System

Abstract

To provide a system.SOLUTION: Provided is a system comprising: means for collecting access logs on an advertiser site; means for storing the collected access logs in a database; means for pre-processing for cleaning and standardizing the stored access log data; means for building a generative AI model by making it learn a user's behavior patterns using the pre-processed data; means for generating a next action on the basis of an initial behavior of the user accessing the advertiser site using the generative AI model that has already learned; and means for dynamically changing the user's experience on the advertiser site on the basis of the generated next action.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] Traditional advertiser sites could only provide a uniform user experience (UX), making it difficult to provide an optimal UX tailored to each individual user's behavioral patterns. [Means for solving the problem]

[0005] The system of the present invention builds an AI (UX generation AI) that learns from the access logs of advertiser sites and generates user actions that lead to sales. This UX generation AI generates and suggests next actions that will lead to sales based on the initial behavior of users who visit the advertiser site. The advertiser site then dynamically changes its site UX based on these suggestions. This makes it possible to provide an optimal UX for each user and improve sales conversion rates. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention builds an AI (UX generation AI) that learns from the access logs of advertiser sites. This AI generates and suggests next actions that will lead to a sale based on the initial actions of users who visit the advertiser site. Specifically, based on the initial actions taken by users when they visit the site (e.g., accessing a specific product page, searching for specific keywords, etc.), it generates actions such as which page to direct users to next or which product to recommend.

[0029] "Example 2"

[0030] The generated action is reflected on the advertiser's site, dynamically changing the site's UX. Specifically, when a user visits the site, the content displayed changes based on the generated action. For example, if an action recommending a specific product is generated, information about that product will be displayed preferentially when the user visits the site. This makes it possible to provide an optimal UX for each user and improve conversion rates.

[0031] "Example 3"

[0032] The system of the present invention understands user behavior patterns by studying the access logs of advertiser sites and generates optimal actions based on those patterns. Specifically, the system learns user behavior patterns from past access logs and generates the next action based on those patterns. For example, if the system learns a pattern that users who visit a specific product page have a high probability of purchasing another specific product, it generates the next action based on that pattern.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Collect access logs from the advertiser's website, including the initial actions users take when visiting the website (e.g., accessing a specific product page, searching for a specific keyword, etc.).

[0036] Step 2: The collected access logs are trained by AI (UX generation AI). The AI ​​learns user behavior patterns and generates the next action based on them.

[0037] Step 3: The generated action is reflected on the advertiser's site. Specifically, when a user visits the site, the content displayed is changed based on the generated action.

[0038] "Example 2"

[0039] Step 1: Collect initial user actions when visiting your site.

[0040] Step 2: Based on the collected initial behavior, AI (UX generation AI) generates the next action that leads to a successful conclusion.

[0041] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[0042] "Example 3"

[0043] Step 1: Collect access logs from the advertiser's site to understand user behavior patterns.

[0044] Step 2: Learn user behavior patterns from the collected access logs and generate the next action based on those patterns.

[0045] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form 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."

[0048] Conventional advertiser sites lacked the means to effectively utilize user behavior data to improve conversion rates. In particular, it was difficult to appropriately suggest the next action based on the user's initial behavior and dynamically change the user experience on the site. This meant that it was not possible to make suggestions that were in line with the user's interests and concerns, making it difficult to improve conversion rates.

[0049] 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.

[0050] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for training a generative AI model using the preprocessed data, means for generating and suggesting a next action based on a user's initial behavior, means for sending the generated next action to the user's terminal, and means for dynamically changing the user experience on the site based on the suggestion. This makes it possible to effectively utilize user behavior data and improve the conversion rate.

[0051] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[0052] An "access log" is a record of behavioral data when a user accesses a website, and includes information such as the pages viewed, search keywords, and the date and time of the visit.

[0053] "Database" means a system for storing collected access logs, enabling efficient management and retrieval of data.

[0054] "Preprocessing" refers to processes such as cleaning and normalizing collected data to make it easier to analyze.

[0055] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn user behavior patterns and generate the next action.

[0056] "User initial actions" are the first actions a user takes when accessing a website, including viewing a specific product page or searching for a specific keyword.

[0057] "Next Actions" are suggestions for what a user should do next based on their initial behavior, and can include directing them to a specific page or recommending a product.

[0058] "User experience" refers to the overall experience a user has when using a website, including the ease of use of the site and the quality of the information provided.

[0059] "Dynamic changes" refers to changing the content and structure of a website in real time based on user behavior data.

[0060] MODE FOR CARRYING OUT THE INVENTION

[0061] System Overview

[0062] The system of the present invention collects access logs from advertiser sites and builds a generative AI model that learns user behavior patterns based on these logs. This AI model generates and suggests next actions based on the user's initial behavior. Specifically, based on the user's initial behavior when visiting a site (e.g., accessing a specific product page, searching for a specific keyword, etc.), it generates actions such as which page to direct the user to next or which product to recommend.

[0063] Hardware and software used

[0064] The server collects, stores, and preprocesses access logs, trains the AI ​​model, and generates the next action. Specifically, it uses the following hardware and software:

[0065] Hardware: High-performance servers (CPU, GPU, memory, storage)

[0066] Software: Database management systems (e.g., MySQL (registered trademark), PostgreSQL), machine learning libraries (e.g., TENSORFLOW (registered trademark), PyTorch)

[0067] The device records the user's behavior data and sends it to the server, and also receives suggestions for next actions sent from the server and displays them to the user.

[0068] Hardware: User's device (e.g. smartphone, computer)

[0069] Software: web browser, mobile application

[0070] Specific operation of the system

[0071] 1. Collection of access logs

[0072] The server collects real-time behavioral data of users who visit the advertiser's site, specifically recording information such as which pages users viewed and which keywords they searched for.

[0073] 2. Data storage

[0074] The server stores the collected access logs in a database, including user IDs, visit dates and times, viewed pages, and search keywords.

[0075] 3. Data Preprocessing

[0076] The server preprocesses the stored data, specifically cleaning the data (filling in missing values ​​and removing outliers) and normalizing (scaling) the data.

[0077] 4. Training the AI ​​model

[0078] The server uses the preprocessed data to train a generative AI model using machine learning libraries such as TensorFlow and PyTorch.

[0079] 5. Generate the next action

[0080] The server uses the trained AI model to generate the next action based on the user's initial behavior, specifically predicting which page the user should be directed to next and which product to recommend.

[0081] 6. Submit your proposal

[0082] The server then sends the generated next action to the user's device, which then suggests appropriate pages and products to the user.

[0083] Specific examples

[0084] Suppose a user visits an advertiser's website and views a page for a specific smartphone model. The device records this behavior and sends it to the server. The server stores this data in a database, preprocesses it, and trains a generative AI model. The trained AI model determines that the user should next be directed to a page for smartphone accessories and related products, and sends this suggestion to the device. The device displays the suggestion to the user, who then views the suggested page.

[0085] Prompt Sentence Examples

[0086] "When a user visits an advertiser's website and views a specific product page, please build an AI model that will determine which page to direct them to next and which product to recommend. Specifically, this is a system that will suggest the next action that will lead to a sale based on the user's initial behavioral data."

[0087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0088] Step 1:

[0089] Collection of access logs

[0090] The server collects real-time behavioral data of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavioral data, and the output is the collected access log.

[0091] Step 2:

[0092] Data storage

[0093] The server stores the collected access logs in a database. The stored data includes the user ID, visit date and time, viewed pages, search keywords, etc. The collected access logs are the input, and the access logs stored in the database are the output.

[0094] Step 3:

[0095] Data Preprocessing

[0096] The server preprocesses the stored data. Specifically, it cleans the data (fills in missing values ​​and removes outliers), normalizes the data (scales it), etc. The input is the access log stored in the database, and the output is the preprocessed data.

[0097] Step 4:

[0098] Training an AI model

[0099] The server uses the preprocessed data to train a generative AI model. For training, it uses machine learning libraries such as TensorFlow and PyTorch. The input is the preprocessed data, and the output is a trained generative AI model.

[0100] Step 5:

[0101] Generate the next action

[0102] The server uses the trained AI model to generate the next action based on the user's initial behavior. Specifically, it predicts which page the user should be directed to next and which product should be recommended. The input is the user's initial behavior data, and the output is the generated next action.

[0103] Step 6:

[0104] Submit a proposal

[0105] The server sends the generated next action to the user's device, which then suggests appropriate pages or products to the user. The input is the generated next action, and the output is the suggestion sent to the user's device.

[0106] Step 7:

[0107] Receiving and Viewing Suggestions

[0108] The terminal receives the next action suggestions sent from the server and displays them to the user. The input is the suggestion sent from the server, and the output is the suggestion displayed to the user.

[0109] Step 8:

[0110] User Behavior

[0111] The user accepts the suggestion displayed on the device and performs the next action, such as viewing the suggested product page or purchasing the recommended product. The input is the suggestion displayed on the device, and the output is new behavioral data of the user.

[0112] (Application example 1)

[0113] Next, a description will be given of Application Example 1 of Embodiment 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."

[0114] On conventional advertiser sites, it was difficult to appropriately suggest the next action that would lead to a sale based on the user's initial behavior. As a result, it was not possible to stimulate the user's desire to purchase, and it was not possible to expect an improvement in the sale rate. In addition, it was not possible to provide an optimized site user experience for each user, which meant it was not possible to improve user satisfaction.

[0115] 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.

[0116] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial actions of users who visit the advertiser's site, means for dynamically changing the site user experience based on the suggestions, and means for analyzing the user's initial actions and suggesting in real time which product to view next and which page to proceed to. This makes it possible to appropriately suggest next actions that lead to a contract based on the user's initial actions, which is expected to improve the contract rate and user satisfaction.

[0117] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[0118] An "access log" is data that records the behavioral history of users when they access a website, and includes information such as page views and search keywords.

[0119] "Artificial intelligence" is a technology that allows computer systems to mimic human intelligence in learning and reasoning, giving them the ability to perform specific tasks automatically.

[0120] "User initial actions" are the first actions a user takes when visiting a website, such as accessing a specific product page or searching for a specific keyword.

[0121] "Conclusion" refers to a user purchasing a product or service on the website, meaning that the transaction is concluded.

[0122] "Next Action" refers to the next action a user should take on a website, suggesting actions that are more likely to lead to a sale.

[0123] "Site user experience" refers to the overall experience a user has when using a website, including ease of use and satisfaction.

[0124] "Dynamic change" refers to changing the content and structure of a website in real time in response to user behavior and circumstances.

[0125] "Real-time suggestions" refers to instantly analyzing user behavior and immediately suggesting the next action based on the results.

[0126] The system for implementing this invention constructs an artificial intelligence that learns from the access logs of advertiser sites and generates user actions that lead to sales. A specific embodiment of this system will be described below.

[0127] System configuration

[0128] The system consists of the following main components:

[0129] 1. Server: Collects access logs from advertiser sites and stores them as learning data.

[0130] 2. Artificial Intelligence (AI): Generates and suggests next actions based on the user's initial behavior.

[0131] 3. User Device: The device through which a user accesses an advertiser's site (e.g., smartphone, tablet, PC).

[0132] 4. Database: Data storage for storing access logs and user behavior data.

[0133] Program processing

[0134] Data collection and learning

[0135] The server collects access logs of users who visit the advertiser's site. These access logs include information such as which pages users viewed and what keywords they searched for. The collected data is stored in a database and used by the AI ​​as learning data.

[0136] User behavior analysis

[0137] The AI ​​analyzes the collected access logs and learns the initial behavioral patterns of users, generating a model that predicts what actions users should take to close a deal.

[0138] Suggested next actions

[0139] When a user visits an advertiser's website, AI analyzes the user's initial behavior in real time and suggests which products to view next and which pages to go to. These suggestions are displayed on the user's device to guide the user's actions.

[0140] Hardware and software used

[0141] Hardware: Servers, user devices (smartphones, tablets, PCs)

[0142] Software: Python, Pandas, Scikit-learn, database management system (e.g., MySQL)

[0143] Specific examples

[0144] For example, if a user views "Product A page" on an advertiser's website, gets 5 page views, and searches for "special price," AI will suggest that the user should next view "Product B page." This suggestion increases the user's desire to purchase and contributes to improving the conversion rate.

[0145] Prompt Sentence Examples

[0146] If a user views Product A's page, has 5 page views, and their search keyword is "Special Offer," predict which page they will view next.

[0147] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[0148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] The server collects access logs of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavior data, and the output is access log data.

[0151] Step 2:

[0152] The server saves the collected access log data in a database. The input is the access log data, and the output is the log data saved in the database. Specifically, the data is stored using a database management system (e.g., MySQL).

[0153] Step 3:

[0154] The server provides the access log data stored in the database to the artificial intelligence to use as training data. The input is the access log data obtained from the database, and the output is a trained artificial intelligence model. Specifically, the data is preprocessed using Python's Pandas library, and the model is trained using the Scikit-learn library.

[0155] Step 4:

[0156] When a user accesses an advertiser's website, the device sends the user's initial behavior data to the server. The input is the user's initial behavior data, and the output is the data sent to the server. Specifically, the device captures the user's behavior in real time and sends it to the server.

[0157] Step 5:

[0158] The server inputs the received initial behavior data into the AI ​​to predict the next action. The input is the user's initial behavior data, and the output is a proposal for the next action. Specifically, the data is input into a trained AI model to obtain a prediction result.

[0159] Step 6:

[0160] The server sends the predicted next action to the user's device. The input is the prediction result, and the output is a suggestion to be displayed on the user's device. Specifically, the server formats the prediction result and sends it to the user's device.

[0161] Step 7:

[0162] The user's device displays the received proposal to the user. The input is the proposal sent from the server, and the output is the information displayed to the user. Specifically, the proposal content is displayed in the user interface.

[0163] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[0164] Example 2

[0165] Next, a description will be given of Example 2 of Form 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."

[0166] On conventional advertiser sites, it was difficult to effectively utilize user behavior data to provide an optimized user experience (UX) for each individual user. As a result, there was an issue of insufficient improvement in conversion rates. In particular, it was not possible to dynamically change the content displayed on the site based on the user's initial behavior, making it difficult to respond to the different needs of each user.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0168] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, and a means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visited the advertiser's site. This enables a system that includes a means for collecting user behavior data and saving the generated actions in a database, and a means for acquiring the generated actions when the user visits the site again and dynamically changing the display content. This makes it possible to provide an optimized UX for each user and improve the conversion rate.

[0169] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[0170] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as page views, clicks, and length of stay.

[0171] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and is particularly used to analyze user behavior data and generate optimal actions.

[0172] "User action" refers to a specific operation or action a user takes on a website, such as clicking on an item, adding it to a cart, or purchasing it.

[0173] "User experience (UX)" refers to the overall experience and satisfaction a user feels when using a website, and is influenced by factors such as the site's ease of use, design, and the quality of the information provided.

[0174] "Dynamic change" refers to changing the content and functionality of a website in real time in order to provide optimal information according to the user's behavior and situation.

[0175] "Behavioral data" refers to data about a series of actions or behaviors a user performs on a website, including browsing history, click patterns, purchase history, etc.

[0176] A "database" is a system for efficiently storing, managing, and retrieving data, and is used to store generated action and user behavior data.

[0177] "Generated actions" refers to the next optimal action or suggestion generated by artificial intelligence after analyzing user behavioral data.

[0178] "Displayed Content" refers to the information and content displayed to users on a website, including text, images, videos, links, etc.

[0179] The present invention is a system for dynamically optimizing the user experience (UX) of an advertiser's site. A specific embodiment of this system will be described below.

[0180] System Overview

[0181] This system consists of three main elements: a server, a device, and a user. The server collects user behavior data and generates optimal actions using a generative AI model. The device obtains the actions generated by the server when a user visits the site and dynamically changes the displayed content. The user experiences an optimized UX by visiting the site.

[0182] Hardware and software used

[0183] Server: Use a high-performance server machine (e.g., AWS (registered trademark) EC2 instance).

[0184] Database: Use a relational database such as MySQL or PostgreSQL.

[0185] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[0186] Analytics tools: We use user behavior analytics tools such as Google Analytics and Mixpanel.

[0187] Data processing and calculation

[0188] The server collects user behavior data (e.g., browsing history, click patterns, purchase history, etc.) in real time. The collected data is stored in a database. The server then inputs prompt statements into a generative AI model to generate optimal actions. The generated actions are stored in the database, and when the user visits the site again, the device retrieves them and dynamically changes the displayed content.

[0189] Specific examples

[0190] For example, if a user visits an online shopping site and frequently browses pages about sporting goods, the server might input the following prompts into the generative AI model:

[0191] Recommend the best product for this user.

[0192] The generative AI model analyzes the input data and generates an action, "recommend sporting goods." The server stores this action in a database, and the device retrieves it when the user visits the site again. The device then displays a banner for sporting goods on the homepage based on the retrieved action.

[0193] In this way, we can provide an optimized UX for each user and improve conversion rates.

[0194] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0195] Step 1:

[0196] A user visits the site.

[0197] Input: The user opens a browser and enters the URL of the advertiser's site.

[0198] Output: A user visits the site and some initial behavioral data is generated.

[0199] Specific behavior: A user visits an online shopping site and the homepage is displayed.

[0200] Step 2:

[0201] The server collects user behavior data.

[0202] Input: Behavioral data such as user browsing history, click patterns, and purchase history.

