leads to wasteful consumption and inappropriate product choices, which increases the user's financial burden. The purpose of this invention is to solve this problem by providing a system that takes into account the user's emotional state and increases the validity of purchases.

[0309] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving an operation by a user to add a product to an online shopping cart, a means for prompting the user to input a purchase reason and an expected frequency of use for the product, and a means for transmitting the input data of the purchase reason and expected frequency of use to the server. This makes it possible to evaluate the validity of a purchase while taking into account the emotional state of the user, prevent wasteful consumption, and suggest appropriate products.

[0310] "User" refers to a consumer who selects and purchases products on an online shopping site.

[0311] "Online shopping cart" refers to a virtual basket that temporarily stores items selected by a user on an online shopping site.

[0312] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0313] "Expected frequency of use" refers to numbers or terms that predict how often a user will use the product they are about to purchase.

[0314] "Emotional state" refers to the psychological and emotional state a user is in when purchasing a product, including states such as excitement, joy, sadness, and anger.

[0315] "Server" refers to a computer system that transmits and receives data over the Internet and processes and stores user input data and history data.

[0316] "Purchase history data" refers to records of purchases a user has made in the past on online shopping sites.

[0317] "Frequency of use" refers to how often a user actually uses the product they purchased.

[0318] The "threshold" refers to a set numerical value used to determine whether the predicted results of usage frequency, etc. exceed a reference value.

[0319] "Warning message" refers to a notification that prompts a user to reconsider their purchase if the predicted usage frequency falls below a threshold.

[0320] "Alternative Products" refers to suggested products that may replace the product selected by the user, including, among other things, products that may improve the user's health or financial situation.

[0321] An "emotion recognition interface" refers to a system that analyzes input data such as the user's face and voice to understand the user's emotional state.

[0322] This invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[0323] Overall system overview

[0324] The system operates in cooperation with users, terminals, and servers.

[0325] 1. User adds product to cart

[0326] When a user adds a product to their cart on an online shopping site, the device displays a form for inputting the reason for purchase and expected frequency of use, and an emotion recognition interface is also displayed to recognize the user's emotional state.

[0327] Specifically, when a user adds a "camera" to their cart, they input the following: "To enjoy taking photos while traveling," as the reason for the purchase, and set the expected frequency of use as "once a week." At the same time, the emotion recognition interface collects the user's facial and voice data and analyzes their emotional state.

[0328] 2. Sending input data

[0329] The device sends the purchase reason, expected frequency of use, and emotional data entered by the user to the server. The data sent includes the product ID, purchase reason, frequency of use, and emotional data. A secure communication protocol (e.g., HTTPS) is used to send the data.

[0330] 3. Data Analysis

[0331] The server receives user data and emotional data and stores them in a database. The server then references the user's past purchase history and emotional data and uses a generative AI model to predict actual usage frequency. This is done by statistically analyzing the user's past purchase history and current emotional state.

[0332] 4. Warnings and alternative products

[0333] If the predicted usage frequency falls below a set threshold (e.g., 0.5), the server generates a warning message based on the user's emotional state. For example, if the user is in an "excited" state, the server generates a message saying, "Please calm down and reconsider this purchase." At the same time, it suggests alternative products such as "financial products for savings" or "health improvement equipment."

[0334] Specific examples

[0335] User operation example

[0336] 1. A user goes online and adds a camera (ID: 123) to their cart.

[0337] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0338] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[0339] System processing flow

[0340] 1. The device accepts user input and emotion data and sends it to the server.

[0341] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[0342] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0343] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0344] In this way, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding their consumption behavior in a healthier and more efficient direction.

[0345] Prompt Sentence Examples

[0346] "Purchase a camera to enjoy taking photos on your trip, but reconsider whether you really need it. Provide specific warning messages and alternative product suggestions based on past purchase history and emotional state."

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] User adds product to cart

[0350] User Actions

[0351] A user selects a product on an online shopping site and adds it to their cart. Specifically, the user selects a camera and clicks the "Add to cart" button.

[0352] input

[0353] Product ID and user action (add to cart).

[0354] output

[0355] A list of items added to the cart.

[0356] Specific actions

[0357] When a user clicks the Add to Cart button on the site, the selected product data (product ID, product name, etc.) is added to the cart list.

[0358] Step 2:

[0359] Input of purchase reason, frequency of use, and emotional state

[0360] Terminal handling

[0361] When an item is added to the cart, the device displays a form for entering the reason for purchase and expected frequency of use, while simultaneously activating an emotion recognition interface.

[0362] input

[0363] The reason for purchase and frequency of use entered by the user, and emotional data collected by the device (facial recognition, voice, etc.).

[0364] output

[0365] Reasons for purchase, frequency of use, and emotional state.

[0366] Specific actions

[0367] The user enters "to enjoy taking photos of my travels" and sets the frequency of use to "once a week." At the same time, the camera and microphone collect emotional data and send it to the emotion analysis engine.

[0368] Step 3:

[0369] Sending input data

[0370] Terminal handling

[0371] The device collects data on the user's reasons for purchasing, frequency of use, and emotions, and sends it to the server.

[0372] input

[0373] Reasons for purchase, frequency of use, and emotional data.

[0374] output

[0375] Purchasing reasons, frequency of use, and emotional data sent to the server.

[0376] Specific actions

[0377] The collected data is securely sent to a server using the HTTPS protocol, including product ID, purchase reason, frequency of use, and sentiment data.

[0378] Step 4:

[0379] Data analysis

[0380] Server Processing

[0381] The server stores the received data in a database, compares it with past purchase history and sentiment data, and uses a generative AI model to predict actual usage frequency.

[0382] input

[0383] Received data (purchase reasons, frequency of use, emotional data), past purchase history data.

[0384] output

[0385] Predicted frequency of use.

[0386] Specific actions

[0387] The server accesses the database to retrieve past usage data for similar products. At the same time, the sentiment analysis engine analyzes the current sentiment data, and the generative AI model performs statistical analysis to predict usage frequency.

[0388] Step 5:

[0389] Generate warning messages and substitute products

[0390] Server Processing

[0391] The server compares the predicted usage frequency with a set threshold, and if it falls below the threshold, generates a warning message and alternative products based on the user's emotional state.

[0392] input

[0393] Predicted usage frequency, thresholds, and sentiment data.

[0394] output

[0395] Warning message and list of alternative products.

[0396] Specific actions

[0397] If the generative AI model determines that the predicted frequency of use is below a threshold, it will take into account the user's emotional state and generate a warning message such as, "Is this purchase really necessary? Please think about it calmly," and list alternative products such as "financial savings products" and "health improvement equipment."

[0398] Step 6:

[0399] Warning messages and alternative product displays

[0400] Terminal handling

[0401] The terminal displays the warning message and alternative products received from the server to the user.

[0402] input

[0403] Warning messages and alternative product data.

[0404] output

[0405] What the user sees.

[0406] Specific actions

[0407] The device displays the warning message and alternative products received from the server using a user interface such as a dialog box or pop-up. For example, in addition to information about the camera the user added to their cart, the device may display a warning message and a list of alternative products, encouraging the user to reconsider their purchase.

[0408] In this way, data is input and output, and data processing and calculation are performed at each step, and the overall processing of the system progresses. As a result, users can avoid wasteful consumption and choose more beneficial products.

[0409] (Application example 2)

[0410] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0411] Today's online shoppers often make impulsive purchases, which can result in wasteful spending. Furthermore, due to the influence of emotions, purchased products are often not actually used. Under these circumstances, a system that improves the effectiveness of emotion-based purchasing decisions is needed.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0413] In this invention, the server includes emotion recognition means for recognizing the emotional state of the user, means for transmitting the input purchase reason and expected use frequency data and emotion data to the server, and means for referencing the user's past purchase history data and emotion data to predict the actual use frequency of the product. This makes it possible to determine the effectiveness of a purchase while taking the user's emotional state into account and prevent wasteful consumption.

[0414] An "online shopping cart" is a virtual shopping cart that allows users to select and temporarily store products online.

[0415] The "reason for purchase" is an explanation of the user's motivation or purpose for purchasing a product.

[0416] "Expected frequency of use" is information indicating how often the user plans to use the product they are considering purchasing.

[0417] "Emotion recognition" is a technology that determines a user's current feelings and mental state based on facial expressions, tone of voice, etc.

[0418] "Emotion data" is information about a user's emotions extracted by emotion recognition.

[0419] "Server" means a central processing system that receives and analyzes data sent by users.

[0420] "Purchase history data" refers to data that records information about products purchased by a user in the past.

[0421] "Actual usage frequency" is data indicating how often a purchased product is actually used.

[0422] A "warning message" is a notification that encourages users to reconsider their purchase.

[0423] An "alternative product" is a product that is suggested as an alternative to the product selected by the user.

[0424] "Tone" is the tone and style of expression used in a message or proposal.

[0425] The present invention is a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. The purpose of this system is to prevent wasteful consumption by users and improve the effectiveness of emotion-based purchasing decisions. Specific embodiments for implementing the present invention are described below.

[0426] Overall system overview

[0427] 1. User adds product to cart

[0428] The device receives an operation by the user to add a product to the cart on an online shopping site. Next, a form is displayed in which the user enters the reason for purchase and the expected frequency of use. At this time, an interface for emotion recognition is also displayed. For example, when a user adds a "camera" to the cart using a smartphone, the user enters that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the smartphone camera is used to capture the user's face, and emotion recognition technology (e.g., Microsoft® Azure® Face API) is used to recognize the user's emotional state.

[0429] 2. Sending input data

[0430] The purchase reason, expected frequency of use, and emotion data input by the user are transmitted to the server by the terminal.

[0431] 3. Data Analysis

[0432] The server receives the purchase reason, expected frequency of use, and emotional data sent by the user and stores them in a database. The server then references the user's past purchase history data to obtain actual usage frequency data for similar products. It then analyzes the emotional data to understand the user's current emotional state. By combining these data, it predicts the usage frequency of a newly added product to the cart. For example, it predicts the actual usage frequency of the product through statistical analysis of the historical data and analysis of the emotional data.

[0433] 4. Warnings and alternative products

[0434] If the predicted usage frequency falls below a set threshold, the server generates a warning message urging the user to reconsider their purchase. This warning message is created in an appropriate tone based on the user's emotional state. For example, if the user is excited, a more emphatic warning message is displayed. At the same time, the server suggests alternative products such as financial or health-related products. These suggestions are also provided with appropriate content based on the user's emotional state.

[0435] Specific examples

[0436] If a user adds a camera (product ID: CAM123) to their cart online, enters "to enjoy taking photos while traveling" as the reason for the purchase, and enters "once a week" as the expected frequency of use, and the emotion recognition interface recognizes the user's emotional state as "excited," the following process will occur:

[0437] 1. The device accepts the user's input and emotion data and sends it to the server.

[0438] 2. The server analyzes the frequency of use of similar products previously purchased by the user based on their past purchase history, and predicts the actual frequency of use taking into account their emotional state.

[0439] 3. Based on the prediction results, if a user is determined to be in an excited state, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0440] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0441] The above is a specific embodiment. This system allows users to avoid emotionally driven impulse buying and to engage in effective consumption behavior.

[0442] Example prompt sentence:

[0443] A user adds a camera to their cart. The reason for the purchase is "to enjoy taking photos while traveling." The expected usage frequency is "once a week." Facial emotion recognition detects excitement. Generate a warning message to encourage reconsideration of the purchase and suggest a related camera accessory pack as an alternative.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] User adds product to cart

[0447] A user adds a product to a cart on an online shopping site. This action causes the device to receive a product addition command. Next, a form for inputting the reason for purchase and expected frequency of use is displayed. An interface for emotion recognition is then displayed. The input data is the reason for purchase (e.g., "to enjoy taking photos of travel"), expected frequency of use (e.g., "once a week"), and an image of the user's face. Emotion data is obtained using emotion recognition technology (e.g., Microsoft Azure's Face API).

[0448] Step 2:

[0449] Submitting user-entered data

[0450] The user inputs the reason for purchase and expected frequency of use, and the emotional data captured by the emotion recognition interface is compiled on the device. The device then sends this data in bulk to the server. The input data includes the reason for purchase, expected frequency of use, and emotional data, and is sent via an HTTP request.

[0451] Step 3:

[0452] Receiving and storing data by the server

[0453] The server receives the purchase reason, expected frequency of use, and emotion data sent from the device. The received data is stored in a database within the server. The stored data is used for subsequent analysis.

[0454] Step 4:

[0455] Obtaining past purchase history data

[0456] The server retrieves the user's past purchase history data and uses a database query to look up usage frequency data for similar products. This history data includes purchase dates, usage frequency, and other relevant information for each product.

[0457] Step 5:

[0458] Emotional Data Analysis

[0459] The server analyzes the received emotion data. It analyzes the data obtained through emotion recognition (e.g., excitement, joy, sadness, etc.). It uses an emotion engine to determine the user's current emotional state. The analysis results are used for subsequent prediction processing.

[0460] Step 6:

[0461] Usage frequency prediction

[0462] The server combines past purchase history data with current sentiment data to predict the frequency of use of newly added items to the cart. It uses statistical methods and machine learning models (e.g., generative AI models) to predict the actual frequency of use of the items. The input data are past purchase history and sentiment data, and the output is the predicted frequency of use.

[0463] Step 7:

[0464] Generate a warning message

[0465] If the predicted usage frequency falls below a set threshold, the server generates a warning message encouraging the user to reconsider their purchase. The tone of the generated message is adjusted based on the user's emotional state. For example, if the user is excited, a warning message with an accentuated tone is displayed.

[0466] Step 8:

[0467] Alternative product suggestions

[0468] The server then generates a warning message and suggests alternative products, such as financial or health-related products, that are relevant to the user's emotional state and purchasing reasons. The server also generates information about the alternative products, described in an appropriate tone.

[0469] Step 9:

[0470] Warning messages and alternative product displays

[0471] The terminal displays the warning message and information about alternative products sent from the server to the user, giving the user the opportunity to reconsider their purchase or consider alternative products.

[0472] The above are the specific processing steps of the system that realizes the application example.

[0473] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0474] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0475] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0476] [Second embodiment]

[0477] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0478] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0479] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0480] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0481] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0482] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0483] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0484] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0485] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0486] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0487] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0488] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0489] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[0490] Overall flow

[0491] 1. User adds product to cart

[0492] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use.

[0493] 2. Sending input data

[0494] The user enters the reason for purchase and expected frequency of use, and this data is sent to the server.

[0495] 3. Data Analysis

[0496] The server analyzes the received user data and predicts actual usage frequency by referencing the user's past purchase history data.

[0497] The server generates a warning message if the predicted usage frequency falls below a set threshold.

[0498] 4. Warnings and alternative products

[0499] It receives a response from the server and displays alternative products (financial products or health-related products) to the user along with a warning message.

[0500] Program processing steps and examples

[0501] 1. User adds product to cart

[0502] Terminal handling

[0503] When a user adds an item to their cart on an online shopping site, they are prompted with a form asking them to enter their reason for purchase and expected frequency of use.

[0504] For example, if a user adds a "camera" to their cart, they might purchase the camera "to enjoy taking photos while traveling" and enter the expected frequency of use as "once a week."

[0505] 2. Sending input data

[0506] Terminal handling

[0507] The purchase reason and expected frequency of use entered by the user are sent to the server.

[0508] 3. Data Analysis

[0509] Server Processing

[0510] The server receives the user data and stores it in a database.

[0511] The server refers to the user's past purchase history data and predicts how often similar products will be used.

[0512] For example, based on data on how often a user has used cameras they have purchased in the past, it predicts that the actual frequency of use of a new camera will be about "once a month."

[0513] If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[0514] 4. Warnings and alternative products

[0515] Terminal handling

[0516] Receives the response from the server and displays a warning message to the user.

[0517] For example, you might see a message like, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0518] At the same time, alternative products such as "financial savings products" and "health improvement devices" are proposed.

[0519] Specific examples

[0520] User operation example

[0521] 1. A user adds a camera to their cart online.

[0522] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0523] System processing flow

[0524] 1. The device accepts user input and sends it to the server.

[0525] 2. The server analyzes the user's past purchase history to determine how frequently the user has used the camera they previously purchased.

[0526] 3. If the predicted results indicate that the actual usage frequency is low, a warning message is generated.

[0527] 4. Along with the warning, offer alternative product suggestions.

