System

Abstract

A system is provided.SOLUTION: A system including a user terminal configured to collect operation history data of a user, a server configured to analyze the operation history data transmitted from the user terminal, a server configured to generate a preference profile of the user based on an analysis result, a server configured to generate a candidate to be proposed based on the preference profile, a server configured to transmit the candidate to be proposed to the user terminal, and the user terminal configured to display the candidate to be proposed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the number of options for smartphones and communication plans has increased, making it difficult for users to choose the most suitable one from the many options. Furthermore, store staff must deal with many customers individually, which takes time and reduces work efficiency. In this situation, there is a need for a system and method that can quickly suggest the most suitable product and plan to a user. Furthermore, this is intended to reduce the burden on store staff and improve work efficiency. [Means for solving the problem]

[0005] The present invention solves the problems by a system including: a user terminal for collecting user operation history data; a server for analyzing the operation history data transmitted from the user terminal; a server for generating a user preference profile based on the analysis result; a server for generating suggested candidates based on the preference profile; a server for transmitting the suggested candidates to the user terminal; and a user terminal for displaying the suggested candidates. This allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving work efficiency.

[0006] A "user terminal" is an electronic device that a user uses to view and manipulate information.

[0007] "Operation history data" refers to data that includes a record of operations and browsing that a user has performed on a user terminal.

[0008] A "server" is a central control unit for receiving, storing, analyzing, and transmitting data over a network.

[0009] "Analysis" is the process of understanding and interpreting information such as operation history data using calculations and algorithms.

[0010] A "preference profile" is a data set that organizes and records information about a user's interests and preferences.

[0011] "Suggested options" are a list of products and plans recommended based on the user's preference profile.

[0012] "Display" refers to the act of visually showing information on the screen of a user terminal. [Brief explanation of the drawings]

[0013] [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 illustrating 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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system for helping users find the smartphone and plan that suits them. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0035] System configuration

[0036] 1. User Device

[0037] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0038] The user terminal has a function of collecting operation history data of the user.

[0039] Operation history data includes pages viewed, links clicked, and time spent on the site.

[0040] 2. Server

[0041] The server is a central control unit installed in a cloud environment or on-premise environment.

[0042] The server has a function of receiving and analyzing the operation history data sent from the user terminal.

[0043] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0044] Program Operation

[0045] Data collection

[0046] When a user browses a website to search for a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. Past purchase history and current contract plan data are also collected and sent to the server.

[0047] Data analysis and preference profile generation

[0048] The server analyzes the received operation history data and purchase history data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements.

[0049] Generate and submit suggestions

[0050] The server generates a list of products and plans suitable for the user based on the user's preference profile, and sends this recommendation list to the user's terminal.

[0051] Displaying and taking action on recommendation results

[0052] The user's device analyzes the recommendation list and displays it in an easy-to-read format. If the user is interested in the recommended products and plans, they can click on the details to proceed with the purchase or plan change.

[0053] Specific examples

[0054] Example 1: Recommending a new smartphone

[0055] Suppose a user is browsing a website looking for a new smartphone. The device collects operation history showing frequent visits to pages for smartphones with powerful cameras. The server analyzes this and creates a list of newly released smartphones with powerful cameras. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0056] Example 2: Recommending a new plan

[0057] Let's say a user frequently checks for plans with larger data capacities. The device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and proceeds with the user switching to that plan.

[0058] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user browses a website looking for a new smartphone or plan.

[0062] Step 2:

[0063] The user's device collects data on the user's operation history, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0064] Step 3:

[0065] The device sends the collected operation history data to the server in real time.

[0066] Step 4:

[0067] Prepares for analysis of the operation history data, past purchase history data, and current contract plan data received by the server. Filters out unnecessary and duplicate data.

[0068] Step 5:

[0069] The server uses machine learning algorithms to analyze the operation history data, thereby identifying user preferences and behavioral patterns.

[0070] Step 6:

[0071] Based on the analysis, the server generates a user preference profile, which includes the product features that interest the user and the plan elements that they prefer.

[0072] Step 7:

[0073] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[0074] Step 8:

[0075] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[0076] Step 9:

[0077] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan.

[0078] Step 10:

[0079] Users can check the recommended products and plans, and if they are interested, they can click on the details. The device will guide them through the process of purchasing or changing plans.

[0080] Step 11:

[0081] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[0082] Step 12:

[0083] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[0084] Example 1

[0085] 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."

[0086] The current smartphone and plan selection process has the problem that it is difficult for users to find products and services that suit their preferences, and it takes a lot of time and effort. It also increases the burden on store staff and tends to reduce overall work efficiency. A system that solves these problems and allows users to efficiently find the best products and plans is needed.

[0087] 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.

[0088] In this invention, the server includes: a user terminal that collects and transmits user operation history data and purchase history data in real time; a server that receives and analyzes the operation history data and purchase history data transmitted from the user terminal; a server that generates a user preference profile based on the analyzed data; a server that generates recommendation candidates based on the preference profile; a server that transmits the recommendation candidates to the user terminal; and a server that receives and displays the recommendation candidates. This enables users to efficiently find products and plans that suit them, reduces the burden on store staff, and improves overall business efficiency.

[0089] A "user terminal" is an electronic device used by a user, such as a smartphone, tablet, or PC.

[0090] "Operation history data" refers to data such as the pages a user viewed, the links they clicked, and the length of time they stayed on the site.

[0091] "Purchase history data" refers to data on products and services purchased by a user in the past.

[0092] "Means of collecting and transmitting in real time" refers to the function of instantly acquiring information and transmitting it to the server every time a user performs an operation.

[0093] A "server" is a central control device that has the function of receiving, analyzing, and storing data sent from user terminals.

[0094] A "preference profile" is a collection of information about a user's interests and preferences that is generated by the server by analyzing the user's operation history and purchase history.

[0095] "Recommended candidates" refers to a list of products and services that are suitable for the user, generated by the server based on the preference profile.

[0096] "Means for receiving and analyzing" refers to the function by which the server receives data sent from the user's device and processes it using machine learning algorithms, etc.

[0097] "Means for generating" refers to the function by which the server creates preference profiles and recommendation candidates from the analysis results.

[0098] The "transmitting means" is a function that sends the recommendation candidates generated by the server to the user terminal.

[0099] "Means for receiving and displaying" refers to the function by which the user terminal receives the recommended candidates sent from the server and displays them in a format that is easy for the user to view.

[0100] This invention is a system that allows users to find a smartphone and plan that suits them, and is composed of a user terminal, a server, and its communication protocol.

[0101] User terminal

[0102] User terminals are electronic devices such as smartphones, tablets, and PCs. User terminals collect operation history data and purchase history data in real time and send it to a server. Specific hardware examples include smartphones, which are common mobile devices. Software used includes dedicated applications for data collection and transmission.

[0103] server

[0104] The server is a central control device installed in a cloud environment or on-premise environment. It has the function of receiving and analyzing operation history data and purchase history data sent from user devices. Machine learning algorithms such as Python's Sci-Kit Learn and TENSORFLOW (registered trademark) are used for data analysis. Based on the preference profile generated by the server, it generates recommended candidates for products and plans suitable for the user and sends them to the user device.

[0105] Specific examples

[0106] Example 1: Recommending a new smartphone

[0107] Suppose a user is browsing a website looking for a new smartphone. The user's device collects this operation history and sends it to the server. For example, the user's operation history may record that the user frequently visits pages for smartphones with high camera performance. The server analyzes this data and creates a list of new smartphones with high camera performance. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0108] Example 2: Recommending a new plan

[0109] Suppose a user frequently checks for plans with larger data capacities. The user's device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0110] Example prompt

[0111] Prompt: "Describe a system where a user's device captures page browsing history in real time on a smartphone with a powerful camera and sends it to a server. The server then uses machine learning algorithms to generate a preference profile and create and send a list of smartphone recommendations that are best suited to the user."

[0112] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1: Data collection

[0115] A user browses a website to find a new smartphone or plan. The user's device collects this operation history data (pages viewed, links clicked, time spent, etc.) and purchase history data in real time. The input is the user's browsing behavior and purchasing behavior, and this data is captured. The collected operation history data and purchase history data are generated as output.

[0116] Specifically, when a user searches for "smartphones with high camera performance" on their smartphone and accesses a specific product page, the access information is immediately recorded.

[0117] Step 2: Send data

[0118] The operation history data and purchase history data collected by the user terminal are periodically sent to the server. The data collected in step 1 is the input, and is sent to the server. The server receives the data as the output.

[0119] Specifically, each time a user views a camera performance comparison page, the accessed URL and the duration of stay are sent to the server.

[0120] Step 3: Data analysis

[0121] The server analyzes the operation history data and purchase history data it receives. As input, it receives data sent from the user's device and processes the data using a machine learning algorithm (e.g., Python's Sci-Kit Learn or TensorFlow). As output, it generates the analyzed data.

[0122] Specifically, the server retrieves the operation history data stored in the database and extracts the characteristics of pages frequently visited by users and products purchased by them.

[0123] Step 4: Generate a preference profile

[0124] The server generates a user preference profile based on the analysis results. The input is the data analyzed in step 3, and the preference profile is generated based on this. The generated preference profile is obtained as the output.

[0125] Specifically, the server adds keywords preferred by the user (e.g., "high-performance camera" and "large-capacity battery") to the profile and generates a different recommendation model for each user.

[0126] Step 5: Generate a recommendation list

[0127] Based on the preference profile generated by the server, a list of products and plans suitable for the user is created. The preference profile is taken as input, and recommendation candidates are generated based on this. The recommendation list is obtained as output.

[0128] Specifically, the server retrieves recommended smartphones and plans from the database and lists products that match criteria such as "high-performance camera" and "large-capacity battery."

[0129] Step 6: Submit your recommendation list

[0130] The server sends the generated recommendation list to the user terminal. The generated recommendation list is the input, and is sent to the user terminal. The user terminal receives the recommendation list as the output.

[0131] Specifically, the server sends the recommendation list it has built to the user's device in JSON format. The user's device receives this data and prepares to display it on the screen.

[0132] Step 7: View the Recommendations List

[0133] The user device analyzes the recommendation list and displays it in an easy-to-read format for the user. The input is the recommendation list sent from the server and is displayed to the user. The output is the user checking the recommendation list and accessing products and plans that interest them.

[0134] Specifically, after the user device receives the recommendation list, it displays it in a list format. The user becomes interested in the "smartphone with a high-performance camera" and clicks on the details page. The user then presses the purchase button to complete the purchase process.

[0135] (Application example 1)

[0136] 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."

[0137] Currently, users must research and compare many options to find the smartphone and plan that best suits them, which takes time and effort. Furthermore, the procedures for online purchases and contract changes are cumbersome. Therefore, there is a need for a system that allows users to quickly and efficiently find the product and plan that best suits them, and easily make purchases and contract changes.

[0138] 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.

[0139] In this invention, the server includes: means for a user terminal to collect user operation history data; means for the server to analyze the operation history data transmitted from the user terminal; means for the server to generate a user preference profile based on the analysis results; means for the server to generate suggested candidates based on the preference profile; means for the server to transmit the suggested candidates to the user terminal; means for the user terminal to display the suggested candidates; and means for the user terminal to provide an interface that allows the user terminal to confirm recommended products and plans and then make a purchase or change a contract. This allows users to quickly and easily find the products and plans that are best suited to them, and to make a purchase or change a contract without going through complicated procedures.

[0140] A "user terminal" is an electronic device operated by a user, such as a smartphone, tablet, or personal computer.

[0141] "Operation history data" is data that includes operation information such as pages viewed by a user, links clicked, and the time spent on each page.

[0142] A "server" is a central control device installed in a cloud environment or on-premise environment that analyzes data sent from user terminals and executes specified functions.

[0143] A "preference profile" is a data profile that includes personalized information that reflects a user's interests and preferences based on the user's operation history data and purchase history data.

[0144] "Suggested candidates" are a list of products and plans for the user that are generated based on the preference profile.

[0145] The "interface" is an operation screen that displays recommended products and plans on the user's terminal, allowing the user to check them and make purchases or change contracts.

[0146] This invention is a system that allows users to find the smartphone and plan that suits them, and is composed of a user terminal and a server. How this system works will be explained below.

[0147] System configuration

[0148] 1. User Device

[0149] The user terminal is an electronic device such as a smartphone, a tablet, or a personal computer.

[0150] The user terminal has a function to collect user operation history data, which includes the pages the user viewed, the links they clicked, and the duration of their stay.

[0151] It also has the function of collecting past purchase history and current contract plan data and sending it to the server.

[0152] 2. Server

[0153] The server is installed in a cloud environment or on-premise environment and acts as a central control device.

[0154] The server has the function of receiving and analyzing operation history data sent from the user terminal in real time.

[0155] The server uses machine learning algorithms (e.g., TensorFlow) to generate a preference profile based on the user's interests and preferences, including the user's preferred product features and preferred plan elements.

[0156] The server generates a list of products and plans (candidate suggestions) suitable for the user based on the preference profile and sends it to the user's terminal.

[0157] 3. Adding functions to user devices

[0158] The user terminal has a function to display recommended products and plans.

[0159] It has the function of providing an interface that allows users to check the recommended products and plans and then make purchases or change their contracts.

[0160] Specific operation examples

[0161] Data collection and analysis

[0162] Suppose a user is browsing a website looking for a new smartphone. For example, if the user frequently visits pages about smartphones with high camera capabilities, the user's device will collect this operation history in real time and send it to the server. Data on previously purchased smartphones and current contract plans will also be sent to the server.

[0163] The server analyzes this operation history data and past purchase history data, and uses a machine learning algorithm to generate a preference profile that indicates the user's preference for smartphones with high camera performance.

[0164] Generate and display suggestions

[0165] The server creates a list of the latest smartphones with excellent camera capabilities based on the user's preference profile and sends it to the user's device, which then displays the list in an easy-to-understand manner, allowing the user to check detailed information about the smartphones that interest them.

[0166] Purchase and contract modification interface

[0167] If a user is interested after checking the recommended products and plans, the system provides an interface that allows the user to proceed with the purchase process directly on the user's device. This interface allows users to easily purchase a smartphone or change plans.

[0168] Prompt Sentence Examples

[0169] As a concrete example, the following prompts are input into a generative AI model to generate a user preference profile and recommendation list.

[0170] User ID: 1

[0171] Operation History:

[0172] Page: Smartphone List

[0173] Click: iPhone(R) 13

[0174] Stay time: 300 seconds

[0175] Page: Compare Plans

[0176] Click: Large amount of data

[0177] Stay time: 180 seconds

[0178] Purchase History:

[0179] Purchase: Galaxy S10

[0180] Purchase date: 2020-06-15

[0181] Current plan:

[0182] Plan: Unlimited data

[0183] Contract start date: 2021-01-01

[0184] Use this data to recommend the best smartphone and plan for your users.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] Users browse websites when searching for smartphones and plans.

[0188] Input: User actions (page transitions, link clicks, time spent, etc.)

[0189] Operation: The user device collects operation history data in real time.

[0190] Output: Collected operation history data

[0191] Step 2:

[0192] The user terminal transmits the user's operation history data to the server.

[0193] Input: Operation history data

[0194] How it works: The user device sends the collected data to the server via an HTTP POST request.

[0195] Output: Operation history data received by the server

[0196] Step 3:

[0197] The server receives the operation history data and analyzes it.

[0198] Input: Operation history data received by the server

[0199] How it works: The server analyzes the data and extracts information to identify the user's interests and preferences. The data is analyzed using machine learning algorithms such as TensorFlow.

[0200] Output: User preference profile

[0201] Step 4:

[0202] The server generates suggestions based on the preference profile.

[0203] Input: User preference profile

[0204] How it works: The server analyzes your preference profile and generates a list of products and plans that suit you based on that profile.

[0205] Output: A list of possible suggestions

[0206] Step 5:

[0207] The list of proposal candidates is transmitted to the user terminal.

[0208] Input: A list of suggestions

[0209] Operation: The server sends the generated list to the user's device via an HTTP GET request.

[0210] Output: A list of proposal candidates received by the user device

[0211] Step 6:

[0212] The user terminal displays a list of proposal candidates.

[0213] Input: A list of proposal candidates received by the user device

[0214] Behavior: The user device displays the list in an appropriate user interface so that the user can view it.

[0215] Output: A list of suggestions that can be visually reviewed by the user.

[0216] Step 7:

[0217] The user checks the recommended products and plans and proceeds to purchase or change their contract.

[0218] Input: The user's choice for a specific product or plan within a list of potential offers

[0219] Operation: The user terminal provides an interface that allows operations such as purchases and contract changes to be performed, and sends that information to the server.