[0203] Output: Collected behavioral data is stored in a database.

[0204] Specific operation: The server uses analytical tools such as Google Analytics and Mixpanel to collect user behavior data in real time and store it in a database.

[0205] Step 3:

[0206] The server inputs prompt statements into the generative AI model and generates the optimal action.

[0207] Input: Collected behavioral data and a prompt (e.g., "Recommend the best product for this user").

[0208] Output: The optimal action obtained from the generative AI model.

[0209] Specific operation: Based on the collected behavioral data, the server inputs a prompt statement such as "Recommend the best product for this user" into the generative AI model (e.g., GPT-4) and generates the optimal action.

[0210] Step 4:

[0211] The server saves the generated action in the database.

[0212] Input: The optimal action obtained from the generative AI model.

[0213] Output: Actions stored in the database.

[0214] Specific operation: The server stores the generated actions in a database such as MySQL or PostgreSQL.

[0215] Step 5:

[0216] The terminal acquires the generated action from the server when the user visits.

[0217] Input: The request when the user returns to the site.

[0218] Output: The generated actions retrieved from the server.

[0219] Specific operation: When the user visits the site again, the device sends a request to the server and retrieves the generated action.

[0220] Step 6:

[0221] Dynamically change the display content based on the actions taken by the device.

[0222] Input: The generated action retrieved from the server.

[0223] Output: The dynamically changed display content.

[0224] Specific behavior: The device dynamically changes the content displayed based on the action taken, such as displaying a sports goods banner on the home page.

[0225] Step 7:

[0226] Users experience an optimized UX.

[0227] Input: Dynamically changed display content.

[0228] Output: Improved user satisfaction and higher conversion rates.

[0229] What it does: By simply visiting the site, users experience a personalized UX, with sporting goods information displayed first.

[0230] (Application example 2)

[0231] Next, a description will be given of Application Example 2 of Form 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."

[0232] On traditional advertiser sites, it was difficult to provide an optimal user experience for each user, making it difficult to improve conversion rates. Furthermore, there was a lack of effective ways to utilize users' past purchase and browsing histories, making it impossible to recommend appropriate products to users. This resulted in a failure to attract users' interest, resulting in a lower conversion rate.

[0233] 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.

[0234] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visit the advertiser's site, means for dynamically changing the user experience of the site based on the suggestions, and means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions. This makes it possible to provide an optimal user experience for each user and improve the conversion rate.

[0235] "Advertiser Site" means a website that displays advertisements and an online platform that users can visit to view and purchase products and services.

[0236] An "access log" is data that records the behavioral history of a user when they visit a website, and includes information such as the date and time of the visit, the pages viewed, and the links clicked.

[0237] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn, reason, and make decisions, particularly with the ability to analyze user behavior patterns and generate the next action.

[0238] "User experience" refers to the overall experience a user has when using a website or application, and includes factors such as ease of use, satisfaction, and convenience.

[0239] "Purchase history" is a record of products and services purchased by a user in the past, and includes information such as the purchase date and time, product name, and price.

[0240] "Browsing history" refers to a record of the pages and products a user has viewed on a website, including the date and time of the viewing, the pages viewed, and information about the products viewed.

[0241] "Dynamic change" refers to changing the content and functions of a website in real time according to the user's behavior and situation, and flexibly changing from a fixed display.

[0242] The "conversion rate" is an indicator that shows the percentage of users who actually purchase products or services among those who visit a website, and is an important indicator for measuring the effectiveness of marketing and sales.

[0243] A system for implementing this invention includes a means for learning the access log of an advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that will lead to a contract based on the initial behavior of a user who visits the advertiser's site, a means for dynamically changing the user experience of the site based on the suggestions, and a means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions.

[0244] System configuration

[0245] The server uses the following hardware and software:

[0246] Hardware: A server with a powerful processor, sufficient memory, and storage

[0247] Software: Python, API request library (requests), API for generative AI models

[0248] Data processing and calculation

[0249] 1. Obtaining user information: When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history using an API request.

[0250] 2. Sending prompts to the generative AI model: The server sends the acquired user information as prompts to the generative AI model, which then generates the optimal action for the user (such as recommended products).

[0251] 3. Dynamically changing the site content: The server dynamically changes the site content based on the generated action. Specifically, the recommended products are reflected in the site content.

[0252] Specific examples

[0253] For example, if a user has previously purchased "smartphone accessories" and recently browsed "smartwatches," the generative AI model will generate an action that recommends "smartwatch accessories."

[0254] Prompt Sentence Examples

[0255] User's past purchase history: Smartphone accessories, browsing history: Smartwatch

[0256] By sending this prompt to a generative AI model, the most appropriate product recommendation for each user is made, providing an optimal user experience and improving conversion rates.

[0257] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0258] Step 1:

[0259] When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history.

[0260] Input: User ID

[0261] Data processing: Use API requests to retrieve user purchase and browsing history.

[0262] Output: User purchase and browsing history data

[0263] Step 2:

[0264] The server sends the acquired user information to the generative AI model as a prompt.

[0265] Input: User purchase and browsing history data

[0266] Data calculation: Convert user information into a text prompt and send it to the API of the generative AI model.

[0267] Output: Recommended actions from the generative AI model (e.g., recommended products)

[0268] Step 3:

[0269] The server dynamically changes the content displayed on the site based on the generated actions.

[0270] Input: Recommended actions from a generative AI model

[0271] Data processing: Obtain site content data and update it to prioritize the display of recommended products.

[0272] Output: Updated site content data

[0273] Step 4:

[0274] When a user visits a site, the user views dynamically changed display content.

[0275] Input: Updated site content data

[0276] Data Calculation: Display the updated content in the user's browser.

[0277] Output: User-optimized display

[0278] Step 5:

[0279] The server records the user's new behavior data in the access log.

[0280] Input: User behavior data (e.g. clicks, pages viewed)

[0281] Data processing: Add new behavioral data to the access log.

[0282] Output: Updated access log

[0283] Example 3

[0284] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0285] On conventional advertiser sites, it was difficult to fully understand users' behavioral patterns and propose optimal actions. As a result, there were problems with low conversion rates and insufficient advertising effectiveness. Furthermore, it was not possible to make proposals optimized for each user, making it difficult to meet the needs of individual users.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0287] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for building a generative AI model that learns user behavior patterns using the preprocessed data, means for generating a next action based on the learned behavior pattern, means for sending the generated action to the terminal, means for the user to take action based on the action displayed on the terminal, and means for recording the action again as an access log. This makes it possible to accurately understand user behavior patterns and propose actions optimized for each user.

[0288] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[0289] An "access log" is data that records the behavioral history of users when they visit a website, including actions such as page views, clicks, and purchases.

[0290] A "database" is a system for storing collected access logs, and includes relational databases, NoSQL databases, etc.

[0291] "Preprocessing" refers to the process of preparing the collected access logs in a format that is easy to analyze, and includes data cleaning and normalization.

[0292] A "generative AI model" is a model that uses machine learning algorithms to learn user behavior patterns and predict their next actions.

[0293] An "action" is what the user should do next, such as purchasing a particular product or visiting a particular page.

[0294] "Terminal" refers to a device used by a user, including a PC, smartphone, tablet, etc.

[0295] "Behavioral patterns" refer to the tendency of a series of actions that a user takes on a website, and are learned from past access logs.

[0296] "Suggestion" refers to the next action that the generative AI model suggests to the user based on the behavioral patterns it has learned.

[0297] "Conversion rate" refers to the percentage of users who take a suggested action and actually achieve their goal, such as purchasing a product.

[0298] This invention is a system that collects access logs from advertiser sites, learns user behavior patterns, and then generates and suggests optimal next actions to users. Specific embodiments of this system are described below.

[0299] Server Processing

[0300] The server collects access logs for the advertiser's website. The access logs include information such as the pages visited by users, the links clicked, and the products purchased. This data is collected using web server logs such as Apache (registered trademark) and Nginx.

[0301] The server then stores the collected access logs in a relational database such as MySQL or PostgreSQL, and the stored data includes user IDs, visited pages, and action timestamps.

[0302] The stored access logs are subjected to preprocessing such as data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This process is often performed using the Python Pandas library.

[0303] Using the preprocessed data, the server builds a generative AI model, which is built using machine learning frameworks such as TensorFlow and PyTorch. The model learns user behavior patterns from past access logs and predicts the next action to be taken.

[0304] Based on the learned behavioral patterns, the server generates the next optimal action for the user. For example, if a user visits a specific product page, it will suggest the next product they are likely to purchase. This suggestion is made in real time using a generative AI model.

[0305] The generated actions are sent to the terminal in JSON format via the REST API.

[0306] Terminal handling

[0307] The device receives the optimal action sent from the server and presents it to the user, for example, as a pop-up on a web page or by sending an email notification.

[0308] User Action

[0309] The user checks the next action displayed on the device and purchases the product if necessary. The user's response is also recorded as an access log and will be used for the next learning.

[0310] Specific examples

[0311] For example, suppose a user visits the "Smartphone A" page on an advertiser's website. The server studies past access logs and knows that users who visit "Smartphone A" are highly likely to purchase "Smartphone Case B." In this case, the server suggests to the user that they purchase "Smartphone Case B" as their next action.

[0312] Prompt Sentence Examples

[0313] "If a user visits the page on smartphone A, please suggest the next product they are likely to purchase."

[0314] In this way, a system is realized in which the server, the terminal, and the user work together to generate optimal actions based on the user's behavioral patterns and present them to the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0315] Step 1:

[0316] The server collects access logs for the advertiser's website, specifically recording actions taken by users on the website, such as page views, clicks, and purchases. The input includes user behavior data, and the output is stored in a log file.

[0317] Step 2:

[0318] The server stores the collected access logs in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input includes the collected access logs, and the output is structured data stored in the database.

[0319] Step 3:

[0320] The server preprocesses the stored access logs. Specifically, it performs data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This processing is performed using the Python Pandas library. The input includes the raw data stored in the database, and the output is the preprocessed, clean data.

[0321] Step 4:

[0322] The server uses the preprocessed data to build a generative AI model that learns user behavior patterns. Specifically, it trains a neural network using a machine learning framework such as TensorFlow or PyTorch. The input includes the preprocessed data, and the output is a trained generative AI model.

[0323] Step 5:

[0324] The server generates the next action based on the learned behavioral patterns. Specifically, it uses a generative AI model to predict the next action the user should take. The inputs include the trained generative AI model and real-time user behavior data, and the output is the optimal next action.

[0325] Step 6:

[0326] The server sends the generated action to the device. Specifically, it sends data in JSON format via a REST API. The input contains the generated action, and the output is the action data sent to the device.

[0327] Step 7:

[0328] The device then presents the optimal action received from the server to the user, for example, by displaying it as a pop-up on a web page or by sending an email notification. The input includes the action data sent from the server, and the output is the action presented to the user.

[0329] Step 8:

[0330] The user checks the next action displayed on the terminal and purchases the product if necessary. Specifically, the user purchases the product on the website according to the presented action. The input includes the action displayed on the terminal, and the output is the user's purchasing behavior.

[0331] Step 9:

[0332] The server records the user's response again as an access log. Specifically, it saves the user's actions as a new access log. The input contains the user's behavior data, and the output is an updated access log.

[0333] (Application example 3)

[0334] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0335] Conventional ad delivery systems were unable to fully grasp user behavior patterns, making it difficult to display the right ad at the right time. As a result, they were unable to attract user interest and could not expect to improve conversion rates. In addition, because ads were not displayed in an optimized format for each user, there was a problem of reduced advertising effectiveness.

[0336] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for learning the access log of the advertiser site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that lead to a contract based on the initial behavior of a user who visited the advertiser site, a means for dynamically changing the site user experience based on the suggestions, and a means for learning the user's past website visit history and displaying advertisements that are likely to interest the user in real time. This makes it possible to grasp the user's behavioral patterns in detail and display appropriate advertisements at the optimal timing.

[0337] "Advertiser Site" means a website for displaying advertisements and an online platform intended for users to visit.

[0338] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as the pages visited and the length of time spent on the website.

[0339] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and has the ability to analyze user behavior patterns and generate the next action.

[0340] "User experience" refers to the experiences and feelings that users have when using a website or application, and affects the ease of use and satisfaction of the site.

[0341] "Dynamic change" means changing the content and layout of a website in real time according to the user's behavior and situation, providing an optimized display for each user.

[0342] "Website visit history" refers to a record of websites a user has visited in the past, including information such as pages visited, time spent there, and links clicked.

[0343] "Displaying in real time" means instantly displaying ads or content based on the user's current behavior and situation, providing information without delay.

[0344] The system for carrying out this invention learns access logs of advertiser sites, analyzes user behavior patterns, and displays optimal advertisements in real time. A specific embodiment of this system will be described below.

[0345] The server first collects access logs from the advertiser's website and stores them in a database. These access logs include information such as the pages visited by users, the time spent there, and the links clicked. The server then uses these access logs to build an artificial intelligence model to learn user behavior patterns. This model is trained using Python libraries such as pandas and scikit-learn.

[0346] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time and generates the next optimal action to take. This action is to display an advertisement that the user is likely to be interested in. The server references the user's past website visit history and selects the most appropriate advertisement based on information such as the pages the user previously visited and the length of time they spent there.

[0347] For example, if a user previously visited a specific fashion brand's website and stayed on a specific product page for 120 seconds, the server would prioritize displaying new products and sales information from the same brand to that user. In this way, ads are displayed that are optimized for each user, which is expected to improve conversion rates.

[0348] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to generate advertisements based on user behavior patterns.

[0349] Example prompt sentence:

[0350] Predict the next ad to display based on the user's history of previously visited websites. For example, if a user visits the website of "Fashion Brand A" and stays on a specific product page for 120 seconds, display information about new products and sales from "Fashion Brand A" to that user.

[0351] This system makes it possible to grasp user behavior patterns in detail and display appropriate advertisements at the optimal time, which is expected to improve advertising effectiveness and conversion rates.

[0352] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0353] Step 1:

[0354] The server collects access logs for the advertiser's website and stores them in a database. It receives information such as the pages visited by the user, the time spent there, and the links clicked as input, and stores this data in the database. Specifically, the web server collects access logs in real time and stores them in a database management system (e.g., MySQL or PostgreSQL).

[0355] Step 2:

[0356] The server uses the collected access logs to build an AI model to learn user behavior patterns. As input, it uses the access logs stored in the database and processes the data to extract features (for example, number of page visits, average length of stay, etc.). As output, it generates a trained AI model. Specifically, it preprocesses the data using Python's pandas and trains the model using scikit-learn's RandomForestClassifier, etc.

[0357] Step 3:

[0358] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time. As input, it receives the user's current behavior data (pages visited, time spent, etc.) and inputs this into the artificial intelligence model that was previously constructed. As output, it generates the next optimal action to be taken (the advertisement to be displayed). Specifically, it inputs the data collected in real time into the model and obtains the predicted results.

[0359] Step 4:

[0360] The server references the user's past website visit history and selects advertisements that are likely to interest the user. The server uses the user's past visit history data as input and processes the data by analyzing past behavioral patterns. The output is the selection of the most suitable advertisement. Specifically, it retrieves past visit history from a database and analyzes it using an artificial intelligence model.

[0361] Step 5:

[0362] The server displays the selected advertisement to the user in real time. It uses the selected advertisement data as input and displays the advertisement on the user's screen as output. Specifically, it dynamically changes the content of the web page to insert the advertisement.

[0363] Step 6:

[0364] The server again collects user responses after the ad is displayed as an access log and stores it in a database. It receives user response data to the ad (clicks, time spent, etc.) as input and stores this in the database. Specifically, the web server collects user responses in real time and stores them in a database management system.

[0365] This series of processes allows for a detailed understanding of user behavior patterns and enables the display of appropriate advertisements at optimal times, which is expected to improve advertising effectiveness and conversion rates.

[0366] 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.

[0367] "Example 1"

[0368] One embodiment of the present invention is a system that incorporates an emotion engine. This system combines an AI (UX generation AI) that learns from the access logs of advertisers' websites and generates the next action that leads to a sale based on the user's initial behavior (UX generation AI), with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine infers the user's emotions from their actions and reactions when visiting the website, and the UX generation AI generates the next action based on those emotions. For example, if the emotion engine detects the user's excitement while browsing a product page, the UX generation AI takes that excitement into account and generates an action, such as highlighting the "Buy Now" button. This provides a personalized UX that reflects the user's emotions, contributing to an improved conversion rate.

[0369] "Example 2"

[0370] Another embodiment of the present invention is a system in which an emotion engine and a UX generation AI work together. In this system, the emotion engine recognizes a user's emotions in real time and feeds that information back to the UX generation AI. The UX generation AI generates the next action based on that feedback, dynamically changing the site's UX. For example, if the emotion engine detects a user's anxiety while reading a product review, the UX generation AI generates an action to alleviate that anxiety, such as highlighting information about a "worry-free return guarantee." This provides a UX that responds to the user's emotions, improving user satisfaction and conversion rates.

[0371] "Example 3"

[0372] Furthermore, another embodiment of the present invention is a system that combines an emotion engine and a UX generation AI. In this system, the emotion engine recognizes the user's emotions, and the UX generation AI generates the next action based on those emotions. Specifically, the emotion engine infers the user's emotions from their actions and reactions when visiting a website, and the UX generation AI generates the next action based on those emotions. For example, if the emotion engine detects the user's state of excitement while viewing a product page, the UX generation AI takes that state of excitement into account and generates an action, such as highlighting the "Buy Now" button. This provides a personalized UX that corresponds to the user's emotions, contributing to an improvement in the conversion rate.