[0528] In this way, the present invention helps users avoid wasteful consumption and purchase more beneficial products. By utilizing the user's past behavior data, the server can make more accurate predictions and promote conscious consumption behavior by the user.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] A user adds a product to a cart on an online shopping site. The device receives this action and displays a form that asks the user to enter the reason for purchase and expected frequency of use. Once the user enters and confirms this information, the input data is saved on the device.

[0532] Step 2:

[0533] The terminal sends the input data of the user's reason for purchase and expected frequency of use to the server. This transmission includes all data such as product information, reason for purchase, and expected frequency of use.

[0534] Step 3:

[0535] The server analyzes the received user data. Specifically, the server accesses a database, references the user's past purchase history, and obtains usage frequency data for similar products.

[0536] Step 4:

[0537] The server compares the past purchase history data with the user's input data. Based on the actual usage frequency of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction process uses statistical analysis of the historical data.

[0538] Step 5:

[0539] The server compares the predicted usage frequency with a configured threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, the server generates a warning message, which includes a message encouraging the user to reconsider their purchase.

[0540] Step 6:

[0541] The server generates a list of alternative products along with a warning message. The alternative products are mainly financial and health-related products. This list is retrieved from a database and is selected with the user's convenience and health in mind.

[0542] Step 7:

[0543] The device receives a response from the server, which includes a warning message and information about alternative products.

[0544] Step 8:

[0545] The device displays a warning message to the user, such as "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0546] Step 9:

[0547] The device displays a list of alternative products to the user, including the name and a brief description of each alternative product, allowing the user to reconsider their purchase or switch to an alternative product.

[0548] Example 1

[0549] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0550] Conventional online shopping systems lack the means to predict the frequency of use or effectiveness of a product after the user has purchased it, which leads to problems such as increased wasteful consumption and unnecessary purchases.In addition, there is a lack of information to help users reconsider their purchases or suggestions for alternative products, which makes it difficult for them to make more beneficial product choices.

[0551] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0552] In this invention, the server includes means for referencing the user's past purchase history data and predicting the actual frequency of use of the product, means for the server to predict the frequency of use using a machine learning model, means for storing the data in a database, means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a set threshold, means for suggesting alternative products along with the warning message, and means for displaying the warning message and information about the alternative products to the user. This allows the user to obtain useful information when purchasing a product, avoid wasteful consumption, and select more beneficial products.

[0553] "User" refers to a consumer who uses the system to purchase products.

[0554] An "online shopping cart" is a virtual cart that allows users to temporarily store items they wish to purchase on an online shopping site.

[0555] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0556] "Expected frequency of use" refers to a prediction of how often a user will use the product they are about to purchase.

[0557] "Server" refers to a computer system that receives, processes, and stores data from users.

[0558] "Means of transmission" refers to the method or technology used to transfer data from the user's device to the server.

[0559] "Purchase history data" refers to information about products a user has purchased in the past and how often they have been used.

[0560] A "machine learning model" refers to an algorithm or mathematical model that allows a computer to generate patterns and make predictions based on past data.

[0561] A "database" refers to a system that organizes and stores data so that it can be searched and retrieved as needed.

[0562] A "threshold" refers to a specific numerical standard, and is a reference value for setting conditions under which judgments and processing differ depending on whether the standard is exceeded or not.

[0563] "Warning message" refers to a notification message that alerts the user to a specific action or situation.

[0564] "Substitute products" refer to products that are offered as alternatives to the product a user is considering purchasing.

[0565] "Financial product" means a product offered for investment or asset management, including, for example, savings plans and mutual funds.

[0566] "Health-related products" are products designed to promote the health of users, including, for example, fitness equipment and health supplements.

[0567] "Means for displaying" refers to the method or technology for visually displaying information sent from the server on the user's device.

[0568] The present invention provides a system for predicting the frequency and duration of a user's purchase of a product through online shopping, and determining the effectiveness of the purchase. This system is implemented through the following steps.

[0569] User adds product to cart

[0570] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and the expected frequency of use. The device generates the input form using HTML and JavaScript and provides the user interface. In this example, a user adds a "camera" to their cart and enters the reason for purchase as "to enjoy taking photos on trips" and the expected frequency of use as "once a week."

[0571] Sending input data

[0572] The device sends the purchase reason and expected usage frequency entered by the user to the server via an HTTP POST request, and the data is sent securely.

[0573] Data analysis

[0574] The server stores the received data in a database (e.g., MySQL or PostgreSQL) and references the user's past purchase history. Next, the server uses a machine learning model (e.g., scikit-learn or TensorFlow) to predict the actual usage frequency of the product. If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[0575] Warnings and alternative products

[0576] The response from the server is sent to the device, which then displays a warning message and alternative products to the user. For example, the warning message might say, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase." At the same time, alternative products such as "financial savings products" and "health improvement devices" are suggested.

[0577] Specific examples

[0578] A specific example of a user's actions might be adding a camera to their cart online, inputting the reason for the purchase as "to enjoy taking photos while traveling" and the expected frequency of use as "once a week."

[0579] Prompt Sentence Examples

[0580] Examples of prompts to input to a generative AI model include:

[0581] "A user adds a camera to their cart and enters the reason for the purchase, "to enjoy taking photos while traveling," and the expected frequency of use, "once a week." The server receives this information, predicts that the user will use the camera infrequently based on their past purchase history, and displays a warning message and alternative products."

[0582] This invention allows users to avoid wasteful consumption and receive assistance in selecting beneficial products. The server utilizes the user's past behavioral data to make highly accurate predictions, enabling the user to promote conscious consumption behavior.

[0583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0584] Step 1: User adds product to cart

[0585] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and expected frequency of use. The input here is the product name added to the cart by the user, the reason for purchase, and expected frequency of use. The device generates the input form using HTML and JavaScript and displays it to the user.

[0586] Specific behavior:

[0587] A user adds an item to their cart.

[0588] The terminal generates and displays an input form using HTML and JavaScript.

[0589] The user enters the reason for purchase and frequency of use.

[0590] Step 2: Submitting input data

[0591] The device sends the data entered by the user, including the reason for purchase and expected frequency of use, to the server. This is done using an HTTP POST request. The input data includes the product name, reason for purchase, and expected frequency of use. This data is then passed to the server as output.

[0592] Specific behavior:

[0593] The user clicks the submit button.

[0594] The device generates an HTTP POST request.

[0595] Data on purchase reason and frequency of use is sent to the server.

[0596] Step 3: Save your data

[0597] The server stores the received data in a database. The input is the user's reason for purchasing and expected frequency of use, and the output is the data stored in the database. Databases such as MySQL or PostgreSQL are often used here.

[0598] Specific behavior:

[0599] The server receives the data.

[0600] The server establishes a database connection.

[0601] Execute an INSERT query on the database to save the data.

[0602] Step 4: Get your past purchase history

[0603] The server retrieves the user's past purchase history data from the database. The input is the user ID, and the output is the past purchase history data.

[0604] Specific behavior:

[0605] The server queries the database for past purchase history based on the user ID.

[0606] The database returns historical purchase data.

[0607] Step 5: Predicting usage frequency

[0608] The server uses a machine learning model to predict the frequency of new product purchases based on the acquired past purchase history. The input is past purchase history data and new product data, and the output is the predicted frequency of use. Machine learning libraries such as scikit-learn and TensorFlow are used here.

[0609] Specific behavior:

[0610] The server inputs past purchase history data into the machine learning model.

[0611] Machine learning models predict the frequency of new product use.

[0612] The predicted usage frequency is returned to the server.

[0613] Step 6: Generate a warning message

[0614] If the predicted usage frequency is below a set threshold, the server generates a warning message. The inputs are the predicted usage frequency and the threshold, and the output is the warning message.

[0615] Specific behavior:

[0616] The server compares the predicted usage frequency with a threshold.

[0617] If the usage rate falls below a threshold, the server generates a warning message.

[0618] Step 7: Suggest alternative products

[0619] The server suggests alternative products along with a warning message, such as financial products or health-related products. The input is the warning message, and the output is a list of alternative products.

[0620] Specific behavior:

[0621] The server generates a list of alternative products.

[0622] The server includes a warning message and information about alternative products in an HTTP response and sends it to the terminal.

[0623] Step 8: Display warning messages and alternative products

[0624] The terminal receives the response from the server and displays a warning message and alternative products to the user. The input is the response data from the server, and the output is the displayed message and product list.

[0625] Specific behavior:

[0626] The terminal receives an HTTP response from the server.

[0627] The device generates a warning message and a list of alternative products using HTML and JavaScript.

[0628] The user is presented with a warning message and alternative products.

[0629] (Application example 1)

[0630] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0631] When shopping online, it is common for users to fail to use purchased products appropriately, resulting in wasteful consumption. This not only reduces user satisfaction, but can also be a factor in increasing the burden on the environment. In particular, it is difficult to predict how much a user will actually use a product, making it difficult to make purchases based on that judgment. Therefore, there is a need for methods to support efficient consumption behavior. In addition, there is a lack of methods to suggest appropriate alternative products to encourage users to reconsider their purchase.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0633] In this invention, the server includes: means for receiving a user's operation to add a product to an online shopping cart; means for prompting the user to input a reason for purchase and an expected frequency of use for the product; means for transmitting the input data on the reason for purchase and expected frequency of use to the server; means for referencing the user's past purchase history data and predicting the actual frequency of use of the product; means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a preset threshold; means for suggesting alternative products along with the warning message; means for displaying the warning message and information about the alternative products to the user; means for generating alternative products using an artificial intelligence model if the expected frequency of use and the actual frequency of use do not match; and means for inputting the warning message and the content of the suggested alternative products as prompts to the artificial intelligence model. This allows users to avoid wasteful consumption and purchase products that are more effective and meet their needs. Furthermore, supporting efficient consumption behavior is expected to reduce environmental impact.

[0634] "User" refers to a consumer who purchases or uses a product.

[0635] An "online shopping cart" refers to a virtual shopping basket on an online shopping site that has the function of temporarily storing items that users intend to purchase.

[0636] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0637] "Expected frequency of use" refers to how often a user plans to use the product they have purchased.

[0638] "Server" refers to a computer system for processing and managing data.

[0639] "Purchase history data" refers to data regarding information about products purchased by a user in the past and their usage status.

[0640] "Actual frequency of use" refers to how often a user has used a product they have purchased in the past.

[0641] "Threshold" refers to a set reference value below which specific action is taken.

[0642] "Warning message" refers to a notification displayed to the user to encourage caution or reconsideration.

[0643] "Substitute products" are products that are suggested to replace the product a user is considering purchasing with other suitable products.

[0644] An "artificial intelligence model" refers to a type of computer program that processes large amounts of data, learns, and makes predictions and suggestions.

[0645] A "prompt sentence" is an instruction sentence input to an artificial intelligence model, and includes conditions and questions for obtaining a specific output.

[0646] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[0647] Overall flow

[0648] 1. User adds product to cart

[0649] When a user adds an item to their cart on an online shopping site, they are prompted to enter the reason for the purchase and the expected frequency of use. For example, if a user adds a "camera" to their cart, they will purchase the camera "to enjoy taking photos on trips" and enter the expected frequency of use as "once a week."

[0650] 2. Sending input data

[0651] The reason for purchase and expected frequency of use entered by the user are sent to the server. Data can be easily sent to the server using a device such as a smartphone.

[0652] 3. Data Analysis

[0653] The server analyzes the user's past purchase history data to predict actual usage frequency. This analysis is performed using a server system using Python and the Django framework. For example, based on the usage frequency data of a user's previously purchased camera, it predicts that the actual usage frequency of a new camera will be about "once a month."

[0654] 4. Warnings and alternative products

[0655] If the predicted usage frequency falls below a set threshold, the server generates a warning message for the user. At the same time, it uses an artificial intelligence model (generative AI model) to suggest alternative products to the user. For example, the server might suggest "savings products" or "health improvement equipment" along with a message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase."

[0656] Hardware and software used

[0657] Hardware: User's smartphone, server computer

[0658] Software: Python, Django framework, generative AI models

[0659] Specific examples of processing and prompts

[0660] For example, if a user adds a camera to their cart using the "Shopping Advisor" app on their smartphone and enters "to enjoy taking photos while traveling" and "to use once a week," the process proceeds as follows: The server receives the input data, predicts the actual frequency of use based on past purchase history data, and if the predicted value falls below a threshold, generates a warning message and suggests alternative products.

[0661] Example prompt sentence:

[0662] When a user purchases a product, the system asks them to input their expected usage frequency and reason for purchase. Predict the actual usage frequency from the user's past purchase history, and if the predicted usage frequency is below a threshold, display a warning message and suggest alternative products.

[0663] This allows users to avoid wasteful consumption and support efficient and beneficial consumption behavior. Furthermore, by using a generative AI model, more accurate alternative product suggestions can be realized.

[0664] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0665] Step 1:

[0666] The user adds an item to the cart.

[0667] Input: The user selects the product they want to purchase and adds it to their cart.

[0668] Output: The product to be purchased is added to the cart, and a form is displayed to enter the reason for purchase and expected frequency of use.

[0669] Step 2:

[0670] The device prompts the user to enter the reason for purchase and expected frequency of use.

[0671] Input: Product information added to cart. Enter the reason for purchase (e.g., to enjoy taking photos while traveling) and expected frequency of use (e.g., once a week).

[0672] Output: Data on purchase reasons and expected frequency of use.

[0673] Step 3:

[0674] The terminal transmits the input data on the reason for purchase and the expected frequency of use to the server.

[0675] Input: Purchasing reason and expected frequency of use data.

[0676] Output: This data is sent to the server.

[0677] Step 4:

[0678] Based on the data received by the server, the server refers to the user's past purchase history data and predicts the actual frequency of use of the product.

[0679] Inputs: Purchasing reason, expected frequency of use, and the user's past purchasing history data.

[0680] Output: The predicted usage frequency of the product.

[0681] How it works: The server retrieves past purchase history from the database, analyzes usage frequency data for similar products, and uses an AI model to calculate the predicted usage frequency of newly added products.

[0682] Step 5:

[0683] If the server predicts that the frequency of use will fall below a set threshold, it generates a warning message encouraging users to reconsider their purchase.

[0684] Input: The expected frequency of use of the product. Threshold (e.g., 0.5).

[0685] Output: A warning message.

[0686] How it works: The server compares the predicted usage frequency to a threshold and generates a warning message if it falls below the threshold. The message might include, "This product is unlikely to be used as frequently as expected. Please reconsider your purchase."

[0687] Step 6:

[0688] The server inputs a prompt sentence into the generative AI model to suggest alternative products along with a warning message.

[0689] Input: Warning message, suggested alternative products, prompt (e.g., prompting the user to input their expected usage frequency and reason for purchasing the product, and suggesting alternative products).

[0690] Output: A list of suggested alternative products.

[0691] How it works: The server inputs a prompt into the generative AI model, which then generates appropriate alternative products (e.g., financial products for savings, health improvement devices, etc.).

[0692] Step 7:

[0693] The device will display a warning message and information about alternative products to the user.

[0694] Input: Warning message, list of suggested alternative products.

[0695] Output: A warning message and a list of alternative products that are displayed to the user.

[0696] Behavior: The device displays a warning message received from the server and a list of alternative products to the user, encouraging them to reconsider. For example, a message like "The camera is unlikely to be used as frequently as expected. Consider purchasing the following product instead" is displayed along with a list of alternative products.

[0697] This allows users to avoid wasteful consumption and purchase products efficiently and appropriately. Furthermore, by using generative AI models, more accurate alternative product suggestions can be realized.

[0698] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0699] The present invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[0700] Overall system overview

[0701] 1. User adds product to cart

[0702] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use, and an interface is also displayed to recognize the user's emotional state.

[0703] 2. Sending input data

[0704] The user inputs the reason for purchase and the expected frequency of use, and emotional data is also acquired. This data is sent to the server.

[0705] 3. Data Analysis

[0706] The server analyzes the received user data and emotion data, accesses a database to reference past purchase history data, and predicts the actual frequency of use for each product.

[0707] 4. Warnings and alternative products

[0708] Based on the user's emotional state, the server adjusts the tone and content of warning messages to encourage reconsideration of the purchase and suggests alternative financial or health products.

[0709] Program processing explanation

[0710] 1. User adds product to cart

[0711] Terminal handling

[0712] When a user adds an item to their cart on an online shopping site, they are prompted to enter their reason for purchase and expected frequency of use. An interface for emotion recognition is also displayed. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the system uses facial recognition and text input to recognize the user's emotional state.

[0713] 2. Sending input data

[0714] Terminal handling

[0715] The purchase reason, expected frequency of use, and emotional data entered by the user are sent to the server.