[0220] Output: Data on the results of completing the purchase or contract change procedure

[0221] 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.

[0222] This invention is a system that helps users find the smartphone and plan that best suits them. In particular, by combining it with an emotion engine that recognizes the user's emotions, the system can make more accurate recommendations. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0223] System configuration

[0224] 1. User Device

[0225] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0226] The user terminal has a function of collecting operation history data of the user.

[0227] Operation history data includes pages viewed, links clicked, and time spent on each page.

[0228] It also has an emotion engine that recognizes the user's emotions.

[0229] The emotion engine collects emotion data from the user's facial expressions and voice tone, and sends it to the server.

[0230] 2. Server

[0231] The server is a central control unit installed in a cloud environment or on-premise environment.

[0232] The server has a function of receiving and analyzing the operation history data and emotion data sent from the user terminal.

[0233] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0234] Based on the emotion data, the priority of the proposed candidates is set.

[0235] Program Operation

[0236] Data collection

[0237] When a user browses a website to find a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. At the same time, emotional data is collected from the user's facial expressions and tone of voice, and this data is also sent to the server.

[0238] Data analysis and preference profile generation

[0239] The server analyzes the received operation history data, past purchase history data, and current contract plan data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements. Furthermore, it analyzes emotional data and reflects in the profile the emotions the user displayed when viewing certain products and plans.

[0240] Generate and submit suggestions

[0241] The server generates a list of products and plans suitable for the user based on the preference profile. Product and plan information is retrieved from an up-to-date database. Based on the emotion data, the server prioritizes the proposal candidates and sends them to the user's device.

[0242] Displaying and taking action on recommendation results

[0243] The user's device analyzes the recommendation list and displays it in an easy-to-read format. Detailed information about each product and plan is also displayed, with priorities based on emotional data. The user can check the recommended products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change.

[0244] Specific examples

[0245] Example 1: Recommending a new smartphone

[0246] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and creates a list of newly released smartphones with high camera capabilities. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0247] Example 2: Recommending a new plan

[0248] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0249] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall work efficiency. In addition, by using emotion data, it is possible to make even more accurate recommendations.

[0250] The processing flow will be explained below.

[0251] Step 1:

[0252] A user browses a website looking for a new smartphone or plan.

[0253] Step 2:

[0254] The user's device collects operation history data, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0255] Step 3:

[0256] The user device collects emotional data in real time from the user's facial expressions, voice tone, etc. This data is analyzed using an emotion engine.

[0257] Step 4:

[0258] The device sends the collected operation history data and emotion data to the server in real time.

[0259] Step 5:

[0260] The server prepares for analyzing the received operation history data, emotion data, past purchase history data, and current contract plan data. It filters out unnecessary and duplicate data.

[0261] Step 6:

[0262] The server uses machine learning algorithms to analyze operation history data and emotion data, thereby identifying patterns of change in user preferences and emotions.

[0263] Step 7:

[0264] Based on the analysis results, the server creates a user preference profile, which includes the product features the user is interested in and the elements of the plan they prefer. Furthermore, using emotional data, the profile also reflects the emotions the user expressed when viewing certain products and plans.

[0265] Step 8:

[0266] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[0267] Step 9:

[0268] The server prioritizes the proposed products based on the emotion data. For example, it gives higher priority to products or plans that make the user smile.

[0269] Step 10:

[0270] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[0271] Step 11:

[0272] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan, reflecting priorities based on emotional data.

[0273] Step 12:

[0274] The user can check the recommended products and plans, and if they are interested, click on the details. The device will guide the user through the process of purchasing or changing plans.

[0275] Step 13:

[0276] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[0277] Step 14:

[0278] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[0279] Example 2

[0280] 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."

[0281] Conventional recommendation systems make suggestions based solely on a user's operation history and purchase history, making it difficult to provide accurate suggestions that reflect the user's current emotions and interests. In particular, they have been unable to accurately capture what a user likes and what elements excite or satisfy them. As a result, the accuracy of suggestions is low, making it difficult to improve user satisfaction.

[0282] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user terminal to collect user operation history data and emotion data; means for the server to analyze the operation history data and emotion data transmitted from the user terminal; means for the server to generate a user preference profile from the analysis result using a machine learning algorithm; means for the server to generate candidates to be proposed based on the preference profile; means for the server to set priorities of the candidates to be proposed based on emotion data; means for the server to transmit the proposed candidates to the user terminal; and means for the user terminal to display the proposed candidates. This enables highly accurate suggestions that reflect the user's current emotions and real-time interests.

[0283] A "user terminal" is a device operated by a user, such as a smartphone, tablet, or PC.

[0284] "Operation history data" refers to data related to user actions, such as the page history when a user browses a website, the links clicked, and the time spent on each page.

[0285] "Emotional data" is data collected from a user's facial expressions and vocal tone that indicates the user's emotional state.

[0286] The "server" is a central control device that receives data sent from a user terminal, analyzes it, generates recommendation results, and sends them to the user terminal.

[0287] "Analysis" is the process of extracting information from collected data to clarify user preferences and trends.

[0288] A "machine learning algorithm" is a mathematical technique that generates models based on past data and makes predictions and classifications for future data.

[0289] A "preference profile" is a collection of information that reflects a user's interests and preferences, and includes characteristics of products and services that the user prefers.

[0290] "Suggested candidates" is a list of products and plans generated by the server based on the user's preference profile.

[0291] "Priority" is an evaluation that ranks the suggested candidates in terms of their importance to the user.

[0292] "SSL / TLS" is a protocol for encrypting data and communicating securely.

[0293] A "graphical user interface" is a computer interface that uses images and text to visually present information to a user and facilitate operation.

[0294] This invention is a system that helps users find the smartphone and communication plan that best suits them. In particular, by combining an engine that recognizes the user's emotions, the system can make more accurate suggestions. The system consists of a user terminal, a server, and its communication protocol.

[0295] System configuration

[0296] 1. User Device

[0297] User devices are electronic devices such as smartphones, tablets, and PCs. They have the ability to collect user operation history data and emotional data from facial expressions and voice tones. Specifically, when a user browses a website, the device captures data such as the pages visited, the links clicked, and the time spent on each page, and simultaneously collects emotional data.

[0298] 2. Server

[0299] The server is a central control device installed in a cloud or on-premise environment. It receives and analyzes operation history data and emotion data sent from user devices. The server applies machine learning algorithms using Python's Scikit-learn library and other tools to generate a preference profile. The preference profile includes the user's preferred product features and preferred plan elements.

[0300] 3. Communication Protocol

[0301] Data is transmitted between the user terminal and the server using a secure communication protocol such as SSL / TLS.

[0302] System Operation

[0303] 1. Data Collection

[0304] When a user browses a website to find a new smartphone or plan, the user's device captures their activity history in real time and also collects emotional data. This data is then sent to the server using SSL / TLS.

[0305] 2. Data analysis and generation of preference profiles

[0306] The server analyzes the received operation history data and emotion data and uses a machine learning algorithm to generate a user preference profile. The preference profile reflects the user's preferred product features and preferred plan elements. The server also prioritizes the proposed options based on the emotion data.

[0307] 3. Generate and send proposal candidates

[0308] The server generates a list of products and plans suitable for the user based on the user's preference profile. This list is retrieved from an up-to-date database and prioritized based on the user's emotional data. The server then transmits this list to the user's device.

[0309] 4. Displaying recommended results and taking action

[0310] The user's device displays a list of recommendations. Detailed information about each product or plan is also displayed, and the user can click on it to view more information. If the user is interested in a product or plan, they can proceed with the online purchase or plan change process.

[0311] Specific examples

[0312] Example 1: Recommending a new smartphone

[0313] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and suggests a new smartphone with high camera capabilities. The user's device displays this, which piques the user's interest, and the user proceeds with the purchase process.

[0314] Example 2: Recommending a new plan

[0315] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this and the user is prompted to switch to that plan.

[0316] Prompt Sentence Examples

[0317] Below is an example of a prompt to input to the generative AI model.

[0318] Example prompt 1:

[0319] When users are searching for a smartphone, they often browse pages of smartphones with high camera performance and smile when they do so. Therefore, we would like you to recommend the best smartphone for them.

[0320] Example prompt 2:

[0321] Users frequently check the plans with large data capacities and look satisfied when they do so. Please recommend the best plan for them.

[0322] This system allows users to receive highly accurate suggestions that reflect their current emotions and interests, which increases user satisfaction and improves the efficiency of sales operations.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1: A user browses to a website.

[0325] When a user browses a website looking for a smartphone or plan, they visit specific pages, click links, and spend a certain amount of time on each page, generating data that feeds into the system.

[0326] Step 2: The user terminal collects operation history data and emotion data.

[0327] The user's device captures the user's operation history data (pages visited, links clicked, time spent, etc.) in real time, and simultaneously collects emotional data from the user's facial expressions and tone of voice. This input data forms the basis for subsequent analysis processing. The device temporarily stores this data.

[0328] Step 3: The user terminal transmits the collected data to the server.

[0329] The operation history data and emotion data collected by the user device are sent to the server using a secure communication protocol such as SSL / TLS. In this process, the user device generates a data packet and transfers it to the server via the network.

[0330] Step 4: The server parses the received data.

[0331] The server receives operation history data and emotion data sent from the user's device. The server preprocesses the received data (e.g., filling in missing values, normalizing data, etc.) and prepares it for analysis. The server then analyzes the data using a machine learning algorithm (e.g., using Python's Scikit-learn library). The server then extracts patterns based on the user's interests and preferences.

[0332] Step 5: The server generates a preference profile.

[0333] Based on the analysis results, the server generates a user preference profile, including the product features the user is particularly interested in and the attributes of the plan they prefer. The server then builds the preference profile into a data model and stores the information in a database.

[0334] Step 6: The server generates proposal candidates.

[0335] The server generates a list of suitable products and plans from an up-to-date database based on the user's preference profile, and prioritizes the candidates using emotion data. The output data is a list of candidates that is saved and ready to be sent to the user's device.

[0336] Step 7: The server sends the proposal candidates to the user terminal.

[0337] The server sends the list of proposal candidates to the user terminal. In this transmission process, a data packet is generated and transmitted to the user terminal via the network. Secure communication protocols such as SSL / TLS are also used here.

[0338] Step 8: The user terminal displays the recommendation list.

[0339] The user device analyzes the recommendation list received from the server and displays it in an easy-to-read format. Using a user interface (GUI), detailed information about each product and plan is also displayed, allowing the user to click on it for more information.

[0340] Step 9: The user performs the action.

[0341] Users click on the recommended products or plans, check their details, and if they are interested, proceed with the purchase or plan change process. The user's device supports this process, providing the necessary links and forms to ensure a seamless user experience.

[0342] (Application example 2)

[0343] 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."

[0344] Conventional recommendation systems typically recommend products and services based on user operation history and purchase history data. However, it is difficult to make recommendations that reflect the user's emotions and current psychological state using only this data, and there are limitations to providing optimal products and services for users. In particular, more accurate recommendations are required to improve the shopping experience in online environments such as virtual stores. Furthermore, a system that can quickly respond to changes in a user's interests and preferences is also required.

[0345] 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.

[0346] In this invention, the server includes a means for a user terminal to collect emotional data such as a user's facial expression and voice tone, a means for the server to analyze operation history data and emotional data transmitted from the user terminal, and a means for generating a user preference profile based on the analysis results, thereby enabling highly accurate recommendations based on emotional data such as facial expression and voice tone in addition to the user's operation history data.

[0347] A "user terminal" is an electronic device operated by a user, and includes devices such as smartphones, tablets, and personal computers.

[0348] "Operation history data" refers to data related to a user's web browsing and application operations, such as the pages the user viewed, the links they clicked, and the time spent on each page.

[0349] "Emotion data" refers to data relating to the user's emotional state obtained from the user's facial expressions and vocal tone, and is data for grasping the user's psychological state and emotions in real time.

[0350] A "server" is a central control device that receives data sent from user devices and performs processes such as analysis, profile generation, and generation of recommendation candidates, and is operated in a cloud environment or on-premise environment.

[0351] A "preference profile" is a data profile that reflects a user's interests and preferences and is generated by analyzing the user's operation history data and emotional data.

[0352] "Recommendation candidates" are a list of products and services suggested to the user, generated by the server based on the preference profile and emotional data.

[0353] This invention is a system that provides products and plans suited to users based on their emotional data and operation history data. The main components are a user terminal, a server, and a communication protocol for exchanging data between them.

[0354] User terminal

[0355] A user terminal is an electronic device operated by a user, including a smartphone, tablet, personal computer, etc. A user terminal has the following functions:

[0356] 1. Collection of operation history data: Capture and save operation history data in real time, such as the pages viewed by users, the links clicked, and the time spent on each page.

[0357] 2. Emotion data collection: Using the user's camera and microphone, facial expressions and voice tones are collected and stored as emotion data. For this purpose, an emotion engine (such as the Emotion Recognition library) is used.

[0358] server

[0359] The server is a central control unit that can be operated in a cloud or on-premise environment. The server has the following functions:

[0360] 1. Data analysis: Operation history data and emotion data sent from the user's device are received and analyzed using machine learning algorithms, thereby generating a user preference profile.

[0361] 2. Recommendation generation: Generate a list of products and plans that are best suited to the user based on their preference profile and sentiment data.

[0362] 3. Sending recommendation candidates: The generated recommendation candidates are sent to the user's device and displayed to the user.

[0363] Specific examples

[0364] New smartphone recommendation

[0365] Suppose a user is browsing a virtual store looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, showing that the user smiles while browsing. The server analyzes this operation history and emotional data and creates a list of new smartphones with high camera capabilities. The user's device displays this list, and the user, excited by the list, proceeds with the purchase.

[0366] New plan recommendation

[0367] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0368] Prompt Sentence Examples

[0369] For example, if the user's facial expression is recognized as "joy," the following prompt sentence can be passed to the generative AI model to generate a detailed recommendation.

[0370] "The user expressed the emotion 'Delighted' while browsing Smartphone A. Please generate the following recommendation: 'This smartphone has excellent camera performance, making it ideal for those who enjoy taking photos.'"

[0371] As described above, this system increases user satisfaction by generating a user preference profile based on a variety of information, including the user's emotional data, and recommending products and plans based on that profile.

[0372] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0373] Step 1:

[0374] When a user starts browsing a virtual store, their operation history data (pages viewed, links clicked, time spent, etc.) is collected in real time by the user's device. This data is temporarily stored in the device and later sent to the server. The input is the user's web operation, and the output is the collection of operation history data.

[0375] Step 2:

[0376] At the same time, the camera and microphone on the user's device capture the user's facial expressions and voice tone, and use an emotion engine (such as the Emotion Recognition library) to collect emotional data in real time. This emotional data is also temporarily stored on the device and later sent to the server. The input is the user's facial expressions and voice, and the output is the collection of emotional data.

[0377] Step 3:

[0378] Operation history data and emotion data are periodically sent to the server. The server is prepared to analyze the received data. As soon as the server receives this data, it saves it in storage for analysis. The input is the operation history data and emotion data sent from the device, and the output is the saving of the data.

[0379] Step 4:

[0380] The server uses machine learning algorithms to analyze operation history data and emotion data. The data analysis generates a user preference profile. The specific analysis process involves extracting patterns of the user's interests and reflecting them in the preference profile. The input is the data stored in storage, and the output is the generated preference profile.

[0381] Step 5:

[0382] The server generates a list of products and plans suitable for the user based on the generated preference profile and emotional data. In this process, the priority of the products and plans to be listed is determined based on the information contained in the preference profile. The input is the preference profile and emotional data, and the output is a proposal list.

[0383] Step 6:

[0384] The server generates a list of suggestions and sends it to the user's device. The server also sends advice based on the reasons for the suggestions and emotional data. The input is the list of suggestions, and the output is the data sent to the device.

[0385] Step 7:

[0386] The user's device analyzes the received proposal list and displays it in an easy-to-read format. The user can check the proposed products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change procedure. The input is the proposal list received from the server, and the output is the recommendation results displayed on the user's device display.

[0387] Through the above steps, more accurate recommendations can be realized based on the user's emotional data and operation history data.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] [Second embodiment]

[0392] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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."

[0404] This invention is a system for helping users find the smartphone and plan that suits them. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0405] System configuration

[0406] 1. User Device

[0407] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0408] The user terminal has a function of collecting operation history data of the user.

[0409] Operation history data includes pages viewed, links clicked, and time spent on the site.

[0410] 2. Server

[0411] The server is a central control unit installed in a cloud environment or on-premise environment.

[0412] The server has a function of receiving and analyzing the operation history data sent from the user terminal.

[0413] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0414] Program Operation

[0415] Data collection

[0416] When a user browses a website to search for a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. Past purchase history and current contract plan data are also collected and sent to the server.