[0373] The processing flow of each embodiment will be described below.

[0374] "Example 1"

[0375] Step 1: A user visits an advertiser's site.

[0376] Step 2: The emotion engine infers emotions from the user's actions and reactions.

[0377] Step 3: UX generation AI generates the next action based on the emotional information from the emotion engine.

[0378] Step 4: The site dynamically changes the UX based on the action generated.

[0379] "Example 2"

[0380] Step 1: A user visits an advertiser's site.

[0381] Step 2: The emotion engine recognizes the user's emotions in real time.

[0382] Step 3: The emotional information recognized by the emotion engine is fed back to the UX generation AI.

[0383] Step 4: UX Generation AI generates next actions based on feedback and dynamically changes the site's UX.

[0384] "Example 3"

[0385] Step 1: A user visits an advertiser's site.

[0386] Step 2: The emotion engine infers emotions from the user's actions and reactions.

[0387] Step 3: UX generation AI generates the next action based on the emotional information from the emotion engine.

[0388] Step 4: The site dynamically changes the UX based on the action generated.

[0389] Example 1

[0390] Next, a description will be given of Example 1 of Form 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."

[0391] Conventional advertiser sites generate next actions based solely on user behavioral data, making it difficult to provide personalized suggestions that take user emotions into account. As a result, improvements in conversion rates have been limited. The present invention aims to combine user behavioral data and emotional data to generate more accurate next actions and improve conversion rates.

[0392] 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.

[0393] In this invention, the server includes means for collecting user behavioral data, means for collecting user emotion data, means for transmitting the collected behavioral data and emotion data to the server, means for cleansing and preprocessing the transmitted data, means for training an AI model using the preprocessed data, means for inferring the user's next action in real time using the trained AI model, and means for displaying the inferred action to the user, thereby enabling personalized suggestions that combine the user's behavioral data and emotion data.

[0394] "User behavior data" refers to information about actions users take on a website, such as clicks, page transitions, and search keywords.

[0395] "User emotion data" refers to information about the user's emotional state estimated from their facial expressions and voice.

[0396] "Server" means a computer system for collecting, processing, and storing user behavioral and emotional data, and for training and running AI models.

[0397] "Cleansing" is the process of removing missing values ​​and outliers from collected data and shaping the data.

[0398] "Preprocessing" is the process of converting data into a format suitable for training an AI model.

[0399] An "AI model" is an artificial intelligence algorithm that infers the next action based on a user's behavioral and emotional data.

[0400] "Training" is the process of training an AI model using large amounts of data to learn and improve its prediction accuracy.

[0401] "Real-time inference" is the process of instantly analyzing user behavioral and emotional data and instantly generating the next action.

[0402] "Personalized suggestions" are suggestions optimized for each user, generated based on the user's individual behavioral and emotional data.

[0403] MODE FOR CARRYING OUT THE INVENTION

[0404] The present invention is a system that learns access logs from advertiser sites and generates the next action based on user behavioral and emotional data. This system collects user behavioral and emotional data, sends it to a server for processing, and makes personalized suggestions.

[0405] server

[0406] The server is a computer system that collects, processes, and stores user behavioral and emotional data. Specifically, the server uses Apache Hadoop to distribute large amounts of access log data, cleansing and preprocessing the data. Next, TensorFlow is used to train an AI model (UX generation AI) that generates the next action that leads to a sale based on the user's initial behavior. This AI model analyzes user behavior, such as accessing a specific product page or searching for specific keywords, and determines which page to direct the user to next and which product to recommend.

[0407] Terminal

[0408] The device collects user behavior data in real time when the user visits an advertiser's website. Specifically, it uses JavaScript (registered trademark) to collect data such as user clicks, page transitions, and search keywords, and sends this data to a server. The device also has an emotion engine that estimates emotions from the user's facial expressions and voice. For example, it combines OpenCV and TensorFlow to analyze the user's facial expressions and determine whether the user is excited.

[0409] User

[0410] A user visits an advertiser's site and views a specific product page or searches for a specific keyword. The user's behavioral and emotional data is collected in real time and sent to the server. Based on this data, the server uses UX generation AI to generate the next action and make personalized suggestions to the user. For example, if a user is detected to be excited while browsing a product page, the server generates an action such as highlighting the "Buy Now" button.

[0411] Specific examples

[0412] Example 1

[0413] When a user visits an advertiser's website and accesses a specific product page, the device collects this behavioral data and sends it to the server, which then uses UX generation AI to suggest related product pages that the user might be interested in next.

[0414] Example 2

[0415] A user searches for a specific keyword on an advertiser's website. The device collects this search data and sends it to a server. The server then uses UX generation AI to recommend products related to the user's searched keyword.

[0416] Example 3

[0417] When a user is browsing a product page, the emotion engine detects the user's excitement, and the server uses this information to generate an action for the UX generation AI to highlight the "Buy Now" button.

[0418] Prompt Sentence Examples

[0419] "Build an AI model that generates next actions based on a user's initial behavior using access logs from advertisers' websites. Design a system that collects user behavioral and emotional data in real time and makes personalized suggestions."

[0420] In this way, by explaining the system processing from the perspectives of the server, terminal, and user, the role and specific operation of each component becomes clear.

[0421] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0422] Step 1:

[0423] The terminal collects user behavior data when the user visits an advertiser's site. Specifically, JavaScript (registered trademark) is used to obtain data such as user clicks, page transitions, and search keywords in real time. The input is user operation data, and the output is collected behavior data. When a user searches for "smartphone," this behavior data records the search keyword and search time.

[0424] Step 2:

[0425] The device also collects user emotion data. Specifically, it uses the device's built-in camera and microphone to analyze the user's facial expressions and voice. By combining OpenCV and TensorFlow, it infers emotions from the user's facial expressions and evaluates the intensity of the emotions through voice analysis. The input is the user's facial and voice data, and the output is the analyzed emotion data. For example, if a user smiles while browsing a product page, the degree of their smile is recorded.

[0426] Step 3:

[0427] The device sends the collected behavioral data and emotional data to the server. The input is the collected behavioral data and emotional data, and the output is the data sent to the server. For example, if a user searches for "smartphone" and smiles while doing so, that information is sent to the server.

[0428] Step 4:

[0429] The server cleanses and preprocesses the transmitted data. Specifically, it complements missing values, removes outliers, and converts the data into a format suitable for AI model learning. The input is the transmitted behavioral and emotional data, and the output is the preprocessed data. For example, if the user's search keywords are incomplete, it performs a process to complement them.

[0430] Step 5:

[0431] The server uses the preprocessed data to train a UX generation AI model using TensorFlow. The input is the preprocessed data, and the output is the trained AI model. This model generates next actions that lead to a sale based on the user's initial behavior. For example, if a user searches for "smartphone," the model learns to recommend "smartphone accessories" next.

[0432] Step 6:

[0433] The server uses a trained UX generation AI model to infer the user's next action in real time. The input is the user's behavioral and emotional data, and the output is the inferred next action. Specifically, the server uses the behavioral and emotional data from when the user visited the site as input to determine which page to direct them to next and which product to recommend. For example, if a user searches for "smartphone" and an excited state is detected, the server generates an action to highlight the "Buy Now" button.

[0434] Step 7:

[0435] The device displays the next action received from the server to the user. The input is the next action sent from the server, and the output is a personalized suggestion displayed to the user. Specifically, the suggestion generated based on the user's behavioral and emotional data is reflected on the webpage. For example, the "Buy Now" button is highlighted, or a banner recommending related products is displayed.

[0436] (Application example 1)

[0437] Next, a description will be given of Application Example 1 of Embodiment 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."

[0438] Conventional advertising systems can suggest the next action based on user behavior data, but they cannot make personalized suggestions that take user emotions into account, limiting their ability to improve conversion rates. Furthermore, they do not dynamically change the site user experience based on user emotions, making it difficult to maximize user interest and attention.

[0439] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for learning the access log of the advertiser site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting a next action that will lead to a contract based on the initial behavior of a user who visited the advertiser site, a means for combining an emotion engine that recognizes the user's emotions, and a means for dynamically changing the site user experience based on the suggestion. This makes it possible to integrate user behavioral data and emotion data to generate the next action and make personalized suggestions that are optimized for each user.

[0440] An "advertiser site" is a website operated by a company or organization that places advertisements.

[0441] An "access log" is data that records the behavioral history of users when they visit a website.

[0442] "Artificial intelligence" is a technology that allows computers to learn and reason by imitating human intelligence.

[0443] "User actions" refer to specific operations or actions that users take on a website.

[0444] "Initial actions" refers to the first action or behavior a user takes when visiting a website.

[0445] An "emotion engine" is a technology for inferring emotions from a user's actions and reactions.

[0446] "Site user experience" refers to the experience and satisfaction a user feels when using a website.

[0447] "Dynamic change" refers to changing the content and display of a website in real time in response to user behavior and emotions.

[0448] "Conversion rate" refers to the percentage of users who visit a website and actually purchase a product or use a service.

[0449] "Personalization" refers to providing optimal content and suggestions based on individual user characteristics and behavior.

[0450] The system for implementing this invention learns access logs from advertiser sites, integrates user behavior data and emotion data, and generates the next action. A specific embodiment of this system will be described below.

[0451] System Configuration

[0452] Hardware

[0453] Server: A high-performance server for collecting, learning, and analyzing data.

[0454] User device: The device used by the user, such as a smartphone, tablet, or computer.

[0455] software

[0456] Artificial Intelligence (AI): An AI model that learns from user behavior data and generates the next action.

[0457] Emotion engine: Software for inferring emotions from user actions and reactions.

[0458] Database: A database for storing user behavioral and emotional data.

[0459] API: An interface for collecting user behavior data and sending it to a server.

[0460] Data processing and calculation

[0461] 1. Collecting User Behavior Data:

[0462] Behavioral data when users visit an advertiser's site (e.g., accessing a specific product page, searching for specific keywords, etc.) is collected through an API.

[0463] 2. Emotion Analysis:

[0464] The emotion engine is used to infer user emotions from collected behavioral data, such as detecting excitement levels from mouse movements and click frequency while users are browsing product pages.

[0465] 3. Generate the next action:

[0466] It uses artificial intelligence to generate next actions based on user behavioral and emotional data, such as highlighting the "Buy Now" button if the user is excited.

[0467] Specific examples

[0468] For example, if a user visits an advertiser's website on their smartphone and is viewing a specific product page, if the emotion engine detects the user's excitement, the AI ​​will generate an action to highlight the "Buy Now" button. This action is a personalized suggestion based on the user's emotions, contributing to an improved conversion rate.

[0469] Prompt Sentence Examples

[0470] If a user visits an advertiser's site and views a particular product page, and the emotion engine detects a state of excitement in the user, what action will the artificial intelligence generate?

[0471] In this way, the emotion-aware advertising assistant system can integrate user behavioral data and emotional data to generate the next action and make personalized suggestions optimized for each user.

[0472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0473] Step 1:

[0474] A user visits an advertiser's site. The user accesses the advertiser's site using a device such as a smartphone or PC. At this time, the user's behavioral data (e.g., access to a specific product page, search for specific keywords, etc.) is collected from the device. The input is the user's behavioral data, and the output is the collected behavioral data.

[0475] Step 2:

[0476] The device sends the collected behavioral data to the server. The device uses an API to send the collected behavioral data to the server. The input is the collected behavioral data, and the output is the behavioral data sent to the server.

[0477] Step 3:

[0478] The server stores the behavioral data in a database. The server stores the received behavioral data in a database. The input is the behavioral data sent to the server, and the output is the behavioral data stored in the database.

[0479] Step 4:

[0480] The server uses an emotion engine to estimate the user's emotions from the behavioral data. The server uses the emotion engine to analyze the user's emotions from the stored behavioral data. For example, it detects the user's excitement level from the mouse movements and frequency of clicks while the user is viewing a product page. The input is the behavioral data stored in the database, and the output is the estimated user's emotion data.

[0481] Step 5:

[0482] The server uses artificial intelligence to generate the next action. The server uses artificial intelligence to generate the next action based on the behavioral data and emotional data. For example, if the user is excited, it generates an action to highlight the "Buy Now" button. The input is the behavioral data and emotional data, and the output is the generated next action.

[0483] Step 6:

[0484] The server sends the generated next action to the terminal. The server sends the generated next action to the terminal. The input is the generated next action, and the output is the next action sent to the terminal.

[0485] Step 7:

[0486] The device dynamically changes the site user experience based on the next action. The device dynamically changes the display or operation of the site based on the next action it receives, for example, highlighting a "Buy Now" button. The input is the next action sent to the device, and the output is the dynamically changed site user experience.

[0487] Example 2

[0488] Next, a description will be given of Example 2 of Form 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."

[0489] Conventional advertiser sites can dynamically change the user experience (UX) by generating the next action based on user behavior data, but because the UX is not optimized with user emotions in mind, there are limitations to improving user satisfaction and conversion rates. Additionally, there is a lack of a system for providing the optimal UX for each user, making it difficult to provide a UX that meets the needs of each individual user.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0491] In this invention, the server includes: means for learning the access log of the advertiser's site; means for building artificial intelligence that generates user actions that lead to a contract; means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visit the advertiser's site; means for dynamically changing the site user experience based on the suggestions; an emotion recognition engine that recognizes user emotions in real time; and means for generating next actions based on feedback from the emotion recognition engine. This makes it possible to optimize UX by taking into account both user behavioral data and emotion data, providing an optimal UX for each user, and improving conversion rates and user satisfaction.

[0492] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[0493] An "access log" is a record of behavioral data when a user visits a website, and includes information such as page browsing history, click history, and length of stay.

[0494] "Artificial intelligence" is a technology that allows computers to learn and reason by imitating human intelligence, and generates the next action based on user behavioral and emotional data.

[0495] "User experience" refers to the experience and satisfaction a user feels when using a website, and is influenced by factors such as the site's design, functionality, and content quality.

[0496] An "emotion recognition engine" is a technology that recognizes emotions in real time from a user's facial expressions, voice, text input, etc., and is used to understand the user's emotional state.

[0497] "Feedback" refers to the process of returning information to the system to determine the next action based on the information it has obtained, and refers to sending emotional data from the emotion recognition engine to the artificial intelligence.

[0498] "Dynamic change" means changing the content and functionality of a website in real time based on the user's behavior and emotions, in order to provide the best possible experience for each user.

[0499] MODE FOR CARRYING OUT THE INVENTION

[0500] This invention is a system that dynamically changes the user experience (UX) of an advertiser's website, and generates the next action based on user behavioral data and emotional data. Specific embodiments of this system are described below.

[0501] Hardware and software used

[0502] Server: The server hosts the generative AI model and emotion recognition engine, which recognizes user emotions in real time and dynamically changes the UX.

[0503] Device: The device used by the user (PC, smartphone, tablet, etc.) receives the dynamic UX changes sent from the server.

[0504] Generative AI model: The generative AI model generates the next action based on the user's behavioral and emotional data.

[0505] Emotion Recognition Engine: The emotion recognition engine recognizes user emotions in real time and feeds that information back into the generative AI model.

[0506] Program processing

[0507] 1. User visit: A user visits the advertiser's site. For example, the user opens a browser and enters the advertiser's URL to access the site.

[0508] 2. Data Collection: The server collects user behavior data (clicks, scrolling, time spent, etc.), which gives information such as which pages users view and which links they click.

[0509] 3. Emotion Recognition: The emotion recognition engine recognizes users' emotions in real time, for example, detecting whether a user is feeling anxious from their facial expressions and tone of voice while reading a product review.

[0510] 4. Feedback: The server feeds back the emotion data recognized by the emotion recognition engine to the generative AI model. For example, it sends information that "the user is feeling anxious" to the generative AI model.

[0511] 5. Action Generation: The generative AI model generates the next action based on the feedback emotional and behavioral data. For example, if the user is feeling anxious, it generates an action to highlight the "Worry-Free Return Guarantee" information to alleviate that anxiety.

[0512] 6. UX Modification: Dynamically modify the site's UX based on the server-generated actions, for example dynamically modifying HTML and CSS to prioritize specific product information.

[0513] 7. Display: The device displays the new UX sent from the server. For example, the "No Worry Return Guarantee" information is highlighted on the page the user is viewing.

[0514] Specific examples

[0515] Example 1: When a user visits a site and is looking for a specific product, a generative AI model prioritizes displaying information about that product.

[0516] Example 2: If an emotion recognition engine detects anxiety while a user is reading a product review, a generative AI model will highlight information about the "worry-free return guarantee."

[0517] Prompt Sentence Examples

[0518] "Create an action that prioritizes the display of specific products when a user visits your site."

[0519] "If a user feels anxious while reading a product review, generate an action to alleviate that anxiety."

[0520] This system makes it possible to provide the optimal UX for each user, improving conversion rates and user satisfaction.

[0521] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0522] Step 1:

[0523] A user visits the site.

[0524] A user opens a browser and enters the advertiser's URL to access the site. The input is the user's access behavior, and the output is the site's homepage being displayed.

[0525] Step 2:

[0526] The server collects user behavior data.