[0716] 3. Data Analysis

[0717] Server Processing

[0718] The server receives user data and emotion data and stores them in a database.

[0719] The server references the user's past purchase history data to obtain usage frequency data for similar products, and analyzes the user's emotional data to understand their current emotional state.

[0720] The server predicts the frequency of use of newly added items based on past purchase history data and user emotional data. This prediction process combines statistical analysis of historical data and analysis of emotional data.

[0721] 4. Warnings and alternative products

[0722] Server Processing

[0723] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, a warning message is generated based on the user's emotional state. For example, if emotion analysis determines that the user is in an impulsive state, a more emphatic warning message is sent.

[0724] The server will then provide a warning message along with alternative product suggestions (such as financial products or health improvement tools), which will be explained in a tone appropriate to the user's emotional state.

[0725] Specific examples

[0726] User operation example

[0727] 1. A user goes online and adds a camera (ID: 123) to their cart.

[0728] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0729] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[0730] System processing flow

[0731] 1. The device accepts user input and emotion data and sends it to the server.

[0732] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[0733] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0734] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0735] In this way, the present invention can guide users' consumption behavior in a healthier and more efficient direction by avoiding wasteful consumption and suggesting more beneficial products while taking into account their emotional state.

[0736] The processing flow will be explained below.

[0737] The present invention provides a system that, when a user purchases a product through online shopping, predicts the frequency and duration of use of the product, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase.

[0738] Step 1:

[0739] A user adds an item to their cart on an online shopping site. The device receives this action and displays a form that prompts the user to enter the reason for purchase and expected frequency of use. It also displays an interface for emotion recognition. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the device will use facial recognition and text input to identify the user's emotional state.

[0740] Step 2:

[0741] When the user inputs the reason for purchase, expected frequency of use, and emotional data and presses the confirm button, this data is saved on the device, which then sends it to the server.

[0742] Step 3:

[0743] The server analyzes the received user data, expected usage frequency, and emotion data. Specifically, the server accesses a database, references the user's past purchase history, and extracts usage frequency data for similar products.

[0744] Step 4:

[0745] The server compares past purchase history data with the user's input data. Based on the actual usage frequency data of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction reflects not only the historical data but also the user's emotional data.

[0746] Step 5:

[0747] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency is below this threshold, the emotion engine analyzes the user's emotional state and determines the appropriate tone and content of the warning message. For example, if the user's emotional state is "excited," a stronger warning message is generated.

[0748] Step 6:

[0749] The server generates a warning message along with a list of alternative products, including financial and health-related products, with descriptions that reflect the emotion data.

[0750] Step 7:

[0751] The device receives the response from the server and displays a warning message to the user, for example, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0752] Step 8:

[0753] The device presents the user with a list of alternative products, including the name and a brief description of each alternative, presented in a tone that reflects the user's emotional state—for example, a more gentle suggestion would be used if the user returned to a calm state.

[0754] As a specific example, consider the case where a user is trying to purchase a camera. The user adds a "camera" to their cart, enters the reason for the purchase as "to enjoy taking photos while traveling," and enters the expected frequency of use as "once a week." The emotion recognition interface recognizes that the user is in an "excited" state. The server analyzes past purchase data and determines that the actual predicted frequency of use is about "once a month." Therefore, the server generates a strong warning message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase," and suggests alternative products such as a "savings product" or a "health improvement device."

[0755] As described above, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding users' consumption behavior in a healthy and efficient direction.

[0756] Example 2

[0757] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0758] In conventional online shopping systems, users often make impulse purchases based on their emotions, and there is a lack of means to evaluate the validity of their purchases. This leads to wasteful consumption and inappropriate product choices, which increases the user's financial burden. The purpose of this invention is to solve this problem by providing a system that takes into account the user's emotional state and increases the validity of purchases.

[0759] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving an operation by a user to add a product to an online shopping cart, a means for prompting the user to input a purchase reason and an expected frequency of use for the product, and a means for transmitting the input data of the purchase reason and expected frequency of use to the server. This makes it possible to evaluate the validity of a purchase while taking into account the emotional state of the user, prevent wasteful consumption, and suggest appropriate products.

[0760] "User" refers to a consumer who selects and purchases products on an online shopping site.

[0761] "Online shopping cart" refers to a virtual basket that temporarily stores items selected by a user on an online shopping site.

[0762] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[0763] "Expected frequency of use" refers to numbers or terms that predict how often a user will use the product they are about to purchase.

[0764] "Emotional state" refers to the psychological and emotional state a user is in when purchasing a product, including states such as excitement, joy, sadness, and anger.

[0765] "Server" refers to a computer system that transmits and receives data over the Internet and processes and stores user input data and history data.

[0766] "Purchase history data" refers to records of purchases a user has made in the past on online shopping sites.

[0767] "Frequency of use" refers to how often a user actually uses the product they purchased.

[0768] The "threshold" refers to a set numerical value used to determine whether the predicted results of usage frequency, etc. exceed a reference value.

[0769] "Warning message" refers to a notification that prompts a user to reconsider their purchase if the predicted usage frequency falls below a threshold.

[0770] "Alternative Products" refers to suggested products that may replace the product selected by the user, including, among other things, products that may improve the user's health or financial situation.

[0771] An "emotion recognition interface" refers to a system that analyzes input data such as the user's face and voice to understand the user's emotional state.

[0772] This invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[0773] Overall system overview

[0774] The system operates in cooperation with users, terminals, and servers.

[0775] 1. User adds product to cart

[0776] When a user adds a product to their cart on an online shopping site, the device displays a form for inputting the reason for purchase and expected frequency of use, and an emotion recognition interface is also displayed to recognize the user's emotional state.

[0777] Specifically, when a user adds a "camera" to their cart, they input the following: "To enjoy taking photos while traveling," as the reason for the purchase, and set the expected frequency of use as "once a week." At the same time, the emotion recognition interface collects the user's facial and voice data and analyzes their emotional state.

[0778] 2. Sending input data

[0779] The device sends the purchase reason, expected frequency of use, and emotional data entered by the user to the server. The data sent includes the product ID, purchase reason, frequency of use, and emotional data. A secure communication protocol (e.g., HTTPS) is used to send the data.

[0780] 3. Data Analysis

[0781] The server receives user data and emotional data and stores them in a database. The server then references the user's past purchase history and emotional data and uses a generative AI model to predict actual usage frequency. This is done by statistically analyzing the user's past purchase history and current emotional state.

[0782] 4. Warnings and alternative products

[0783] If the predicted usage frequency falls below a set threshold (e.g., 0.5), the server generates a warning message based on the user's emotional state. For example, if the user is in an "excited" state, the server generates a message saying, "Please calm down and reconsider this purchase." At the same time, it suggests alternative products such as "financial products for savings" or "health improvement equipment."

[0784] Specific examples

[0785] User operation example

[0786] 1. A user goes online and adds a camera (ID: 123) to their cart.

[0787] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0788] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[0789] System processing flow

[0790] 1. The device accepts user input and emotion data and sends it to the server.

[0791] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[0792] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0793] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0794] In this way, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding their consumption behavior in a healthier and more efficient direction.

[0795] Prompt Sentence Examples

[0796] "Purchase a camera to enjoy taking photos on your trip, but reconsider whether you really need it. Provide specific warning messages and alternative product suggestions based on past purchase history and emotional state."

[0797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0798] Step 1:

[0799] User adds product to cart

[0800] User Actions

[0801] A user selects a product on an online shopping site and adds it to their cart. Specifically, the user selects a camera and clicks the "Add to cart" button.

[0802] input

[0803] Product ID and user action (add to cart).

[0804] output

[0805] A list of items added to the cart.

[0806] Specific actions

[0807] When a user clicks the Add to Cart button on the site, the selected product data (product ID, product name, etc.) is added to the cart list.

[0808] Step 2:

[0809] Input of purchase reason, frequency of use, and emotional state

[0810] Terminal handling

[0811] When an item is added to the cart, the device displays a form for entering the reason for purchase and expected frequency of use, while simultaneously activating an emotion recognition interface.

[0812] input

[0813] The reason for purchase and frequency of use entered by the user, and emotional data collected by the device (facial recognition, voice, etc.).

[0814] output

[0815] Reasons for purchase, frequency of use, and emotional state.

[0816] Specific actions

[0817] The user enters "to enjoy taking photos of my travels" and sets the frequency of use to "once a week." At the same time, the camera and microphone collect emotional data and send it to the emotion analysis engine.

[0818] Step 3:

[0819] Sending input data

[0820] Terminal handling

[0821] The device collects data on the user's reasons for purchasing, frequency of use, and emotions, and sends it to the server.

[0822] input

[0823] Reasons for purchase, frequency of use, and emotional data.

[0824] output

[0825] Purchasing reasons, frequency of use, and emotional data sent to the server.

[0826] Specific actions

[0827] The collected data is securely sent to a server using the HTTPS protocol, including product ID, purchase reason, frequency of use, and sentiment data.

[0828] Step 4:

[0829] Data analysis

[0830] Server Processing

[0831] The server stores the received data in a database, compares it with past purchase history and sentiment data, and uses a generative AI model to predict actual usage frequency.

[0832] input

[0833] Received data (purchase reasons, frequency of use, emotional data), past purchase history data.

[0834] output

[0835] Predicted frequency of use.

[0836] Specific actions

[0837] The server accesses the database to retrieve past usage data for similar products. At the same time, the sentiment analysis engine analyzes the current sentiment data, and the generative AI model performs statistical analysis to predict usage frequency.

[0838] Step 5:

[0839] Generate warning messages and substitute products

[0840] Server Processing

[0841] The server compares the predicted usage frequency with a set threshold, and if it falls below the threshold, generates a warning message and alternative products based on the user's emotional state.

[0842] input

[0843] Predicted usage frequency, thresholds, and sentiment data.

[0844] output

[0845] Warning message and list of alternative products.

[0846] Specific actions

[0847] If the generative AI model determines that the predicted frequency of use is below a threshold, it will take into account the user's emotional state and generate a warning message such as, "Is this purchase really necessary? Please think about it calmly," and list alternative products such as "financial savings products" and "health improvement equipment."

[0848] Step 6:

[0849] Warning messages and alternative product displays

[0850] Terminal handling

[0851] The terminal displays the warning message and alternative products received from the server to the user.

[0852] input

[0853] Warning messages and alternative product data.

[0854] output

[0855] What the user sees.

[0856] Specific actions

[0857] The device displays the warning message and alternative products received from the server using a user interface such as a dialog box or pop-up. For example, in addition to information about the camera the user added to their cart, the device may display a warning message and a list of alternative products, encouraging the user to reconsider their purchase.

[0858] In this way, data is input and output, and data processing and calculation are performed at each step, and the overall processing of the system progresses. As a result, users can avoid wasteful consumption and choose more beneficial products.

[0859] (Application example 2)

[0860] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0861] Today's online shoppers often make impulsive purchases, which can result in wasteful spending. Furthermore, due to the influence of emotions, purchased products are often not actually used. Under these circumstances, a system that improves the effectiveness of emotion-based purchasing decisions is needed.

[0862] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0863] In this invention, the server includes emotion recognition means for recognizing the emotional state of the user, means for transmitting the input purchase reason and expected use frequency data and emotion data to the server, and means for referencing the user's past purchase history data and emotion data to predict the actual use frequency of the product. This makes it possible to determine the effectiveness of a purchase while taking the user's emotional state into account and prevent wasteful consumption.

[0864] An "online shopping cart" is a virtual shopping cart that allows users to select and temporarily store products online.

[0865] The "reason for purchase" is an explanation of the user's motivation or purpose for purchasing a product.

[0866] "Expected frequency of use" is information indicating how often the user plans to use the product they are considering purchasing.

[0867] "Emotion recognition" is a technology that determines a user's current feelings and mental state based on facial expressions, tone of voice, etc.

[0868] "Emotion data" is information about a user's emotions extracted by emotion recognition.

[0869] "Server" means a central processing system that receives and analyzes data sent by users.

[0870] "Purchase history data" refers to data that records information about products purchased by a user in the past.

[0871] "Actual usage frequency" is data indicating how often a purchased product is actually used.

[0872] A "warning message" is a notification that encourages users to reconsider their purchase.

[0873] An "alternative product" is a product that is suggested as an alternative to the product selected by the user.

[0874] "Tone" is the tone and style of expression used in a message or proposal.

[0875] The present invention is a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. The purpose of this system is to prevent wasteful consumption by users and improve the effectiveness of emotion-based purchasing decisions. Specific embodiments for implementing the present invention are described below.

[0876] Overall system overview

[0877] 1. User adds product to cart

[0878] The device receives an operation from the user to add a product to the cart on an online shopping site. Next, a form is displayed in which the user enters the reason for purchase and expected frequency of use. At this time, an interface for emotion recognition is also displayed. For example, when a user adds a "camera" to the cart using a smartphone, the user enters that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the smartphone camera is used to capture the user's face, and emotion recognition technology (for example, Microsoft Azure's Face API) is used to recognize the user's emotional state.

[0879] 2. Sending input data

[0880] The purchase reason, expected frequency of use, and emotion data input by the user are transmitted to the server by the terminal.

[0881] 3. Data Analysis

[0882] The server receives the purchase reason, expected frequency of use, and emotional data sent by the user and stores them in a database. The server then references the user's past purchase history data to obtain actual usage frequency data for similar products. It then analyzes the emotional data to understand the user's current emotional state. By combining these data, it predicts the usage frequency of a newly added product to the cart. For example, it predicts the actual usage frequency of the product through statistical analysis of the historical data and analysis of the emotional data.

[0883] 4. Warnings and alternative products

[0884] If the predicted usage frequency falls below a set threshold, the server generates a warning message urging the user to reconsider their purchase. This warning message is created in an appropriate tone based on the user's emotional state. For example, if the user is excited, a more emphatic warning message is displayed. At the same time, the server suggests alternative products such as financial or health-related products. These suggestions are also provided with appropriate content based on the user's emotional state.

[0885] Specific examples

[0886] If a user adds a camera (product ID: CAM123) to their cart online, enters "to enjoy taking photos while traveling" as the reason for the purchase, and enters "once a week" as the expected frequency of use, and the emotion recognition interface recognizes the user's emotional state as "excited," the following process will occur:

[0887] 1. The device accepts the user's input and emotion data and sends it to the server.

[0888] 2. The server analyzes the frequency of use of similar products previously purchased by the user based on their past purchase history, and predicts the actual frequency of use taking into account their emotional state.

[0889] 3. Based on the prediction results, if a user is determined to be in an excited state, a warning message will be sent to emphasize that the user should reconsider their purchase.

[0890] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[0891] The above is a specific embodiment. This system allows users to avoid emotionally driven impulse buying and to engage in effective consumption behavior.

[0892] Example prompt sentence:

[0893] A user adds a camera to their cart. The reason for the purchase is "to enjoy taking photos while traveling." The expected usage frequency is "once a week." Facial emotion recognition detects excitement. Generate a warning message to encourage reconsideration of the purchase and suggest a related camera accessory pack as an alternative.

[0894] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0895] Step 1:

[0896] User adds product to cart

[0897] A user adds a product to a cart on an online shopping site. This action causes the device to receive a product addition command. Next, a form for inputting the reason for purchase and expected frequency of use is displayed. An interface for emotion recognition is then displayed. The input data is the reason for purchase (e.g., "to enjoy taking photos of travel"), expected frequency of use (e.g., "once a week"), and an image of the user's face. Emotion data is obtained using emotion recognition technology (e.g., Microsoft Azure's Face API).

[0898] Step 2:

[0899] Submitting user-entered data

[0900] The user inputs the reason for purchase and expected frequency of use, and the emotional data captured by the emotion recognition interface is compiled on the device. The device then sends this data in bulk to the server. The input data includes the reason for purchase, expected frequency of use, and emotional data, and is sent via an HTTP request.

[0901] Step 3:

[0902] Receiving and storing data by the server

[0903] The server receives the purchase reason, expected frequency of use, and emotion data sent from the device. The received data is stored in a database within the server. The stored data is used for subsequent analysis.

[0904] Step 4:

[0905] Obtaining past purchase history data

[0906] The server retrieves the user's past purchase history data and uses a database query to look up usage frequency data for similar products. This history data includes purchase dates, usage frequency, and other relevant information for each product.

[0907] Step 5:

[0908] Emotional Data Analysis

[0909] The server analyzes the received emotion data. It analyzes the data obtained through emotion recognition (e.g., excitement, joy, sadness, etc.). It uses an emotion engine to determine the user's current emotional state. The analysis results are used for subsequent prediction processing.