[0417] Data analysis and preference profile generation

[0418] The server analyzes the received operation history data and purchase history data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements.

[0419] Generate and submit suggestions

[0420] The server generates a list of products and plans suitable for the user based on the user's preference profile, and sends this recommendation list to the user's terminal.

[0421] Displaying and taking action on recommendation results

[0422] The user's device analyzes the recommendation list and displays it in an easy-to-read format. If the user is interested in the recommended products and plans, they can click on the details to proceed with the purchase or plan change.

[0423] Specific examples

[0424] Example 1: Recommending a new smartphone

[0425] Suppose a user is browsing a website looking for a new smartphone. The device collects operation history showing frequent visits to pages for smartphones with powerful cameras. The server analyzes this and creates a list of newly released smartphones with powerful cameras. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0426] Example 2: Recommending a new plan

[0427] Let's say a user frequently checks for plans with larger data capacities. The device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and proceeds with the user switching to that plan.

[0428] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] A user browses a website looking for a new smartphone or plan.

[0432] Step 2:

[0433] The user's device collects data on the user's operation history, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0434] Step 3:

[0435] The device sends the collected operation history data to the server in real time.

[0436] Step 4:

[0437] Prepares for analysis of the operation history data, past purchase history data, and current contract plan data received by the server. Filters out unnecessary and duplicate data.

[0438] Step 5:

[0439] The server uses machine learning algorithms to analyze the operation history data, thereby identifying user preferences and behavioral patterns.

[0440] Step 6:

[0441] Based on the analysis, the server generates a user preference profile, which includes the product features that interest the user and the plan elements that they prefer.

[0442] Step 7:

[0443] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[0444] Step 8:

[0445] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[0446] Step 9:

[0447] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan.

[0448] Step 10:

[0449] Users can check the recommended products and plans, and if they are interested, they can click on the details. The device will guide them through the process of purchasing or changing plans.

[0450] Step 11:

[0451] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[0452] Step 12:

[0453] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[0454] Example 1

[0455] 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."

[0456] The current smartphone and plan selection process has the problem that it is difficult for users to find products and services that suit their preferences, and it takes a lot of time and effort. It also increases the burden on store staff and tends to reduce overall work efficiency. A system that solves these problems and allows users to efficiently find the best products and plans is needed.

[0457] 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.

[0458] In this invention, the server includes: a user terminal that collects and transmits user operation history data and purchase history data in real time; a server that receives and analyzes the operation history data and purchase history data transmitted from the user terminal; a server that generates a user preference profile based on the analyzed data; a server that generates recommendation candidates based on the preference profile; a server that transmits the recommendation candidates to the user terminal; and a server that receives and displays the recommendation candidates. This enables users to efficiently find products and plans that suit them, reduces the burden on store staff, and improves overall business efficiency.

[0459] A "user terminal" is an electronic device used by a user, such as a smartphone, tablet, or PC.

[0460] "Operation history data" refers to data such as the pages a user viewed, the links they clicked, and the length of time they stayed on the site.

[0461] "Purchase history data" refers to data on products and services purchased by a user in the past.

[0462] "Means of collecting and transmitting in real time" refers to the function of instantly acquiring information and transmitting it to the server every time a user performs an operation.

[0463] A "server" is a central control device that has the function of receiving, analyzing, and storing data sent from user terminals.

[0464] A "preference profile" is a collection of information about a user's interests and preferences that is generated by the server by analyzing the user's operation history and purchase history.

[0465] "Recommended candidates" refers to a list of products and services that are suitable for the user, generated by the server based on the preference profile.

[0466] "Means for receiving and analyzing" refers to the function by which the server receives data sent from the user's device and processes it using machine learning algorithms, etc.

[0467] "Means for generating" refers to the function by which the server creates preference profiles and recommendation candidates from the analysis results.

[0468] The "transmitting means" is a function that sends the recommendation candidates generated by the server to the user terminal.

[0469] "Means for receiving and displaying" refers to the function by which the user terminal receives the recommended candidates sent from the server and displays them in a format that is easy for the user to view.

[0470] This invention is a system that allows users to find a smartphone and plan that suits them, and is composed of a user terminal, a server, and its communication protocol.

[0471] User terminal

[0472] User terminals are electronic devices such as smartphones, tablets, and PCs. User terminals collect operation history data and purchase history data in real time and send it to a server. Specific hardware examples include smartphones, which are common mobile devices. Software used includes dedicated applications for data collection and transmission.

[0473] server

[0474] The server is a central control device installed in a cloud or on-premise environment. It has the function of receiving and analyzing operation history data and purchase history data sent from user devices. Machine learning algorithms such as Python's Sci-Kit Learn and TensorFlow are used for data analysis. Based on the preference profile generated by the server, it generates recommended candidates for products and plans suitable for the user and sends them to the user's device.

[0475] Specific examples

[0476] Example 1: Recommending a new smartphone

[0477] Suppose a user is browsing a website looking for a new smartphone. The user's device collects this operation history and sends it to the server. For example, the user's operation history may record that the user frequently visits pages for smartphones with high camera performance. The server analyzes this data and creates a list of new smartphones with high camera performance. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0478] Example 2: Recommending a new plan

[0479] Suppose a user frequently checks for plans with larger data capacities. The user's device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0480] Example prompt

[0481] Prompt: "Describe a system where a user's device captures page browsing history in real time on a smartphone with a powerful camera and sends it to a server. The server then uses machine learning algorithms to generate a preference profile and create and send a list of smartphone recommendations that are best suited to the user."

[0482] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0483] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0484] Step 1: Data collection

[0485] A user browses a website to find a new smartphone or plan. The user's device collects this operation history data (pages viewed, links clicked, time spent, etc.) and purchase history data in real time. The input is the user's browsing behavior and purchasing behavior, and this data is captured. The collected operation history data and purchase history data are generated as output.

[0486] Specifically, when a user searches for "smartphones with high camera performance" on their smartphone and accesses a specific product page, the access information is immediately recorded.

[0487] Step 2: Send data

[0488] The operation history data and purchase history data collected by the user terminal are periodically sent to the server. The data collected in step 1 is the input, and is sent to the server. The server receives the data as the output.

[0489] Specifically, each time a user views a camera performance comparison page, the accessed URL and the duration of stay are sent to the server.

[0490] Step 3: Data analysis

[0491] The server analyzes the operation history data and purchase history data it receives. As input, it receives data sent from the user's device and processes the data using a machine learning algorithm (e.g., Python's Sci-Kit Learn or TensorFlow). As output, it generates the analyzed data.

[0492] Specifically, the server retrieves the operation history data stored in the database and extracts the characteristics of pages frequently visited by users and products purchased by them.

[0493] Step 4: Generate a preference profile

[0494] The server generates a user preference profile based on the analysis results. The input is the data analyzed in step 3, and the preference profile is generated based on this. The generated preference profile is obtained as the output.

[0495] Specifically, the server adds keywords preferred by the user (e.g., "high-performance camera" and "large-capacity battery") to the profile and generates a different recommendation model for each user.

[0496] Step 5: Generate a recommendation list

[0497] Based on the preference profile generated by the server, a list of products and plans suitable for the user is created. The preference profile is taken as input, and recommendation candidates are generated based on this. The recommendation list is obtained as output.

[0498] Specifically, the server retrieves recommended smartphones and plans from the database and lists products that match criteria such as "high-performance camera" and "large-capacity battery."

[0499] Step 6: Submit your recommendation list

[0500] The server sends the generated recommendation list to the user terminal. The generated recommendation list is the input, and is sent to the user terminal. The user terminal receives the recommendation list as the output.

[0501] Specifically, the server sends the recommendation list it has built to the user's device in JSON format. The user's device receives this data and prepares to display it on the screen.

[0502] Step 7: View the Recommendations List

[0503] The user device analyzes the recommendation list and displays it in an easy-to-read format for the user. The input is the recommendation list sent from the server and is displayed to the user. The output is the user checking the recommendation list and accessing products and plans that interest them.

[0504] Specifically, after the user device receives the recommendation list, it displays it in a list format. The user becomes interested in the "smartphone with a high-performance camera" and clicks on the details page. The user then presses the purchase button to complete the purchase process.

[0505] (Application example 1)

[0506] 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."

[0507] Currently, users must research and compare many options to find the smartphone and plan that best suits them, which takes time and effort. Furthermore, the procedures for online purchases and contract changes are cumbersome. Therefore, there is a need for a system that allows users to quickly and efficiently find the product and plan that best suits them, and easily make purchases and contract changes.

[0508] 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.

[0509] In this invention, the server includes: means for a user terminal to collect user operation history data; means for the server to analyze the operation history data transmitted from the user terminal; means for the server to generate a user preference profile based on the analysis results; means for the server to generate suggested candidates based on the preference profile; means for the server to transmit the suggested candidates to the user terminal; means for the user terminal to display the suggested candidates; and means for the user terminal to provide an interface that allows the user terminal to confirm recommended products and plans and then make a purchase or change a contract. This allows users to quickly and easily find the products and plans that are best suited to them, and to make a purchase or change a contract without going through complicated procedures.

[0510] A "user terminal" is an electronic device operated by a user, such as a smartphone, tablet, or personal computer.

[0511] "Operation history data" is data that includes operation information such as pages viewed by a user, links clicked, and the time spent on each page.

[0512] A "server" is a central control device installed in a cloud environment or on-premise environment that analyzes data sent from user terminals and executes specified functions.

[0513] A "preference profile" is a data profile that includes personalized information that reflects a user's interests and preferences based on the user's operation history data and purchase history data.

[0514] "Suggested candidates" are a list of products and plans for the user that are generated based on the preference profile.

[0515] The "interface" is an operation screen that displays recommended products and plans on the user's terminal, allowing the user to check them and make purchases or change contracts.

[0516] This invention is a system that allows users to find the smartphone and plan that suits them, and is composed of a user terminal and a server. How this system works will be explained below.

[0517] System configuration

[0518] 1. User Device

[0519] The user terminal is an electronic device such as a smartphone, a tablet, or a personal computer.

[0520] The user terminal has a function to collect user operation history data, which includes the pages the user viewed, the links they clicked, and the duration of their stay.

[0521] It also has the function of collecting past purchase history and current contract plan data and sending it to the server.

[0522] 2. Server

[0523] The server is installed in a cloud environment or on-premise environment and acts as a central control device.

[0524] The server has the function of receiving and analyzing operation history data sent from the user terminal in real time.

[0525] The server uses machine learning algorithms (e.g., TensorFlow) to generate a preference profile based on the user's interests and preferences, including the user's preferred product features and preferred plan elements.

[0526] The server generates a list of products and plans (candidate suggestions) suitable for the user based on the preference profile and sends it to the user's terminal.

[0527] 3. Adding functions to user devices

[0528] The user terminal has a function to display recommended products and plans.

[0529] It has the function of providing an interface that allows users to check the recommended products and plans and then make purchases or change their contracts.

[0530] Specific operation examples

[0531] Data collection and analysis

[0532] Suppose a user is browsing a website looking for a new smartphone. For example, if the user frequently visits pages about smartphones with high camera capabilities, the user's device will collect this operation history in real time and send it to the server. Data on previously purchased smartphones and current contract plans will also be sent to the server.

[0533] The server analyzes this operation history data and past purchase history data, and uses a machine learning algorithm to generate a preference profile that indicates the user's preference for smartphones with high camera performance.

[0534] Generate and display suggestions

[0535] The server creates a list of the latest smartphones with excellent camera capabilities based on the user's preference profile and sends it to the user's device, which then displays the list in an easy-to-understand manner, allowing the user to check detailed information about the smartphones that interest them.

[0536] Purchase and contract modification interface

[0537] If a user is interested after checking the recommended products and plans, the system provides an interface that allows the user to proceed with the purchase process directly on the user's device. This interface allows users to easily purchase a smartphone or change plans.

[0538] Prompt Sentence Examples

[0539] As a concrete example, the following prompts are input into a generative AI model to generate a user preference profile and recommendation list.

[0540] User ID: 1

[0541] Operation History:

[0542] Page: Smartphone List

[0543] Click: iPhone 13

[0544] Stay time: 300 seconds

[0545] Page: Compare Plans

[0546] Click: Large amount of data

[0547] Stay time: 180 seconds

[0548] Purchase History:

[0549] Purchase: Galaxy S10

[0550] Purchase date: 2020-06-15

[0551] Current plan:

[0552] Plan: Unlimited data

[0553] Contract start date: 2021-01-01

[0554] Use this data to recommend the best smartphone and plan for your users.

[0555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0556] Step 1:

[0557] Users browse websites when searching for smartphones and plans.

[0558] Input: User actions (page transitions, link clicks, time spent, etc.)

[0559] Operation: The user device collects operation history data in real time.

[0560] Output: Collected operation history data

[0561] Step 2:

[0562] The user terminal transmits the user's operation history data to the server.

[0563] Input: Operation history data

[0564] How it works: The user device sends the collected data to the server via an HTTP POST request.

[0565] Output: Operation history data received by the server

[0566] Step 3:

[0567] The server receives the operation history data and analyzes it.

[0568] Input: Operation history data received by the server

[0569] How it works: The server analyzes the data and extracts information to identify the user's interests and preferences. The data is analyzed using machine learning algorithms such as TensorFlow.

[0570] Output: User preference profile

[0571] Step 4:

[0572] The server generates suggestions based on the preference profile.

[0573] Input: User preference profile

[0574] How it works: The server analyzes your preference profile and generates a list of products and plans that suit you based on that profile.

[0575] Output: A list of possible suggestions

[0576] Step 5:

[0577] The list of proposal candidates is transmitted to the user terminal.

[0578] Input: A list of suggestions

[0579] Operation: The server sends the generated list to the user's device via an HTTP GET request.

[0580] Output: A list of proposal candidates received by the user device

[0581] Step 6:

[0582] The user terminal displays a list of proposal candidates.

[0583] Input: A list of proposal candidates received by the user device

[0584] Behavior: The user device displays the list in an appropriate user interface so that the user can view it.

[0585] Output: A list of suggestions that can be visually reviewed by the user.

[0586] Step 7:

[0587] The user checks the recommended products and plans and proceeds to purchase or change their contract.

[0588] Input: The user's choice for a specific product or plan within a list of potential offers

[0589] Operation: The user terminal provides an interface that allows operations such as purchases and contract changes to be performed, and sends that information to the server.

[0590] Output: Data on the results of completing the purchase or contract change procedure

[0591] 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.

[0592] This invention is a system that helps users find the smartphone and plan that best suits them. In particular, by combining it with an emotion engine that recognizes the user's emotions, the system can make more accurate recommendations. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0593] System configuration

[0594] 1. User Device

[0595] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0596] The user terminal has a function of collecting operation history data of the user.

[0597] Operation history data includes pages viewed, links clicked, and time spent on each page.

[0598] It also has an emotion engine that recognizes the user's emotions.

[0599] The emotion engine collects emotion data from the user's facial expressions and voice tone, and sends it to the server.

[0600] 2. Server

[0601] The server is a central control unit installed in a cloud environment or on-premise environment.

[0602] The server has a function of receiving and analyzing the operation history data and emotion data sent from the user terminal.

[0603] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0604] Based on the emotion data, the priority of the proposed candidates is set.

[0605] Program Operation

[0606] Data collection

[0607] When a user browses a website to find a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. At the same time, emotional data is collected from the user's facial expressions and tone of voice, and this data is also sent to the server.

[0608] Data analysis and preference profile generation

[0609] The server analyzes the received operation history data, past purchase history data, and current contract plan data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements. Furthermore, it analyzes emotional data and reflects in the profile the emotions the user displayed when viewing certain products and plans.

[0610] Generate and submit suggestions

[0611] The server generates a list of products and plans suitable for the user based on the preference profile. Product and plan information is retrieved from an up-to-date database. Based on the emotion data, the server prioritizes the proposal candidates and sends them to the user's device.

[0612] Displaying and taking action on recommendation results

[0613] The user's device analyzes the recommendation list and displays it in an easy-to-read format. Detailed information about each product and plan is also displayed, with priorities based on emotional data. The user can check the recommended products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change.

[0614] Specific examples

[0615] Example 1: Recommending a new smartphone

[0616] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and creates a list of newly released smartphones with high camera capabilities. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0617] Example 2: Recommending a new plan

[0618] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0619] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall work efficiency. In addition, by using emotion data, it is possible to make even more accurate recommendations.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] A user browses a website looking for a new smartphone or plan.

[0623] Step 2:

[0624] The user's device collects operation history data, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0625] Step 3:

[0626] The user device collects emotional data in real time from the user's facial expressions, voice tone, etc. This data is analyzed using an emotion engine.