[0527] The server collects user behavior data in real time, such as clicks, scrolls, and time spent on the site. The input is user behavior data, and the output is a log of the collected behavior data. Specifically, it records information such as which pages the user is viewing and which links they clicked.

[0528] Step 3:

[0529] The emotion recognition engine recognizes the user's emotions in real time.

[0530] An emotion recognition engine recognizes emotions from a user's facial expressions, voice, text input, etc. The input is the user's facial expression data and voice data, and the output is recognized emotion data. For example, when a user is reading a product review, it can detect whether the user is feeling anxious from their facial expression or tone of voice.

[0531] Step 4:

[0532] The server feeds the emotion data back to the generative AI model.

[0533] The server sends the emotion data recognized by the emotion recognition engine to the generative AI model. The input is emotion data, and the output is feedback to the generative AI model. For example, information that "the user is feeling anxious" is sent to the generative AI model.

[0534] Step 5:

[0535] The generative AI model generates the next action.

[0536] The generative AI model generates the next action based on the fed-back emotional and behavioral data. The input is emotional and behavioral data, and the output is the generated action. For example, if the user is feeling anxious, the model generates an action to highlight information about the "worry-free return guarantee" as an action to alleviate that anxiety.

[0537] Step 6:

[0538] Dynamically change the site's UX based on server-generated actions.

[0539] The server dynamically changes the site's UX based on the actions generated by the generative AI model. The input is the generated action, and the output is the changed UX. For example, dynamically changing HTML and CSS to prioritize the display of specific product information.

[0540] Step 7:

[0541] The device will display the new UX.

[0542] The device displays the new UX sent from the server. The input is the modified UX, and the output is the new UX displayed on the user's device. For example, the "Worry-Free Return Guarantee" information is highlighted on the page the user is viewing.

[0543] (Application example 2)

[0544] Next, a description will be given of Application Example 2 of Form 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."

[0545] While conventional advertiser sites can generate the next action based on the user's behavioral patterns and dynamically change the user experience on the site, they have not been able to provide an optimal user experience that takes user emotions into consideration. Therefore, in order to further improve user satisfaction and conversion rates, a system is needed that can recognize user emotions in real time and dynamically change the content displayed on the site based on that.

[0546] 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.

[0547] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, and a means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visited the advertiser's site. This makes it possible to learn the behavioral patterns and emotions of users, generate next actions based on them, and dynamically change the user experience on the site.

[0548] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[0549] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as the date and time of the visit, the pages viewed, and the links clicked.

[0550] "Artificial intelligence" is a technology that allows computer systems to mimic human intelligence in learning and reasoning, giving them the ability to perform specific tasks automatically.

[0551] "User experience" refers to the experience and satisfaction a user feels when using a website or application, and is influenced by factors such as ease of use, design, and functionality.

[0552] The "emotion engine" is a technology that recognizes emotions in real time from a user's facial expressions, voice, etc., and is used to analyze the user's psychological state.

[0553] "Feedback" refers to the return of information to the system to determine the next action based on the information it has obtained, and the system adjusts its behavior based on the user's actions and emotions.

[0554] "Dynamic change" refers to the system automatically changing the display content and functions in real time according to the situation, in order to provide the optimal experience for each user.

[0555] A system for implementing this invention includes a means for learning the access log of an advertiser's site, a means for constructing artificial intelligence that generates user actions that lead to a conclusion, a means for generating and suggesting next actions that lead to a conclusion based on the initial behavior of a user who visits the advertiser's site, an emotion engine that recognizes user emotions in real time, and a user experience generation artificial intelligence that generates next actions based on feedback from the emotion engine.

[0556] System Program

[0557] The program of this system operates as follows.

[0558] Hardware and Software

[0559] Hardware: Smartphone camera

[0560] Software: OpenCV (image processing library), Keras (deep learning library), UX generation AI module

[0561] Data processing and calculation

[0562] 1. Image capture: Capture the user's face using the smartphone camera, which allows us to obtain facial expression data.

[0563] 2. Emotion Recognition: Detect faces using OpenCV and recognize emotions using a Keras model. Specifically, the captured face image is converted to grayscale, and the facial region is extracted and input into the emotion recognition model.

[0564] 3. UX Generation: The recognized emotion is fed back to the UX Generation AI to generate the next action. For example, if the user feels "anxious," the UX Generation AI will generate an action that highlights the information about the "worry-free return guarantee."

[0565] 4. UX Update: Dynamically change the user experience on your site based on the actions generated, allowing you to provide the best experience for each user.

[0566] Specific examples

[0567] When a user is browsing an online shopping site on their smartphone, the camera captures the user's face, and if the emotion engine detects "anxiety," the UX generation AI generates an action to highlight the "worry-free return guarantee." Based on this action, the content displayed on the site dynamically changes, helping to alleviate the user's anxiety.

[0568] Prompt Sentence Examples

[0569] When a user is browsing an online shopping site, the camera captures the user's face, and if the emotion engine detects "anxiety," create a program in which the UX generation AI generates an action that highlights the information about the "worry-free return guarantee."

[0570] In this way, by providing a user experience that responds to the user's emotions, user satisfaction and conversion rates can be improved.

[0571] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0572] Step 1:

[0573] The device captures the user's face using the smartphone camera, where the input is real-time video data and the output is the captured face image, which is used in subsequent processing steps.

[0574] Step 2:

[0575] The device uses OpenCV to detect the face area from the captured face image. The input is the face image obtained in step 1, and the output is coordinate data indicating the face area. The face area is cut out based on this coordinate data.

[0576] Step 3:

[0577] The device converts the cropped face image to grayscale and performs preprocessing to input it into the Keras model. The input is the face region data obtained in step 2, and the output is the preprocessed face image data. This data is input into the emotion recognition model.

[0578] Step 4:

[0579] The device inputs the preprocessed facial image data into a Keras model to recognize the user's emotions. The input is the facial image data obtained in step 3, and the output is the recognized emotion label (e.g., "anxious," "excited," etc.). This emotion label is used in subsequent processing steps.

[0580] Step 5:

[0581] The server feeds the recognized emotion label back to the UX generation AI to generate the next action. The input is the emotion label obtained in step 4, and the output is the generated action (e.g., highlight the "Worry-Free Return Guarantee" information). This action is used to dynamically change the content displayed on the site.

[0582] Step 6:

[0583] The server dynamically changes the user experience of the site based on the generated actions. The input is the action taken in step 5, and the output is the modified site display. This allows for an optimal experience for each user.

[0584] Example 3

[0585] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0586] Conventional advertiser sites have been unable to fully understand user behavior patterns and emotions, making it difficult to improve conversion rates. Furthermore, they were unable to generate actions optimized for each user or dynamically change the site's user experience (UX). This made it difficult to provide a personalized experience based on the user's interests and emotions.

[0587] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0588] In this invention, the server includes means for collecting access logs of advertiser sites, means for analyzing the collected access logs and learning user behavior patterns, means for generating a next action based on the learned behavior patterns, means for reflecting the generated action on the advertiser site, means for collecting user behavior and reactions in real time and estimating emotions, means for generating a next action based on the estimated emotions, and means for reflecting the generated action on the advertiser site. This makes it possible to generate optimal actions based on user behavior patterns and emotions, and dynamically change the UX of the site.

[0589] An "advertiser site" is a website for displaying advertisements, which users can access to view the content of the advertisements.

[0590] An "access log" is data that records information when a user accesses a website, and includes information such as IP address, access date and time, and visited pages.

[0591] "Behavioral patterns" refers to the tendency or pattern of a series of actions taken by a user on a website, including actions such as visiting or clicking on specific pages.

[0592] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions and classifications.

[0593] A "natural language processing model" refers to an algorithm or mathematical model for understanding and generating human language, and is used to analyze and generate text data.

[0594] An "emotion engine" is a system for inferring emotions from a user's behavior and reactions, and analyzes emotions using natural language processing models, etc.

[0595] "UX generation AI" refers to an artificial intelligence system that generates the next action based on a user's behavioral patterns and emotions in order to optimize the user experience (UX).

[0596] "Dynamic change" refers to changing the content or presentation of a website in real time, including changing elements of a web page in response to user behavior or emotion.

[0597] This invention is a system that collects access logs from advertiser sites, analyzes user behavior patterns and emotions, generates optimal actions, and dynamically changes the site's user experience (UX). This system is implemented using the following hardware and software.

[0598] Hardware and software used

[0599] 1. Server

[0600] Web server software: Use Apache, Nginx, etc. to store user access data in log files.

[0601] Database: Use a database such as MySQL or PostgreSQL to store and manage the collected access logs.

[0602] Machine learning libraries: Using programming languages ​​such as Python and R and machine learning libraries such as Scikit-learn and TensorFlow to learn user behavior patterns.

[0603] Natural language processing models, such as OpenAI's GPT-4 and IBM Watson (registered trademark), are used to estimate user sentiment.

[0604] 2. Terminal

[0605] Web browser: Used by the user to access the advertiser's site.

[0606] JavaScript and HTML: Used to dynamically change the content of the site.

[0607] Specific operation of the system

[0608] 1. Collection of access logs

[0609] When a user accesses an advertiser's site, the server records information such as the user's IP address, the date and time of access, and the pages visited in a log file.

[0610] The server periodically analyzes the log files and stores them in a database.

[0611] 2. Learning behavioral patterns

[0612] The access logs collected by the server are analyzed to learn user behavior patterns. For example, it learns that users who visit specific product page A are highly likely to also visit product page B.

[0613] The server trains the machine learning model and extracts behavioral patterns.

[0614] 3. Generate the next action

[0615] The server generates the next action based on the behavioral patterns it has learned. For example, it generates an action to recommend product page B to a user who visited product page A.

[0616] Saves the server-generated actions to the database.

[0617] 4. Reflecting Actions

[0618] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[0619] The device displays the generated action to the user.

[0620] 5. Emotion Estimation

[0621] The server collects user behavior and reactions in real time to estimate emotions, such as page scrolling speed and click frequency.

[0622] The server inputs this data into an emotion engine to estimate the user's emotions.

[0623] 6. Emotion-based action generation

[0624] The server generates the next action using the UX generation AI based on the output of the emotion engine. For example, if the user is excited, it generates an action to highlight the "Buy Now" button.

[0625] The server-generated actions are reflected back to the advertiser site.

[0626] Examples of concrete examples and prompts

[0627] Example 1: Learning behavioral patterns and generating actions

[0628] A user visits a specific product page A.

[0629] The server collects access logs and records that the user visited product page A.

[0630] The server analyzes past access logs and learns a pattern that after a user visits product page A, there is a high probability that they will visit product page B.

[0631] Based on this pattern, the server generates an action to recommend product page B to users who visit product page A.

[0632] Prompt Sentence Examples

[0633] When a user visits product page A, generate an action to recommend product page B based on patterns learned from past access logs.

[0634] Example 2: Collaboration between emotion engine and UX generation AI

[0635] While viewing a product page, users engage in behaviors that indicate excitement (e.g., scrolling quickly down the page).

[0636] The server inputs this behavior into an emotion engine to estimate the user's excitement level.

[0637] Based on the output of the emotion engine, the server generates an action for the UX generation AI to highlight the "Buy Now" button.

[0638] Prompt Sentence Examples

[0639] When a user is browsing a product page and behaves in a way that indicates excitement, generate an action based on the output of the emotion engine to highlight the "Buy Now" button.

[0640] The above is a specific embodiment of the system of the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0641] Step 1:

[0642] Collection of access logs

[0643] The server collects access logs for the advertiser's website. Specifically, it uses web server software such as Apache or Nginx to store user access data in log files.

[0644] Input: Information such as the user's IP address, access date and time, and visited pages.

[0645] Output: Access data recorded in a log file.

[0646] Specific operation: When a user accesses an advertiser's site, the server records the access information in a log file.

[0647] Step 2:

[0648] Learning behavioral patterns

[0649] The system analyzes the access logs collected by the server and learns user behavior patterns. This analysis is done using programming languages ​​such as Python and R and machine learning libraries such as Scikit-learn and TensorFlow.

[0650] Input: Access data recorded in the log file.

[0651] Output: Learned behavioral pattern model.

[0652] How it works: The server reads past access logs, analyzes user behavior over time, and trains a machine learning model to extract behavioral patterns.

[0653] Step 3:

[0654] Generate the next action

[0655] The server generates the next action based on the learned behavioral patterns. For example, it generates an action to recommend product page B to a user who visited specific product page A.

[0656] Input: Learned behavioral pattern model, current user behavior data.

[0657] Output: The next action generated.

[0658] Specific operation: When a user visits product page A, the server refers to the behavioral pattern model and generates an action to recommend product page B.

[0659] Step 4:

[0660] Reflecting Actions

[0661] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[0662] Input: The generated next action.

[0663] Output: A dynamically modified web page.

[0664] Specific operation: The server generates JavaScript code to add a link to product page B to product page A, and the device displays the link to product page B to the user.

[0665] Step 5:

[0666] Emotion estimation

[0667] The server collects user behavior and reactions in real time and estimates sentiment using tools such as Google Analytics and Hotjar.

[0668] Input: User behavior data (page scrolling speed, click frequency, etc.).

[0669] Output: Estimated user sentiment.

[0670] Specific operation: When a user is viewing a product page, the server collects behavioral data such as page scrolling speed and click frequency, and inputs this data into an emotion engine to estimate the user's emotions.

[0671] Step 6:

[0672] Emotion-based action generation

[0673] The server generates the next action using the UX generation AI based on the output of the emotion engine. For example, if the user is excited, it generates an action to highlight the "Buy Now" button.

[0674] Input: Estimated user sentiment, current user behavior data.

[0675] Output: The next action generated.

[0676] What it does: The server receives the output of the emotion engine, inputs it into the UX generation AI, and generates an action to highlight the "Buy Now" button.

[0677] Step 7:

[0678] Reflecting emotions in actions

[0679] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[0680] Input: The generated next action.

[0681] Output: A dynamically modified web page.

[0682] What happens: The server generates JavaScript code that highlights the "Buy Now" button, and the device displays the highlighted "Buy Now" button to the user.

[0683] (Application example 3)

[0684] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0685] While conventional advertising systems could generate the next action based on a user's behavioral patterns, it was difficult to provide a personalized user experience that took the user's emotions into account. As a result, they were unable to display the optimal ad based on the user's interests and emotions, and could not expect to improve conversion rates. Furthermore, there was a lack of means to dynamically change the site's user experience, making it difficult to display ads that are optimized for each user.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0687] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for constructing an artificial intelligence that generates user actions that lead to a conclusion, a means for generating and suggesting a next action that will lead to a conclusion based on the initial behavior of a user who visited the advertiser's site, an emotion engine that recognizes the user's emotions, and a user experience generation artificial intelligence that generates the next action based on the emotions recognized by the emotion engine. This makes it possible to display optimal advertisements based on the user's behavior patterns and emotions, and to dynamically change the user experience on the site.

[0688] "Advertiser Site" means a website for displaying advertisements and an online platform intended for users to visit.

[0689] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as page views and clicks.

[0690] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and has the ability to analyze user behavior patterns and generate optimal actions.

[0691] "User experience" refers to the overall experience a user has when using a website or application, including the ease of use of the interface and the attractiveness of the content.

[0692] An "emotion engine" is a technology for recognizing and analyzing a user's emotions, and infers the user's emotional state from their actions and reactions.

[0693] "User experience generation artificial intelligence" is an artificial intelligence that generates the next action based on the user's emotions recognized by an emotion engine, and is a technology for providing a personalized user experience.

[0694] "Dynamic change" refers to changing the content and interface of a website or application in real time based on user behavior and emotions, providing an experience optimized for each user.

[0695] The system for implementing this invention learns access logs from advertiser sites and generates optimal actions based on the behavioral patterns and emotions of users. A specific embodiment of this system will be described below.

[0696] System Configuration

[0697] Hardware

[0698] Server: A high-performance server for processing data and running artificial intelligence models.

[0699] Device: The smartphone or computer that the user uses to access the service.

[0700] Sensors: Camera and microphone to recognize user emotions.

[0701] software

[0702] Python: A programming language used for data processing and implementing artificial intelligence models.

[0703] scikit-learn: A machine learning library for learning user behavior patterns.

[0704] Custom Sentiment Engine: Software for analyzing user sentiment in real time.

[0705] Custom Ad Recommendation Engine: Software for generating optimal ads based on user sentiment and behavioral patterns.

[0706] Data processing and calculation

[0707] Collecting and learning from access logs

[0708] The server collects access logs when users visit the advertiser's site. These access logs include page browsing history, click information, and time spent on the site. The collected data is analyzed using machine learning algorithms such as clustering and classification using scikit-learn.

[0709] Emotion recognition

[0710] The device's built-in camera and microphone capture the user's facial expressions and tone of voice in real time, and this data is analyzed by a custom sentiment engine to estimate the user's emotional state.

[0711] Generate the next action

[0712] The server combines the user's behavioral patterns learned from the access log with the emotional data recognized by the emotion engine to generate the next ad to be displayed. This process uses a custom ad recommendation engine. The generated ad is personalized according to the user's emotional state and is displayed at the optimal time.

[0713] Specific examples

[0714] For example, if the emotion engine detects a user's excitement while browsing a page for "Product A," it will then highlight an ad for "Product B." In this way, it is possible to provide optimal ads based on the user's behavioral patterns and emotions.