[0910] Step 6:

[0911] Usage frequency prediction

[0912] The server combines past purchase history data with current sentiment data to predict the frequency of use of newly added items to the cart. It uses statistical methods and machine learning models (e.g., generative AI models) to predict the actual frequency of use of the items. The input data are past purchase history and sentiment data, and the output is the predicted frequency of use.

[0913] Step 7:

[0914] Generate a warning message

[0915] If the predicted usage frequency falls below a set threshold, the server generates a warning message encouraging the user to reconsider their purchase. The tone of the generated message is adjusted based on the user's emotional state. For example, if the user is excited, a warning message with an accentuated tone is displayed.

[0916] Step 8:

[0917] Alternative product suggestions

[0918] The server then generates a warning message and suggests alternative products, such as financial or health-related products, that are relevant to the user's emotional state and purchasing reasons. The server also generates information about the alternative products, described in an appropriate tone.

[0919] Step 9:

[0920] Warning messages and alternative product displays

[0921] The terminal displays the warning message and information about alternative products sent from the server to the user, giving the user the opportunity to reconsider their purchase or consider alternative products.

[0922] The above are the specific processing steps of the system that realizes the application example.

[0923] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0924] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0925] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0926] [Third embodiment]

[0927] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0928] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0929] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0930] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0931] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0932] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0933] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0934] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0935] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0936] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0937] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0938] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0939] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[0940] Overall flow

[0941] 1. User adds product to cart

[0942] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use.

[0943] 2. Sending input data

[0944] The user enters the reason for purchase and expected frequency of use, and this data is sent to the server.

[0945] 3. Data Analysis

[0946] The server analyzes the received user data and predicts actual usage frequency by referencing the user's past purchase history data.

[0947] The server generates a warning message if the predicted usage frequency falls below a set threshold.

[0948] 4. Warnings and alternative products

[0949] It receives a response from the server and displays alternative products (financial products or health-related products) to the user along with a warning message.

[0950] Program processing steps and examples

[0951] 1. User adds product to cart

[0952] Terminal handling

[0953] When a user adds an item to their cart on an online shopping site, they are prompted with a form asking them to enter their reason for purchase and expected frequency of use.

[0954] For example, if a user adds a "camera" to their cart, they might purchase the camera "to enjoy taking photos while traveling" and enter the expected frequency of use as "once a week."

[0955] 2. Sending input data

[0956] Terminal handling

[0957] The purchase reason and expected frequency of use entered by the user are sent to the server.

[0958] 3. Data Analysis

[0959] Server Processing

[0960] The server receives the user data and stores it in a database.

[0961] The server refers to the user's past purchase history data and predicts how often similar products will be used.

[0962] For example, based on data on how often a user has used cameras they have purchased in the past, it predicts that the actual frequency of use of a new camera will be about "once a month."

[0963] If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[0964] 4. Warnings and alternative products

[0965] Terminal handling

[0966] Receives the response from the server and displays a warning message to the user.

[0967] For example, you might see a message like, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0968] At the same time, alternative products such as "financial savings products" and "health improvement devices" are proposed.

[0969] Specific examples

[0970] User operation example

[0971] 1. A user adds a camera to their cart online.

[0972] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[0973] System processing flow

[0974] 1. The device accepts user input and sends it to the server.

[0975] 2. The server analyzes the user's past purchase history to determine how frequently the user has used the camera they previously purchased.

[0976] 3. If the predicted results indicate that the actual usage frequency is low, a warning message is generated.

[0977] 4. Along with the warning, offer alternative product suggestions.

[0978] In this way, the present invention helps users avoid wasteful consumption and purchase more beneficial products. By utilizing the user's past behavior data, the server can make more accurate predictions and promote conscious consumption behavior by the user.

[0979] The processing flow will be explained below.

[0980] Step 1:

[0981] A user adds a product to a cart on an online shopping site. The device receives this action and displays a form that asks the user to enter the reason for purchase and expected frequency of use. Once the user enters and confirms this information, the input data is saved on the device.

[0982] Step 2:

[0983] The terminal sends the input data of the user's reason for purchase and expected frequency of use to the server. This transmission includes all data such as product information, reason for purchase, and expected frequency of use.

[0984] Step 3:

[0985] The server analyzes the received user data. Specifically, the server accesses a database, references the user's past purchase history, and obtains usage frequency data for similar products.

[0986] Step 4:

[0987] The server compares the past purchase history data with the user's input data. Based on the actual usage frequency of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction process uses statistical analysis of the historical data.

[0988] Step 5:

[0989] The server compares the predicted usage frequency with a configured threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, the server generates a warning message, which includes a message encouraging the user to reconsider their purchase.

[0990] Step 6:

[0991] The server generates a list of alternative products along with a warning message. The alternative products are mainly financial and health-related products. This list is retrieved from a database and is selected with the user's convenience and health in mind.

[0992] Step 7:

[0993] The device receives a response from the server, which includes a warning message and information about alternative products.

[0994] Step 8:

[0995] The device displays a warning message to the user, such as "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[0996] Step 9:

[0997] The device displays a list of alternative products to the user, including the name and a brief description of each alternative product, allowing the user to reconsider their purchase or switch to an alternative product.

[0998] Example 1

[0999] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1000] Conventional online shopping systems lack the means to predict the frequency of use or effectiveness of a product after the user has purchased it, which leads to problems such as increased wasteful consumption and unnecessary purchases.In addition, there is a lack of information to help users reconsider their purchases or suggestions for alternative products, which makes it difficult for them to make more beneficial product choices.

[1001] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1002] In this invention, the server includes means for referencing the user's past purchase history data and predicting the actual frequency of use of the product, means for the server to predict the frequency of use using a machine learning model, means for storing the data in a database, means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a set threshold, means for suggesting alternative products along with the warning message, and means for displaying the warning message and information about the alternative products to the user. This allows the user to obtain useful information when purchasing a product, avoid wasteful consumption, and select more beneficial products.

[1003] "User" refers to a consumer who uses the system to purchase products.

[1004] An "online shopping cart" is a virtual cart that allows users to temporarily store items they wish to purchase on an online shopping site.

[1005] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1006] "Expected frequency of use" refers to a prediction of how often a user will use the product they are about to purchase.

[1007] "Server" refers to a computer system that receives, processes, and stores data from users.

[1008] "Means of transmission" refers to the method or technology used to transfer data from the user's device to the server.

[1009] "Purchase history data" refers to information about products a user has purchased in the past and how often they have been used.

[1010] A "machine learning model" refers to an algorithm or mathematical model that allows a computer to generate patterns and make predictions based on past data.

[1011] A "database" refers to a system that organizes and stores data so that it can be searched and retrieved as needed.

[1012] A "threshold" refers to a specific numerical standard, and is a reference value for setting conditions under which judgments and processing differ depending on whether the standard is exceeded or not.

[1013] "Warning message" refers to a notification message that alerts the user to a specific action or situation.

[1014] "Substitute products" refer to products that are offered as alternatives to the product a user is considering purchasing.

[1015] "Financial product" means a product offered for investment or asset management, including, for example, savings plans and mutual funds.

[1016] "Health-related products" are products designed to promote the health of users, including, for example, fitness equipment and health supplements.

[1017] "Means for displaying" refers to the method or technology for visually displaying information sent from the server on the user's device.

[1018] The present invention provides a system for predicting the frequency and duration of a user's purchase of a product through online shopping, and determining the effectiveness of the purchase. This system is implemented through the following steps.

[1019] User adds product to cart

[1020] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and the expected frequency of use. The device generates the input form using HTML and JavaScript and provides the user interface. In this example, a user adds a "camera" to their cart and enters the reason for purchase as "to enjoy taking photos on trips" and the expected frequency of use as "once a week."

[1021] Sending input data

[1022] The device sends the purchase reason and expected usage frequency entered by the user to the server via an HTTP POST request, and the data is sent securely.

[1023] Data analysis

[1024] The server stores the received data in a database (e.g., MySQL or PostgreSQL) and references the user's past purchase history. Next, the server uses a machine learning model (e.g., scikit-learn or TensorFlow) to predict the actual usage frequency of the product. If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[1025] Warnings and alternative products

[1026] The response from the server is sent to the device, which then displays a warning message and alternative products to the user. For example, the warning message might say, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase." At the same time, alternative products such as "financial savings products" and "health improvement devices" are suggested.

[1027] Specific examples

[1028] A specific example of a user's actions might be adding a camera to their cart online, inputting the reason for the purchase as "to enjoy taking photos while traveling" and the expected frequency of use as "once a week."

[1029] Prompt Sentence Examples

[1030] Examples of prompts to input to a generative AI model include:

[1031] "A user adds a camera to their cart and enters the reason for the purchase, "to enjoy taking photos while traveling," and the expected frequency of use, "once a week." The server receives this information, predicts that the user will use the camera infrequently based on their past purchase history, and displays a warning message and alternative products."

[1032] This invention allows users to avoid wasteful consumption and receive assistance in selecting beneficial products. The server utilizes the user's past behavioral data to make highly accurate predictions, enabling the user to promote conscious consumption behavior.

[1033] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1034] Step 1: User adds product to cart

[1035] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and expected frequency of use. The input here is the product name added to the cart by the user, the reason for purchase, and expected frequency of use. The device generates the input form using HTML and JavaScript and displays it to the user.

[1036] Specific behavior:

[1037] A user adds an item to their cart.

[1038] The terminal generates and displays an input form using HTML and JavaScript.

[1039] The user enters the reason for purchase and frequency of use.

[1040] Step 2: Submitting input data

[1041] The device sends the data entered by the user, including the reason for purchase and expected frequency of use, to the server. This is done using an HTTP POST request. The input data includes the product name, reason for purchase, and expected frequency of use. This data is then passed to the server as output.

[1042] Specific behavior:

[1043] The user clicks the submit button.

[1044] The device generates an HTTP POST request.

[1045] Data on purchase reason and frequency of use is sent to the server.

[1046] Step 3: Save your data

[1047] The server stores the received data in a database. The input is the user's reason for purchasing and expected frequency of use, and the output is the data stored in the database. Databases such as MySQL or PostgreSQL are often used here.

[1048] Specific behavior:

[1049] The server receives the data.

[1050] The server establishes a database connection.

[1051] Execute an INSERT query on the database to save the data.

[1052] Step 4: Get your past purchase history

[1053] The server retrieves the user's past purchase history data from the database. The input is the user ID, and the output is the past purchase history data.

[1054] Specific behavior:

[1055] The server queries the database for past purchase history based on the user ID.

[1056] The database returns historical purchase data.

[1057] Step 5: Predicting usage frequency

[1058] The server uses a machine learning model to predict the frequency of new product purchases based on the acquired past purchase history. The input is past purchase history data and new product data, and the output is the predicted frequency of use. Machine learning libraries such as scikit-learn and TensorFlow are used here.

[1059] Specific behavior:

[1060] The server inputs past purchase history data into the machine learning model.

[1061] Machine learning models predict the frequency of new product use.

[1062] The predicted usage frequency is returned to the server.

[1063] Step 6: Generate a warning message

[1064] If the predicted usage frequency is below a set threshold, the server generates a warning message. The inputs are the predicted usage frequency and the threshold, and the output is the warning message.

[1065] Specific behavior:

[1066] The server compares the predicted usage frequency with a threshold.

[1067] If the usage rate falls below a threshold, the server generates a warning message.

[1068] Step 7: Suggest alternative products

[1069] The server suggests alternative products along with a warning message, such as financial products or health-related products. The input is the warning message, and the output is a list of alternative products.

[1070] Specific behavior:

[1071] The server generates a list of alternative products.

[1072] The server includes a warning message and information about alternative products in an HTTP response and sends it to the terminal.

[1073] Step 8: Display warning messages and alternative products

[1074] The terminal receives the response from the server and displays a warning message and alternative products to the user. The input is the response data from the server, and the output is the displayed message and product list.

[1075] Specific behavior:

[1076] The terminal receives an HTTP response from the server.

[1077] The device generates a warning message and a list of alternative products using HTML and JavaScript.

[1078] The user is presented with a warning message and alternative products.

[1079] (Application example 1)

[1080] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1081] When shopping online, it is common for users to fail to use purchased products appropriately, resulting in wasteful consumption. This not only reduces user satisfaction, but can also be a factor in increasing the burden on the environment. In particular, it is difficult to predict how much a user will actually use a product, making it difficult to make purchases based on that judgment. Therefore, there is a need for methods to support efficient consumption behavior. In addition, there is a lack of methods to suggest appropriate alternative products to encourage users to reconsider their purchase.

[1082] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1083] In this invention, the server includes: means for receiving a user's operation to add a product to an online shopping cart; means for prompting the user to input a reason for purchase and an expected frequency of use for the product; means for transmitting the input data on the reason for purchase and expected frequency of use to the server; means for referencing the user's past purchase history data and predicting the actual frequency of use of the product; means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a preset threshold; means for suggesting alternative products along with the warning message; means for displaying the warning message and information about the alternative products to the user; means for generating alternative products using an artificial intelligence model if the expected frequency of use and the actual frequency of use do not match; and means for inputting the warning message and the content of the suggested alternative products as prompts to the artificial intelligence model. This allows users to avoid wasteful consumption and purchase products that are more effective and meet their needs. Furthermore, supporting efficient consumption behavior is expected to reduce environmental impact.

[1084] "User" refers to a consumer who purchases or uses a product.

[1085] An "online shopping cart" refers to a virtual shopping basket on an online shopping site that has the function of temporarily storing items that users intend to purchase.

[1086] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1087] "Expected frequency of use" refers to how often a user plans to use the product they have purchased.

[1088] "Server" refers to a computer system for processing and managing data.

[1089] "Purchase history data" refers to data regarding information about products purchased by a user in the past and their usage status.

[1090] "Actual frequency of use" refers to how often a user has used a product they have purchased in the past.

[1091] "Threshold" refers to a set reference value below which specific action is taken.

[1092] "Warning message" refers to a notification displayed to the user to encourage caution or reconsideration.

[1093] "Substitute products" are products that are suggested to replace the product a user is considering purchasing with other suitable products.

[1094] An "artificial intelligence model" refers to a type of computer program that processes large amounts of data, learns, and makes predictions and suggestions.

[1095] A "prompt sentence" is an instruction sentence input to an artificial intelligence model, and includes conditions and questions for obtaining a specific output.

[1096] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[1097] Overall flow

[1098] 1. User adds product to cart

[1099] When a user adds an item to their cart on an online shopping site, they are prompted to enter the reason for the purchase and the expected frequency of use. For example, if a user adds a "camera" to their cart, they will purchase the camera "to enjoy taking photos on trips" and enter the expected frequency of use as "once a week."

[1100] 2. Sending input data

[1101] The reason for purchase and expected frequency of use entered by the user are sent to the server. Data can be easily sent to the server using a device such as a smartphone.

[1102] 3. Data Analysis

[1103] The server analyzes the user's past purchase history data to predict actual usage frequency. This analysis is performed using a server system using Python and the Django framework. For example, based on the usage frequency data of a user's previously purchased camera, it predicts that the actual usage frequency of a new camera will be about "once a month."

[1104] 4. Warnings and alternative products

[1105] If the predicted usage frequency falls below a set threshold, the server generates a warning message for the user. At the same time, it uses an artificial intelligence model (generative AI model) to suggest alternative products to the user. For example, the server might suggest "savings products" or "health improvement equipment" along with a message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase."

[1106] Hardware and software used

[1107] Hardware: User's smartphone, server computer

[1108] Software: Python, Django framework, generative AI models

[1109] Specific examples of processing and prompts

[1110] For example, if a user adds a camera to their cart using the "Shopping Advisor" app on their smartphone and enters "to enjoy taking photos while traveling" and "to use once a week," the process proceeds as follows: The server receives the input data, predicts the actual frequency of use based on past purchase history data, and if the predicted value falls below a threshold, generates a warning message and suggests alternative products.

[1111] Example prompt sentence:

[1112] When a user purchases a product, the system asks them to input their expected usage frequency and reason for purchase. Predict the actual usage frequency from the user's past purchase history, and if the predicted usage frequency is below a threshold, display a warning message and suggest alternative products.

[1113] This allows users to avoid wasteful consumption and support efficient and beneficial consumption behavior. Furthermore, by using a generative AI model, more accurate alternative product suggestions can be realized.

[1114] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1115] Step 1:

[1116] The user adds an item to the cart.