[0627] Step 4:

[0628] The device sends the collected operation history data and emotion data to the server in real time.

[0629] Step 5:

[0630] The server prepares for analyzing the received operation history data, emotion data, past purchase history data, and current contract plan data. It filters out unnecessary and duplicate data.

[0631] Step 6:

[0632] The server uses machine learning algorithms to analyze operation history data and emotion data, thereby identifying patterns of change in user preferences and emotions.

[0633] Step 7:

[0634] Based on the analysis results, the server creates a user preference profile, which includes the product features the user is interested in and the elements of the plan they prefer. Furthermore, using emotional data, the profile also reflects the emotions the user expressed when viewing certain products and plans.

[0635] Step 8:

[0636] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[0637] Step 9:

[0638] The server prioritizes the proposed products based on the emotion data. For example, it gives higher priority to products or plans that make the user smile.

[0639] Step 10:

[0640] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[0641] Step 11:

[0642] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan, reflecting priorities based on emotional data.

[0643] Step 12:

[0644] The user can check the recommended products and plans, and if they are interested, click on the details. The device will guide the user through the process of purchasing or changing plans.

[0645] Step 13:

[0646] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[0647] Step 14:

[0648] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[0649] Example 2

[0650] 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."

[0651] Conventional recommendation systems make suggestions based solely on a user's operation history and purchase history, making it difficult to provide accurate suggestions that reflect the user's current emotions and interests. In particular, they have been unable to accurately capture what a user likes and what elements excite or satisfy them. As a result, the accuracy of suggestions is low, making it difficult to improve user satisfaction.

[0652] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user terminal to collect user operation history data and emotion data; means for the server to analyze the operation history data and emotion data transmitted from the user terminal; means for the server to generate a user preference profile from the analysis result using a machine learning algorithm; means for the server to generate candidates to be proposed based on the preference profile; means for the server to set priorities of the candidates to be proposed based on emotion data; means for the server to transmit the proposed candidates to the user terminal; and means for the user terminal to display the proposed candidates. This enables highly accurate suggestions that reflect the user's current emotions and real-time interests.

[0653] A "user terminal" is a device operated by a user, such as a smartphone, tablet, or PC.

[0654] "Operation history data" refers to data related to user actions, such as the page history when a user browses a website, the links clicked, and the time spent on each page.

[0655] "Emotional data" is data collected from a user's facial expressions and vocal tone that indicates the user's emotional state.

[0656] The "server" is a central control device that receives data sent from a user terminal, analyzes it, generates recommendation results, and sends them to the user terminal.

[0657] "Analysis" is the process of extracting information from collected data to clarify user preferences and trends.

[0658] A "machine learning algorithm" is a mathematical technique that generates models based on past data and makes predictions and classifications for future data.

[0659] A "preference profile" is a collection of information that reflects a user's interests and preferences, and includes characteristics of products and services that the user prefers.

[0660] "Suggested candidates" is a list of products and plans generated by the server based on the user's preference profile.

[0661] "Priority" is an evaluation that ranks the suggested candidates in terms of their importance to the user.

[0662] "SSL / TLS" is a protocol for encrypting data and communicating securely.

[0663] A "graphical user interface" is a computer interface that uses images and text to visually present information to a user and facilitate operation.

[0664] This invention is a system that helps users find the smartphone and communication plan that best suits them. In particular, by combining an engine that recognizes the user's emotions, the system can make more accurate suggestions. The system consists of a user terminal, a server, and its communication protocol.

[0665] System configuration

[0666] 1. User Device

[0667] User devices are electronic devices such as smartphones, tablets, and PCs. They have the ability to collect user operation history data and emotional data from facial expressions and voice tones. Specifically, when a user browses a website, the device captures data such as the pages visited, the links clicked, and the time spent on each page, and simultaneously collects emotional data.

[0668] 2. Server

[0669] The server is a central control device installed in a cloud or on-premise environment. It receives and analyzes operation history data and emotion data sent from user devices. The server applies machine learning algorithms using Python's Scikit-learn library and other tools to generate a preference profile. The preference profile includes the user's preferred product features and preferred plan elements.

[0670] 3. Communication Protocol

[0671] Data is transmitted between the user terminal and the server using a secure communication protocol such as SSL / TLS.

[0672] System Operation

[0673] 1. Data Collection

[0674] When a user browses a website to find a new smartphone or plan, the user's device captures their activity history in real time and also collects emotional data. This data is then sent to the server using SSL / TLS.

[0675] 2. Data analysis and generation of preference profiles

[0676] The server analyzes the received operation history data and emotion data and uses a machine learning algorithm to generate a user preference profile. The preference profile reflects the user's preferred product features and preferred plan elements. The server also prioritizes the proposed options based on the emotion data.

[0677] 3. Generate and send proposal candidates

[0678] The server generates a list of products and plans suitable for the user based on the user's preference profile. This list is retrieved from an up-to-date database and prioritized based on the user's emotional data. The server then transmits this list to the user's device.

[0679] 4. Displaying recommended results and taking action

[0680] The user's device displays a list of recommendations. Detailed information about each product or plan is also displayed, and the user can click on it to view more information. If the user is interested in a product or plan, they can proceed with the online purchase or plan change process.

[0681] Specific examples

[0682] Example 1: Recommending a new smartphone

[0683] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and suggests a new smartphone with high camera capabilities. The user's device displays this, which piques the user's interest, and the user proceeds with the purchase process.

[0684] Example 2: Recommending a new plan

[0685] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this and the user is prompted to switch to that plan.

[0686] Prompt Sentence Examples

[0687] Below is an example of a prompt to input to the generative AI model.

[0688] Example prompt 1:

[0689] When users are searching for a smartphone, they often browse pages of smartphones with high camera performance and smile when they do so. Therefore, we would like you to recommend the best smartphone for them.

[0690] Example prompt 2:

[0691] Users frequently check the plans with large data capacities and look satisfied when they do so. Please recommend the best plan for them.

[0692] This system allows users to receive highly accurate suggestions that reflect their current emotions and interests, which increases user satisfaction and improves the efficiency of sales operations.

[0693] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0694] Step 1: A user browses to a website.

[0695] When a user browses a website looking for a smartphone or plan, they visit specific pages, click links, and spend a certain amount of time on each page, generating data that feeds into the system.

[0696] Step 2: The user terminal collects operation history data and emotion data.

[0697] The user's device captures the user's operation history data (pages visited, links clicked, time spent, etc.) in real time, and simultaneously collects emotional data from the user's facial expressions and tone of voice. This input data forms the basis for subsequent analysis processing. The device temporarily stores this data.

[0698] Step 3: The user terminal transmits the collected data to the server.

[0699] The operation history data and emotion data collected by the user device are sent to the server using a secure communication protocol such as SSL / TLS. In this process, the user device generates a data packet and transfers it to the server via the network.

[0700] Step 4: The server parses the received data.

[0701] The server receives operation history data and emotion data sent from the user's device. The server preprocesses the received data (e.g., filling in missing values, normalizing data, etc.) and prepares it for analysis. The server then analyzes the data using a machine learning algorithm (e.g., using Python's Scikit-learn library). The server then extracts patterns based on the user's interests and preferences.

[0702] Step 5: The server generates a preference profile.

[0703] Based on the analysis results, the server generates a user preference profile, including the product features the user is particularly interested in and the attributes of the plan they prefer. The server then builds the preference profile into a data model and stores the information in a database.

[0704] Step 6: The server generates proposal candidates.

[0705] The server generates a list of suitable products and plans from an up-to-date database based on the user's preference profile, and prioritizes the candidates using emotion data. The output data is a list of candidates that is saved and ready to be sent to the user's device.

[0706] Step 7: The server sends the proposal candidates to the user terminal.

[0707] The server sends the list of proposal candidates to the user terminal. In this transmission process, a data packet is generated and transmitted to the user terminal via the network. Secure communication protocols such as SSL / TLS are also used here.

[0708] Step 8: The user terminal displays the recommendation list.

[0709] The user device analyzes the recommendation list received from the server and displays it in an easy-to-read format. Using a user interface (GUI), detailed information about each product and plan is also displayed, allowing the user to click on it for more information.

[0710] Step 9: The user performs the action.

[0711] Users click on the recommended products or plans, check their details, and if they are interested, proceed with the purchase or plan change process. The user's device supports this process, providing the necessary links and forms to ensure a seamless user experience.

[0712] (Application example 2)

[0713] 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."

[0714] Conventional recommendation systems typically recommend products and services based on user operation history and purchase history data. However, it is difficult to make recommendations that reflect the user's emotions and current psychological state using only this data, and there are limitations to providing optimal products and services for users. In particular, more accurate recommendations are required to improve the shopping experience in online environments such as virtual stores. Furthermore, a system that can quickly respond to changes in a user's interests and preferences is also required.

[0715] 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.

[0716] In this invention, the server includes a means for a user terminal to collect emotional data such as a user's facial expression and voice tone, a means for the server to analyze operation history data and emotional data transmitted from the user terminal, and a means for generating a user preference profile based on the analysis results, thereby enabling highly accurate recommendations based on emotional data such as facial expression and voice tone in addition to the user's operation history data.

[0717] A "user terminal" is an electronic device operated by a user, and includes devices such as smartphones, tablets, and personal computers.

[0718] "Operation history data" refers to data related to a user's web browsing and application operations, such as the pages the user viewed, the links they clicked, and the time spent on each page.

[0719] "Emotion data" refers to data relating to the user's emotional state obtained from the user's facial expressions and vocal tone, and is data for grasping the user's psychological state and emotions in real time.

[0720] A "server" is a central control device that receives data sent from user devices and performs processes such as analysis, profile generation, and generation of recommendation candidates, and is operated in a cloud environment or on-premise environment.

[0721] A "preference profile" is a data profile that reflects a user's interests and preferences and is generated by analyzing the user's operation history data and emotional data.

[0722] "Recommendation candidates" are a list of products and services suggested to the user, generated by the server based on the preference profile and emotional data.

[0723] This invention is a system that provides products and plans suited to users based on their emotional data and operation history data. The main components are a user terminal, a server, and a communication protocol for exchanging data between them.

[0724] User terminal

[0725] A user terminal is an electronic device operated by a user, including a smartphone, tablet, personal computer, etc. A user terminal has the following functions:

[0726] 1. Collection of operation history data: Capture and save operation history data in real time, such as the pages viewed by users, the links clicked, and the time spent on each page.

[0727] 2. Emotion data collection: Using the user's camera and microphone, facial expressions and voice tones are collected and stored as emotion data. For this purpose, an emotion engine (such as the Emotion Recognition library) is used.

[0728] server

[0729] The server is a central control unit that can be operated in a cloud or on-premise environment. The server has the following functions:

[0730] 1. Data analysis: Operation history data and emotion data sent from the user's device are received and analyzed using machine learning algorithms, thereby generating a user preference profile.

[0731] 2. Recommendation generation: Generate a list of products and plans that are best suited to the user based on their preference profile and sentiment data.

[0732] 3. Sending recommendation candidates: The generated recommendation candidates are sent to the user's device and displayed to the user.

[0733] Specific examples

[0734] New smartphone recommendation

[0735] Suppose a user is browsing a virtual store looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, showing that the user smiles while browsing. The server analyzes this operation history and emotional data and creates a list of new smartphones with high camera capabilities. The user's device displays this list, and the user, excited by the list, proceeds with the purchase.

[0736] New plan recommendation

[0737] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0738] Prompt Sentence Examples

[0739] For example, if the user's facial expression is recognized as "joy," the following prompt sentence can be passed to the generative AI model to generate a detailed recommendation.

[0740] "The user expressed the emotion 'Delighted' while browsing Smartphone A. Please generate the following recommendation: 'This smartphone has excellent camera performance, making it ideal for those who enjoy taking photos.'"

[0741] As described above, this system increases user satisfaction by generating a user preference profile based on a variety of information, including the user's emotional data, and recommending products and plans based on that profile.

[0742] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0743] Step 1:

[0744] When a user starts browsing a virtual store, their operation history data (pages viewed, links clicked, time spent, etc.) is collected in real time by the user's device. This data is temporarily stored in the device and later sent to the server. The input is the user's web operation, and the output is the collection of operation history data.

[0745] Step 2:

[0746] At the same time, the camera and microphone on the user's device capture the user's facial expressions and voice tone, and use an emotion engine (such as the Emotion Recognition library) to collect emotional data in real time. This emotional data is also temporarily stored on the device and later sent to the server. The input is the user's facial expressions and voice, and the output is the collection of emotional data.

[0747] Step 3:

[0748] Operation history data and emotion data are periodically sent to the server. The server is prepared to analyze the received data. As soon as the server receives this data, it saves it in storage for analysis. The input is the operation history data and emotion data sent from the device, and the output is the saving of the data.

[0749] Step 4:

[0750] The server uses machine learning algorithms to analyze operation history data and emotion data. The data analysis generates a user preference profile. The specific analysis process involves extracting patterns of the user's interests and reflecting them in the preference profile. The input is the data stored in storage, and the output is the generated preference profile.

[0751] Step 5:

[0752] The server generates a list of products and plans suitable for the user based on the generated preference profile and emotional data. In this process, the priority of the products and plans to be listed is determined based on the information contained in the preference profile. The input is the preference profile and emotional data, and the output is a proposal list.

[0753] Step 6:

[0754] The server generates a list of suggestions and sends it to the user's device. The server also sends advice based on the reasons for the suggestions and emotional data. The input is the list of suggestions, and the output is the data sent to the device.

[0755] Step 7:

[0756] The user's device analyzes the received proposal list and displays it in an easy-to-read format. The user can check the proposed products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change procedure. The input is the proposal list received from the server, and the output is the recommendation results displayed on the user's device display.

[0757] Through the above steps, more accurate recommendations can be realized based on the user's emotional data and operation history data.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] [Third embodiment]

[0762] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0763] 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.

[0764] 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).

[0765] 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.

[0766] 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.

[0767] 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).

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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."

[0774] This invention is a system for helping users find the smartphone and plan that suits them. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0775] System configuration

[0776] 1. User Device

[0777] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0778] The user terminal has a function of collecting operation history data of the user.

[0779] Operation history data includes pages viewed, links clicked, and time spent on the site.

[0780] 2. Server

[0781] The server is a central control unit installed in a cloud environment or on-premise environment.

[0782] The server has a function of receiving and analyzing the operation history data sent from the user terminal.

[0783] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0784] Program Operation

[0785] Data collection

[0786] When a user browses a website to search for a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. Past purchase history and current contract plan data are also collected and sent to the server.

[0787] Data analysis and preference profile generation

[0788] The server analyzes the received operation history data and purchase history data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements.

[0789] Generate and submit suggestions

[0790] The server generates a list of products and plans suitable for the user based on the user's preference profile, and sends this recommendation list to the user's terminal.

[0791] Displaying and taking action on recommendation results

[0792] The user's device analyzes the recommendation list and displays it in an easy-to-read format. If the user is interested in the recommended products and plans, they can click on the details to proceed with the purchase or plan change.

[0793] Specific examples

[0794] Example 1: Recommending a new smartphone

[0795] Suppose a user is browsing a website looking for a new smartphone. The device collects operation history showing frequent visits to pages for smartphones with powerful cameras. The server analyzes this and creates a list of newly released smartphones with powerful cameras. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0796] Example 2: Recommending a new plan

[0797] Let's say a user frequently checks for plans with larger data capacities. The device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and proceeds with the user switching to that plan.

[0798] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0799] The processing flow will be explained below.

[0800] Step 1:

[0801] A user browses a website looking for a new smartphone or plan.

[0802] Step 2:

[0803] The user's device collects data on the user's operation history, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0804] Step 3:

[0805] The device sends the collected operation history data to the server in real time.

[0806] Step 4:

[0807] Prepares for analysis of the operation history data, past purchase history data, and current contract plan data received by the server. Filters out unnecessary and duplicate data.

[0808] Step 5:

[0809] The server uses machine learning algorithms to analyze the operation history data, thereby identifying user preferences and behavioral patterns.

[0810] Step 6:

[0811] Based on the analysis, the server generates a user preference profile, which includes the product features that interest the user and the plan elements that they prefer.

[0812] Step 7:

[0813] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[0814] Step 8:

[0815] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[0816] Step 9:

[0817] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan.

[0818] Step 10:

[0819] Users can check the recommended products and plans, and if they are interested, they can click on the details. The device will guide them through the process of purchasing or changing plans.

[0820] Step 11:

[0821] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[0822] Step 12:

[0823] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[0824] Example 1

[0825] 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."