[0715] Prompt Sentence Examples

[0716] When a user is browsing a product page, if the emotion engine detects the user's excitement, generate the next ad to display. Recommend the most appropriate ad by taking into account the user's access log and emotion data.

[0717] In this way, it becomes possible to serve personalized advertisements based on the user's behavioral patterns and emotions.

[0718] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0719] Step 1:

[0720] The server collects access logs when users visit the advertiser's site. As input, it receives data such as the user's page browsing history, click information, and time spent on the site, and stores this data in a database. As output, it obtains the collected access log data.

[0721] Step 2:

[0722] The server learns user behavior patterns using the collected access log data. It receives the access log data as input and applies machine learning algorithms such as clustering and classification using scikit-learn. The output is a model that shows user behavior patterns.

[0723] Step 3:

[0724] The device uses a camera and microphone to capture facial expressions and tone of voice to recognize the user's emotions in real time. As input, it receives the user's facial expression data and voice data and sends them to a custom emotion engine (SentimentEngine). As output, it obtains the user's emotional state.

[0725] Step 4:

[0726] The server combines the emotion data recognized by the emotion engine with the behavioral pattern model to generate the next action. As input, it receives the user's emotion data and behavioral pattern model, and generates the optimal advertisement using a custom ad recommendation engine. The output is a personalized advertisement.

[0727] Step 5:

[0728] The device displays the generated personalized advertisement to the user. As input, it receives the advertisement data sent from the server and displays it on the user's screen. As output, the advertisement optimized for the user is displayed.

[0729] Step 6:

[0730] When a user takes action on a displayed ad (click, purchase, etc.), the user's behavior data is collected as input and sent back to the server. New access log data is obtained as output.

[0731] Step 7:

[0732] The server updates the behavioral pattern model using newly collected access log data. It receives the new access log data as input and performs additional learning on the existing model. The updated behavioral pattern model is obtained as output.

[0733] In this way, it is possible to provide personalized advertising based on user behavior patterns and emotions, dynamically modifying the user experience on the site.

[0734] 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.

[0735] 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> ) 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.

[0736] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0737] 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.

[0738] [Second embodiment]

[0739] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0740] 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.

[0741] 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).

[0742] 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.

[0743] 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.

[0744] 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).

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0751] "Example 1"

[0752] The system of the present invention builds an AI (UX generation AI) that learns from the access logs of advertiser sites. This AI generates and suggests next actions that will lead to a sale based on the initial actions of users who visit the advertiser site. Specifically, based on the initial actions taken by users when they visit the site (e.g., accessing a specific product page, searching for specific keywords, etc.), it generates actions such as which page to direct users to next or which product to recommend.

[0753] "Example 2"

[0754] The generated action is reflected on the advertiser's site, dynamically changing the site's UX. Specifically, when a user visits the site, the content displayed changes based on the generated action. For example, if an action recommending a specific product is generated, information about that product will be displayed preferentially when the user visits the site. This makes it possible to provide an optimal UX for each user and improve conversion rates.

[0755] "Example 3"

[0756] The system of the present invention understands user behavior patterns by studying the access logs of advertiser sites and generates optimal actions based on those patterns. Specifically, the system learns user behavior patterns from past access logs and generates the next action based on those patterns. For example, if the system learns a pattern that users who visit a specific product page have a high probability of purchasing another specific product, it generates the next action based on that pattern.

[0757] The processing flow of each embodiment will be described below.

[0758] "Example 1"

[0759] Step 1: Collect access logs from the advertiser's website, including the initial actions users take when visiting the website (e.g., accessing a specific product page, searching for a specific keyword, etc.).

[0760] Step 2: The collected access logs are trained by AI (UX generation AI). The AI ​​learns user behavior patterns and generates the next action based on them.

[0761] Step 3: The generated action is reflected on the advertiser's site. Specifically, when a user visits the site, the content displayed is changed based on the generated action.

[0762] "Example 2"

[0763] Step 1: Collect initial user actions when visiting your site.

[0764] Step 2: Based on the collected initial behavior, AI (UX generation AI) generates the next action that leads to a successful conclusion.

[0765] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[0766] "Example 3"

[0767] Step 1: Collect access logs from the advertiser's site to understand user behavior patterns.

[0768] Step 2: Learn user behavior patterns from the collected access logs and generate the next action based on those patterns.

[0769] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[0770] Example 1

[0771] Next, a description will be given of Example 1 of Form 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."

[0772] Conventional advertiser sites lacked the means to effectively utilize user behavior data to improve conversion rates. In particular, it was difficult to appropriately suggest the next action based on the user's initial behavior and dynamically change the user experience on the site. This meant that it was not possible to make suggestions that were in line with the user's interests and concerns, making it difficult to improve conversion rates.

[0773] 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.

[0774] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for training a generative AI model using the preprocessed data, means for generating and suggesting a next action based on a user's initial behavior, means for sending the generated next action to the user's terminal, and means for dynamically changing the user experience on the site based on the suggestion. This makes it possible to effectively utilize user behavior data and improve the conversion rate.

[0775] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[0776] An "access log" is a record of behavioral data when a user accesses a website, and includes information such as the pages viewed, search keywords, and the date and time of the visit.

[0777] "Database" means a system for storing collected access logs, enabling efficient management and retrieval of data.

[0778] "Preprocessing" refers to processes such as cleaning and normalizing collected data to make it easier to analyze.

[0779] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn user behavior patterns and generate the next action.

[0780] "User initial actions" are the first actions a user takes when accessing a website, including viewing a specific product page or searching for a specific keyword.

[0781] "Next Actions" are suggestions for what a user should do next based on their initial behavior, and can include directing them to a specific page or recommending a product.

[0782] "User experience" refers to the overall experience a user has when using a website, including the ease of use of the site and the quality of the information provided.

[0783] "Dynamic changes" refers to changing the content and structure of a website in real time based on user behavior data.

[0784] MODE FOR CARRYING OUT THE INVENTION

[0785] System Overview

[0786] The system of the present invention collects access logs from advertiser sites and builds a generative AI model that learns user behavior patterns based on these logs. This AI model generates and suggests next actions based on the user's initial behavior. Specifically, based on the user's initial behavior when visiting a site (e.g., accessing a specific product page, searching for a specific keyword, etc.), it generates actions such as which page to direct the user to next or which product to recommend.

[0787] Hardware and software used

[0788] The server collects, stores, and preprocesses access logs, trains the AI ​​model, and generates the next action. Specifically, it uses the following hardware and software:

[0789] Hardware: High-performance servers (CPU, GPU, memory, storage)

[0790] Software: Database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, PyTorch)

[0791] The device records the user's behavior data and sends it to the server, and also receives suggestions for next actions sent from the server and displays them to the user.

[0792] Hardware: User's device (e.g. smartphone, computer)

[0793] Software: web browser, mobile application

[0794] Specific operation of the system

[0795] 1. Collection of access logs

[0796] The server collects real-time behavioral data of users who visit the advertiser's site, specifically recording information such as which pages users viewed and which keywords they searched for.

[0797] 2. Data storage

[0798] The server stores the collected access logs in a database, including user IDs, visit dates and times, viewed pages, and search keywords.

[0799] 3. Data Preprocessing

[0800] The server preprocesses the stored data, specifically cleaning the data (filling in missing values ​​and removing outliers) and normalizing (scaling) the data.

[0801] 4. Training the AI ​​model

[0802] The server uses the preprocessed data to train a generative AI model using machine learning libraries such as TensorFlow and PyTorch.

[0803] 5. Generate the next action

[0804] The server uses the trained AI model to generate the next action based on the user's initial behavior, specifically predicting which page the user should be directed to next and which product to recommend.

[0805] 6. Submit your proposal

[0806] The server then sends the generated next action to the user's device, which then suggests appropriate pages and products to the user.

[0807] Specific examples

[0808] Suppose a user visits an advertiser's website and views a page for a specific smartphone model. The device records this behavior and sends it to the server. The server stores this data in a database, preprocesses it, and trains a generative AI model. The trained AI model determines that the user should next be directed to a page for smartphone accessories and related products, and sends this suggestion to the device. The device displays the suggestion to the user, who then views the suggested page.

[0809] Prompt Sentence Examples

[0810] "When a user visits an advertiser's website and views a specific product page, please build an AI model that will determine which page to direct them to next and which product to recommend. Specifically, this is a system that will suggest the next action that will lead to a sale based on the user's initial behavioral data."

[0811] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0812] Step 1:

[0813] Collection of access logs

[0814] The server collects real-time behavioral data of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavioral data, and the output is the collected access log.

[0815] Step 2:

[0816] Data storage

[0817] The server stores the collected access logs in a database. The stored data includes the user ID, visit date and time, viewed pages, search keywords, etc. The collected access logs are the input, and the access logs stored in the database are the output.

[0818] Step 3:

[0819] Data Preprocessing

[0820] The server preprocesses the stored data. Specifically, it cleans the data (fills in missing values ​​and removes outliers), normalizes the data (scales it), etc. The input is the access log stored in the database, and the output is the preprocessed data.

[0821] Step 4:

[0822] Training an AI model

[0823] The server uses the preprocessed data to train a generative AI model. For training, it uses machine learning libraries such as TensorFlow and PyTorch. The input is the preprocessed data, and the output is a trained generative AI model.

[0824] Step 5:

[0825] Generate the next action

[0826] The server uses the trained AI model to generate the next action based on the user's initial behavior. Specifically, it predicts which page the user should be directed to next and which product should be recommended. The input is the user's initial behavior data, and the output is the generated next action.

[0827] Step 6:

[0828] Submit a proposal

[0829] The server sends the generated next action to the user's device, which then suggests appropriate pages or products to the user. The input is the generated next action, and the output is the suggestion sent to the user's device.

[0830] Step 7:

[0831] Receiving and Viewing Suggestions

[0832] The terminal receives the next action suggestions sent from the server and displays them to the user. The input is the suggestion sent from the server, and the output is the suggestion displayed to the user.

[0833] Step 8:

[0834] User Behavior

[0835] The user accepts the suggestion displayed on the device and performs the next action, such as viewing the suggested product page or purchasing the recommended product. The input is the suggestion displayed on the device, and the output is new behavioral data of the user.

[0836] (Application example 1)

[0837] Next, a description will be given of Application Example 1 of Form 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."

[0838] On conventional advertiser sites, it was difficult to appropriately suggest the next action that would lead to a sale based on the user's initial behavior. As a result, it was not possible to stimulate the user's desire to purchase, and it was not possible to expect an improvement in the sale rate. In addition, it was not possible to provide an optimized site user experience for each user, which meant it was not possible to improve user satisfaction.

[0839] 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.

[0840] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial actions of users who visit the advertiser's site, means for dynamically changing the site user experience based on the suggestions, and means for analyzing the user's initial actions and suggesting in real time which product to view next and which page to proceed to. This makes it possible to appropriately suggest next actions that lead to a contract based on the user's initial actions, which is expected to improve the contract rate and user satisfaction.

[0841] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[0842] An "access log" is data that records the behavioral history of users when they access a website, and includes information such as page views and search keywords.

[0843] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, giving them the ability to perform specific tasks automatically.

[0844] "User initial actions" are the first actions a user takes when visiting a website, such as accessing a specific product page or searching for a specific keyword.

[0845] "Conclusion" refers to a user purchasing a product or service on the website, meaning that the transaction is concluded.

[0846] "Next Action" refers to the next action a user should take on a website, suggesting actions that are more likely to lead to a sale.

[0847] "Site user experience" refers to the overall experience a user has when using a website, including ease of use and satisfaction.

[0848] "Dynamic change" refers to changing the content and structure of a website in real time in response to user behavior and circumstances.

[0849] "Real-time suggestions" refers to instantly analyzing user behavior and immediately suggesting the next action based on the results.

[0850] The system for implementing this invention constructs an artificial intelligence that learns from the access logs of advertiser sites and generates user actions that lead to sales. A specific embodiment of this system will be described below.

[0851] System configuration

[0852] The system consists of the following main components:

[0853] 1. Server: Collects access logs from advertiser sites and stores them as learning data.

[0854] 2. Artificial Intelligence (AI): Generates and suggests next actions based on the user's initial behavior.

[0855] 3. User Device: The device through which a user accesses an advertiser's site (e.g., smartphone, tablet, PC).

[0856] 4. Database: Data storage for storing access logs and user behavior data.

[0857] Program processing

[0858] Data collection and learning

[0859] The server collects access logs of users who visit the advertiser's site. These access logs include information such as which pages users viewed and what keywords they searched for. The collected data is stored in a database and used by the AI ​​as learning data.

[0860] User behavior analysis

[0861] The AI ​​analyzes the collected access logs and learns the initial behavioral patterns of users, generating a model that predicts what actions users should take to close a deal.

[0862] Suggested next actions

[0863] When a user visits an advertiser's website, AI analyzes the user's initial behavior in real time and suggests which products to view next and which pages to go to. These suggestions are displayed on the user's device to guide the user's actions.

[0864] Hardware and software used

[0865] Hardware: Servers, user devices (smartphones, tablets, PCs)

[0866] Software: Python, Pandas, Scikit-learn, database management system (e.g., MySQL)

[0867] Specific examples

[0868] For example, if a user views "Product A page" on an advertiser's website, gets 5 page views, and searches for "special price," AI will suggest that the user should next view "Product B page." This suggestion increases the user's desire to purchase and contributes to improving the conversion rate.

[0869] Prompt Sentence Examples

[0870] If a user views Product A's page, has 5 page views, and their search keyword is "Special Offer," predict which page they will view next.

[0871] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[0872] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0873] Step 1:

[0874] The server collects access logs of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavior data, and the output is access log data.

[0875] Step 2:

[0876] The server saves the collected access log data in a database. The input is the access log data, and the output is the log data saved in the database. Specifically, the data is stored using a database management system (e.g., MySQL).

[0877] Step 3:

[0878] The server provides the access log data stored in the database to the artificial intelligence to use as training data. The input is the access log data obtained from the database, and the output is a trained artificial intelligence model. Specifically, the data is preprocessed using Python's Pandas library, and the model is trained using the Scikit-learn library.

[0879] Step 4:

[0880] When a user accesses an advertiser's website, the device sends the user's initial behavior data to the server. The input is the user's initial behavior data, and the output is the data sent to the server. Specifically, the device captures the user's behavior in real time and sends it to the server.

[0881] Step 5:

[0882] The server inputs the received initial behavior data into the AI ​​to predict the next action. The input is the user's initial behavior data, and the output is a proposal for the next action. Specifically, the data is input into a trained AI model to obtain a prediction result.

[0883] Step 6:

[0884] The server sends the predicted next action to the user's device. The input is the prediction result, and the output is a suggestion to be displayed on the user's device. Specifically, the server formats the prediction result and sends it to the user's device.

[0885] Step 7:

[0886] The user's device displays the received proposal to the user. The input is the proposal sent from the server, and the output is the information displayed to the user. Specifically, the proposal content is displayed in the user interface.

[0887] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[0888] Example 2

[0889] Next, a description will be given of Example 2 of Form 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."

[0890] On conventional advertiser sites, it was difficult to effectively utilize user behavior data to provide an optimized user experience (UX) for each individual user. As a result, there was an issue of insufficient improvement in conversion rates. In particular, it was not possible to dynamically change the content displayed on the site based on the user's initial behavior, making it difficult to respond to the different needs of each user.

[0891] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0892] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, and a means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visited the advertiser's site. This enables a system that includes a means for collecting user behavior data and saving the generated actions in a database, and a means for acquiring the generated actions when the user visits the site again and dynamically changing the display content. This makes it possible to provide an optimized UX for each user and improve the conversion rate.

[0893] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[0894] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as page views, clicks, and length of stay.

[0895] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and is particularly used to analyze user behavior data and generate optimal actions.

[0896] "User action" refers to a specific operation or action a user takes on a website, such as clicking on an item, adding it to a cart, or purchasing it.

[0897] "User experience (UX)" refers to the overall experience and satisfaction a user feels when using a website, and is influenced by factors such as the site's ease of use, design, and the quality of the information provided.

[0898] "Dynamic change" refers to changing the content and functionality of a website in real time in order to provide optimal information according to the user's behavior and situation.

[0899] "Behavioral data" refers to data about a series of actions or behaviors a user performs on a website, including browsing history, click patterns, purchase history, etc.

[0900] A "database" is a system for efficiently storing, managing, and retrieving data, and is used to store generated action and user behavior data.

[0901] "Generated actions" refers to the next optimal action or suggestion generated by artificial intelligence after analyzing user behavioral data.

[0902] "Displayed Content" refers to the information and content displayed to users on a website, including text, images, videos, links, etc.

[0903] The present invention is a system for dynamically optimizing the user experience (UX) of an advertiser's site. A specific embodiment of this system will be described below.

[0904] System Overview

[0905] This system consists of three main elements: a server, a device, and a user. The server collects user behavior data and generates optimal actions using a generative AI model. The device obtains the actions generated by the server when a user visits the site and dynamically changes the displayed content. The user experiences an optimized UX by visiting the site.

[0906] Hardware and software used

[0907] Server: Use a high-performance server machine (e.g., AWS EC2 instance).

[0908] Database: Use a relational database such as MySQL or PostgreSQL.

[0909] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[0910] Analytics tools: Use user behavior analytics tools such as Google Analytics and Mixpanel.