[1117] Input: The user selects the product they want to purchase and adds it to their cart.

[1118] Output: The product to be purchased is added to the cart, and a form is displayed to enter the reason for purchase and expected frequency of use.

[1119] Step 2:

[1120] The device prompts the user to enter the reason for purchase and expected frequency of use.

[1121] Input: Product information added to cart. Enter the reason for purchase (e.g., to enjoy taking photos while traveling) and expected frequency of use (e.g., once a week).

[1122] Output: Data on purchase reasons and expected frequency of use.

[1123] Step 3:

[1124] The terminal transmits the input data on the reason for purchase and the expected frequency of use to the server.

[1125] Input: Purchasing reason and expected frequency of use data.

[1126] Output: This data is sent to the server.

[1127] Step 4:

[1128] Based on the data received by the server, the server refers to the user's past purchase history data and predicts the actual frequency of use of the product.

[1129] Inputs: Purchasing reason, expected frequency of use, and the user's past purchasing history data.

[1130] Output: The predicted usage frequency of the product.

[1131] How it works: The server retrieves past purchase history from the database, analyzes usage frequency data for similar products, and uses an AI model to calculate the predicted usage frequency of newly added products.

[1132] Step 5:

[1133] If the server predicts that the frequency of use will fall below a set threshold, it generates a warning message encouraging users to reconsider their purchase.

[1134] Input: The expected frequency of use of the product. Threshold (e.g., 0.5).

[1135] Output: A warning message.

[1136] How it works: The server compares the predicted usage frequency to a threshold and generates a warning message if it falls below the threshold. The message might include, "This product is unlikely to be used as frequently as expected. Please reconsider your purchase."

[1137] Step 6:

[1138] The server inputs a prompt sentence into the generative AI model to suggest alternative products along with a warning message.

[1139] Input: Warning message, suggested alternative products, prompt (e.g., prompting the user to input their expected usage frequency and reason for purchasing the product, and suggesting alternative products).

[1140] Output: A list of suggested alternative products.

[1141] How it works: The server inputs a prompt into the generative AI model, which then generates appropriate alternative products (e.g., financial products for savings, health improvement devices, etc.).

[1142] Step 7:

[1143] The device will display a warning message and information about alternative products to the user.

[1144] Input: Warning message, list of suggested alternative products.

[1145] Output: A warning message and a list of alternative products that are displayed to the user.

[1146] Behavior: The device displays a warning message received from the server and a list of alternative products to the user, encouraging them to reconsider. For example, a message like "The camera is unlikely to be used as frequently as expected. Consider purchasing the following product instead" is displayed along with a list of alternative products.

[1147] This allows users to avoid wasteful consumption and purchase products efficiently and appropriately. Furthermore, by using generative AI models, more accurate alternative product suggestions can be realized.

[1148] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1149] The present invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[1150] Overall system overview

[1151] 1. User adds product to cart

[1152] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use, and an interface is also displayed to recognize the user's emotional state.

[1153] 2. Sending input data

[1154] The user inputs the reason for purchase and the expected frequency of use, and emotional data is also acquired. This data is sent to the server.

[1155] 3. Data Analysis

[1156] The server analyzes the received user data and emotion data, accesses a database to reference past purchase history data, and predicts the actual frequency of use for each product.

[1157] 4. Warnings and alternative products

[1158] Based on the user's emotional state, the server adjusts the tone and content of warning messages to encourage reconsideration of the purchase and suggests alternative financial or health products.

[1159] Program processing explanation

[1160] 1. User adds product to cart

[1161] Terminal handling

[1162] When a user adds an item to their cart on an online shopping site, they are prompted to enter their reason for purchase and expected frequency of use. An interface for emotion recognition is also displayed. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the system uses facial recognition and text input to recognize the user's emotional state.

[1163] 2. Sending input data

[1164] Terminal handling

[1165] The purchase reason, expected frequency of use, and emotional data entered by the user are sent to the server.

[1166] 3. Data Analysis

[1167] Server Processing

[1168] The server receives user data and emotion data and stores them in a database.

[1169] The server references the user's past purchase history data to obtain usage frequency data for similar products, and analyzes the user's emotional data to understand their current emotional state.

[1170] The server predicts the frequency of use of newly added items based on past purchase history data and user emotional data. This prediction process combines statistical analysis of historical data and analysis of emotional data.

[1171] 4. Warnings and alternative products

[1172] Server Processing

[1173] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, a warning message is generated based on the user's emotional state. For example, if emotion analysis determines that the user is in an impulsive state, a more emphatic warning message is sent.

[1174] The server will then provide a warning message along with alternative product suggestions (such as financial products or health improvement tools), which will be explained in a tone appropriate to the user's emotional state.

[1175] Specific examples

[1176] User operation example

[1177] 1. A user goes online and adds a camera (ID: 123) to their cart.

[1178] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[1179] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[1180] System processing flow

[1181] 1. The device accepts user input and emotion data and sends it to the server.

[1182] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[1183] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1184] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1185] In this way, the present invention can guide users' consumption behavior in a healthier and more efficient direction by avoiding wasteful consumption and suggesting more beneficial products while taking into account their emotional state.

[1186] The processing flow will be explained below.

[1187] The present invention provides a system that, when a user purchases a product through online shopping, predicts the frequency and duration of use of the product, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase.

[1188] Step 1:

[1189] A user adds an item to their cart on an online shopping site. The device receives this action and displays a form that prompts the user to enter the reason for purchase and expected frequency of use. It also displays an interface for emotion recognition. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the device will use facial recognition and text input to identify the user's emotional state.

[1190] Step 2:

[1191] When the user inputs the reason for purchase, expected frequency of use, and emotional data and presses the confirm button, this data is saved on the device, which then sends it to the server.

[1192] Step 3:

[1193] The server analyzes the received user data, expected usage frequency, and emotion data. Specifically, the server accesses a database, references the user's past purchase history, and extracts usage frequency data for similar products.

[1194] Step 4:

[1195] The server compares past purchase history data with the user's input data. Based on the actual usage frequency data of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction reflects not only the historical data but also the user's emotional data.

[1196] Step 5:

[1197] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency is below this threshold, the emotion engine analyzes the user's emotional state and determines the appropriate tone and content of the warning message. For example, if the user's emotional state is "excited," a stronger warning message is generated.

[1198] Step 6:

[1199] The server generates a warning message along with a list of alternative products, including financial and health-related products, with descriptions that reflect the emotion data.

[1200] Step 7:

[1201] The device receives the response from the server and displays a warning message to the user, for example, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[1202] Step 8:

[1203] The device presents the user with a list of alternative products, including the name and a brief description of each alternative, presented in a tone that reflects the user's emotional state—for example, a more gentle suggestion would be used if the user returned to a calm state.

[1204] As a specific example, consider the case where a user is trying to purchase a camera. The user adds a "camera" to their cart, enters the reason for the purchase as "to enjoy taking photos while traveling," and enters the expected frequency of use as "once a week." The emotion recognition interface recognizes that the user is in an "excited" state. The server analyzes past purchase data and determines that the actual predicted frequency of use is about "once a month." Therefore, the server generates a strong warning message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase," and suggests alternative products such as a "savings product" or a "health improvement device."

[1205] As described above, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding users' consumption behavior in a healthy and efficient direction.

[1206] Example 2

[1207] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1208] In conventional online shopping systems, users often make impulse purchases based on their emotions, and there is a lack of means to evaluate the validity of their purchases. This leads to wasteful consumption and inappropriate product choices, which increases the user's financial burden. The purpose of this invention is to solve this problem by providing a system that takes into account the user's emotional state and increases the validity of purchases.

[1209] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving an operation by a user to add a product to an online shopping cart, a means for prompting the user to input a purchase reason and an expected frequency of use for the product, and a means for transmitting the input data of the purchase reason and expected frequency of use to the server. This makes it possible to evaluate the validity of a purchase while taking into account the emotional state of the user, prevent wasteful consumption, and suggest appropriate products.

[1210] "User" refers to a consumer who selects and purchases products on an online shopping site.

[1211] "Online shopping cart" refers to a virtual basket that temporarily stores items selected by a user on an online shopping site.

[1212] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1213] "Expected frequency of use" refers to numbers or terms that predict how often a user will use the product they are about to purchase.

[1214] "Emotional state" refers to the psychological and emotional state a user is in when purchasing a product, including states such as excitement, joy, sadness, and anger.

[1215] "Server" refers to a computer system that transmits and receives data over the Internet and processes and stores user input data and history data.

[1216] "Purchase history data" refers to records of purchases a user has made in the past on online shopping sites.

[1217] "Frequency of use" refers to how often a user actually uses the product they purchased.

[1218] The "threshold" refers to a set numerical value used to determine whether the predicted results of usage frequency, etc. exceed a reference value.

[1219] "Warning message" refers to a notification that prompts a user to reconsider their purchase if the predicted usage frequency falls below a threshold.

[1220] "Alternative Products" refers to suggested products that may replace the product selected by the user, including, among other things, products that may improve the user's health or financial situation.

[1221] An "emotion recognition interface" refers to a system that analyzes input data such as the user's face and voice to understand the user's emotional state.

[1222] This invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[1223] Overall system overview

[1224] The system operates in cooperation with users, terminals, and servers.

[1225] 1. User adds product to cart

[1226] When a user adds a product to their cart on an online shopping site, the device displays a form for inputting the reason for purchase and expected frequency of use, and an emotion recognition interface is also displayed to recognize the user's emotional state.

[1227] Specifically, when a user adds a "camera" to their cart, they input the following: "To enjoy taking photos while traveling," as the reason for the purchase, and set the expected frequency of use as "once a week." At the same time, the emotion recognition interface collects the user's facial and voice data and analyzes their emotional state.

[1228] 2. Sending input data

[1229] The device sends the purchase reason, expected frequency of use, and emotional data entered by the user to the server. The data sent includes the product ID, purchase reason, frequency of use, and emotional data. A secure communication protocol (e.g., HTTPS) is used to send the data.

[1230] 3. Data Analysis

[1231] The server receives user data and emotional data and stores them in a database. The server then references the user's past purchase history and emotional data and uses a generative AI model to predict actual usage frequency. This is done by statistically analyzing the user's past purchase history and current emotional state.

[1232] 4. Warnings and alternative products

[1233] If the predicted usage frequency falls below a set threshold (e.g., 0.5), the server generates a warning message based on the user's emotional state. For example, if the user is in an "excited" state, the server generates a message saying, "Please calm down and reconsider this purchase." At the same time, it suggests alternative products such as "financial products for savings" or "health improvement equipment."

[1234] Specific examples

[1235] User operation example

[1236] 1. A user goes online and adds a camera (ID: 123) to their cart.

[1237] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[1238] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[1239] System processing flow

[1240] 1. The device accepts user input and emotion data and sends it to the server.

[1241] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[1242] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1243] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1244] In this way, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding their consumption behavior in a healthier and more efficient direction.

[1245] Prompt Sentence Examples

[1246] "Purchase a camera to enjoy taking photos on your trip, but reconsider whether you really need it. Provide specific warning messages and alternative product suggestions based on past purchase history and emotional state."

[1247] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1248] Step 1:

[1249] User adds product to cart

[1250] User Actions

[1251] A user selects a product on an online shopping site and adds it to their cart. Specifically, the user selects a camera and clicks the "Add to cart" button.

[1252] input

[1253] Product ID and user action (add to cart).

[1254] output

[1255] A list of items added to the cart.

[1256] Specific actions

[1257] When a user clicks the Add to Cart button on the site, the selected product data (product ID, product name, etc.) is added to the cart list.

[1258] Step 2:

[1259] Input of purchase reason, frequency of use, and emotional state

[1260] Terminal handling

[1261] When an item is added to the cart, the device displays a form for entering the reason for purchase and expected frequency of use, while simultaneously activating an emotion recognition interface.

[1262] input

[1263] The reason for purchase and frequency of use entered by the user, and emotional data collected by the device (facial recognition, voice, etc.).

[1264] output

[1265] Reasons for purchase, frequency of use, and emotional state.

[1266] Specific actions

[1267] The user enters "to enjoy taking photos of my travels" and sets the frequency of use to "once a week." At the same time, the camera and microphone collect emotional data and send it to the emotion analysis engine.

[1268] Step 3:

[1269] Sending input data

[1270] Terminal handling

[1271] The device collects data on the user's reasons for purchasing, frequency of use, and emotions, and sends it to the server.

[1272] input

[1273] Reasons for purchase, frequency of use, and emotional data.

[1274] output

[1275] Purchasing reasons, frequency of use, and emotional data sent to the server.

[1276] Specific actions

[1277] The collected data is securely sent to a server using the HTTPS protocol, including product ID, purchase reason, frequency of use, and sentiment data.

[1278] Step 4:

[1279] Data analysis

[1280] Server Processing

[1281] The server stores the received data in a database, compares it with past purchase history and sentiment data, and uses a generative AI model to predict actual usage frequency.

[1282] input

[1283] Received data (purchase reasons, frequency of use, emotional data), past purchase history data.

[1284] output

[1285] Predicted frequency of use.

[1286] Specific actions

[1287] The server accesses the database to retrieve past usage data for similar products. At the same time, the sentiment analysis engine analyzes the current sentiment data, and the generative AI model performs statistical analysis to predict usage frequency.

[1288] Step 5:

[1289] Generate warning messages and substitute products

[1290] Server Processing

[1291] The server compares the predicted usage frequency with a set threshold, and if it falls below the threshold, generates a warning message and alternative products based on the user's emotional state.

[1292] input

[1293] Predicted usage frequency, thresholds, and sentiment data.

[1294] output

[1295] Warning message and list of alternative products.

[1296] Specific actions

[1297] If the generative AI model determines that the predicted frequency of use is below a threshold, it will take into account the user's emotional state and generate a warning message such as, "Is this purchase really necessary? Please think about it calmly," and list alternative products such as "financial savings products" and "health improvement equipment."

[1298] Step 6:

[1299] Warning messages and alternative product displays

[1300] Terminal handling

[1301] The terminal displays the warning message and alternative products received from the server to the user.

[1302] input

[1303] Warning messages and alternative product data.

[1304] output

[1305] What the user sees.

[1306] Specific actions

[1307] The device displays the warning message and alternative products received from the server using a user interface such as a dialog box or pop-up. For example, in addition to information about the camera the user added to their cart, the device may display a warning message and a list of alternative products, encouraging the user to reconsider their purchase.

[1308] In this way, data is input and output, and data processing and calculation are performed at each step, and the overall processing of the system progresses. As a result, users can avoid wasteful consumption and choose more beneficial products.

[1309] (Application example 2)

[1310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1311] Today's online shoppers often make impulsive purchases, which can result in wasteful spending. Furthermore, due to the influence of emotions, purchased products are often not actually used. Under these circumstances, a system that improves the effectiveness of emotion-based purchasing decisions is needed.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1313] In this invention, the server includes emotion recognition means for recognizing the emotional state of the user, means for transmitting the input purchase reason and expected use frequency data and emotion data to the server, and means for referencing the user's past purchase history data and emotion data to predict the actual use frequency of the product. This makes it possible to determine the effectiveness of a purchase while taking the user's emotional state into account and prevent wasteful consumption.

[1314] An "online shopping cart" is a virtual shopping cart that allows users to select and temporarily store products online.

[1315] The "reason for purchase" is an explanation of the user's motivation or purpose for purchasing a product.

[1316] "Expected frequency of use" is information indicating how often the user plans to use the product they are considering purchasing.

[1317] "Emotion recognition" is a technology that determines a user's current feelings and mental state based on facial expressions, tone of voice, etc.

[1318] "Emotion data" is information about a user's emotions extracted by emotion recognition.

[1319] "Server" means a central processing system that receives and analyzes data sent by users.

[1320] "Purchase history data" refers to data that records information about products purchased by a user in the past.

[1321] "Actual usage frequency" is data indicating how often a purchased product is actually used.

[1322] A "warning message" is a notification that encourages users to reconsider their purchase.

[1323] An "alternative product" is a product that is suggested as an alternative to the product selected by the user.

[1324] "Tone" is the tone and style of expression used in a message or proposal.

[1325] The present invention is a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. The purpose of this system is to prevent wasteful consumption by users and improve the effectiveness of emotion-based purchasing decisions. Specific embodiments for implementing the present invention are described below.