[0826] The current smartphone and plan selection process has the problem that it is difficult for users to find products and services that suit their preferences, and it takes a lot of time and effort. It also increases the burden on store staff and tends to reduce overall work efficiency. A system that solves these problems and allows users to efficiently find the best products and plans is needed.

[0827] 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.

[0828] In this invention, the server includes: a user terminal that collects and transmits user operation history data and purchase history data in real time; a server that receives and analyzes the operation history data and purchase history data transmitted from the user terminal; a server that generates a user preference profile based on the analyzed data; a server that generates recommendation candidates based on the preference profile; a server that transmits the recommendation candidates to the user terminal; and a server that receives and displays the recommendation candidates. This enables users to efficiently find products and plans that suit them, reduces the burden on store staff, and improves overall business efficiency.

[0829] A "user terminal" is an electronic device used by a user, such as a smartphone, tablet, or PC.

[0830] "Operation history data" refers to data such as the pages a user viewed, the links they clicked, and the length of time they stayed on the site.

[0831] "Purchase history data" refers to data on products and services purchased by a user in the past.

[0832] "Means of collecting and transmitting in real time" refers to the function of instantly acquiring information and transmitting it to the server every time a user performs an operation.

[0833] A "server" is a central control device that has the function of receiving, analyzing, and storing data sent from user terminals.

[0834] A "preference profile" is a collection of information about a user's interests and preferences that is generated by the server by analyzing the user's operation history and purchase history.

[0835] "Recommended candidates" refers to a list of products and services that are suitable for the user, generated by the server based on the preference profile.

[0836] "Means for receiving and analyzing" refers to the function by which the server receives data sent from the user's device and processes it using machine learning algorithms, etc.

[0837] "Means for generating" refers to the function by which the server creates preference profiles and recommendation candidates from the analysis results.

[0838] The "transmitting means" is a function that sends the recommendation candidates generated by the server to the user terminal.

[0839] "Means for receiving and displaying" refers to the function by which the user terminal receives the recommended candidates sent from the server and displays them in a format that is easy for the user to view.

[0840] This invention is a system that allows users to find a smartphone and plan that suits them, and is composed of a user terminal, a server, and its communication protocol.

[0841] User terminal

[0842] User terminals are electronic devices such as smartphones, tablets, and PCs. User terminals collect operation history data and purchase history data in real time and send it to a server. Specific hardware examples include smartphones, which are common mobile devices. Software used includes dedicated applications for data collection and transmission.

[0843] server

[0844] The server is a central control device installed in a cloud or on-premise environment. It has the function of receiving and analyzing operation history data and purchase history data sent from user devices. Machine learning algorithms such as Python's Sci-Kit Learn and TensorFlow are used for data analysis. Based on the preference profile generated by the server, it generates recommended candidates for products and plans suitable for the user and sends them to the user's device.

[0845] Specific examples

[0846] Example 1: Recommending a new smartphone

[0847] Suppose a user is browsing a website looking for a new smartphone. The user's device collects this operation history and sends it to the server. For example, the user's operation history may record that the user frequently visits pages for smartphones with high camera performance. The server analyzes this data and creates a list of new smartphones with high camera performance. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0848] Example 2: Recommending a new plan

[0849] Suppose a user frequently checks for plans with larger data capacities. The user's device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0850] Example prompt

[0851] Prompt: "Describe a system where a user's device captures page browsing history in real time on a smartphone with a powerful camera and sends it to a server. The server then uses machine learning algorithms to generate a preference profile and create and send a list of smartphone recommendations that are best suited to the user."

[0852] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[0853] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0854] Step 1: Data collection

[0855] A user browses a website to find a new smartphone or plan. The user's device collects this operation history data (pages viewed, links clicked, time spent, etc.) and purchase history data in real time. The input is the user's browsing behavior and purchasing behavior, and this data is captured. The collected operation history data and purchase history data are generated as output.

[0856] Specifically, when a user searches for "smartphones with high camera performance" on their smartphone and accesses a specific product page, the access information is immediately recorded.

[0857] Step 2: Send data

[0858] The operation history data and purchase history data collected by the user terminal are periodically sent to the server. The data collected in step 1 is the input, and is sent to the server. The server receives the data as the output.

[0859] Specifically, each time a user views a camera performance comparison page, the accessed URL and the duration of stay are sent to the server.

[0860] Step 3: Data analysis

[0861] The server analyzes the operation history data and purchase history data it receives. As input, it receives data sent from the user's device and processes the data using a machine learning algorithm (e.g., Python's Sci-Kit Learn or TensorFlow). As output, it generates the analyzed data.

[0862] Specifically, the server retrieves the operation history data stored in the database and extracts the characteristics of pages frequently visited by users and products purchased by them.

[0863] Step 4: Generate a preference profile

[0864] The server generates a user preference profile based on the analysis results. The input is the data analyzed in step 3, and the preference profile is generated based on this. The generated preference profile is obtained as the output.

[0865] Specifically, the server adds keywords preferred by the user (e.g., "high-performance camera" and "large-capacity battery") to the profile and generates a different recommendation model for each user.

[0866] Step 5: Generate a recommendation list

[0867] Based on the preference profile generated by the server, a list of products and plans suitable for the user is created. The preference profile is taken as input, and recommendation candidates are generated based on this. The recommendation list is obtained as output.

[0868] Specifically, the server retrieves recommended smartphones and plans from the database and lists products that match criteria such as "high-performance camera" and "large-capacity battery."

[0869] Step 6: Submit your recommendation list

[0870] The server sends the generated recommendation list to the user terminal. The generated recommendation list is the input, and is sent to the user terminal. The user terminal receives the recommendation list as the output.

[0871] Specifically, the server sends the recommendation list it has built to the user's device in JSON format. The user's device receives this data and prepares to display it on the screen.

[0872] Step 7: View the Recommendations List

[0873] The user device analyzes the recommendation list and displays it in an easy-to-read format for the user. The input is the recommendation list sent from the server and is displayed to the user. The output is the user checking the recommendation list and accessing products and plans that interest them.

[0874] Specifically, after the user device receives the recommendation list, it displays it in a list format. The user becomes interested in the "smartphone with a high-performance camera" and clicks on the details page. The user then presses the purchase button to complete the purchase process.

[0875] (Application example 1)

[0876] 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."

[0877] Currently, users must research and compare many options to find the smartphone and plan that best suits them, which takes time and effort. Furthermore, the procedures for online purchases and contract changes are cumbersome. Therefore, there is a need for a system that allows users to quickly and efficiently find the product and plan that best suits them, and easily make purchases and contract changes.

[0878] 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.

[0879] In this invention, the server includes: means for a user terminal to collect user operation history data; means for the server to analyze the operation history data transmitted from the user terminal; means for the server to generate a user preference profile based on the analysis results; means for the server to generate suggested candidates based on the preference profile; means for the server to transmit the suggested candidates to the user terminal; means for the user terminal to display the suggested candidates; and means for the user terminal to provide an interface that allows the user terminal to confirm recommended products and plans and then make a purchase or change a contract. This allows users to quickly and easily find the products and plans that are best suited to them, and to make a purchase or change a contract without going through complicated procedures.

[0880] A "user terminal" is an electronic device operated by a user, such as a smartphone, tablet, or personal computer.

[0881] "Operation history data" is data that includes operation information such as pages viewed by a user, links clicked, and the time spent on each page.

[0882] A "server" is a central control device installed in a cloud environment or on-premise environment that analyzes data sent from user terminals and executes specified functions.

[0883] A "preference profile" is a data profile that includes personalized information that reflects a user's interests and preferences based on the user's operation history data and purchase history data.

[0884] "Suggested candidates" are a list of products and plans for the user that are generated based on the preference profile.

[0885] The "interface" is an operation screen that displays recommended products and plans on the user's terminal, allowing the user to check them and make purchases or change contracts.

[0886] This invention is a system that allows users to find the smartphone and plan that suits them, and is composed of a user terminal and a server. How this system works will be explained below.

[0887] System configuration

[0888] 1. User Device

[0889] The user terminal is an electronic device such as a smartphone, a tablet, or a personal computer.

[0890] The user terminal has a function to collect user operation history data, which includes the pages the user viewed, the links they clicked, and the duration of their stay.

[0891] It also has the function of collecting past purchase history and current contract plan data and sending it to the server.

[0892] 2. Server

[0893] The server is installed in a cloud environment or on-premise environment and acts as a central control device.

[0894] The server has the function of receiving and analyzing operation history data sent from the user terminal in real time.

[0895] The server uses machine learning algorithms (e.g., TensorFlow) to generate a preference profile based on the user's interests and preferences, including the user's preferred product features and preferred plan elements.

[0896] The server generates a list of products and plans (candidate suggestions) suitable for the user based on the preference profile and sends it to the user's terminal.

[0897] 3. Adding functions to user devices

[0898] The user terminal has a function to display recommended products and plans.

[0899] It has the function of providing an interface that allows users to check the recommended products and plans and then make purchases or change their contracts.

[0900] Specific operation examples

[0901] Data collection and analysis

[0902] Suppose a user is browsing a website looking for a new smartphone. For example, if the user frequently visits pages about smartphones with high camera capabilities, the user's device will collect this operation history in real time and send it to the server. Data on previously purchased smartphones and current contract plans will also be sent to the server.

[0903] The server analyzes this operation history data and past purchase history data, and uses a machine learning algorithm to generate a preference profile that indicates the user's preference for smartphones with high camera performance.

[0904] Generate and display suggestions

[0905] The server creates a list of the latest smartphones with excellent camera capabilities based on the user's preference profile and sends it to the user's device, which then displays the list in an easy-to-understand manner, allowing the user to check detailed information about the smartphones that interest them.

[0906] Purchase and contract modification interface

[0907] If a user is interested after checking the recommended products and plans, the system provides an interface that allows the user to proceed with the purchase process directly on the user's device. This interface allows users to easily purchase a smartphone or change plans.

[0908] Prompt Sentence Examples

[0909] As a concrete example, the following prompts are input into a generative AI model to generate a user preference profile and recommendation list.

[0910] User ID: 1

[0911] Operation History:

[0912] Page: Smartphone List

[0913] Click: iPhone 13

[0914] Stay time: 300 seconds

[0915] Page: Compare Plans

[0916] Click: Large amount of data

[0917] Stay time: 180 seconds

[0918] Purchase History:

[0919] Purchase: Galaxy S10

[0920] Purchase date: 2020-06-15

[0921] Current plan:

[0922] Plan: Unlimited data

[0923] Contract start date: 2021-01-01

[0924] Use this data to recommend the best smartphone and plan for your users.

[0925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0926] Step 1:

[0927] Users browse websites when searching for smartphones and plans.

[0928] Input: User actions (page transitions, link clicks, time spent, etc.)

[0929] Operation: The user device collects operation history data in real time.

[0930] Output: Collected operation history data

[0931] Step 2:

[0932] The user terminal transmits the user's operation history data to the server.

[0933] Input: Operation history data

[0934] How it works: The user device sends the collected data to the server via an HTTP POST request.

[0935] Output: Operation history data received by the server

[0936] Step 3:

[0937] The server receives the operation history data and analyzes it.

[0938] Input: Operation history data received by the server

[0939] How it works: The server analyzes the data and extracts information to identify the user's interests and preferences. The data is analyzed using machine learning algorithms such as TensorFlow.

[0940] Output: User preference profile

[0941] Step 4:

[0942] The server generates suggestions based on the preference profile.

[0943] Input: User preference profile

[0944] How it works: The server analyzes your preference profile and generates a list of products and plans that suit you based on that profile.

[0945] Output: A list of possible suggestions

[0946] Step 5:

[0947] The list of proposal candidates is transmitted to the user terminal.

[0948] Input: A list of suggestions

[0949] Operation: The server sends the generated list to the user's device via an HTTP GET request.

[0950] Output: A list of proposal candidates received by the user device

[0951] Step 6:

[0952] The user terminal displays a list of proposal candidates.

[0953] Input: A list of proposal candidates received by the user device

[0954] Behavior: The user device displays the list in an appropriate user interface so that the user can view it.

[0955] Output: A list of suggestions that can be visually reviewed by the user.

[0956] Step 7:

[0957] The user checks the recommended products and plans and proceeds to purchase or change their contract.

[0958] Input: The user's choice for a specific product or plan within a list of potential offers

[0959] Operation: The user terminal provides an interface that allows operations such as purchases and contract changes to be performed, and sends that information to the server.

[0960] Output: Data on the results of completing the purchase or contract change procedure

[0961] 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.

[0962] This invention is a system that helps users find the smartphone and plan that best suits them. In particular, by combining it with an emotion engine that recognizes the user's emotions, the system can make more accurate recommendations. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[0963] System configuration

[0964] 1. User Device

[0965] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[0966] The user terminal has a function of collecting operation history data of the user.

[0967] Operation history data includes pages viewed, links clicked, and time spent on each page.

[0968] It also has an emotion engine that recognizes the user's emotions.

[0969] The emotion engine collects emotion data from the user's facial expressions and voice tone, and sends it to the server.

[0970] 2. Server

[0971] The server is a central control unit installed in a cloud environment or on-premise environment.

[0972] The server has a function of receiving and analyzing the operation history data and emotion data sent from the user terminal.

[0973] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[0974] Based on the emotion data, the priority of the proposed candidates is set.

[0975] Program Operation

[0976] Data collection

[0977] When a user browses a website to find a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. At the same time, emotional data is collected from the user's facial expressions and tone of voice, and this data is also sent to the server.

[0978] Data analysis and preference profile generation

[0979] The server analyzes the received operation history data, past purchase history data, and current contract plan data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements. Furthermore, it analyzes emotional data and reflects in the profile the emotions the user displayed when viewing certain products and plans.

[0980] Generate and submit suggestions

[0981] The server generates a list of products and plans suitable for the user based on the preference profile. Product and plan information is retrieved from an up-to-date database. Based on the emotion data, the server prioritizes the proposal candidates and sends them to the user's device.

[0982] Displaying and taking action on recommendation results

[0983] The user's device analyzes the recommendation list and displays it in an easy-to-read format. Detailed information about each product and plan is also displayed, with priorities based on emotional data. The user can check the recommended products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change.

[0984] Specific examples

[0985] Example 1: Recommending a new smartphone

[0986] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and creates a list of newly released smartphones with high camera capabilities. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[0987] Example 2: Recommending a new plan

[0988] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[0989] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall work efficiency. In addition, by using emotion data, it is possible to make even more accurate recommendations.

[0990] The processing flow will be explained below.

[0991] Step 1:

[0992] A user browses a website looking for a new smartphone or plan.

[0993] Step 2:

[0994] The user's device collects operation history data, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[0995] Step 3:

[0996] The user device collects emotional data in real time from the user's facial expressions, voice tone, etc. This data is analyzed using an emotion engine.

[0997] Step 4:

[0998] The device sends the collected operation history data and emotion data to the server in real time.

[0999] Step 5:

[1000] The server prepares for analyzing the received operation history data, emotion data, past purchase history data, and current contract plan data. It filters out unnecessary and duplicate data.

[1001] Step 6:

[1002] The server uses machine learning algorithms to analyze operation history data and emotion data, thereby identifying patterns of change in user preferences and emotions.

[1003] Step 7:

[1004] Based on the analysis results, the server creates a user preference profile, which includes the product features the user is interested in and the elements of the plan they prefer. Furthermore, using emotional data, the profile also reflects the emotions the user expressed when viewing certain products and plans.

[1005] Step 8:

[1006] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[1007] Step 9:

[1008] The server prioritizes the proposed products based on the emotion data. For example, it gives higher priority to products or plans that make the user smile.

[1009] Step 10:

[1010] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[1011] Step 11:

[1012] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan, reflecting priorities based on emotional data.

[1013] Step 12:

[1014] The user can check the recommended products and plans, and if they are interested, click on the details. The device will guide the user through the process of purchasing or changing plans.

[1015] Step 13:

[1016] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[1017] Step 14:

[1018] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[1019] Example 2

[1020] 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."

[1021] Conventional recommendation systems make suggestions based solely on a user's operation history and purchase history, making it difficult to provide accurate suggestions that reflect the user's current emotions and interests. In particular, they have been unable to accurately capture what a user likes and what elements excite or satisfy them. As a result, the accuracy of suggestions is low, making it difficult to improve user satisfaction.

[1022] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user terminal to collect user operation history data and emotion data; means for the server to analyze the operation history data and emotion data transmitted from the user terminal; means for the server to generate a user preference profile from the analysis result using a machine learning algorithm; means for the server to generate candidates to be proposed based on the preference profile; means for the server to set priorities of the candidates to be proposed based on emotion data; means for the server to transmit the proposed candidates to the user terminal; and means for the user terminal to display the proposed candidates. This enables highly accurate suggestions that reflect the user's current emotions and real-time interests.