[0911] Data processing and calculation

[0912] The server collects user behavior data (e.g., browsing history, click patterns, purchase history, etc.) in real time. The collected data is stored in a database. The server then inputs prompt statements into a generative AI model to generate optimal actions. The generated actions are stored in the database, and when the user visits the site again, the device retrieves them and dynamically changes the displayed content.

[0913] Specific examples

[0914] For example, if a user visits an online shopping site and frequently browses pages about sporting goods, the server might input the following prompts into the generative AI model:

[0915] Recommend the best product for this user.

[0916] The generative AI model analyzes the input data and generates an action, "recommend sporting goods." The server stores this action in a database, and the device retrieves it when the user visits the site again. The device then displays a banner for sporting goods on the homepage based on the retrieved action.

[0917] In this way, we can provide an optimized UX for each user and improve conversion rates.

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] Step 1:

[0920] A user visits the site.

[0921] Input: The user opens a browser and enters the URL of the advertiser's site.

[0922] Output: A user visits the site and some initial behavioral data is generated.

[0923] Specific behavior: A user visits an online shopping site and the homepage is displayed.

[0924] Step 2:

[0925] The server collects user behavior data.

[0926] Input: Behavioral data such as user browsing history, click patterns, and purchase history.

[0927] Output: Collected behavioral data is stored in a database.

[0928] Specific operation: The server uses analytical tools such as Google Analytics and Mixpanel to collect user behavior data in real time and store it in a database.

[0929] Step 3:

[0930] The server inputs prompt statements into the generative AI model and generates the optimal action.

[0931] Input: Collected behavioral data and a prompt (e.g., "Recommend the best product for this user").

[0932] Output: The optimal action obtained from the generative AI model.

[0933] Specific operation: Based on the collected behavioral data, the server inputs a prompt statement such as "Please recommend the best product for this user" into the generative AI model (e.g., GPT-4) and generates the optimal action.

[0934] Step 4:

[0935] The server saves the generated action in the database.

[0936] Input: The optimal action obtained from the generative AI model.

[0937] Output: Actions stored in the database.

[0938] Specific operation: The server stores the generated actions in a database such as MySQL or PostgreSQL.

[0939] Step 5:

[0940] The terminal acquires the generated action from the server when the user visits.

[0941] Input: The request when the user returns to the site.

[0942] Output: The generated actions retrieved from the server.

[0943] Specific operation: When the user visits the site again, the device sends a request to the server and retrieves the generated action.

[0944] Step 6:

[0945] Dynamically change the display content based on the actions taken by the device.

[0946] Input: The generated action retrieved from the server.

[0947] Output: The dynamically changed display content.

[0948] Specific behavior: The device dynamically changes the content displayed based on the action taken, such as displaying a sports goods banner on the home page.

[0949] Step 7:

[0950] Users experience an optimized UX.

[0951] Input: Dynamically changed display content.

[0952] Output: Improved user satisfaction and higher conversion rates.

[0953] What it does: By simply visiting the site, users experience a personalized UX, with sporting goods information displayed first.

[0954] (Application example 2)

[0955] Next, a description will be given of Application Example 2 of Form 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."

[0956] On traditional advertiser sites, it was difficult to provide an optimal user experience for each user, making it difficult to improve conversion rates. Furthermore, there was a lack of effective ways to utilize users' past purchase and browsing histories, making it impossible to recommend appropriate products to users. This resulted in a failure to attract users' interest, resulting in a lower conversion rate.

[0957] 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.

[0958] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visit the advertiser's site, means for dynamically changing the user experience of the site based on the suggestions, and means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions. This makes it possible to provide an optimal user experience for each user and improve the conversion rate.

[0959] "Advertiser Site" means a website that displays advertisements and an online platform that users can visit to view and purchase products and services.

[0960] An "access log" is data that records the behavioral history of a user when they visit a website, and includes information such as the date and time of the visit, the pages viewed, and the links clicked.

[0961] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn, reason, and make decisions, particularly with the ability to analyze user behavior patterns and generate the next action.

[0962] "User experience" refers to the overall experience a user has when using a website or application, and includes factors such as ease of use, satisfaction, and convenience.

[0963] "Purchase history" is a record of products and services purchased by a user in the past, and includes information such as the purchase date and time, product name, and price.

[0964] "Browsing history" refers to a record of the pages and products a user has viewed on a website, including the date and time of the viewing, the pages viewed, and information about the products viewed.

[0965] "Dynamic change" refers to changing the content and functions of a website in real time according to the user's behavior and situation, and flexibly changing from a fixed display.

[0966] The "conversion rate" is an indicator that shows the percentage of users who actually purchase products or services among those who visit a website, and is an important indicator for measuring the effectiveness of marketing and sales.

[0967] A system for implementing this invention includes a means for learning the access log of an advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that will lead to a contract based on the initial behavior of a user who visits the advertiser's site, a means for dynamically changing the user experience of the site based on the suggestions, and a means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions.

[0968] System configuration

[0969] The server uses the following hardware and software:

[0970] Hardware: A server with a powerful processor, sufficient memory, and storage

[0971] Software: Python, API request library (requests), API for generative AI models

[0972] Data processing and calculation

[0973] 1. Obtaining user information: When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history using an API request.

[0974] 2. Sending prompts to the generative AI model: The server sends the acquired user information as prompts to the generative AI model, which then generates the optimal action for the user (such as recommended products).

[0975] 3. Dynamically changing the site content: The server dynamically changes the site content based on the generated action. Specifically, the recommended products are reflected in the site content.

[0976] Specific examples

[0977] For example, if a user has previously purchased "smartphone accessories" and recently browsed "smartwatches," the generative AI model will generate an action that recommends "smartwatch accessories."

[0978] Prompt Sentence Examples

[0979] User's past purchase history: Smartphone accessories, browsing history: Smartwatch

[0980] By sending this prompt to a generative AI model, the most appropriate product recommendation for each user is made, providing an optimal user experience and improving conversion rates.

[0981] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0982] Step 1:

[0983] When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history.

[0984] Input: User ID

[0985] Data processing: Use API requests to retrieve user purchase and browsing history.

[0986] Output: User purchase and browsing history data

[0987] Step 2:

[0988] The server sends the acquired user information to the generative AI model as a prompt.

[0989] Input: User purchase and browsing history data

[0990] Data calculation: Convert user information into a text prompt and send it to the API of the generative AI model.

[0991] Output: Recommended actions from the generative AI model (e.g., recommended products)

[0992] Step 3:

[0993] The server dynamically changes the content displayed on the site based on the generated actions.

[0994] Input: Recommended actions from a generative AI model

[0995] Data processing: Obtain site content data and update it to prioritize the display of recommended products.

[0996] Output: Updated site content data

[0997] Step 4:

[0998] When a user visits a site, the user views dynamically changed display content.

[0999] Input: Updated site content data

[1000] Data Calculation: Display the updated content in the user's browser.

[1001] Output: User-optimized display

[1002] Step 5:

[1003] The server records the user's new behavior data in the access log.

[1004] Input: User behavior data (e.g. clicks, pages viewed)

[1005] Data processing: Add new behavioral data to the access log.

[1006] Output: Updated access log

[1007] Example 3

[1008] Next, a description will be given of Example 3 of Form Example 3. 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."

[1009] On conventional advertiser sites, it was difficult to fully understand users' behavioral patterns and propose optimal actions. As a result, there were problems with low conversion rates and insufficient advertising effectiveness. Furthermore, it was not possible to make proposals optimized for each user, making it difficult to meet the needs of individual users.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1011] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for building a generative AI model that learns user behavior patterns using the preprocessed data, means for generating a next action based on the learned behavior pattern, means for sending the generated action to the terminal, means for the user to take action based on the action displayed on the terminal, and means for recording the action again as an access log. This makes it possible to accurately understand user behavior patterns and propose actions optimized for each user.

[1012] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[1013] An "access log" is data that records the behavioral history of users when they visit a website, including actions such as page views, clicks, and purchases.

[1014] A "database" is a system for storing collected access logs, and includes relational databases, NoSQL databases, etc.

[1015] "Preprocessing" refers to the process of preparing the collected access logs in a format that is easy to analyze, and includes data cleaning and normalization.

[1016] A "generative AI model" is a model that uses machine learning algorithms to learn user behavior patterns and predict their next actions.

[1017] An "action" is what the user should do next, such as purchasing a particular product or visiting a particular page.

[1018] "Terminal" refers to a device used by a user, including a PC, smartphone, tablet, etc.

[1019] "Behavioral patterns" refer to the tendency of a series of actions that a user takes on a website, and are learned from past access logs.

[1020] "Suggestion" refers to the next action that the generative AI model suggests to the user based on the behavioral patterns it has learned.

[1021] "Conversion rate" refers to the percentage of users who take a suggested action and actually achieve their goal, such as purchasing a product.

[1022] This invention is a system that collects access logs from advertiser sites, learns user behavior patterns, and then generates and suggests optimal next actions to users. Specific embodiments of this system are described below.

[1023] Server Processing

[1024] The server collects access logs for the advertiser's website. The access logs include information such as the pages visited by users, the links clicked, and the products purchased. This data is collected using web server logs such as Apache and Nginx.

[1025] The server then stores the collected access logs in a relational database such as MySQL or PostgreSQL, and the stored data includes user IDs, visited pages, and action timestamps.

[1026] The stored access logs are subjected to preprocessing such as data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This process is often performed using the Python Pandas library.

[1027] Using the preprocessed data, the server builds a generative AI model, which is built using machine learning frameworks such as TensorFlow and PyTorch. The model learns user behavior patterns from past access logs and predicts the next action to be taken.

[1028] Based on the learned behavioral patterns, the server generates the next optimal action for the user. For example, if a user visits a specific product page, it will suggest the next product they are likely to purchase. This suggestion is made in real time using a generative AI model.

[1029] The generated actions are sent to the terminal in JSON format via the REST API.

[1030] Terminal handling

[1031] The device receives the optimal action sent from the server and presents it to the user, for example, as a pop-up on a web page or by sending an email notification.

[1032] User Action

[1033] The user checks the next action displayed on the device and purchases the product if necessary. The user's response is also recorded as an access log and will be used for the next learning.

[1034] Specific examples

[1035] For example, suppose a user visits the "Smartphone A" page on an advertiser's website. The server studies past access logs and knows that users who visit "Smartphone A" are highly likely to purchase "Smartphone Case B." In this case, the server suggests to the user that they purchase "Smartphone Case B" as their next action.

[1036] Prompt Sentence Examples

[1037] "If a user visits the page on smartphone A, please suggest the next product they are likely to purchase."

[1038] In this way, a system is realized in which the server, the terminal, and the user work together to generate optimal actions based on the user's behavioral patterns and present them to the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1039] Step 1:

[1040] The server collects access logs for the advertiser's website, specifically recording actions taken by users on the website, such as page views, clicks, and purchases. The input includes user behavior data, and the output is stored in a log file.

[1041] Step 2:

[1042] The server stores the collected access logs in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input includes the collected access logs, and the output is structured data stored in the database.

[1043] Step 3:

[1044] The server preprocesses the stored access logs. Specifically, it performs data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This processing is performed using the Python Pandas library. The input includes the raw data stored in the database, and the output is the preprocessed, clean data.

[1045] Step 4:

[1046] The server uses the preprocessed data to build a generative AI model that learns user behavior patterns. Specifically, it trains a neural network using a machine learning framework such as TensorFlow or PyTorch. The input includes the preprocessed data, and the output is a trained generative AI model.

[1047] Step 5:

[1048] The server generates the next action based on the learned behavioral patterns. Specifically, it uses a generative AI model to predict the next action the user should take. The inputs include the trained generative AI model and real-time user behavior data, and the output is the optimal next action.

[1049] Step 6:

[1050] The server sends the generated action to the device. Specifically, it sends data in JSON format via a REST API. The input contains the generated action, and the output is the action data sent to the device.

[1051] Step 7:

[1052] The device then presents the optimal action received from the server to the user, for example, by displaying it as a pop-up on a web page or by sending an email notification. The input includes the action data sent from the server, and the output is the action presented to the user.

[1053] Step 8:

[1054] The user checks the next action displayed on the terminal and purchases the product if necessary. Specifically, the user purchases the product on the website according to the presented action. The input includes the action displayed on the terminal, and the output is the user's purchasing behavior.

[1055] Step 9:

[1056] The server records the user's response again as an access log. Specifically, it saves the user's actions as a new access log. The input contains the user's behavior data, and the output is an updated access log.

[1057] (Application example 3)

[1058] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1059] Conventional ad delivery systems were unable to fully grasp user behavior patterns, making it difficult to display the right ad at the right time. As a result, they were unable to attract user interest and could not expect to improve conversion rates. In addition, because ads were not displayed in an optimized format for each user, there was a problem of reduced advertising effectiveness.

[1060] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for learning the access log of the advertiser site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that lead to a contract based on the initial behavior of a user who visited the advertiser site, a means for dynamically changing the site user experience based on the suggestions, and a means for learning the user's past website visit history and displaying advertisements that are likely to interest the user in real time. This makes it possible to grasp the user's behavioral patterns in detail and display appropriate advertisements at the optimal timing.

[1061] "Advertiser Site" means a website for displaying advertisements and an online platform intended for users to visit.

[1062] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as the pages visited and the length of time spent on the website.

[1063] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and has the ability to analyze user behavior patterns and generate the next action.

[1064] "User experience" refers to the experiences and feelings that users have when using a website or application, and affects the ease of use and satisfaction of the site.

[1065] "Dynamic change" means changing the content and layout of a website in real time according to the user's behavior and situation, providing an optimized display for each user.

[1066] "Website visit history" refers to a record of websites a user has visited in the past, including information such as pages visited, time spent there, and links clicked.

[1067] "Displaying in real time" means instantly displaying ads or content based on the user's current behavior and situation, providing information without delay.

[1068] The system for carrying out this invention learns access logs of advertiser sites, analyzes user behavior patterns, and displays optimal advertisements in real time. A specific embodiment of this system will be described below.

[1069] The server first collects access logs from the advertiser's website and stores them in a database. These access logs include information such as the pages visited by users, the time spent there, and the links clicked. The server then uses these access logs to build an artificial intelligence model to learn user behavior patterns. This model is trained using Python libraries such as pandas and scikit-learn.

[1070] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time and generates the next optimal action to take. This action is to display an advertisement that the user is likely to be interested in. The server references the user's past website visit history and selects the most appropriate advertisement based on information such as the pages the user previously visited and the length of time they spent there.

[1071] For example, if a user previously visited a specific fashion brand's website and stayed on a specific product page for 120 seconds, the server would prioritize displaying new products and sales information from the same brand to that user. In this way, ads are displayed that are optimized for each user, which is expected to improve conversion rates.

[1072] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to generate advertisements based on user behavior patterns.

[1073] Example prompt sentence:

[1074] Predict the next ad to display based on the user's history of previously visited websites. For example, if a user visits the website of "Fashion Brand A" and stays on a specific product page for 120 seconds, display information about new products and sales from "Fashion Brand A" to that user.

[1075] This system makes it possible to grasp user behavior patterns in detail and display appropriate advertisements at the optimal time, which is expected to improve advertising effectiveness and conversion rates.

[1076] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1077] Step 1:

[1078] The server collects access logs for the advertiser's website and stores them in a database. It receives information such as the pages visited by the user, the time spent there, and the links clicked as input, and stores this data in the database. Specifically, the web server collects access logs in real time and stores them in a database management system (e.g., MySQL or PostgreSQL).

[1079] Step 2:

[1080] The server uses the collected access logs to build an AI model to learn user behavior patterns. As input, it uses the access logs stored in the database and processes the data to extract features (for example, number of page visits, average length of stay, etc.). As output, it generates a trained AI model. Specifically, it preprocesses the data using Python's pandas and trains the model using scikit-learn's RandomForestClassifier, etc.

[1081] Step 3:

[1082] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time. As input, it receives the user's current behavior data (pages visited, time spent, etc.) and inputs this into the artificial intelligence model that was previously constructed. As output, it generates the next optimal action to be taken (the advertisement to be displayed). Specifically, it inputs the data collected in real time into the model and obtains the predicted results.

[1083] Step 4:

[1084] The server references the user's past website visit history and selects advertisements that are likely to interest the user. The server uses the user's past visit history data as input and processes the data by analyzing past behavioral patterns. The output is the selection of the most suitable advertisement. Specifically, it retrieves past visit history from a database and analyzes it using an artificial intelligence model.

[1085] Step 5:

[1086] The server displays the selected advertisement to the user in real time. It uses the selected advertisement data as input and displays the advertisement on the user's screen as output. Specifically, it dynamically changes the content of the web page to insert the advertisement.

[1087] Step 6:

[1088] The server again collects user responses after the ad is displayed as an access log and stores it in a database. It receives user response data to the ad (clicks, time spent, etc.) as input and stores this in the database. Specifically, the web server collects user responses in real time and stores them in a database management system.

[1089] This series of processes allows for a detailed understanding of user behavior patterns and makes it possible to display appropriate advertisements at optimal times, which is expected to improve advertising effectiveness and conversion rates.

[1090] 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.