[1326] Overall system overview

[1327] 1. User adds product to cart

[1328] The device receives an operation from the user to add a product to the cart on an online shopping site. Next, a form is displayed in which the user enters the reason for purchase and expected frequency of use. At this time, an interface for emotion recognition is also displayed. For example, when a user adds a "camera" to the cart using a smartphone, the user enters that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the smartphone camera is used to capture the user's face, and emotion recognition technology (for example, Microsoft Azure's Face API) is used to recognize the user's emotional state.

[1329] 2. Sending input data

[1330] The purchase reason, expected frequency of use, and emotion data input by the user are transmitted to the server by the terminal.

[1331] 3. Data Analysis

[1332] The server receives the purchase reason, expected frequency of use, and emotional data sent by the user and stores them in a database. The server then references the user's past purchase history data to obtain actual usage frequency data for similar products. It then analyzes the emotional data to understand the user's current emotional state. By combining these data, it predicts the usage frequency of a newly added product to the cart. For example, it predicts the actual usage frequency of the product through statistical analysis of the historical data and analysis of the emotional data.

[1333] 4. Warnings and alternative products

[1334] If the predicted usage frequency falls below a set threshold, the server generates a warning message urging the user to reconsider their purchase. This warning message is created in an appropriate tone based on the user's emotional state. For example, if the user is excited, a more emphatic warning message is displayed. At the same time, the server suggests alternative products such as financial or health-related products. These suggestions are also provided with appropriate content based on the user's emotional state.

[1335] Specific examples

[1336] If a user adds a camera (product ID: CAM123) to their cart online, enters "to enjoy taking photos while traveling" as the reason for the purchase, and enters "once a week" as the expected frequency of use, and the emotion recognition interface recognizes the user's emotional state as "excited," the following process will occur:

[1337] 1. The device accepts the user's input and emotion data and sends it to the server.

[1338] 2. The server analyzes the frequency of use of similar products previously purchased by the user based on their past purchase history, and predicts the actual frequency of use taking into account their emotional state.

[1339] 3. Based on the prediction results, if a user is determined to be in an excited state, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1340] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1341] The above is a specific embodiment. This system allows users to avoid emotionally driven impulse buying and to engage in effective consumption behavior.

[1342] Example prompt sentence:

[1343] A user adds a camera to their cart. The reason for the purchase is "to enjoy taking photos while traveling." The expected usage frequency is "once a week." Facial emotion recognition detects excitement. Generate a warning message to encourage reconsideration of the purchase and suggest a related camera accessory pack as an alternative.

[1344] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1345] Step 1:

[1346] User adds product to cart

[1347] A user adds a product to a cart on an online shopping site. This action causes the device to receive a product addition command. Next, a form for inputting the reason for purchase and expected frequency of use is displayed. An interface for emotion recognition is then displayed. The input data is the reason for purchase (e.g., "to enjoy taking photos of travel"), expected frequency of use (e.g., "once a week"), and an image of the user's face. Emotion data is obtained using emotion recognition technology (e.g., Microsoft Azure's Face API).

[1348] Step 2:

[1349] Submitting user-entered data

[1350] The user inputs the reason for purchase and expected frequency of use, and the emotional data captured by the emotion recognition interface is compiled on the device. The device then sends this data in bulk to the server. The input data includes the reason for purchase, expected frequency of use, and emotional data, and is sent via an HTTP request.

[1351] Step 3:

[1352] Receiving and storing data by the server

[1353] The server receives the purchase reason, expected frequency of use, and emotion data sent from the device. The received data is stored in a database within the server. The stored data is used for subsequent analysis.

[1354] Step 4:

[1355] Obtaining past purchase history data

[1356] The server retrieves the user's past purchase history data and uses a database query to look up usage frequency data for similar products. This history data includes purchase dates, usage frequency, and other relevant information for each product.

[1357] Step 5:

[1358] Emotional Data Analysis

[1359] The server analyzes the received emotion data. It analyzes the data obtained through emotion recognition (e.g., excitement, joy, sadness, etc.). It uses an emotion engine to determine the user's current emotional state. The analysis results are used for subsequent prediction processing.

[1360] Step 6:

[1361] Usage frequency prediction

[1362] The server combines past purchase history data with current sentiment data to predict the frequency of use of newly added items to the cart. It uses statistical methods and machine learning models (e.g., generative AI models) to predict the actual frequency of use of the items. The input data are past purchase history and sentiment data, and the output is the predicted frequency of use.

[1363] Step 7:

[1364] Generate a warning message

[1365] If the predicted usage frequency falls below a set threshold, the server generates a warning message encouraging the user to reconsider their purchase. The tone of the generated message is adjusted based on the user's emotional state. For example, if the user is excited, a warning message with an accentuated tone is displayed.

[1366] Step 8:

[1367] Alternative product suggestions

[1368] The server then generates a warning message and suggests alternative products, such as financial or health-related products, that are relevant to the user's emotional state and purchasing reasons. The server also generates information about the alternative products, described in an appropriate tone.

[1369] Step 9:

[1370] Warning messages and alternative product displays

[1371] The terminal displays the warning message and information about alternative products sent from the server to the user, giving the user the opportunity to reconsider their purchase or consider alternative products.

[1372] The above are the specific processing steps of the system that realizes the application example.

[1373] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1374] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1375] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1376] [Fourth embodiment]

[1377] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1378] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1379] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1380] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1381] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1382] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1383] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1384] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1385] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1386] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1387] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1388] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1389] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1390] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[1391] Overall flow

[1392] 1. User adds product to cart

[1393] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use.

[1394] 2. Sending input data

[1395] The user enters the reason for purchase and expected frequency of use, and this data is sent to the server.

[1396] 3. Data Analysis

[1397] The server analyzes the received user data and predicts actual usage frequency by referencing the user's past purchase history data.

[1398] The server generates a warning message if the predicted usage frequency falls below a set threshold.

[1399] 4. Warnings and alternative products

[1400] It receives a response from the server and displays alternative products (financial products or health-related products) to the user along with a warning message.

[1401] Program processing steps and examples

[1402] 1. User adds product to cart

[1403] Terminal handling

[1404] When a user adds an item to their cart on an online shopping site, they are prompted with a form asking them to enter their reason for purchase and expected frequency of use.

[1405] For example, if a user adds a "camera" to their cart, they might purchase the camera "to enjoy taking photos while traveling" and enter the expected frequency of use as "once a week."

[1406] 2. Sending input data

[1407] Terminal handling

[1408] The purchase reason and expected frequency of use entered by the user are sent to the server.

[1409] 3. Data Analysis

[1410] Server Processing

[1411] The server receives the user data and stores it in a database.

[1412] The server refers to the user's past purchase history data and predicts how often similar products will be used.

[1413] For example, based on data on how often a user has used cameras they have purchased in the past, it predicts that the actual frequency of use of a new camera will be about "once a month."

[1414] If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[1415] 4. Warnings and alternative products

[1416] Terminal handling

[1417] Receives the response from the server and displays a warning message to the user.

[1418] For example, you might see a message like, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[1419] At the same time, alternative products such as "financial savings products" and "health improvement devices" are proposed.

[1420] Specific examples

[1421] User operation example

[1422] 1. A user adds a camera to their cart online.

[1423] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[1424] System processing flow

[1425] 1. The device accepts user input and sends it to the server.

[1426] 2. The server analyzes the user's past purchase history to determine how frequently the user has used the camera they previously purchased.

[1427] 3. If the predicted results indicate that the actual usage frequency is low, a warning message is generated.

[1428] 4. Along with the warning, offer alternative product suggestions.

[1429] In this way, the present invention helps users avoid wasteful consumption and purchase more beneficial products. By utilizing the user's past behavior data, the server can make more accurate predictions and promote conscious consumption behavior by the user.

[1430] The processing flow will be explained below.

[1431] Step 1:

[1432] A user adds a product to a cart on an online shopping site. The device receives this action and displays a form that asks the user to enter the reason for purchase and expected frequency of use. Once the user enters and confirms this information, the input data is saved on the device.

[1433] Step 2:

[1434] The terminal sends the input data of the user's reason for purchase and expected frequency of use to the server. This transmission includes all data such as product information, reason for purchase, and expected frequency of use.

[1435] Step 3:

[1436] The server analyzes the received user data. Specifically, the server accesses a database, references the user's past purchase history, and obtains usage frequency data for similar products.

[1437] Step 4:

[1438] The server compares the past purchase history data with the user's input data. Based on the actual usage frequency of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction process uses statistical analysis of the historical data.

[1439] Step 5:

[1440] The server compares the predicted usage frequency with a configured threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, the server generates a warning message, which includes a message encouraging the user to reconsider their purchase.

[1441] Step 6:

[1442] The server generates a list of alternative products along with a warning message. The alternative products are mainly financial and health-related products. This list is retrieved from a database and is selected with the user's convenience and health in mind.

[1443] Step 7:

[1444] The device receives a response from the server, which includes a warning message and information about alternative products.

[1445] Step 8:

[1446] The device displays a warning message to the user, such as "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[1447] Step 9:

[1448] The device displays a list of alternative products to the user, including the name and a brief description of each alternative product, allowing the user to reconsider their purchase or switch to an alternative product.

[1449] Example 1

[1450] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1451] Conventional online shopping systems lack the means to predict the frequency of use or effectiveness of a product after the user has purchased it, which leads to problems such as increased wasteful consumption and unnecessary purchases.In addition, there is a lack of information to help users reconsider their purchases or suggestions for alternative products, which makes it difficult for them to make more beneficial product choices.

[1452] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1453] In this invention, the server includes means for referencing the user's past purchase history data and predicting the actual frequency of use of the product, means for the server to predict the frequency of use using a machine learning model, means for storing the data in a database, means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a set threshold, means for suggesting alternative products along with the warning message, and means for displaying the warning message and information about the alternative products to the user. This allows the user to obtain useful information when purchasing a product, avoid wasteful consumption, and select more beneficial products.

[1454] "User" refers to a consumer who uses the system to purchase products.

[1455] An "online shopping cart" is a virtual cart that allows users to temporarily store items they wish to purchase on an online shopping site.

[1456] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1457] "Expected frequency of use" refers to a prediction of how often a user will use the product they are about to purchase.

[1458] "Server" refers to a computer system that receives, processes, and stores data from users.

[1459] "Means of transmission" refers to the method or technology used to transfer data from the user's device to the server.

[1460] "Purchase history data" refers to information about products a user has purchased in the past and how often they have been used.

[1461] A "machine learning model" refers to an algorithm or mathematical model that allows a computer to generate patterns and make predictions based on past data.

[1462] A "database" refers to a system that organizes and stores data so that it can be searched and retrieved as needed.

[1463] A "threshold" refers to a specific numerical standard, and is a reference value for setting conditions under which judgments and processing differ depending on whether the standard is exceeded or not.

[1464] "Warning message" refers to a notification message that alerts the user to a specific action or situation.

[1465] "Substitute products" refer to products that are offered as alternatives to the product a user is considering purchasing.

[1466] "Financial product" means a product offered for investment or asset management, including, for example, savings plans and mutual funds.

[1467] "Health-related products" are products designed to promote the health of users, including, for example, fitness equipment and health supplements.

[1468] "Means for displaying" refers to the method or technology for visually displaying information sent from the server on the user's device.

[1469] The present invention provides a system for predicting the frequency and duration of a user's purchase of a product through online shopping, and determining the effectiveness of the purchase. This system is implemented through the following steps.

[1470] User adds product to cart

[1471] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and the expected frequency of use. The device generates the input form using HTML and JavaScript and provides the user interface. In this example, a user adds a "camera" to their cart and enters the reason for purchase as "to enjoy taking photos on trips" and the expected frequency of use as "once a week."

[1472] Sending input data

[1473] The device sends the purchase reason and expected usage frequency entered by the user to the server via an HTTP POST request, and the data is sent securely.

[1474] Data analysis

[1475] The server stores the received data in a database (e.g., MySQL or PostgreSQL) and references the user's past purchase history. Next, the server uses a machine learning model (e.g., scikit-learn or TensorFlow) to predict the actual usage frequency of the product. If the prediction result is below a set threshold (e.g., 0.5), the server generates a warning message.

[1476] Warnings and alternative products

[1477] The response from the server is sent to the device, which then displays a warning message and alternative products to the user. For example, the warning message might say, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase." At the same time, alternative products such as "financial savings products" and "health improvement devices" are suggested.

[1478] Specific examples

[1479] A specific example of a user's actions might be adding a camera to their cart online, inputting the reason for the purchase as "to enjoy taking photos while traveling" and the expected frequency of use as "once a week."

[1480] Prompt Sentence Examples

[1481] Examples of prompts to input to a generative AI model include:

[1482] "A user adds a camera to their cart and enters the reason for the purchase, "to enjoy taking photos while traveling," and the expected frequency of use, "once a week." The server receives this information, predicts that the user will use the camera infrequently based on their past purchase history, and displays a warning message and alternative products."

[1483] This invention allows users to avoid wasteful consumption and receive assistance in selecting beneficial products. The server utilizes the user's past behavioral data to make highly accurate predictions, enabling the user to promote conscious consumption behavior.

[1484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1485] Step 1: User adds product to cart

[1486] When a user adds a product to their cart on an online shopping site, a form is displayed in which they can enter the reason for purchase and expected frequency of use. The input here is the product name added to the cart by the user, the reason for purchase, and expected frequency of use. The device generates the input form using HTML and JavaScript and displays it to the user.

[1487] Specific behavior:

[1488] A user adds an item to their cart.

[1489] The terminal generates and displays an input form using HTML and JavaScript.

[1490] The user enters the reason for purchase and frequency of use.

[1491] Step 2: Submitting input data

[1492] The device sends the data entered by the user, including the reason for purchase and expected frequency of use, to the server. This is done using an HTTP POST request. The input data includes the product name, reason for purchase, and expected frequency of use. This data is then passed to the server as output.

[1493] Specific behavior:

[1494] The user clicks the submit button.

[1495] The device generates an HTTP POST request.

[1496] Data on purchase reason and frequency of use is sent to the server.

[1497] Step 3: Save your data

[1498] The server stores the received data in a database. The input is the user's reason for purchasing and expected frequency of use, and the output is the data stored in the database. Databases such as MySQL or PostgreSQL are often used here.

[1499] Specific behavior:

[1500] The server receives the data.

[1501] The server establishes a database connection.

[1502] Execute an INSERT query on the database to save the data.

[1503] Step 4: Get your past purchase history

[1504] The server retrieves the user's past purchase history data from the database. The input is the user ID, and the output is the past purchase history data.

[1505] Specific behavior:

[1506] The server queries the database for past purchase history based on the user ID.

[1507] The database returns historical purchase data.

[1508] Step 5: Predicting usage frequency

[1509] The server uses a machine learning model to predict the frequency of new product purchases based on the acquired past purchase history. The input is past purchase history data and new product data, and the output is the predicted frequency of use. Machine learning libraries such as scikit-learn and TensorFlow are used here.

[1510] Specific behavior:

[1511] The server inputs past purchase history data into the machine learning model.

[1512] Machine learning models predict the frequency of new product use.

[1513] The predicted usage frequency is returned to the server.

[1514] Step 6: Generate a warning message

[1515] If the predicted usage frequency is below a set threshold, the server generates a warning message. The inputs are the predicted usage frequency and the threshold, and the output is the warning message.

[1516] Specific behavior:

[1517] The server compares the predicted usage frequency with a threshold.

[1518] If the usage rate falls below a threshold, the server generates a warning message.

[1519] Step 7: Suggest alternative products

[1520] The server suggests alternative products along with a warning message, such as financial products or health-related products. The input is the warning message, and the output is a list of alternative products.

[1521] Specific behavior:

[1522] The server generates a list of alternative products.

[1523] The server includes a warning message and information about alternative products in an HTTP response and sends it to the terminal.

[1524] Step 8: Display warning messages and alternative products

[1525] The terminal receives the response from the server and displays a warning message and alternative products to the user. The input is the response data from the server, and the output is the displayed message and product list.

[1526] Specific behavior:

[1527] The terminal receives an HTTP response from the server.

[1528] The device generates a warning message and a list of alternative products using HTML and JavaScript.

[1529] The user is presented with a warning message and alternative products.

[1530] (Application example 1)

[1531] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1532] When shopping online, it is common for users to fail to use purchased products appropriately, resulting in wasteful consumption. This not only reduces user satisfaction, but can also be a factor in increasing the burden on the environment. In particular, it is difficult to predict how much a user will actually use a product, making it difficult to make purchases based on that judgment. Therefore, there is a need for methods to support efficient consumption behavior. In addition, there is a lack of methods to suggest appropriate alternative products to encourage users to reconsider their purchase.