[1023] A "user terminal" is a device operated by a user, such as a smartphone, tablet, or PC.

[1024] "Operation history data" refers to data related to user actions, such as the page history when a user browses a website, the links clicked, and the time spent on each page.

[1025] "Emotional data" is data collected from a user's facial expressions and vocal tone that indicates the user's emotional state.

[1026] The "server" is a central control device that receives data sent from a user terminal, analyzes it, generates recommendation results, and sends them to the user terminal.

[1027] "Analysis" is the process of extracting information from collected data to clarify user preferences and trends.

[1028] A "machine learning algorithm" is a mathematical technique that generates models based on past data and makes predictions and classifications for future data.

[1029] A "preference profile" is a collection of information that reflects a user's interests and preferences, and includes characteristics of products and services that the user prefers.

[1030] "Suggested candidates" is a list of products and plans generated by the server based on the user's preference profile.

[1031] "Priority" is an evaluation that ranks the suggested candidates in terms of their importance to the user.

[1032] "SSL / TLS" is a protocol for encrypting data and communicating securely.

[1033] A "graphical user interface" is a computer interface that uses images and text to visually present information to a user and facilitate operation.

[1034] This invention is a system that helps users find the smartphone and communication plan that best suits them. In particular, by combining an engine that recognizes the user's emotions, the system can make more accurate suggestions. The system consists of a user terminal, a server, and its communication protocol.

[1035] System configuration

[1036] 1. User Device

[1037] User devices are electronic devices such as smartphones, tablets, and PCs. They have the ability to collect user operation history data and emotional data from facial expressions and voice tones. Specifically, when a user browses a website, the device captures data such as the pages visited, the links clicked, and the time spent on each page, and simultaneously collects emotional data.

[1038] 2. Server

[1039] The server is a central control device installed in a cloud or on-premise environment. It receives and analyzes operation history data and emotion data sent from user devices. The server applies machine learning algorithms using Python's Scikit-learn library and other tools to generate a preference profile. The preference profile includes the user's preferred product features and preferred plan elements.

[1040] 3. Communication Protocol

[1041] Data is transmitted between the user terminal and the server using a secure communication protocol such as SSL / TLS.

[1042] System Operation

[1043] 1. Data Collection

[1044] When a user browses a website to find a new smartphone or plan, the user's device captures their activity history in real time and also collects emotional data. This data is then sent to the server using SSL / TLS.

[1045] 2. Data analysis and generation of preference profiles

[1046] The server analyzes the received operation history data and emotion data and uses a machine learning algorithm to generate a user preference profile. The preference profile reflects the user's preferred product features and preferred plan elements. The server also prioritizes the proposed options based on the emotion data.

[1047] 3. Generate and send proposal candidates

[1048] The server generates a list of products and plans suitable for the user based on the user's preference profile. This list is retrieved from an up-to-date database and prioritized based on the user's emotional data. The server then transmits this list to the user's device.

[1049] 4. Displaying recommended results and taking action

[1050] The user's device displays a list of recommendations. Detailed information about each product or plan is also displayed, and the user can click on it to view more information. If the user is interested in a product or plan, they can proceed with the online purchase or plan change process.

[1051] Specific examples

[1052] Example 1: Recommending a new smartphone

[1053] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and suggests a new smartphone with high camera capabilities. The user's device displays this, which piques the user's interest, and the user proceeds with the purchase process.

[1054] Example 2: Recommending a new plan

[1055] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this and the user is prompted to switch to that plan.

[1056] Prompt Sentence Examples

[1057] Below is an example of a prompt to input to the generative AI model.

[1058] Example prompt 1:

[1059] When users are searching for a smartphone, they often browse pages of smartphones with high camera performance and smile when they do so. Therefore, we would like you to recommend the best smartphone for them.

[1060] Example prompt 2:

[1061] Users frequently check the plans with large data capacities and look satisfied when they do so. Please recommend the best plan for them.

[1062] This system allows users to receive highly accurate suggestions that reflect their current emotions and interests, which increases user satisfaction and improves the efficiency of sales operations.

[1063] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1064] Step 1: A user browses to a website.

[1065] When a user browses a website looking for a smartphone or plan, they visit specific pages, click links, and spend a certain amount of time on each page, generating data that feeds into the system.

[1066] Step 2: The user terminal collects operation history data and emotion data.

[1067] The user's device captures the user's operation history data (pages visited, links clicked, time spent, etc.) in real time, and simultaneously collects emotional data from the user's facial expressions and tone of voice. This input data forms the basis for subsequent analysis processing. The device temporarily stores this data.

[1068] Step 3: The user terminal transmits the collected data to the server.

[1069] The operation history data and emotion data collected by the user device are sent to the server using a secure communication protocol such as SSL / TLS. In this process, the user device generates a data packet and transfers it to the server via the network.

[1070] Step 4: The server parses the received data.

[1071] The server receives operation history data and emotion data sent from the user's device. The server preprocesses the received data (e.g., filling in missing values, normalizing data, etc.) and prepares it for analysis. The server then analyzes the data using a machine learning algorithm (e.g., using Python's Scikit-learn library). The server then extracts patterns based on the user's interests and preferences.

[1072] Step 5: The server generates a preference profile.

[1073] Based on the analysis results, the server generates a user preference profile, including the product features the user is particularly interested in and the attributes of the plan they prefer. The server then builds the preference profile into a data model and stores the information in a database.

[1074] Step 6: The server generates proposal candidates.

[1075] The server generates a list of suitable products and plans from an up-to-date database based on the user's preference profile, and prioritizes the candidates using emotion data. The output data is a list of candidates that is saved and ready to be sent to the user's device.

[1076] Step 7: The server sends the proposal candidates to the user terminal.

[1077] The server sends the list of proposal candidates to the user terminal. In this transmission process, a data packet is generated and transmitted to the user terminal via the network. Secure communication protocols such as SSL / TLS are also used here.

[1078] Step 8: The user terminal displays the recommendation list.

[1079] The user device analyzes the recommendation list received from the server and displays it in an easy-to-read format. Using a user interface (GUI), detailed information about each product and plan is also displayed, allowing the user to click on it for more information.

[1080] Step 9: The user performs the action.

[1081] Users click on the recommended products or plans, check their details, and if they are interested, proceed with the purchase or plan change process. The user's device supports this process, providing the necessary links and forms to ensure a seamless user experience.

[1082] (Application example 2)

[1083] 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."

[1084] Conventional recommendation systems typically recommend products and services based on user operation history and purchase history data. However, it is difficult to make recommendations that reflect the user's emotions and current psychological state using only this data, and there are limitations to providing optimal products and services for users. In particular, more accurate recommendations are required to improve the shopping experience in online environments such as virtual stores. Furthermore, a system that can quickly respond to changes in a user's interests and preferences is also required.

[1085] 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.

[1086] In this invention, the server includes a means for a user terminal to collect emotional data such as a user's facial expression and voice tone, a means for the server to analyze operation history data and emotional data transmitted from the user terminal, and a means for generating a user preference profile based on the analysis results, thereby enabling highly accurate recommendations based on emotional data such as facial expression and voice tone in addition to the user's operation history data.

[1087] A "user terminal" is an electronic device operated by a user, and includes devices such as smartphones, tablets, and personal computers.

[1088] "Operation history data" refers to data related to a user's web browsing and application operations, such as the pages the user viewed, the links they clicked, and the time spent on each page.

[1089] "Emotion data" refers to data relating to the user's emotional state obtained from the user's facial expressions and vocal tone, and is data for grasping the user's psychological state and emotions in real time.

[1090] A "server" is a central control device that receives data sent from user devices and performs processes such as analysis, profile generation, and generation of recommendation candidates, and is operated in a cloud environment or on-premise environment.

[1091] A "preference profile" is a data profile that reflects a user's interests and preferences and is generated by analyzing the user's operation history data and emotional data.

[1092] "Recommendation candidates" are a list of products and services suggested to the user, generated by the server based on the preference profile and emotional data.

[1093] This invention is a system that provides products and plans suited to users based on their emotional data and operation history data. The main components are a user terminal, a server, and a communication protocol for exchanging data between them.

[1094] User terminal

[1095] A user terminal is an electronic device operated by a user, including a smartphone, tablet, personal computer, etc. A user terminal has the following functions:

[1096] 1. Collection of operation history data: Capture and save operation history data in real time, such as the pages viewed by users, the links clicked, and the time spent on each page.

[1097] 2. Emotion data collection: Using the user's camera and microphone, facial expressions and voice tones are collected and stored as emotion data. For this purpose, an emotion engine (such as the Emotion Recognition library) is used.

[1098] server

[1099] The server is a central control unit that can be operated in a cloud or on-premise environment. The server has the following functions:

[1100] 1. Data analysis: Operation history data and emotion data sent from the user's device are received and analyzed using machine learning algorithms, thereby generating a user preference profile.

[1101] 2. Recommendation generation: Generate a list of products and plans that are best suited to the user based on their preference profile and sentiment data.

[1102] 3. Sending recommendation candidates: The generated recommendation candidates are sent to the user's device and displayed to the user.

[1103] Specific examples

[1104] New smartphone recommendation

[1105] Suppose a user is browsing a virtual store looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, showing that the user smiles while browsing. The server analyzes this operation history and emotional data and creates a list of new smartphones with high camera capabilities. The user's device displays this list, and the user, excited by the list, proceeds with the purchase.

[1106] New plan recommendation

[1107] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[1108] Prompt Sentence Examples

[1109] For example, if the user's facial expression is recognized as "joy," the following prompt sentence can be passed to the generative AI model to generate a detailed recommendation.

[1110] "The user expressed the emotion 'Delighted' while browsing Smartphone A. Please generate the following recommendation: 'This smartphone has excellent camera performance, making it ideal for those who enjoy taking photos.'"

[1111] As described above, this system increases user satisfaction by generating a user preference profile based on a variety of information, including the user's emotional data, and recommending products and plans based on that profile.

[1112] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1113] Step 1:

[1114] When a user starts browsing a virtual store, their operation history data (pages viewed, links clicked, time spent, etc.) is collected in real time by the user's device. This data is temporarily stored in the device and later sent to the server. The input is the user's web operation, and the output is the collection of operation history data.

[1115] Step 2:

[1116] At the same time, the camera and microphone on the user's device capture the user's facial expressions and voice tone, and use an emotion engine (such as the Emotion Recognition library) to collect emotional data in real time. This emotional data is also temporarily stored on the device and later sent to the server. The input is the user's facial expressions and voice, and the output is the collection of emotional data.

[1117] Step 3:

[1118] Operation history data and emotion data are periodically sent to the server. The server is prepared to analyze the received data. As soon as the server receives this data, it saves it in storage for analysis. The input is the operation history data and emotion data sent from the device, and the output is the saving of the data.

[1119] Step 4:

[1120] The server uses machine learning algorithms to analyze operation history data and emotion data. The data analysis generates a user preference profile. The specific analysis process involves extracting patterns of the user's interests and reflecting them in the preference profile. The input is the data stored in storage, and the output is the generated preference profile.

[1121] Step 5:

[1122] The server generates a list of products and plans suitable for the user based on the generated preference profile and emotional data. In this process, the priority of the products and plans to be listed is determined based on the information contained in the preference profile. The input is the preference profile and emotional data, and the output is a proposal list.

[1123] Step 6:

[1124] The server generates a list of suggestions and sends it to the user's device. The server also sends advice based on the reasons for the suggestions and emotional data. The input is the list of suggestions, and the output is the data sent to the device.

[1125] Step 7:

[1126] The user's device analyzes the received proposal list and displays it in an easy-to-read format. The user can check the proposed products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change procedure. The input is the proposal list received from the server, and the output is the recommendation results displayed on the user's device display.

[1127] Through the above steps, more accurate recommendations can be realized based on the user's emotional data and operation history data.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] [Fourth embodiment]

[1132] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1133] 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.

[1134] 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).

[1135] 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.

[1136] 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.

[1137] 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).

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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."

[1145] This invention is a system for helping users find the smartphone and plan that suits them. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[1146] System configuration

[1147] 1. User Device

[1148] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[1149] The user terminal has a function of collecting operation history data of the user.

[1150] Operation history data includes pages viewed, links clicked, and time spent on the site.

[1151] 2. Server

[1152] The server is a central control unit installed in a cloud environment or on-premise environment.

[1153] The server has a function of receiving and analyzing the operation history data sent from the user terminal.

[1154] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[1155] Program Operation

[1156] Data collection

[1157] When a user browses a website to search for a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. Past purchase history and current contract plan data are also collected and sent to the server.

[1158] Data analysis and preference profile generation

[1159] The server analyzes the received operation history data and purchase history data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements.

[1160] Generate and submit suggestions

[1161] The server generates a list of products and plans suitable for the user based on the user's preference profile, and sends this recommendation list to the user's terminal.

[1162] Displaying and taking action on recommendation results

[1163] The user's device analyzes the recommendation list and displays it in an easy-to-read format. If the user is interested in the recommended products and plans, they can click on the details to proceed with the purchase or plan change.

[1164] Specific examples

[1165] Example 1: Recommending a new smartphone

[1166] Suppose a user is browsing a website looking for a new smartphone. The device collects operation history showing frequent visits to pages for smartphones with powerful cameras. The server analyzes this and creates a list of newly released smartphones with powerful cameras. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[1167] Example 2: Recommending a new plan

[1168] Let's say a user frequently checks for plans with larger data capacities. The device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and proceeds with the user switching to that plan.

[1169] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[1170] The processing flow will be explained below.

[1171] Step 1:

[1172] A user browses a website looking for a new smartphone or plan.

[1173] Step 2:

[1174] The user's device collects data on the user's operation history, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[1175] Step 3:

[1176] The device sends the collected operation history data to the server in real time.

[1177] Step 4:

[1178] Prepares for analysis of the operation history data, past purchase history data, and current contract plan data received by the server. Filters out unnecessary and duplicate data.

[1179] Step 5:

[1180] The server uses machine learning algorithms to analyze the operation history data, thereby identifying user preferences and behavioral patterns.

[1181] Step 6:

[1182] Based on the analysis, the server generates a user preference profile, which includes the product features that interest the user and the plan elements that they prefer.

[1183] Step 7:

[1184] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[1185] Step 8:

[1186] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[1187] Step 9:

[1188] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan.

[1189] Step 10:

[1190] Users can check the recommended products and plans, and if they are interested, they can click on the details. The device will guide them through the process of purchasing or changing plans.

[1191] Step 11:

[1192] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[1193] Step 12:

[1194] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[1195] Example 1

[1196] 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."

[1197] The current smartphone and plan selection process has the problem that it is difficult for users to find products and services that suit their preferences, and it takes a lot of time and effort. It also increases the burden on store staff and tends to reduce overall work efficiency. A system that solves these problems and allows users to efficiently find the best products and plans is needed.

[1198] 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.

[1199] In this invention, the server includes: a user terminal that collects and transmits user operation history data and purchase history data in real time; a server that receives and analyzes the operation history data and purchase history data transmitted from the user terminal; a server that generates a user preference profile based on the analyzed data; a server that generates recommendation candidates based on the preference profile; a server that transmits the recommendation candidates to the user terminal; and a server that receives and displays the recommendation candidates. This enables users to efficiently find products and plans that suit them, reduces the burden on store staff, and improves overall business efficiency.

[1200] A "user terminal" is an electronic device used by a user, such as a smartphone, tablet, or PC.

[1201] "Operation history data" refers to data such as the pages a user viewed, the links they clicked, and the length of time they stayed on the site.

[1202] "Purchase history data" refers to data on products and services purchased by a user in the past.

[1203] "Means of collecting and transmitting in real time" refers to the function of instantly acquiring information and transmitting it to the server every time a user performs an operation.

[1204] A "server" is a central control device that has the function of receiving, analyzing, and storing data sent from user terminals.

[1205] A "preference profile" is a collection of information about a user's interests and preferences that is generated by the server by analyzing the user's operation history and purchase history.

[1206] "Recommended candidates" refers to a list of products and services that are suitable for the user, generated by the server based on the preference profile.

[1207] "Means for receiving and analyzing" refers to the function by which the server receives data sent from the user's device and processes it using machine learning algorithms, etc.

[1208] "Means for generating" refers to the function by which the server creates preference profiles and recommendation candidates from the analysis results.

[1209] The "transmitting means" is a function that sends the recommendation candidates generated by the server to the user terminal.

[1210] "Means for receiving and displaying" refers to the function by which the user terminal receives the recommended candidates sent from the server and displays them in a format that is easy for the user to view.

[1211] This invention is a system that allows users to find a smartphone and plan that suits them, and is composed of a user terminal, a server, and its communication protocol.