[1091] "Example 1"

[1092] One embodiment of the present invention is a system that incorporates an emotion engine. This system combines an AI (UX generation AI) that learns from the access logs of advertisers' websites and generates the next action that leads to a sale based on the user's initial behavior (UX generation AI), with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine infers the user's emotions from their actions and reactions when visiting the website, and the UX generation AI generates the next action based on those emotions. For example, if the emotion engine detects the user's excitement while browsing a product page, the UX generation AI takes that excitement into account and generates an action, such as highlighting the "Buy Now" button. This provides a personalized UX that reflects the user's emotions, contributing to an improved conversion rate.

[1093] "Example 2"

[1094] Another embodiment of the present invention is a system in which an emotion engine and a UX generation AI work together. In this system, the emotion engine recognizes a user's emotions in real time and feeds that information back to the UX generation AI. The UX generation AI generates the next action based on that feedback, dynamically changing the site's UX. For example, if the emotion engine detects a user's anxiety while reading a product review, the UX generation AI generates an action to alleviate that anxiety, such as highlighting information about a "worry-free return guarantee." This provides a UX that responds to the user's emotions, improving user satisfaction and conversion rates.

[1095] "Example 3"

[1096] Furthermore, another embodiment of the present invention is a system that combines an emotion engine and a UX generation AI. In this system, the emotion engine recognizes the user's emotions, and the UX generation AI generates the next action based on those emotions. Specifically, the emotion engine infers the user's emotions from their actions and reactions when visiting a website, and the UX generation AI generates the next action based on those emotions. For example, if the emotion engine detects the user's state of excitement while viewing a product page, the UX generation AI takes that state of excitement into account and generates an action, such as highlighting the "Buy Now" button. This provides a personalized UX that corresponds to the user's emotions, contributing to an improvement in the conversion rate.

[1097] The processing flow of each embodiment will be described below.

[1098] "Example 1"

[1099] Step 1: A user visits an advertiser's site.

[1100] Step 2: The emotion engine infers emotions from the user's actions and reactions.

[1101] Step 3: UX generation AI generates the next action based on the emotional information from the emotion engine.

[1102] Step 4: The site dynamically changes the UX based on the action generated.

[1103] "Example 2"

[1104] Step 1: A user visits an advertiser's site.

[1105] Step 2: The emotion engine recognizes the user's emotions in real time.

[1106] Step 3: The emotional information recognized by the emotion engine is fed back to the UX generation AI.

[1107] Step 4: UX Generation AI generates next actions based on feedback and dynamically changes the site's UX.

[1108] "Example 3"

[1109] Step 1: A user visits an advertiser's site.

[1110] Step 2: The emotion engine infers emotions from the user's actions and reactions.

[1111] Step 3: UX generation AI generates the next action based on the emotional information from the emotion engine.

[1112] Step 4: The site dynamically changes the UX based on the action generated.

[1113] Example 1

[1114] Next, a description will be given of Example 1 of Form 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."

[1115] Conventional advertiser sites generate next actions based solely on user behavioral data, making it difficult to provide personalized suggestions that take user emotions into account. As a result, improvements in conversion rates have been limited. The present invention aims to combine user behavioral data and emotional data to generate more accurate next actions and improve conversion rates.

[1116] 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.

[1117] In this invention, the server includes means for collecting user behavioral data, means for collecting user emotion data, means for transmitting the collected behavioral data and emotion data to the server, means for cleansing and preprocessing the transmitted data, means for training an AI model using the preprocessed data, means for inferring the user's next action in real time using the trained AI model, and means for displaying the inferred action to the user, thereby enabling personalized suggestions that combine the user's behavioral data and emotion data.

[1118] "User behavior data" refers to information about actions users take on a website, such as clicks, page transitions, and search keywords.

[1119] "User emotion data" refers to information about the user's emotional state estimated from their facial expressions and voice.

[1120] "Server" means a computer system for collecting, processing, and storing user behavioral and emotional data, and for training and running AI models.

[1121] "Cleansing" is the process of removing missing values ​​and outliers from collected data and shaping the data.

[1122] "Preprocessing" is the process of converting data into a format suitable for training an AI model.

[1123] An "AI model" is an artificial intelligence algorithm that infers the next action based on a user's behavioral and emotional data.

[1124] "Training" is the process of training an AI model using large amounts of data to learn and improve its prediction accuracy.

[1125] "Real-time inference" is the process of instantly analyzing user behavioral and emotional data and instantly generating the next action.

[1126] "Personalized suggestions" are suggestions optimized for each user, generated based on the user's individual behavioral and emotional data.

[1127] MODE FOR CARRYING OUT THE INVENTION

[1128] The present invention is a system that learns access logs from advertiser sites and generates the next action based on user behavioral and emotional data. This system collects user behavioral and emotional data, sends it to a server for processing, and makes personalized suggestions.

[1129] server

[1130] The server is a computer system that collects, processes, and stores user behavioral and emotional data. Specifically, the server uses Apache Hadoop to distribute large amounts of access log data, cleansing and preprocessing the data. Next, TensorFlow is used to train an AI model (UX generation AI) that generates the next action that leads to a sale based on the user's initial behavior. This AI model analyzes user behavior, such as accessing a specific product page or searching for specific keywords, and determines which page to direct the user to next and which product to recommend.

[1131] Terminal

[1132] The device collects user behavior data in real time when the user visits an advertiser's website. Specifically, it uses JavaScript (registered trademark) to collect data such as user clicks, page transitions, and search keywords, and sends this data to a server. The device also has an emotion engine that estimates emotions from the user's facial expressions and voice. For example, it combines OpenCV and TensorFlow to analyze the user's facial expressions and determine whether the user is excited.

[1133] User

[1134] A user visits an advertiser's site and views a specific product page or searches for a specific keyword. The user's behavioral and emotional data is collected in real time and sent to the server. Based on this data, the server uses UX generation AI to generate the next action and make personalized suggestions to the user. For example, if a user is detected to be excited while browsing a product page, the server generates an action such as highlighting the "Buy Now" button.

[1135] Specific examples

[1136] Example 1

[1137] When a user visits an advertiser's website and accesses a specific product page, the device collects this behavioral data and sends it to the server, which then uses UX generation AI to suggest related product pages that the user might be interested in next.

[1138] Example 2

[1139] A user searches for a specific keyword on an advertiser's website. The device collects this search data and sends it to a server. The server then uses UX generation AI to recommend products related to the user's searched keyword.

[1140] Example 3

[1141] When a user is browsing a product page, the emotion engine detects the user's excitement, and the server uses this information to generate an action for the UX generation AI to highlight the "Buy Now" button.

[1142] Prompt Sentence Examples

[1143] "Build an AI model that generates next actions based on a user's initial behavior using access logs from advertisers' websites. Design a system that collects user behavioral and emotional data in real time and makes personalized suggestions."

[1144] In this way, by explaining the system processing from the perspectives of the server, terminal, and user, the role and specific operation of each component becomes clear.

[1145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1146] Step 1:

[1147] The terminal collects user behavior data when the user visits an advertiser's site. Specifically, JavaScript (registered trademark) is used to obtain data such as user clicks, page transitions, and search keywords in real time. The input is user operation data, and the output is collected behavior data. When a user searches for "smartphone," this behavior data records the search keyword and search time.

[1148] Step 2:

[1149] The device also collects user emotion data. Specifically, it uses the device's built-in camera and microphone to analyze the user's facial expressions and voice. By combining OpenCV and TensorFlow, it infers emotions from the user's facial expressions and evaluates the intensity of the emotions through voice analysis. The input is the user's facial and voice data, and the output is the analyzed emotion data. For example, if a user smiles while browsing a product page, the degree of their smile is recorded.

[1150] Step 3:

[1151] The device sends the collected behavioral data and emotional data to the server. The input is the collected behavioral data and emotional data, and the output is the data sent to the server. For example, if a user searches for "smartphone" and smiles while doing so, that information is sent to the server.

[1152] Step 4:

[1153] The server cleanses and preprocesses the transmitted data. Specifically, it complements missing values, removes outliers, and converts the data into a format suitable for AI model learning. The input is the transmitted behavioral and emotional data, and the output is the preprocessed data. For example, if the user's search keywords are incomplete, it performs a process to complement them.

[1154] Step 5:

[1155] The server uses the preprocessed data to train a UX generation AI model using TensorFlow. The input is the preprocessed data, and the output is the trained AI model. This model generates next actions that lead to a sale based on the user's initial behavior. For example, if a user searches for "smartphone," the model learns to recommend "smartphone accessories" next.

[1156] Step 6:

[1157] The server uses a trained UX generation AI model to infer the user's next action in real time. The input is the user's behavioral and emotional data, and the output is the inferred next action. Specifically, the server uses the behavioral and emotional data from when the user visited the site as input to determine which page to direct them to next and which product to recommend. For example, if a user searches for "smartphone" and an excited state is detected, the server generates an action to highlight the "Buy Now" button.

[1158] Step 7:

[1159] The device displays the next action received from the server to the user. The input is the next action sent from the server, and the output is a personalized suggestion displayed to the user. Specifically, the suggestion generated based on the user's behavioral and emotional data is reflected on the webpage. For example, the "Buy Now" button is highlighted, or a banner recommending related products is displayed.

[1160] (Application example 1)

[1161] Next, a description will be given of Application Example 1 of Form 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."

[1162] Conventional advertising systems can suggest the next action based on user behavior data, but they cannot make personalized suggestions that take user emotions into account, limiting their ability to improve conversion rates. Furthermore, they do not dynamically change the site user experience based on user emotions, making it difficult to maximize user interest and attention.

[1163] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for learning the access log of the advertiser site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting a next action that will lead to a contract based on the initial behavior of a user who visited the advertiser site, a means for combining an emotion engine that recognizes the user's emotions, and a means for dynamically changing the site user experience based on the suggestion. This makes it possible to integrate user behavioral data and emotion data to generate the next action and make personalized suggestions that are optimized for each user.

[1164] An "advertiser site" is a website operated by a company or organization that places advertisements.

[1165] An "access log" is data that records the behavioral history of users when they visit a website.

[1166] "Artificial intelligence" is a technology that allows computers to learn and reason by imitating human intelligence.

[1167] "User actions" refer to specific operations or actions that users take on a website.

[1168] "Initial actions" refers to the first action or behavior a user takes when visiting a website.

[1169] An "emotion engine" is a technology for inferring emotions from a user's actions and reactions.

[1170] "Site user experience" refers to the experience and satisfaction a user feels when using a website.

[1171] "Dynamic change" refers to changing the content and display of a website in real time in response to user behavior and emotions.

[1172] "Conversion rate" refers to the percentage of users who visit a website and actually purchase a product or use a service.

[1173] "Personalization" refers to providing optimal content and suggestions based on individual user characteristics and behavior.

[1174] The system for implementing this invention learns access logs from advertiser sites, integrates user behavior data and emotion data, and generates the next action. A specific embodiment of this system will be described below.

[1175] System Configuration

[1176] Hardware

[1177] Server: A high-performance server for collecting, learning, and analyzing data.

[1178] User device: The device used by the user, such as a smartphone, tablet, or computer.

[1179] software

[1180] Artificial Intelligence (AI): An AI model that learns from user behavior data and generates the next action.

[1181] Emotion engine: Software for inferring emotions from user actions and reactions.

[1182] Database: A database for storing user behavioral and emotional data.

[1183] API: An interface for collecting user behavior data and sending it to a server.

[1184] Data processing and calculation

[1185] 1. Collecting User Behavior Data:

[1186] Behavioral data when users visit an advertiser's site (e.g., accessing a specific product page, searching for specific keywords, etc.) is collected through an API.

[1187] 2. Emotion Analysis:

[1188] The emotion engine is used to infer user emotions from collected behavioral data, such as detecting excitement levels from mouse movements and click frequency while users are browsing product pages.

[1189] 3. Generate the next action:

[1190] It uses artificial intelligence to generate next actions based on user behavioral and emotional data, such as highlighting the "Buy Now" button if the user is excited.

[1191] Specific examples

[1192] For example, if a user visits an advertiser's website on their smartphone and is viewing a specific product page, if the emotion engine detects the user's excitement, the AI ​​will generate an action to highlight the "Buy Now" button. This action is a personalized suggestion based on the user's emotions, contributing to an improved conversion rate.

[1193] Prompt Sentence Examples

[1194] If a user visits an advertiser's site and views a particular product page, and the emotion engine detects a state of excitement in the user, what action will the artificial intelligence generate?

[1195] In this way, the emotion-aware advertising assistant system can integrate user behavioral data and emotional data to generate the next action and make personalized suggestions optimized for each user.

[1196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1197] Step 1:

[1198] A user visits an advertiser's site. The user accesses the advertiser's site using a device such as a smartphone or PC. At this time, the user's behavioral data (e.g., access to a specific product page, search for specific keywords, etc.) is collected from the device. The input is the user's behavioral data, and the output is the collected behavioral data.

[1199] Step 2:

[1200] The device sends the collected behavioral data to the server. The device uses an API to send the collected behavioral data to the server. The input is the collected behavioral data, and the output is the behavioral data sent to the server.

[1201] Step 3:

[1202] The server stores the behavioral data in a database. The server stores the received behavioral data in a database. The input is the behavioral data sent to the server, and the output is the behavioral data stored in the database.

[1203] Step 4:

[1204] The server uses an emotion engine to estimate the user's emotions from the behavioral data. The server uses the emotion engine to analyze the user's emotions from the stored behavioral data. For example, it detects the user's excitement level from the mouse movements and frequency of clicks while the user is viewing a product page. The input is the behavioral data stored in the database, and the output is the estimated user's emotion data.

[1205] Step 5:

[1206] The server uses artificial intelligence to generate the next action. The server uses artificial intelligence to generate the next action based on the behavioral data and emotional data. For example, if the user is excited, it generates an action to highlight the "Buy Now" button. The input is the behavioral data and emotional data, and the output is the generated next action.

[1207] Step 6:

[1208] The server sends the generated next action to the terminal. The server sends the generated next action to the terminal. The input is the generated next action, and the output is the next action sent to the terminal.

[1209] Step 7:

[1210] The device dynamically changes the site user experience based on the next action. The device dynamically changes the display or operation of the site based on the next action it receives, for example, highlighting a "Buy Now" button. The input is the next action sent to the device, and the output is the dynamically changed site user experience.

[1211] Example 2

[1212] Next, a description will be given of Example 2 of Form 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."

[1213] Conventional advertiser sites can dynamically change the user experience (UX) by generating the next action based on user behavior data, but because the UX is not optimized with user emotions in mind, there are limitations to improving user satisfaction and conversion rates. Additionally, there is a lack of a system for providing the optimal UX for each user, making it difficult to provide a UX that meets the needs of each individual user.

[1214] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1215] In this invention, the server includes: means for learning the access log of the advertiser's site; means for building artificial intelligence that generates user actions that lead to a contract; means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visit the advertiser's site; means for dynamically changing the site user experience based on the suggestions; an emotion recognition engine that recognizes user emotions in real time; and means for generating next actions based on feedback from the emotion recognition engine. This makes it possible to optimize UX by taking into account both user behavioral data and emotion data, providing an optimal UX for each user, and improving conversion rates and user satisfaction.

[1216] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[1217] An "access log" is a record of behavioral data when a user visits a website, and includes information such as page browsing history, click history, and length of stay.

[1218] "Artificial intelligence" is a technology that allows computers to learn and reason by imitating human intelligence, and generates the next action based on user behavioral and emotional data.

[1219] "User experience" refers to the experience and satisfaction a user feels when using a website, and is influenced by factors such as the site's design, functionality, and content quality.

[1220] An "emotion recognition engine" is a technology that recognizes emotions in real time from a user's facial expressions, voice, text input, etc., and is used to understand the user's emotional state.

[1221] "Feedback" refers to the process of returning information to the system to determine the next action based on the information it has obtained, and refers to sending emotional data from the emotion recognition engine to the artificial intelligence.

[1222] "Dynamic change" means changing the content and functionality of a website in real time based on the user's behavior and emotions, in order to provide the best possible experience for each user.

[1223] MODE FOR CARRYING OUT THE INVENTION

[1224] This invention is a system that dynamically changes the user experience (UX) of an advertiser's website, and generates the next action based on user behavioral data and emotional data. Specific embodiments of this system are described below.

[1225] Hardware and software used

[1226] Server: The server hosts the generative AI model and emotion recognition engine, which recognizes user emotions in real time and dynamically changes the UX.

[1227] Device: The device used by the user (PC, smartphone, tablet, etc.) receives the dynamic UX changes sent from the server.

[1228] Generative AI model: The generative AI model generates the next action based on the user's behavioral and emotional data.

[1229] Emotion Recognition Engine: The emotion recognition engine recognizes user emotions in real time and feeds that information back into the generative AI model.

[1230] Program processing

[1231] 1. User visit: A user visits the advertiser's site. For example, the user opens a browser and enters the advertiser's URL to access the site.

[1232] 2. Data Collection: The server collects user behavior data (clicks, scrolling, time spent, etc.), which gives information such as which pages users view and which links they click.

[1233] 3. Emotion Recognition: The emotion recognition engine recognizes users' emotions in real time, for example, detecting whether a user is feeling anxious from their facial expressions and tone of voice while reading a product review.

[1234] 4. Feedback: The server feeds back the emotion data recognized by the emotion recognition engine to the generative AI model. For example, it sends information that "the user is feeling anxious" to the generative AI model.

[1235] 5. Action Generation: The generative AI model generates the next action based on the feedback emotional and behavioral data. For example, if the user is feeling anxious, it generates an action to highlight the "Worry-Free Return Guarantee" information to alleviate that anxiety.