[1533] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1534] In this invention, the server includes: means for receiving a user's operation to add a product to an online shopping cart; means for prompting the user to input a reason for purchase and an expected frequency of use for the product; means for transmitting the input data on the reason for purchase and expected frequency of use to the server; means for referencing the user's past purchase history data and predicting the actual frequency of use of the product; means for generating a warning message urging the user to reconsider the purchase if the predicted frequency of use is below a preset threshold; means for suggesting alternative products along with the warning message; means for displaying the warning message and information about the alternative products to the user; means for generating alternative products using an artificial intelligence model if the expected frequency of use and the actual frequency of use do not match; and means for inputting the warning message and the content of the suggested alternative products as prompts to the artificial intelligence model. This allows users to avoid wasteful consumption and purchase products that are more effective and meet their needs. Furthermore, supporting efficient consumption behavior is expected to reduce environmental impact.

[1535] "User" refers to a consumer who purchases or uses a product.

[1536] An "online shopping cart" refers to a virtual shopping basket on an online shopping site that has the function of temporarily storing items that users intend to purchase.

[1537] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1538] "Expected frequency of use" refers to how often a user plans to use the product they have purchased.

[1539] "Server" refers to a computer system for processing and managing data.

[1540] "Purchase history data" refers to data regarding information about products purchased by a user in the past and their usage status.

[1541] "Actual frequency of use" refers to how often a user has used a product they have purchased in the past.

[1542] "Threshold" refers to a set reference value below which specific action is taken.

[1543] "Warning message" refers to a notification displayed to the user to encourage caution or reconsideration.

[1544] "Substitute products" are products that are suggested to replace the product a user is considering purchasing with other suitable products.

[1545] An "artificial intelligence model" refers to a type of computer program that processes large amounts of data, learns, and makes predictions and suggestions.

[1546] A "prompt sentence" is an instruction sentence input to an artificial intelligence model, and includes conditions and questions for obtaining a specific output.

[1547] The present invention provides a system for predicting the frequency and duration of use of a product when a user purchases it online, and determining the effectiveness of the purchase. This system is implemented as follows.

[1548] Overall flow

[1549] 1. User adds product to cart

[1550] When a user adds an item to their cart on an online shopping site, they are prompted to enter the reason for the purchase and the expected frequency of use. For example, if a user adds a "camera" to their cart, they will purchase the camera "to enjoy taking photos on trips" and enter the expected frequency of use as "once a week."

[1551] 2. Sending input data

[1552] The reason for purchase and expected frequency of use entered by the user are sent to the server. Data can be easily sent to the server using a device such as a smartphone.

[1553] 3. Data Analysis

[1554] The server analyzes the user's past purchase history data to predict actual usage frequency. This analysis is performed using a server system using Python and the Django framework. For example, based on the usage frequency data of a user's previously purchased camera, it predicts that the actual usage frequency of a new camera will be about "once a month."

[1555] 4. Warnings and alternative products

[1556] If the predicted usage frequency falls below a set threshold, the server generates a warning message for the user. At the same time, it uses an artificial intelligence model (generative AI model) to suggest alternative products to the user. For example, the server might suggest "savings products" or "health improvement equipment" along with a message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase."

[1557] Hardware and software used

[1558] Hardware: User's smartphone, server computer

[1559] Software: Python, Django framework, generative AI models

[1560] Specific examples of processing and prompts

[1561] For example, if a user adds a camera to their cart using the "Shopping Advisor" app on their smartphone and enters "to enjoy taking photos while traveling" and "to use once a week," the process proceeds as follows: The server receives the input data, predicts the actual frequency of use based on past purchase history data, and if the predicted value falls below a threshold, generates a warning message and suggests alternative products.

[1562] Example prompt sentence:

[1563] When a user purchases a product, the system asks them to input their expected usage frequency and reason for purchase. Predict the actual usage frequency from the user's past purchase history, and if the predicted usage frequency is below a threshold, display a warning message and suggest alternative products.

[1564] This allows users to avoid wasteful consumption and support efficient and beneficial consumption behavior. Furthermore, by using a generative AI model, more accurate alternative product suggestions can be realized.

[1565] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1566] Step 1:

[1567] The user adds an item to the cart.

[1568] Input: The user selects the product they want to purchase and adds it to their cart.

[1569] Output: The product to be purchased is added to the cart, and a form is displayed to enter the reason for purchase and expected frequency of use.

[1570] Step 2:

[1571] The device prompts the user to enter the reason for purchase and expected frequency of use.

[1572] Input: Product information added to cart. Enter the reason for purchase (e.g., to enjoy taking photos while traveling) and expected frequency of use (e.g., once a week).

[1573] Output: Data on purchase reasons and expected frequency of use.

[1574] Step 3:

[1575] The terminal transmits the input data on the reason for purchase and the expected frequency of use to the server.

[1576] Input: Purchasing reason and expected frequency of use data.

[1577] Output: This data is sent to the server.

[1578] Step 4:

[1579] Based on the data received by the server, the server refers to the user's past purchase history data and predicts the actual frequency of use of the product.

[1580] Inputs: Purchasing reason, expected frequency of use, and the user's past purchasing history data.

[1581] Output: The predicted usage frequency of the product.

[1582] How it works: The server retrieves past purchase history from the database, analyzes usage frequency data for similar products, and uses an AI model to calculate the predicted usage frequency of newly added products.

[1583] Step 5:

[1584] If the server predicts that the frequency of use will fall below a set threshold, it generates a warning message encouraging users to reconsider their purchase.

[1585] Input: The expected frequency of use of the product. Threshold (e.g., 0.5).

[1586] Output: A warning message.

[1587] How it works: The server compares the predicted usage frequency to a threshold and generates a warning message if it falls below the threshold. The message might include, "This product is unlikely to be used as frequently as expected. Please reconsider your purchase."

[1588] Step 6:

[1589] The server inputs a prompt sentence into the generative AI model to suggest alternative products along with a warning message.

[1590] Input: Warning message, suggested alternative products, prompt (e.g., prompting the user to input their expected usage frequency and reason for purchasing the product, and suggesting alternative products).

[1591] Output: A list of suggested alternative products.

[1592] How it works: The server inputs a prompt into the generative AI model, which then generates appropriate alternative products (e.g., financial products for savings, health improvement devices, etc.).

[1593] Step 7:

[1594] The device will display a warning message and information about alternative products to the user.

[1595] Input: Warning message, list of suggested alternative products.

[1596] Output: A warning message and a list of alternative products that are displayed to the user.

[1597] Behavior: The device displays a warning message received from the server and a list of alternative products to the user, encouraging them to reconsider. For example, a message like "The camera is unlikely to be used as frequently as expected. Consider purchasing the following product instead" is displayed along with a list of alternative products.

[1598] This allows users to avoid wasteful consumption and purchase products efficiently and appropriately. Furthermore, by using generative AI models, more accurate alternative product suggestions can be realized.

[1599] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1600] The present invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[1601] Overall system overview

[1602] 1. User adds product to cart

[1603] When a user adds an item to their cart on an online shopping site, they are prompted with a form to enter their reason for purchase and expected frequency of use, and an interface is also displayed to recognize the user's emotional state.

[1604] 2. Sending input data

[1605] The user inputs the reason for purchase and the expected frequency of use, and emotional data is also acquired. This data is sent to the server.

[1606] 3. Data Analysis

[1607] The server analyzes the received user data and emotion data, accesses a database to reference past purchase history data, and predicts the actual frequency of use for each product.

[1608] 4. Warnings and alternative products

[1609] Based on the user's emotional state, the server adjusts the tone and content of warning messages to encourage reconsideration of the purchase and suggests alternative financial or health products.

[1610] Program processing explanation

[1611] 1. User adds product to cart

[1612] Terminal handling

[1613] When a user adds an item to their cart on an online shopping site, they are prompted to enter their reason for purchase and expected frequency of use. An interface for emotion recognition is also displayed. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the system uses facial recognition and text input to recognize the user's emotional state.

[1614] 2. Sending input data

[1615] Terminal handling

[1616] The purchase reason, expected frequency of use, and emotional data entered by the user are sent to the server.

[1617] 3. Data Analysis

[1618] Server Processing

[1619] The server receives user data and emotion data and stores them in a database.

[1620] The server references the user's past purchase history data to obtain usage frequency data for similar products, and analyzes the user's emotional data to understand their current emotional state.

[1621] The server predicts the frequency of use of newly added items based on past purchase history data and user emotional data. This prediction process combines statistical analysis of historical data and analysis of emotional data.

[1622] 4. Warnings and alternative products

[1623] Server Processing

[1624] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency falls below this threshold, a warning message is generated based on the user's emotional state. For example, if emotion analysis determines that the user is in an impulsive state, a more emphatic warning message is sent.

[1625] The server will then provide a warning message along with alternative product suggestions (such as financial products or health improvement tools), which will be explained in a tone appropriate to the user's emotional state.

[1626] Specific examples

[1627] User operation example

[1628] 1. A user goes online and adds a camera (ID: 123) to their cart.

[1629] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[1630] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[1631] System processing flow

[1632] 1. The device accepts user input and emotion data and sends it to the server.

[1633] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[1634] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1635] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1636] In this way, the present invention can guide users' consumption behavior in a healthier and more efficient direction by avoiding wasteful consumption and suggesting more beneficial products while taking into account their emotional state.

[1637] The processing flow will be explained below.

[1638] The present invention provides a system that, when a user purchases a product through online shopping, predicts the frequency and duration of use of the product, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase.

[1639] Step 1:

[1640] A user adds an item to their cart on an online shopping site. The device receives this action and displays a form that prompts the user to enter the reason for purchase and expected frequency of use. It also displays an interface for emotion recognition. For example, if a user adds a "camera" to their cart, they will enter that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the device will use facial recognition and text input to identify the user's emotional state.

[1641] Step 2:

[1642] When the user inputs the reason for purchase, expected frequency of use, and emotional data and presses the confirm button, this data is saved on the device, which then sends it to the server.

[1643] Step 3:

[1644] The server analyzes the received user data, expected usage frequency, and emotion data. Specifically, the server accesses a database, references the user's past purchase history, and extracts usage frequency data for similar products.

[1645] Step 4:

[1646] The server compares past purchase history data with the user's input data. Based on the actual usage frequency data of similar products in the past, the server predicts the usage frequency of the newly added product to the cart. This prediction reflects not only the historical data but also the user's emotional data.

[1647] Step 5:

[1648] The server compares the predicted usage frequency with a set threshold (e.g., 0.5). If the predicted usage frequency is below this threshold, the emotion engine analyzes the user's emotional state and determines the appropriate tone and content of the warning message. For example, if the user's emotional state is "excited," a stronger warning message is generated.

[1649] Step 6:

[1650] The server generates a warning message along with a list of alternative products, including financial and health-related products, with descriptions that reflect the emotion data.

[1651] Step 7:

[1652] The device receives the response from the server and displays a warning message to the user, for example, "Warning: This product may not be used as often as you expect. Please reconsider your purchase."

[1653] Step 8:

[1654] The device presents the user with a list of alternative products, including the name and a brief description of each alternative, presented in a tone that reflects the user's emotional state—for example, a more gentle suggestion would be used if the user returned to a calm state.

[1655] As a specific example, consider the case where a user is trying to purchase a camera. The user adds a "camera" to their cart, enters the reason for the purchase as "to enjoy taking photos while traveling," and enters the expected frequency of use as "once a week." The emotion recognition interface recognizes that the user is in an "excited" state. The server analyzes past purchase data and determines that the actual predicted frequency of use is about "once a month." Therefore, the server generates a strong warning message saying, "Warning: This product may not be used as frequently as you expect. Please reconsider your purchase," and suggests alternative products such as a "savings product" or a "health improvement device."

[1656] As described above, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding users' consumption behavior in a healthy and efficient direction.

[1657] Example 2

[1658] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1659] In conventional online shopping systems, users often make impulse purchases based on their emotions, and there is a lack of means to evaluate the validity of their purchases. This leads to wasteful consumption and inappropriate product choices, which increases the user's financial burden. The purpose of this invention is to solve this problem by providing a system that takes into account the user's emotional state and increases the validity of purchases.

[1660] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving an operation by a user to add a product to an online shopping cart, a means for prompting the user to input a purchase reason and an expected frequency of use for the product, and a means for transmitting the input data of the purchase reason and expected frequency of use to the server. This makes it possible to evaluate the validity of a purchase while taking into account the emotional state of the user, prevent wasteful consumption, and suggest appropriate products.

[1661] "User" refers to a consumer who selects and purchases products on an online shopping site.

[1662] "Online shopping cart" refers to a virtual basket that temporarily stores items selected by a user on an online shopping site.

[1663] "Reason for purchase" refers to the motivation or purpose for a user to purchase a particular product.

[1664] "Expected frequency of use" refers to numbers or terms that predict how often a user will use the product they are about to purchase.

[1665] "Emotional state" refers to the psychological and emotional state a user is in when purchasing a product, including states such as excitement, joy, sadness, and anger.

[1666] "Server" refers to a computer system that transmits and receives data over the Internet and processes and stores user input data and history data.

[1667] "Purchase history data" refers to records of purchases a user has made in the past on online shopping sites.

[1668] "Frequency of use" refers to how often a user actually uses the product they purchased.

[1669] The "threshold" refers to a set numerical value used to determine whether the predicted results of usage frequency, etc. exceed a reference value.

[1670] "Warning message" refers to a notification that prompts a user to reconsider their purchase if the predicted usage frequency falls below a threshold.

[1671] "Alternative Products" refers to suggested products that may replace the product selected by the user, including, among other things, products that may improve the user's health or financial situation.

[1672] An "emotion recognition interface" refers to a system that analyzes input data such as the user's face and voice to understand the user's emotional state.

[1673] This invention provides a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. This system is implemented as follows.

[1674] Overall system overview

[1675] The system operates in cooperation with users, terminals, and servers.

[1676] 1. User adds product to cart

[1677] When a user adds a product to their cart on an online shopping site, the device displays a form for inputting the reason for purchase and expected frequency of use, and an emotion recognition interface is also displayed to recognize the user's emotional state.

[1678] Specifically, when a user adds a "camera" to their cart, they input the following: "To enjoy taking photos while traveling," as the reason for the purchase, and set the expected frequency of use as "once a week." At the same time, the emotion recognition interface collects the user's facial and voice data and analyzes their emotional state.

[1679] 2. Sending input data

[1680] The device sends the purchase reason, expected frequency of use, and emotional data entered by the user to the server. The data sent includes the product ID, purchase reason, frequency of use, and emotional data. A secure communication protocol (e.g., HTTPS) is used to send the data.

[1681] 3. Data Analysis

[1682] The server receives user data and emotional data and stores them in a database. The server then references the user's past purchase history and emotional data and uses a generative AI model to predict actual usage frequency. This is done by statistically analyzing the user's past purchase history and current emotional state.

[1683] 4. Warnings and alternative products

[1684] If the predicted usage frequency falls below a set threshold (e.g., 0.5), the server generates a warning message based on the user's emotional state. For example, if the user is in an "excited" state, the server generates a message saying, "Please calm down and reconsider this purchase." At the same time, it suggests alternative products such as "financial products for savings" or "health improvement equipment."

[1685] Specific examples

[1686] User operation example

[1687] 1. A user goes online and adds a camera (ID: 123) to their cart.

[1688] 2. Enter "To enjoy taking photos while traveling" as the reason for purchase and "Once a week" as the expected frequency of use.

[1689] 3. The emotion-aware interface recognizes the user's emotional state as "excited."

[1690] System processing flow

[1691] 1. The device accepts user input and emotion data and sends it to the server.

[1692] 2. The server analyzes the frequency of use of cameras previously purchased by the user based on past purchase history, and predicts the actual frequency of use taking into account the user's emotional state.

[1693] 3. Based on the prediction results, if the user is determined to be in an excited state through sentiment analysis, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1694] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1695] In this way, the present invention can help users avoid wasteful consumption and suggest more beneficial products while taking into account their emotional state, thereby guiding their consumption behavior in a healthier and more efficient direction.

[1696] Prompt Sentence Examples

[1697] "Purchase a camera to enjoy taking photos on your trip, but reconsider whether you really need it. Provide specific warning messages and alternative product suggestions based on past purchase history and emotional state."

[1698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1699] Step 1:

[1700] User adds product to cart

[1701] User Actions

[1702] A user selects a product on an online shopping site and adds it to their cart. Specifically, the user selects a camera and clicks the "Add to cart" button.