[1212] User terminal

[1213] User terminals are electronic devices such as smartphones, tablets, and PCs. User terminals collect operation history data and purchase history data in real time and send it to a server. Specific hardware examples include smartphones, which are common mobile devices. Software used includes dedicated applications for data collection and transmission.

[1214] server

[1215] The server is a central control device installed in a cloud or on-premise environment. It has the function of receiving and analyzing operation history data and purchase history data sent from user devices. Machine learning algorithms such as Python's Sci-Kit Learn and TensorFlow are used for data analysis. Based on the preference profile generated by the server, it generates recommended candidates for products and plans suitable for the user and sends them to the user's device.

[1216] Specific examples

[1217] Example 1: Recommending a new smartphone

[1218] Suppose a user is browsing a website looking for a new smartphone. The user's device collects this operation history and sends it to the server. For example, the user's operation history may record that the user frequently visits pages for smartphones with high camera performance. The server analyzes this data and creates a list of new smartphones with high camera performance. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[1219] Example 2: Recommending a new plan

[1220] Suppose a user frequently checks for plans with larger data capacities. The user's device captures this operation history and sends it to the server. The server analyzes this data and recommends a plan with larger data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[1221] Example prompt

[1222] Prompt: "Describe a system where a user's device captures page browsing history in real time on a smartphone with a powerful camera and sends it to a server. The server then uses machine learning algorithms to generate a preference profile and create and send a list of smartphone recommendations that are best suited to the user."

[1223] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall operational efficiency.

[1224] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1225] Step 1: Data collection

[1226] A user browses a website to find a new smartphone or plan. The user's device collects this operation history data (pages viewed, links clicked, time spent, etc.) and purchase history data in real time. The input is the user's browsing behavior and purchasing behavior, and this data is captured. The collected operation history data and purchase history data are generated as output.

[1227] Specifically, when a user searches for "smartphones with high camera performance" on their smartphone and accesses a specific product page, the access information is immediately recorded.

[1228] Step 2: Send data

[1229] The operation history data and purchase history data collected by the user terminal are periodically sent to the server. The data collected in step 1 is the input, and is sent to the server. The server receives the data as the output.

[1230] Specifically, each time a user views a camera performance comparison page, the accessed URL and the duration of stay are sent to the server.

[1231] Step 3: Data analysis

[1232] The server analyzes the operation history data and purchase history data it receives. As input, it receives data sent from the user's device and processes the data using a machine learning algorithm (e.g., Python's Sci-Kit Learn or TensorFlow). As output, it generates the analyzed data.

[1233] Specifically, the server retrieves the operation history data stored in the database and extracts the characteristics of pages frequently visited by users and products purchased by them.

[1234] Step 4: Generate a preference profile

[1235] The server generates a user preference profile based on the analysis results. The input is the data analyzed in step 3, and the preference profile is generated based on this. The generated preference profile is obtained as the output.

[1236] Specifically, the server adds keywords preferred by the user (e.g., "high-performance camera" and "large-capacity battery") to the profile and generates a different recommendation model for each user.

[1237] Step 5: Generate a recommendation list

[1238] Based on the preference profile generated by the server, a list of products and plans suitable for the user is created. The preference profile is taken as input, and recommendation candidates are generated based on this. The recommendation list is obtained as output.

[1239] Specifically, the server retrieves recommended smartphones and plans from the database and lists products that match criteria such as "high-performance camera" and "large-capacity battery."

[1240] Step 6: Submit your recommendation list

[1241] The server sends the generated recommendation list to the user terminal. The generated recommendation list is the input, and is sent to the user terminal. The user terminal receives the recommendation list as the output.

[1242] Specifically, the server sends the recommendation list it has built to the user's device in JSON format. The user's device receives this data and prepares to display it on the screen.

[1243] Step 7: View the Recommendations List

[1244] The user device analyzes the recommendation list and displays it in an easy-to-read format for the user. The input is the recommendation list sent from the server and is displayed to the user. The output is the user checking the recommendation list and accessing products and plans that interest them.

[1245] Specifically, after the user device receives the recommendation list, it displays it in a list format. The user becomes interested in the "smartphone with a high-performance camera" and clicks on the details page. The user then presses the purchase button to complete the purchase process.

[1246] (Application example 1)

[1247] 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."

[1248] Currently, users must research and compare many options to find the smartphone and plan that best suits them, which takes time and effort. Furthermore, the procedures for online purchases and contract changes are cumbersome. Therefore, there is a need for a system that allows users to quickly and efficiently find the product and plan that best suits them, and easily make purchases and contract changes.

[1249] 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.

[1250] In this invention, the server includes: means for a user terminal to collect user operation history data; means for the server to analyze the operation history data transmitted from the user terminal; means for the server to generate a user preference profile based on the analysis results; means for the server to generate suggested candidates based on the preference profile; means for the server to transmit the suggested candidates to the user terminal; means for the user terminal to display the suggested candidates; and means for the user terminal to provide an interface that allows the user terminal to confirm recommended products and plans and then make a purchase or change a contract. This allows users to quickly and easily find the products and plans that are best suited to them, and to make a purchase or change a contract without going through complicated procedures.

[1251] A "user terminal" is an electronic device operated by a user, such as a smartphone, tablet, or personal computer.

[1252] "Operation history data" is data that includes operation information such as pages viewed by a user, links clicked, and the time spent on each page.

[1253] A "server" is a central control device installed in a cloud environment or on-premise environment that analyzes data sent from user terminals and executes specified functions.

[1254] A "preference profile" is a data profile that includes personalized information that reflects a user's interests and preferences based on the user's operation history data and purchase history data.

[1255] "Suggested candidates" are a list of products and plans for the user that are generated based on the preference profile.

[1256] The "interface" is an operation screen that displays recommended products and plans on the user's terminal, allowing the user to check them and make purchases or change contracts.

[1257] This invention is a system that allows users to find the smartphone and plan that suits them, and is composed of a user terminal and a server. How this system works will be explained below.

[1258] System configuration

[1259] 1. User Device

[1260] The user terminal is an electronic device such as a smartphone, a tablet, or a personal computer.

[1261] The user terminal has a function to collect user operation history data, which includes the pages the user viewed, the links they clicked, and the duration of their stay.

[1262] It also has the function of collecting past purchase history and current contract plan data and sending it to the server.

[1263] 2. Server

[1264] The server is installed in a cloud environment or on-premise environment and acts as a central control device.

[1265] The server has the function of receiving and analyzing operation history data sent from the user terminal in real time.

[1266] The server uses machine learning algorithms (e.g., TensorFlow) to generate a preference profile based on the user's interests and preferences, including the user's preferred product features and preferred plan elements.

[1267] The server generates a list of products and plans (candidate suggestions) suitable for the user based on the preference profile and sends it to the user's terminal.

[1268] 3. Adding functions to user devices

[1269] The user terminal has a function to display recommended products and plans.

[1270] It has the function of providing an interface that allows users to check the recommended products and plans and then make purchases or change their contracts.

[1271] Specific operation examples

[1272] Data collection and analysis

[1273] Suppose a user is browsing a website looking for a new smartphone. For example, if the user frequently visits pages about smartphones with high camera capabilities, the user's device will collect this operation history in real time and send it to the server. Data on previously purchased smartphones and current contract plans will also be sent to the server.

[1274] The server analyzes this operation history data and past purchase history data, and uses a machine learning algorithm to generate a preference profile that indicates the user's preference for smartphones with high camera performance.

[1275] Generate and display suggestions

[1276] The server creates a list of the latest smartphones with excellent camera capabilities based on the user's preference profile and sends it to the user's device, which then displays the list in an easy-to-understand manner, allowing the user to check detailed information about the smartphones that interest them.

[1277] Purchase and contract modification interface

[1278] If a user is interested after checking the recommended products and plans, the system provides an interface that allows the user to proceed with the purchase process directly on the user's device. This interface allows users to easily purchase a smartphone or change plans.

[1279] Prompt Sentence Examples

[1280] As a concrete example, the following prompts are input into a generative AI model to generate a user preference profile and recommendation list.

[1281] User ID: 1

[1282] Operation History:

[1283] Page: Smartphone List

[1284] Click: iPhone 13

[1285] Stay time: 300 seconds

[1286] Page: Compare Plans

[1287] Click: Large amount of data

[1288] Stay time: 180 seconds

[1289] Purchase History:

[1290] Purchase: Galaxy S10

[1291] Purchase date: 2020-06-15

[1292] Current plan:

[1293] Plan: Unlimited data

[1294] Contract start date: 2021-01-01

[1295] Use this data to recommend the best smartphone and plan for your users.

[1296] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1297] Step 1:

[1298] Users browse websites when searching for smartphones and plans.

[1299] Input: User actions (page transitions, link clicks, time spent, etc.)

[1300] Operation: The user device collects operation history data in real time.

[1301] Output: Collected operation history data

[1302] Step 2:

[1303] The user terminal transmits the user's operation history data to the server.

[1304] Input: Operation history data

[1305] How it works: The user device sends the collected data to the server via an HTTP POST request.

[1306] Output: Operation history data received by the server

[1307] Step 3:

[1308] The server receives the operation history data and analyzes it.

[1309] Input: Operation history data received by the server

[1310] How it works: The server analyzes the data and extracts information to identify the user's interests and preferences. The data is analyzed using machine learning algorithms such as TensorFlow.

[1311] Output: User preference profile

[1312] Step 4:

[1313] The server generates suggestions based on the preference profile.

[1314] Input: User preference profile

[1315] How it works: The server analyzes your preference profile and generates a list of products and plans that suit you based on that profile.

[1316] Output: A list of possible suggestions

[1317] Step 5:

[1318] The list of proposal candidates is transmitted to the user terminal.

[1319] Input: A list of suggestions

[1320] Operation: The server sends the generated list to the user's device via an HTTP GET request.

[1321] Output: A list of proposal candidates received by the user device

[1322] Step 6:

[1323] The user terminal displays a list of proposal candidates.

[1324] Input: A list of proposal candidates received by the user device

[1325] Behavior: The user device displays the list in an appropriate user interface so that the user can view it.

[1326] Output: A list of suggestions that can be visually reviewed by the user.

[1327] Step 7:

[1328] The user checks the recommended products and plans and proceeds to purchase or change their contract.

[1329] Input: The user's choice for a specific product or plan within a list of potential offers

[1330] Operation: The user terminal provides an interface that allows operations such as purchases and contract changes to be performed, and sends that information to the server.

[1331] Output: Data on the results of completing the purchase or contract change procedure

[1332] 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.

[1333] This invention is a system that helps users find the smartphone and plan that best suits them. In particular, by combining it with an emotion engine that recognizes the user's emotions, the system can make more accurate recommendations. The system consists of a user terminal, a server, and its communication protocol. How this system works is explained below.

[1334] System configuration

[1335] 1. User Device

[1336] The user terminal is an electronic device such as a smartphone, tablet, or PC.

[1337] The user terminal has a function of collecting operation history data of the user.

[1338] Operation history data includes pages viewed, links clicked, and time spent on each page.

[1339] It also has an emotion engine that recognizes the user's emotions.

[1340] The emotion engine collects emotion data from the user's facial expressions and voice tone, and sends it to the server.

[1341] 2. Server

[1342] The server is a central control unit installed in a cloud environment or on-premise environment.

[1343] The server has a function of receiving and analyzing the operation history data and emotion data sent from the user terminal.

[1344] The server generates a user preference profile based on the analysis results and has the function of suggesting suitable products and plans.

[1345] Based on the emotion data, the priority of the proposed candidates is set.

[1346] Program Operation

[1347] Data collection

[1348] When a user browses a website to find a new smartphone or plan, the user's device captures this activity history in real time and sends the data to the server. At the same time, emotional data is collected from the user's facial expressions and tone of voice, and this data is also sent to the server.

[1349] Data analysis and preference profile generation

[1350] The server analyzes the received operation history data, past purchase history data, and current contract plan data. Using machine learning algorithms, the server generates a preference profile based on the user's interests and preferences. This profile includes the user's preferred product features and preferred plan elements. Furthermore, it analyzes emotional data and reflects in the profile the emotions the user displayed when viewing certain products and plans.

[1351] Generate and submit suggestions

[1352] The server generates a list of products and plans suitable for the user based on the preference profile. Product and plan information is retrieved from an up-to-date database. Based on the emotion data, the server prioritizes the proposal candidates and sends them to the user's device.

[1353] Displaying and taking action on recommendation results

[1354] The user's device analyzes the recommendation list and displays it in an easy-to-read format. Detailed information about each product and plan is also displayed, with priorities based on emotional data. The user can check the recommended products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change.

[1355] Specific examples

[1356] Example 1: Recommending a new smartphone

[1357] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and creates a list of newly released smartphones with high camera capabilities. The user's device displays this list, which piques the user's interest and prompts them to proceed with the purchase.

[1358] Example 2: Recommending a new plan

[1359] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[1360] This system allows users to easily find the products and plans that are best suited to them, reducing the burden on store staff and improving overall work efficiency. In addition, by using emotion data, it is possible to make even more accurate recommendations.

[1361] The processing flow will be explained below.

[1362] Step 1:

[1363] A user browses a website looking for a new smartphone or plan.

[1364] Step 2:

[1365] The user's device collects operation history data, specifically capturing which pages were viewed, which links were clicked, and the time spent on each page.

[1366] Step 3:

[1367] The user device collects emotional data in real time from the user's facial expressions, voice tone, etc. This data is analyzed using an emotion engine.

[1368] Step 4:

[1369] The device sends the collected operation history data and emotion data to the server in real time.

[1370] Step 5:

[1371] The server prepares for analyzing the received operation history data, emotion data, past purchase history data, and current contract plan data. It filters out unnecessary and duplicate data.

[1372] Step 6:

[1373] The server uses machine learning algorithms to analyze operation history data and emotion data, thereby identifying patterns of change in user preferences and emotions.

[1374] Step 7:

[1375] Based on the analysis results, the server creates a user preference profile, which includes the product features the user is interested in and the elements of the plan they prefer. Furthermore, using emotional data, the profile also reflects the emotions the user expressed when viewing certain products and plans.

[1376] Step 8:

[1377] The server generates a list of products and plans suitable for the user based on the preference profile, with product and plan information retrieved from an up-to-date database.

[1378] Step 9:

[1379] The server prioritizes the proposed products based on the emotion data. For example, it gives higher priority to products or plans that make the user smile.

[1380] Step 10:

[1381] The server sends the generated recommendation list to the user terminal, where the data is converted into an appropriate format and transmitted in a format that complies with the communication protocol.

[1382] Step 11:

[1383] The user's device analyzes the recommendation list received from the server and displays it in an easy-to-read format, along with detailed information about each product and plan, reflecting priorities based on emotional data.

[1384] Step 12:

[1385] The user can check the recommended products and plans, and if they are interested, click on the details. The device will guide the user through the process of purchasing or changing plans.

[1386] Step 13:

[1387] The user device feeds back the user's final action (purchase or plan change) to the server, which receives this feedback and updates its preference profile and recommendation algorithm.

[1388] Step 14:

[1389] The server analyzes the feedback to improve the overall accuracy of the system, which will improve the accuracy of recommendations from next time onwards.

[1390] Example 2

[1391] 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."

[1392] Conventional recommendation systems make suggestions based solely on a user's operation history and purchase history, making it difficult to provide accurate suggestions that reflect the user's current emotions and interests. In particular, they have been unable to accurately capture what a user likes and what elements excite or satisfy them. As a result, the accuracy of suggestions is low, making it difficult to improve user satisfaction.

[1393] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user terminal to collect user operation history data and emotion data; means for the server to analyze the operation history data and emotion data transmitted from the user terminal; means for the server to generate a user preference profile from the analysis result using a machine learning algorithm; means for the server to generate candidates to be proposed based on the preference profile; means for the server to set priorities of the candidates to be proposed based on emotion data; means for the server to transmit the proposed candidates to the user terminal; and means for the user terminal to display the proposed candidates. This enables highly accurate suggestions that reflect the user's current emotions and real-time interests.

[1394] A "user terminal" is a device operated by a user, such as a smartphone, tablet, or PC.

[1395] "Operation history data" refers to data related to user actions, such as the page history when a user browses a website, the links clicked, and the time spent on each page.

[1396] "Emotional data" is data collected from a user's facial expressions and vocal tone that indicates the user's emotional state.

[1397] The "server" is a central control device that receives data sent from a user terminal, analyzes it, generates recommendation results, and sends them to the user terminal.

[1398] "Analysis" is the process of extracting information from collected data to clarify user preferences and trends.

[1399] A "machine learning algorithm" is a mathematical technique that generates models based on past data and makes predictions and classifications for future data.