[1703] input

[1704] Product ID and user action (add to cart).

[1705] output

[1706] A list of items added to the cart.

[1707] Specific actions

[1708] When a user clicks the Add to Cart button on the site, the selected product data (product ID, product name, etc.) is added to the cart list.

[1709] Step 2:

[1710] Input of purchase reason, frequency of use, and emotional state

[1711] Terminal handling

[1712] When an item is added to the cart, the device displays a form for entering the reason for purchase and expected frequency of use, while simultaneously activating an emotion recognition interface.

[1713] input

[1714] The reason for purchase and frequency of use entered by the user, and emotional data collected by the device (facial recognition, voice, etc.).

[1715] output

[1716] Reasons for purchase, frequency of use, and emotional state.

[1717] Specific actions

[1718] The user enters "to enjoy taking photos of my travels" and sets the frequency of use to "once a week." At the same time, the camera and microphone collect emotional data and send it to the emotion analysis engine.

[1719] Step 3:

[1720] Sending input data

[1721] Terminal handling

[1722] The device collects data on the user's reasons for purchasing, frequency of use, and emotions, and sends it to the server.

[1723] input

[1724] Reasons for purchase, frequency of use, and emotional data.

[1725] output

[1726] Purchasing reasons, frequency of use, and emotional data sent to the server.

[1727] Specific actions

[1728] The collected data is securely sent to a server using the HTTPS protocol, including product ID, purchase reason, frequency of use, and sentiment data.

[1729] Step 4:

[1730] Data analysis

[1731] Server Processing

[1732] The server stores the received data in a database, compares it with past purchase history and sentiment data, and uses a generative AI model to predict actual usage frequency.

[1733] input

[1734] Received data (purchase reasons, frequency of use, emotional data), past purchase history data.

[1735] output

[1736] Predicted frequency of use.

[1737] Specific actions

[1738] The server accesses the database to retrieve past usage data for similar products. At the same time, the sentiment analysis engine analyzes the current sentiment data, and the generative AI model performs statistical analysis to predict usage frequency.

[1739] Step 5:

[1740] Generate warning messages and substitute products

[1741] Server Processing

[1742] The server compares the predicted usage frequency with a set threshold, and if it falls below the threshold, generates a warning message and alternative products based on the user's emotional state.

[1743] input

[1744] Predicted usage frequency, thresholds, and sentiment data.

[1745] output

[1746] Warning message and list of alternative products.

[1747] Specific actions

[1748] If the generative AI model determines that the predicted frequency of use is below a threshold, it will take into account the user's emotional state and generate a warning message such as, "Is this purchase really necessary? Please think about it calmly," and list alternative products such as "financial savings products" and "health improvement equipment."

[1749] Step 6:

[1750] Warning messages and alternative product displays

[1751] Terminal handling

[1752] The terminal displays the warning message and alternative products received from the server to the user.

[1753] input

[1754] Warning messages and alternative product data.

[1755] output

[1756] What the user sees.

[1757] Specific actions

[1758] The device displays the warning message and alternative products received from the server using a user interface such as a dialog box or pop-up. For example, in addition to information about the camera the user added to their cart, the device may display a warning message and a list of alternative products, encouraging the user to reconsider their purchase.

[1759] In this way, data is input and output, and data processing and calculation are performed at each step, and the overall processing of the system progresses. As a result, users can avoid wasteful consumption and choose more beneficial products.

[1760] (Application example 2)

[1761] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1762] Today's online shoppers often make impulsive purchases, which can result in wasteful spending. Furthermore, due to the influence of emotions, purchased products are often not actually used. Under these circumstances, a system that improves the effectiveness of emotion-based purchasing decisions is needed.

[1763] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1764] In this invention, the server includes emotion recognition means for recognizing the emotional state of the user, means for transmitting the input purchase reason and expected use frequency data and emotion data to the server, and means for referencing the user's past purchase history data and emotion data to predict the actual use frequency of the product. This makes it possible to determine the effectiveness of a purchase while taking the user's emotional state into account and prevent wasteful consumption.

[1765] An "online shopping cart" is a virtual shopping cart that allows users to select and temporarily store products online.

[1766] The "reason for purchase" is an explanation of the user's motivation or purpose for purchasing a product.

[1767] "Expected frequency of use" is information indicating how often the user plans to use the product they are considering purchasing.

[1768] "Emotion recognition" is a technology that determines a user's current feelings and mental state based on facial expressions, tone of voice, etc.

[1769] "Emotion data" is information about a user's emotions extracted by emotion recognition.

[1770] "Server" means a central processing system that receives and analyzes data sent by users.

[1771] "Purchase history data" refers to data that records information about products purchased by a user in the past.

[1772] "Actual usage frequency" is data indicating how often a purchased product is actually used.

[1773] A "warning message" is a notification that encourages users to reconsider their purchase.

[1774] An "alternative product" is a product that is suggested as an alternative to the product selected by the user.

[1775] "Tone" is the tone and style of expression used in a message or proposal.

[1776] The present invention is a system that predicts the frequency and duration of use of a product when a user purchases it online, and further combines this with an emotion engine that recognizes the user's emotions to determine the validity of the purchase. The purpose of this system is to prevent wasteful consumption by users and improve the effectiveness of emotion-based purchasing decisions. Specific embodiments for implementing the present invention are described below.

[1777] Overall system overview

[1778] 1. User adds product to cart

[1779] The device receives an operation from the user to add a product to the cart on an online shopping site. Next, a form is displayed in which the user enters the reason for purchase and expected frequency of use. At this time, an interface for emotion recognition is also displayed. For example, when a user adds a "camera" to the cart using a smartphone, the user enters that they purchased the camera "to enjoy taking photos on trips" and the expected frequency of use as "once a week." At the same time, the smartphone camera is used to capture the user's face, and emotion recognition technology (for example, Microsoft Azure's Face API) is used to recognize the user's emotional state.

[1780] 2. Sending input data

[1781] The purchase reason, expected frequency of use, and emotion data input by the user are transmitted to the server by the terminal.

[1782] 3. Data Analysis

[1783] The server receives the purchase reason, expected frequency of use, and emotional data sent by the user and stores them in a database. The server then references the user's past purchase history data to obtain actual usage frequency data for similar products. It then analyzes the emotional data to understand the user's current emotional state. By combining these data, it predicts the usage frequency of a newly added product to the cart. For example, it predicts the actual usage frequency of the product through statistical analysis of the historical data and analysis of the emotional data.

[1784] 4. Warnings and alternative products

[1785] If the predicted usage frequency falls below a set threshold, the server generates a warning message urging the user to reconsider their purchase. This warning message is created in an appropriate tone based on the user's emotional state. For example, if the user is excited, a more emphatic warning message is displayed. At the same time, the server suggests alternative products such as financial or health-related products. These suggestions are also provided with appropriate content based on the user's emotional state.

[1786] Specific examples

[1787] If a user adds a camera (product ID: CAM123) to their cart online, enters "to enjoy taking photos while traveling" as the reason for the purchase, and enters "once a week" as the expected frequency of use, and the emotion recognition interface recognizes the user's emotional state as "excited," the following process will occur:

[1788] 1. The device accepts the user's input and emotion data and sends it to the server.

[1789] 2. The server analyzes the frequency of use of similar products previously purchased by the user based on their past purchase history, and predicts the actual frequency of use taking into account their emotional state.

[1790] 3. Based on the prediction results, if a user is determined to be in an excited state, a warning message will be sent to emphasize that the user should reconsider their purchase.

[1791] 4. At the same time, we will propose alternative products such as "financial savings products" and "health improvement devices."

[1792] The above is a specific embodiment. This system allows users to avoid emotionally driven impulse buying and to engage in effective consumption behavior.

[1793] Example prompt sentence:

[1794] A user adds a camera to their cart. The reason for the purchase is "to enjoy taking photos while traveling." The expected usage frequency is "once a week." Facial emotion recognition detects excitement. Generate a warning message to encourage reconsideration of the purchase and suggest a related camera accessory pack as an alternative.

[1795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1796] Step 1:

[1797] User adds product to cart

[1798] A user adds a product to a cart on an online shopping site. This action causes the device to receive a product addition command. Next, a form for inputting the reason for purchase and expected frequency of use is displayed. An interface for emotion recognition is then displayed. The input data is the reason for purchase (e.g., "to enjoy taking photos of travel"), expected frequency of use (e.g., "once a week"), and an image of the user's face. Emotion data is obtained using emotion recognition technology (e.g., Microsoft Azure's Face API).

[1799] Step 2:

[1800] Submitting user-entered data

[1801] The user inputs the reason for purchase and expected frequency of use, and the emotional data captured by the emotion recognition interface is compiled on the device. The device then sends this data in bulk to the server. The input data includes the reason for purchase, expected frequency of use, and emotional data, and is sent via an HTTP request.

[1802] Step 3:

[1803] Receiving and storing data by the server

[1804] The server receives the purchase reason, expected frequency of use, and emotion data sent from the device. The received data is stored in a database within the server. The stored data is used for subsequent analysis.

[1805] Step 4:

[1806] Obtaining past purchase history data

[1807] The server retrieves the user's past purchase history data and uses a database query to look up usage frequency data for similar products. This history data includes purchase dates, usage frequency, and other relevant information for each product.

[1808] Step 5:

[1809] Emotional Data Analysis

[1810] The server analyzes the received emotion data. It analyzes the data obtained through emotion recognition (e.g., excitement, joy, sadness, etc.). It uses an emotion engine to determine the user's current emotional state. The analysis results are used for subsequent prediction processing.

[1811] Step 6:

[1812] Usage frequency prediction

[1813] The server combines past purchase history data with current sentiment data to predict the frequency of use of newly added items to the cart. It uses statistical methods and machine learning models (e.g., generative AI models) to predict the actual frequency of use of the items. The input data are past purchase history and sentiment data, and the output is the predicted frequency of use.

[1814] Step 7:

[1815] Generate a warning message

[1816] If the predicted usage frequency falls below a set threshold, the server generates a warning message encouraging the user to reconsider their purchase. The tone of the generated message is adjusted based on the user's emotional state. For example, if the user is excited, a warning message with an accentuated tone is displayed.

[1817] Step 8:

[1818] Alternative product suggestions

[1819] The server then generates a warning message and suggests alternative products, such as financial or health-related products, that are relevant to the user's emotional state and purchasing reasons. The server also generates information about the alternative products, described in an appropriate tone.

[1820] Step 9:

[1821] Warning messages and alternative product displays

[1822] The terminal displays the warning message and information about alternative products sent from the server to the user, giving the user the opportunity to reconsider their purchase or consider alternative products.

[1823] The above are the specific processing steps of the system that realizes the application example.

[1824] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1825] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1826] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1827] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1828] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1829] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1830] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1831] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1832] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1833] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1834] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1835] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1836] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1837] 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.

[1838] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1839] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1840] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1841] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1842] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1843] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1844] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1845] The following is further disclosed regarding the above embodiment.

[1846] (Claim 1)

[1847] means for receiving an action by a user to add an item to an online shopping cart;

[1848] a means for prompting a user to input a reason for purchasing the product and an expected frequency of use;

[1849] means for transmitting the input data of the purchase reason and the expected frequency of use to a server;

[1850] a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data in the server;

[1851] means for generating a warning message urging the user to reconsider purchasing if the predicted frequency of use is below a set threshold;

[1852] means for suggesting an alternative product together with the warning message;

[1853] means for displaying the warning message and information about alternative products to a user;

[1854] A system including:

[1855] (Claim 2)

[1856] The system of claim 1 , wherein the alternative product is a financial product or a health-related product.

[1857] (Claim 3)

[1858] 10. The system of claim 1, further comprising means for displaying a warning message and suggesting an alternative product only if the predicted frequency of use falls below a set threshold.

[1859] "Example 1"

[1860] (Claim 1)

[1861] means for receiving an action by a user to add an item to an online shopping cart;

[1862] a means for prompting a user to input a reason for purchasing the product and an expected frequency of use;

[1863] means for transmitting the input data of the purchase reason and the expected frequency of use to a server;

[1864] a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data in the server;

[1865] A means for the server to predict usage frequency using a machine learning model;

[1866] means for storing said data in a database;

[1867] means for generating a warning message urging the user to reconsider purchasing if the predicted frequency of use is below a set threshold;

[1868] means for suggesting an alternative product together with the warning message;

[1869] means for displaying the warning message and information about alternative products to a user;

[1870] A system including:

[1871] (Claim 2)

[1872] The system of claim 1 , wherein the alternative product is a financial product or a health-related product.

[1873] (Claim 3)

[1874] 10. The system of claim 1, further comprising means for displaying a warning message and suggesting an alternative product only if the predicted frequency of use falls below a set threshold.

[1875] "Application Example 1"

[1876] (Claim 1)

[1877] means for receiving an action by a user to add an item to an online shopping cart;

[1878] a means for prompting a user to input a reason for purchasing the product and an expected frequency of use;

[1879] means for transmitting the input data of the purchase reason and the expected frequency of use to a server;

[1880] a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data in the server;

[1881] means for generating a warning message urging the user to reconsider purchasing if the predicted frequency of use is below a set threshold;

[1882] means for suggesting an alternative product together with the warning message;

[1883] means for displaying the warning message and information about alternative products to a user;

[1884] Furthermore, a means for generating a substitute product using an artificial intelligence model when the expected frequency of use and the actual frequency of use do not match;

[1885] a means for inputting the warning message and the content of the alternative product suggestions into an artificial intelligence model as prompt sentences;

[1886] A system including:

[1887] (Claim 2)

[1888] 10. The system of claim 1, wherein the alternative products span a variety of categories.

[1889] (Claim 3)

[1890] 10. The system of claim 1, further comprising means for displaying a warning message and suggesting an alternative product only if the predicted frequency of use falls below a set threshold.

[1891] "Example 2: Combining Emotion Engines"

[1892] (Claim 1)

[1893] means for receiving an action by a user to add an item to an online shopping cart;

[1894] a means for prompting a user to input a reason for purchasing the product and an expected frequency of use;

[1895] means for transmitting the input data of the purchase reason and the expected frequency of use to a server;

[1896] means for recognizing and acquiring an emotional state of a user based on said input data;

[1897] a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data and emotion data, in the server;

[1898] means for generating a warning message to encourage a user to reconsider purchasing the product based on the user's emotional state if the predicted frequency of use is below a set threshold;

[1899] means for suggesting an alternative product together with the warning message;

[1900] means for displaying the warning message and information about alternative products to a user;

[1901] A system including:

[1902] (Claim 2)

[1903] The system of claim 1 , wherein the alternative product is a financial product or a health-related product.

[1904] (Claim 3)

[1905] 10. The system of claim 1, further comprising means for displaying a warning message and suggesting alternative products only if the predicted frequency of use falls below a set threshold.

[1906] "Application example 2 when combining emotion engines"

[1907] (Claim 1)

[1908] means for receiving an action by a user to add an item to an online shopping cart;

[1909] a means for prompting a user to input a reason for purchasing the product and an expected frequency of use;

[1910] emotion recognition means for recognizing an emotional state of a user;

[1911] means for transmitting the input purchase reason, expected frequency of use data, and emotion data to a server;

[1912] a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data and emotion data, in the server;

[1913] means for generating a warning message urging the user to reconsider purchasing if the predicted frequency of use is below a set threshold;

[1914] means for suggesting alternative products in an appropriate tone based on the user's emotional state along with the warning message;

[1915] means for displaying the warning message and information about alternative products to a user;

[1916] A system including:

[1917] (Claim 2)

[1918] The system of claim 1 , wherein the alternative product is a financial product or a health-related product.

[1919] (Claim 3)

[1920] 10. The system of claim 1, further comprising means for displaying a warning message and suggesting an alternative product only if the predicted frequency of use falls below a set threshold. [Explanation of symbols]

[1921] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving an action by a user to add an item to an online shopping cart; a means for prompting a user to input a reason for purchasing the product and an expected frequency of use; means for transmitting the input data of the purchase reason and the expected frequency of use to a server; a means for predicting the actual frequency of use of the product by referring to the user's past purchase history data in the server; means for generating a warning message urging the user to reconsider purchasing if the predicted frequency of use is below a set threshold; means for suggesting an alternative product together with the warning message; means for displaying the warning message and information about alternative products to a user; A system including:

2. 2. The system of claim 1, wherein the alternative product is a financial product or a health-related product.

3. 10. The system of claim 1, further comprising means for displaying a warning message and suggesting alternative products only if the predicted frequency of use falls below a set threshold.

Images