[1400] A "preference profile" is a collection of information that reflects a user's interests and preferences, and includes characteristics of products and services that the user prefers.

[1401] "Suggested candidates" is a list of products and plans generated by the server based on the user's preference profile.

[1402] "Priority" is an evaluation that ranks the suggested candidates in terms of their importance to the user.

[1403] "SSL / TLS" is a protocol for encrypting data and communicating securely.

[1404] A "graphical user interface" is a computer interface that uses images and text to visually present information to a user and facilitate operation.

[1405] This invention is a system that helps users find the smartphone and communication plan that best suits them. In particular, by combining an engine that recognizes the user's emotions, the system can make more accurate suggestions. The system consists of a user terminal, a server, and its communication protocol.

[1406] System configuration

[1407] 1. User Device

[1408] User devices are electronic devices such as smartphones, tablets, and PCs. They have the ability to collect user operation history data and emotional data from facial expressions and voice tones. Specifically, when a user browses a website, the device captures data such as the pages visited, the links clicked, and the time spent on each page, and simultaneously collects emotional data.

[1409] 2. Server

[1410] The server is a central control device installed in a cloud or on-premise environment. It receives and analyzes operation history data and emotion data sent from user devices. The server applies machine learning algorithms using Python's Scikit-learn library and other tools to generate a preference profile. The preference profile includes the user's preferred product features and preferred plan elements.

[1411] 3. Communication Protocol

[1412] Data is transmitted between the user terminal and the server using a secure communication protocol such as SSL / TLS.

[1413] System Operation

[1414] 1. Data Collection

[1415] When a user browses a website to find a new smartphone or plan, the user's device captures their activity history in real time and also collects emotional data. This data is then sent to the server using SSL / TLS.

[1416] 2. Data analysis and generation of preference profiles

[1417] The server analyzes the received operation history data and emotion data and uses a machine learning algorithm to generate a user preference profile. The preference profile reflects the user's preferred product features and preferred plan elements. The server also prioritizes the proposed options based on the emotion data.

[1418] 3. Generate and send proposal candidates

[1419] The server generates a list of products and plans suitable for the user based on the user's preference profile. This list is retrieved from an up-to-date database and prioritized based on the user's emotional data. The server then transmits this list to the user's device.

[1420] 4. Displaying recommended results and taking action

[1421] The user's device displays a list of recommendations. Detailed information about each product or plan is also displayed, and the user can click on it to view more information. If the user is interested in a product or plan, they can proceed with the online purchase or plan change process.

[1422] Specific examples

[1423] Example 1: Recommending a new smartphone

[1424] Suppose a user is browsing a website looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, such as smiling faces. The server analyzes this operation history and emotional data and suggests a new smartphone with high camera capabilities. The user's device displays this, which piques the user's interest, and the user proceeds with the purchase process.

[1425] Example 2: Recommending a new plan

[1426] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this and the user is prompted to switch to that plan.

[1427] Prompt Sentence Examples

[1428] Below is an example of a prompt to input to the generative AI model.

[1429] Example prompt 1:

[1430] When users are searching for a smartphone, they often browse pages of smartphones with high camera performance and smile when they do so. Therefore, we would like you to recommend the best smartphone for them.

[1431] Example prompt 2:

[1432] Users frequently check the plans with large data capacities and look satisfied when they do so. Please recommend the best plan for them.

[1433] This system allows users to receive highly accurate suggestions that reflect their current emotions and interests, which increases user satisfaction and improves the efficiency of sales operations.

[1434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1435] Step 1: A user browses to a website.

[1436] When a user browses a website looking for a smartphone or plan, they visit specific pages, click links, and spend a certain amount of time on each page, generating data that feeds into the system.

[1437] Step 2: The user terminal collects operation history data and emotion data.

[1438] The user's device captures the user's operation history data (pages visited, links clicked, time spent, etc.) in real time, and simultaneously collects emotional data from the user's facial expressions and tone of voice. This input data forms the basis for subsequent analysis processing. The device temporarily stores this data.

[1439] Step 3: The user terminal transmits the collected data to the server.

[1440] The operation history data and emotion data collected by the user device are sent to the server using a secure communication protocol such as SSL / TLS. In this process, the user device generates a data packet and transfers it to the server via the network.

[1441] Step 4: The server parses the received data.

[1442] The server receives operation history data and emotion data sent from the user's device. The server preprocesses the received data (e.g., filling in missing values, normalizing data, etc.) and prepares it for analysis. The server then analyzes the data using a machine learning algorithm (e.g., using Python's Scikit-learn library). The server then extracts patterns based on the user's interests and preferences.

[1443] Step 5: The server generates a preference profile.

[1444] Based on the analysis results, the server generates a user preference profile, including the product features the user is particularly interested in and the attributes of the plan they prefer. The server then builds the preference profile into a data model and stores the information in a database.

[1445] Step 6: The server generates proposal candidates.

[1446] The server generates a list of suitable products and plans from an up-to-date database based on the user's preference profile, and prioritizes the candidates using emotion data. The output data is a list of candidates that is saved and ready to be sent to the user's device.

[1447] Step 7: The server sends the proposal candidates to the user terminal.

[1448] The server sends the list of proposal candidates to the user terminal. In this transmission process, a data packet is generated and transmitted to the user terminal via the network. Secure communication protocols such as SSL / TLS are also used here.

[1449] Step 8: The user terminal displays the recommendation list.

[1450] The user device analyzes the recommendation list received from the server and displays it in an easy-to-read format. Using a user interface (GUI), detailed information about each product and plan is also displayed, allowing the user to click on it for more information.

[1451] Step 9: The user performs the action.

[1452] Users click on the recommended products or plans, check their details, and if they are interested, proceed with the purchase or plan change process. The user's device supports this process, providing the necessary links and forms to ensure a seamless user experience.

[1453] (Application example 2)

[1454] 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."

[1455] Conventional recommendation systems typically recommend products and services based on user operation history and purchase history data. However, it is difficult to make recommendations that reflect the user's emotions and current psychological state using only this data, and there are limitations to providing optimal products and services for users. In particular, more accurate recommendations are required to improve the shopping experience in online environments such as virtual stores. Furthermore, a system that can quickly respond to changes in a user's interests and preferences is also required.

[1456] 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.

[1457] In this invention, the server includes a means for a user terminal to collect emotional data such as a user's facial expression and voice tone, a means for the server to analyze operation history data and emotional data transmitted from the user terminal, and a means for generating a user preference profile based on the analysis results, thereby enabling highly accurate recommendations based on emotional data such as facial expression and voice tone in addition to the user's operation history data.

[1458] A "user terminal" is an electronic device operated by a user, and includes devices such as smartphones, tablets, and personal computers.

[1459] "Operation history data" refers to data related to a user's web browsing and application operations, such as the pages the user viewed, the links they clicked, and the time spent on each page.

[1460] "Emotion data" refers to data relating to the user's emotional state obtained from the user's facial expressions and vocal tone, and is data for grasping the user's psychological state and emotions in real time.

[1461] A "server" is a central control device that receives data sent from user devices and performs processes such as analysis, profile generation, and generation of recommendation candidates, and is operated in a cloud environment or on-premise environment.

[1462] A "preference profile" is a data profile that reflects a user's interests and preferences and is generated by analyzing the user's operation history data and emotional data.

[1463] "Recommendation candidates" are a list of products and services suggested to the user, generated by the server based on the preference profile and emotional data.

[1464] This invention is a system that provides products and plans suited to users based on their emotional data and operation history data. The main components are a user terminal, a server, and a communication protocol for exchanging data between them.

[1465] User terminal

[1466] A user terminal is an electronic device operated by a user, including a smartphone, tablet, personal computer, etc. A user terminal has the following functions:

[1467] 1. Collection of operation history data: Capture and save operation history data in real time, such as the pages viewed by users, the links clicked, and the time spent on each page.

[1468] 2. Emotion data collection: Using the user's camera and microphone, facial expressions and voice tones are collected and stored as emotion data. For this purpose, an emotion engine (such as the Emotion Recognition library) is used.

[1469] server

[1470] The server is a central control unit that can be operated in a cloud or on-premise environment. The server has the following functions:

[1471] 1. Data analysis: Operation history data and emotion data sent from the user's device are received and analyzed using machine learning algorithms, thereby generating a user preference profile.

[1472] 2. Recommendation generation: Generate a list of products and plans that are best suited to the user based on their preference profile and sentiment data.

[1473] 3. Sending recommendation candidates: The generated recommendation candidates are sent to the user's device and displayed to the user.

[1474] Specific examples

[1475] New smartphone recommendation

[1476] Suppose a user is browsing a virtual store looking for a new smartphone. The user's device frequently browses pages for smartphones with high camera capabilities, and emotional data is collected, showing that the user smiles while browsing. The server analyzes this operation history and emotional data and creates a list of new smartphones with high camera capabilities. The user's device displays this list, and the user, excited by the list, proceeds with the purchase.

[1477] New plan recommendation

[1478] Suppose a user frequently checks for plans with large data capacities. The user's device captures this operation history and sends it to the server. At the same time, emotional data is collected from the user's facial expressions. The server analyzes this and recommends a plan with large data capacities. The user's device displays this information and the user is prompted to switch to that plan.

[1479] Prompt Sentence Examples

[1480] For example, if the user's facial expression is recognized as "joy," the following prompt sentence can be passed to the generative AI model to generate a detailed recommendation.

[1481] "The user expressed the emotion 'Delighted' while browsing Smartphone A. Please generate the following recommendation: 'This smartphone has excellent camera performance, making it ideal for those who enjoy taking photos.'"

[1482] As described above, this system increases user satisfaction by generating a user preference profile based on a variety of information, including the user's emotional data, and recommending products and plans based on that profile.

[1483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1484] Step 1:

[1485] When a user starts browsing a virtual store, their operation history data (pages viewed, links clicked, time spent, etc.) is collected in real time by the user's device. This data is temporarily stored in the device and later sent to the server. The input is the user's web operation, and the output is the collection of operation history data.

[1486] Step 2:

[1487] At the same time, the camera and microphone on the user's device capture the user's facial expressions and voice tone, and use an emotion engine (such as the Emotion Recognition library) to collect emotional data in real time. This emotional data is also temporarily stored on the device and later sent to the server. The input is the user's facial expressions and voice, and the output is the collection of emotional data.

[1488] Step 3:

[1489] Operation history data and emotion data are periodically sent to the server. The server is prepared to analyze the received data. As soon as the server receives this data, it saves it in storage for analysis. The input is the operation history data and emotion data sent from the device, and the output is the saving of the data.

[1490] Step 4:

[1491] The server uses machine learning algorithms to analyze operation history data and emotion data. The data analysis generates a user preference profile. The specific analysis process involves extracting patterns of the user's interests and reflecting them in the preference profile. The input is the data stored in storage, and the output is the generated preference profile.

[1492] Step 5:

[1493] The server generates a list of products and plans suitable for the user based on the generated preference profile and emotional data. In this process, the priority of the products and plans to be listed is determined based on the information contained in the preference profile. The input is the preference profile and emotional data, and the output is a proposal list.

[1494] Step 6:

[1495] The server generates a list of suggestions and sends it to the user's device. The server also sends advice based on the reasons for the suggestions and emotional data. The input is the list of suggestions, and the output is the data sent to the device.

[1496] Step 7:

[1497] The user's device analyzes the received proposal list and displays it in an easy-to-read format. The user can check the proposed products and plans, and if they are interested, they can click on the details to proceed with the purchase or plan change procedure. The input is the proposal list received from the server, and the output is the recommendation results displayed on the user's device display.

[1498] Through the above steps, more accurate recommendations can be realized based on the user's emotional data and operation history data.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] FIG. 9 is a diagram illustrating 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 actions 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.

[1504] 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.

[1505] 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).

[1506] 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.

[1507] 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."

[1508] 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.

[1509] 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).

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] The following is further disclosed regarding the above embodiment.

[1521] (Claim 1)

[1522] A means for collecting user operation history data in a user terminal;

[1523] A server analyzes the operation history data transmitted from the user terminal;

[1524] means for generating a user preference profile based on the analysis results by the server;

[1525] means for generating candidate suggestions based on the preference profile by the server;

[1526] means for transmitting the proposed candidates to the user terminal by the server;

[1527] a means for displaying the proposed candidates in the user terminal;

[1528] A system including:

[1529] (Claim 2)

[1530] 2. The system according to claim 1, wherein the user terminal collects past purchase history data and current contract plan data and transmits them to the server.

[1531] (Claim 3)

[1532] The system according to claim 1, wherein the server analyzes the operation history data and past purchase history data using a machine learning algorithm.

[1533] "Example 1"

[1534] (Claim 1)

[1535] A means for the user terminal to collect and transmit user operation history data and purchase history data in real time;

[1536] A server receives and analyzes operation history data and purchase history data transmitted from the user terminal;

[1537] means for the server to generate a user preference profile based on the analyzed data;

[1538] means for generating recommendation candidates based on the preference profile by the server;

[1539] a means for transmitting the recommendation candidates to the user terminal by the server;

[1540] a means for receiving and displaying the recommendation candidates in the user terminal;

[1541] A system including:

[1542] (Claim 2)

[1543] 2. The system according to claim 1, wherein the user terminal periodically transmits the user's operation history data and purchase history data to the server.

[1544] (Claim 3)

[1545] The system according to claim 1, wherein the server analyzes the operation history data and purchase history data using a machine learning algorithm to generate a preference profile of the user.

[1546] "Application Example 1"

[1547] (Claim 1)

[1548] A means for collecting user operation history data in a user terminal;

[1549] A server analyzes the operation history data transmitted from the user terminal;

[1550] means for generating a user preference profile based on the analysis results by the server;

[1551] means for generating candidate suggestions based on the preference profile by the server;

[1552] means for transmitting the proposed candidates to the user terminal by the server;

[1553] a means for displaying the proposed candidates in the user terminal;

[1554] means for providing an interface that allows the user terminal to check the recommended products and plans and then purchase or change the contract;

[1555] A system including:

[1556] (Claim 2)

[1557] 2. The system according to claim 1, wherein the user terminal collects past purchase history data and current contract plan data and transmits them to the server.

[1558] (Claim 3)

[1559] The system according to claim 1, wherein the server analyzes the operation history data and past purchase history data using a machine learning algorithm.

[1560] "Example 2: Combining Emotion Engines"

[1561] (Claim 1)

[1562] A means for collecting operation history data and emotion data of a user in a user terminal;

[1563] A server analyzes the operation history data and emotion data transmitted from the user terminal;

[1564] means for generating a user preference profile from the analysis results using a machine learning algorithm in the server;

[1565] means for generating candidate suggestions based on the preference profile by the server;

[1566] a means for setting a priority order of candidates proposed by the server based on emotion data;

[1567] means for transmitting the proposed candidates to the user terminal by the server;

[1568] a means for displaying the proposed candidates in the user terminal;

[1569] A system including:

[1570] (Claim 2)

[1571] 2. The system according to claim 1, wherein the user terminal collects past purchase history data and current contract plan data and transmits them to the server.

[1572] (Claim 3)

[1573] The system of claim 1 , wherein the server analyzes the operation history data, emotion data, and past purchase history data using a machine learning algorithm.

[1574] "Application example 2 when combining emotion engines"

[1575] (Claim 1)

[1576] A means for collecting user operation history data in a user terminal;

[1577] A means for collecting emotional data such as facial expressions and voice tones of the user in the user terminal;

[1578] A server analyzes the operation history data and emotion data transmitted from the user terminal;

[1579] means for generating a user preference profile based on the analysis results by the server;

[1580] means for generating candidate suggestions based on the preference profile and emotion data by the server;

[1581] means for transmitting the proposed candidates to the user terminal by the server;

[1582] a means for displaying the proposed candidates in the user terminal;

[1583] A system including:

[1584] (Claim 2)

[1585] 2. The system according to claim 1, wherein the user terminal collects past purchase history data and current contract plan data and transmits them to the server.

[1586] (Claim 3)

[1587] The system of claim 1, wherein the server analyzes the operation history data, past purchase history data, and emotion data using a machine learning algorithm. [Explanation of symbols]

[1588] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting user operation history data in a user terminal; A server analyzes the operation history data transmitted from the user terminal; means for generating a user preference profile based on the analysis results by the server; means for generating candidate suggestions based on the preference profile by the server; means for transmitting the proposed candidates to the user terminal by the server; a means for displaying the proposed candidates in the user terminal; A system including:

2. 2. The system according to claim 1, wherein the user terminal collects past purchase history data and current contract plan data and transmits them to the server.

3. The system according to claim 1 , wherein the server analyzes the operation history data and the past purchase history data using a machine learning algorithm.

Images