[1236] 6. UX Modification: Dynamically modify the site's UX based on the server-generated actions, for example dynamically modifying HTML and CSS to prioritize specific product information.

[1237] 7. Display: The device displays the new UX sent from the server. For example, the "No Worry Return Guarantee" information is highlighted on the page the user is viewing.

[1238] Specific examples

[1239] Example 1: When a user visits a site and is looking for a specific product, a generative AI model prioritizes displaying information about that product.

[1240] Example 2: If an emotion recognition engine detects anxiety while a user is reading a product review, a generative AI model will highlight information about the "worry-free return guarantee."

[1241] Prompt Sentence Examples

[1242] "Create an action that prioritizes the display of specific products when a user visits your site."

[1243] "If a user feels anxious while reading a product review, generate an action to alleviate that anxiety."

[1244] This system makes it possible to provide the optimal UX for each user, improving conversion rates and user satisfaction.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] A user visits the site.

[1248] A user opens a browser and enters the advertiser's URL to access the site. The input is the user's access behavior, and the output is the site's homepage being displayed.

[1249] Step 2:

[1250] The server collects user behavior data.

[1251] The server collects user behavior data in real time, such as clicks, scrolls, and time spent on the site. The input is user behavior data, and the output is a log of the collected behavior data. Specifically, it records information such as which pages the user is viewing and which links they clicked.

[1252] Step 3:

[1253] The emotion recognition engine recognizes the user's emotions in real time.

[1254] An emotion recognition engine recognizes emotions from a user's facial expressions, voice, text input, etc. The input is the user's facial expression data and voice data, and the output is recognized emotion data. For example, when a user is reading a product review, it can detect whether the user is feeling anxious from their facial expression or tone of voice.

[1255] Step 4:

[1256] The server feeds the emotion data back to the generative AI model.

[1257] The server sends the emotion data recognized by the emotion recognition engine to the generative AI model. The input is emotion data, and the output is feedback to the generative AI model. For example, information that "the user is feeling anxious" is sent to the generative AI model.

[1258] Step 5:

[1259] The generative AI model generates the next action.

[1260] The generative AI model generates the next action based on the fed-back emotional and behavioral data. The input is emotional and behavioral data, and the output is the generated action. For example, if the user is feeling anxious, the model generates an action to highlight information about the "worry-free return guarantee" as an action to alleviate that anxiety.

[1261] Step 6:

[1262] Dynamically change the site's UX based on server-generated actions.

[1263] The server dynamically changes the site's UX based on the actions generated by the generative AI model. The input is the generated action, and the output is the changed UX. For example, dynamically changing HTML and CSS to prioritize the display of specific product information.

[1264] Step 7:

[1265] The device will display the new UX.

[1266] The device displays the new UX sent from the server. The input is the modified UX, and the output is the new UX displayed on the user's device. For example, the "Worry-Free Return Guarantee" information is highlighted on the page the user is viewing.

[1267] (Application example 2)

[1268] Next, a description will be given of Application Example 2 of Form 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."

[1269] While conventional advertiser sites can generate the next action based on the user's behavioral patterns and dynamically change the user experience on the site, they have not been able to provide an optimal user experience that takes user emotions into consideration. Therefore, in order to further improve user satisfaction and conversion rates, a system is needed that can recognize user emotions in real time and dynamically change the content displayed on the site based on that.

[1270] 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.

[1271] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, and a means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visited the advertiser's site. This makes it possible to learn the behavioral patterns and emotions of users, generate next actions based on them, and dynamically change the user experience on the site.

[1272] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[1273] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as the date and time of the visit, the pages viewed, and the links clicked.

[1274] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, giving them the ability to perform specific tasks automatically.

[1275] "User experience" refers to the experience and satisfaction a user feels when using a website or application, and is influenced by factors such as ease of use, design, and functionality.

[1276] The "emotion engine" is a technology that recognizes emotions in real time from a user's facial expressions, voice, etc., and is used to analyze the user's psychological state.

[1277] "Feedback" refers to the return of information to the system to determine the next action based on the information it has obtained, and the system adjusts its behavior based on the user's actions and emotions.

[1278] "Dynamic change" refers to the system automatically changing the display content and functions in real time according to the situation, in order to provide the optimal experience for each user.

[1279] A system for implementing this invention includes a means for learning the access log of an advertiser's site, a means for constructing artificial intelligence that generates user actions that lead to a conclusion, a means for generating and suggesting next actions that lead to a conclusion based on the initial behavior of a user who visits the advertiser's site, an emotion engine that recognizes user emotions in real time, and a user experience generation artificial intelligence that generates next actions based on feedback from the emotion engine.

[1280] System Program

[1281] The program of this system operates as follows.

[1282] Hardware and Software

[1283] Hardware: Smartphone camera

[1284] Software: OpenCV (image processing library), Keras (deep learning library), UX generation AI module

[1285] Data processing and calculation

[1286] 1. Image capture: Capture the user's face using the smartphone camera, which allows us to obtain facial expression data.

[1287] 2. Emotion Recognition: Detect faces using OpenCV and recognize emotions using a Keras model. Specifically, the captured face image is converted to grayscale, and the facial region is extracted and input into the emotion recognition model.

[1288] 3. UX Generation: The recognized emotion is fed back to the UX Generation AI to generate the next action. For example, if the user feels "anxious," the UX Generation AI will generate an action that highlights the information about the "worry-free return guarantee."

[1289] 4. UX Update: Dynamically change the user experience on your site based on the actions taken, allowing you to provide the best experience for each user.

[1290] Specific examples

[1291] When a user is browsing an online shopping site on their smartphone, the camera captures the user's face, and if the emotion engine detects "anxiety," the UX generation AI generates an action to highlight the "worry-free return guarantee." Based on this action, the content displayed on the site dynamically changes, helping to alleviate the user's anxiety.

[1292] Prompt Sentence Examples

[1293] When a user is browsing an online shopping site, the camera captures the user's face, and if the emotion engine detects "anxiety," create a program in which the UX generation AI generates an action that highlights the information about the "worry-free return guarantee."

[1294] In this way, by providing a user experience that responds to the user's emotions, user satisfaction and conversion rates can be improved.

[1295] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1296] Step 1:

[1297] The device captures the user's face using the smartphone camera, where the input is real-time video data and the output is the captured face image, which is used in subsequent processing steps.

[1298] Step 2:

[1299] The device uses OpenCV to detect the face area from the captured face image. The input is the face image obtained in step 1, and the output is coordinate data indicating the face area. The face area is cut out based on this coordinate data.

[1300] Step 3:

[1301] The device converts the cropped face image to grayscale and performs preprocessing to input it into the Keras model. The input is the face region data obtained in step 2, and the output is the preprocessed face image data. This data is input into the emotion recognition model.

[1302] Step 4:

[1303] The device inputs the preprocessed facial image data into a Keras model to recognize the user's emotions. The input is the facial image data obtained in step 3, and the output is the recognized emotion label (e.g., "anxious," "excited," etc.). This emotion label is used in subsequent processing steps.

[1304] Step 5:

[1305] The server feeds the recognized emotion label back to the UX generation AI to generate the next action. The input is the emotion label obtained in step 4, and the output is the generated action (e.g., highlight the "Worry-Free Return Guarantee" information). This action is used to dynamically change the content displayed on the site.

[1306] Step 6:

[1307] The server dynamically changes the user experience of the site based on the generated actions. The input is the action taken in step 5, and the output is the modified site display. This allows for an optimal experience for each user.

[1308] Example 3

[1309] Next, a description will be given of Example 3 of Form Example 3. 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."

[1310] Conventional advertiser sites have been unable to fully understand user behavior patterns and emotions, making it difficult to improve conversion rates. Furthermore, they were unable to generate actions optimized for each user or dynamically change the site's user experience (UX). This made it difficult to provide a personalized experience based on the user's interests and emotions.

[1311] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1312] In this invention, the server includes means for collecting access logs of advertiser sites, means for analyzing the collected access logs and learning user behavior patterns, means for generating a next action based on the learned behavior patterns, means for reflecting the generated action on the advertiser site, means for collecting user behavior and reactions in real time and estimating emotions, means for generating a next action based on the estimated emotions, and means for reflecting the generated action on the advertiser site. This makes it possible to generate optimal actions based on user behavior patterns and emotions, and dynamically change the UX of the site.

[1313] An "advertiser site" is a website for displaying advertisements, which users can access to view the content of the advertisements.

[1314] An "access log" is data that records information when a user accesses a website, and includes information such as IP address, access date and time, and visited pages.

[1315] "Behavioral patterns" refers to the tendency or pattern of a series of actions taken by a user on a website, including actions such as visiting or clicking on specific pages.

[1316] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and makes predictions and classifications.

[1317] A "natural language processing model" refers to an algorithm or mathematical model for understanding and generating human language, and is used to analyze and generate text data.

[1318] An "emotion engine" is a system for inferring emotions from a user's behavior and reactions, and analyzes emotions using natural language processing models, etc.

[1319] "UX generation AI" refers to an artificial intelligence system that generates the next action based on a user's behavioral patterns and emotions in order to optimize the user experience (UX).

[1320] "Dynamic change" refers to changing the content or presentation of a website in real time, including changing elements of a web page in response to user behavior or emotion.

[1321] This invention is a system that collects access logs from advertiser sites, analyzes user behavior patterns and emotions, generates optimal actions, and dynamically changes the site's user experience (UX). This system is implemented using the following hardware and software.

[1322] Hardware and software used

[1323] 1. Server

[1324] Web server software: Use Apache, Nginx, etc. to store user access data in log files.

[1325] Database: Use a database such as MySQL or PostgreSQL to store and manage the collected access logs.

[1326] Machine learning libraries: Using programming languages ​​such as Python and R and machine learning libraries such as Scikit-learn and TensorFlow to learn user behavior patterns.

[1327] Natural language processing models, such as OpenAI's GPT-4 and IBM Watson, are used to estimate user sentiment.

[1328] 2. Terminal

[1329] Web browser: Used by the user to access the advertiser's site.

[1330] JavaScript and HTML: Used to dynamically change the content of the site.

[1331] Specific operation of the system

[1332] 1. Collection of access logs

[1333] When a user accesses an advertiser's site, the server records information such as the user's IP address, the date and time of access, and the pages visited in a log file.

[1334] The server periodically analyzes the log files and stores them in a database.

[1335] 2. Learning behavioral patterns

[1336] The access logs collected by the server are analyzed to learn user behavior patterns. For example, it learns that users who visit specific product page A are highly likely to also visit product page B.

[1337] The server trains the machine learning model and extracts behavioral patterns.

[1338] 3. Generate the next action

[1339] The server generates the next action based on the behavioral patterns it has learned. For example, it generates an action to recommend product page B to a user who visited product page A.

[1340] Saves the server-generated actions to the database.

[1341] 4. Reflecting Actions

[1342] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[1343] The device displays the generated action to the user.

[1344] 5. Emotion Estimation

[1345] The server collects user behavior and reactions in real time to estimate emotions, such as page scrolling speed and click frequency.

[1346] The server inputs this data into an emotion engine to estimate the user's emotions.

[1347] 6. Emotion-based action generation

[1348] The server generates the next action using the UX generation AI based on the output of the emotion engine. For example, if the user is excited, it generates an action to highlight the "Buy Now" button.

[1349] The server-generated actions are reflected back to the advertiser site.

[1350] Examples of concrete examples and prompts

[1351] Example 1: Learning behavioral patterns and generating actions

[1352] A user visits a specific product page A.

[1353] The server collects access logs and records that the user visited product page A.

[1354] The server analyzes past access logs and learns a pattern that after a user visits product page A, there is a high probability that they will visit product page B.

[1355] Based on this pattern, the server generates an action to recommend product page B to users who visit product page A.

[1356] Prompt Sentence Examples

[1357] When a user visits product page A, generate an action to recommend product page B based on patterns learned from past access logs.

[1358] Example 2: Collaboration between emotion engine and UX generation AI

[1359] While viewing a product page, users engage in behaviors that indicate excitement (e.g., scrolling quickly down the page).

[1360] The server inputs this behavior into an emotion engine to estimate the user's excitement level.

[1361] Based on the output of the emotion engine, the server generates an action for the UX generation AI to highlight the "Buy Now" button.

[1362] Prompt Sentence Examples

[1363] When a user is browsing a product page and behaves in a way that indicates excitement, generate an action based on the output of the emotion engine to highlight the "Buy Now" button.

[1364] The above is a specific embodiment of the system of the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1365] Step 1:

[1366] Collection of access logs

[1367] The server collects access logs for the advertiser's website. Specifically, it uses web server software such as Apache or Nginx to store user access data in log files.

[1368] Input: Information such as the user's IP address, access date and time, and visited pages.

[1369] Output: Access data recorded in a log file.

[1370] Specific operation: When a user accesses an advertiser's site, the server records the access information in a log file.

[1371] Step 2:

[1372] Learning behavioral patterns

[1373] The system analyzes the access logs collected by the server and learns user behavior patterns. This analysis is done using programming languages ​​such as Python and R and machine learning libraries such as Scikit-learn and TensorFlow.

[1374] Input: Access data recorded in the log file.

[1375] Output: Learned behavioral pattern model.

[1376] How it works: The server reads past access logs, analyzes user behavior over time, and trains a machine learning model to extract behavioral patterns.

[1377] Step 3:

[1378] Generate the next action

[1379] The server generates the next action based on the learned behavioral patterns. For example, it generates an action to recommend product page B to a user who visited specific product page A.

[1380] Input: Learned behavioral pattern model, current user behavior data.

[1381] Output: The next action generated.

[1382] Specific operation: When a user visits product page A, the server refers to the behavioral pattern model and generates an action to recommend product page B.

[1383] Step 4:

[1384] Reflecting Actions

[1385] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[1386] Input: The generated next action.

[1387] Output: A dynamically modified web page.

[1388] Specific operation: The server generates JavaScript code to add a link to product page B to product page A, and the device displays the link to product page B to the user.

[1389] Step 5:

[1390] Emotion estimation

[1391] The server collects user behavior and reactions in real time and estimates sentiment using tools such as Google Analytics and Hotjar.

[1392] Input: User behavior data (page scrolling speed, click frequency, etc.).

[1393] Output: Estimated user sentiment.

[1394] Specific operation: When a user is viewing a product page, the server collects behavioral data such as page scrolling speed and click frequency, and inputs this data into an emotion engine to estimate the user's emotions.

[1395] Step 6:

[1396] Emotion-based action generation

[1397] The server generates the next action using the UX generation AI based on the output of the emotion engine. For example, if the user is excited, it generates an action to highlight the "Buy Now" button.

[1398] Input: Estimated user sentiment, current user behavior data.

[1399] Output: The next action generated.

[1400] What it does: The server receives the output of the emotion engine, inputs it into the UX generation AI, and generates an action to highlight the "Buy Now" button.

[1401] Step 7:

[1402] Reflecting emotions in actions

[1403] The server reflects the generated actions on the advertiser's site, specifically by dynamically changing the content of the web page using JavaScript (registered trademark) and HTML.

[1404] Input: The generated next action.

[1405] Output: A dynamically modified web page.

[1406] What happens: The server generates JavaScript code that highlights the "Buy Now" button, and the device displays the highlighted "Buy Now" button to the user.

[1407] (Application example 3)

[1408] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1409] While conventional advertising systems could generate the next action based on a user's behavioral patterns, it was difficult to provide a personalized user experience that took the user's emotions into account. As a result, they were unable to display the optimal ad based on the user's interests and emotions, and could not expect to improve conversion rates. Furthermore, there was a lack of means to dynamically change the site's user experience, making it difficult to display ads that are optimized for each user.

[1410] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1411] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for constructing an artificial intelligence that generates user actions that lead to a conclusion, a means for generating and suggesting a next action that will lead to a conclusion based on the initial behavior of a user who visited the advertiser's site, an emotion engine that recognizes the user's emotions, and a user experience generation artificial intelligence that generates the next action based on the emotions recognized by the emotion engine. This makes it possible to display optimal advertisements based on the user's behavior patterns and emotions, and to dynamically change the user experience on the site.

[1412] "Advertiser Site" means a website for displaying advertisements and an online platform intended for users to visit.

[1413] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as page views and clicks.

[1414] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and has the ability to analyze user behavior patterns and generate optimal actions.

[1415] "User experience" refers to the overall experience a user has when using a website or application, including the ease of use of the interface and the attractiveness of the content.

[1416] An "emotion engine" is a technology for recognizing and analyzing a user's emotions, and infers the user's emotional state from their actions and reactions.

[1417] "User experience generation artificial intelligence" is an artificial intelligence that generates the next action based on the user's emotions recognized by an emotion engine, and is a technology for providing a personalized user experience.

[1418] "Dynamic change" refers to changing the content and interface of a website or application in real time based on user behavior and emotions, providing an experience optimized for each user.

[1419] The system for implementing this invention learns access logs from advertiser sites and generates optimal actions based on the behavioral patterns and emotions of users. A specific embodiment of this system will be described below.

[1420] System Configuration

[1421] Hardware

[1422] Server: A high-performance server for processing data and running artificial intelligence models.

[1423] Device: The smartphone or computer that the user uses to access the service.

[1424] Sensors: Camera and microphone to recognize user emotions.

[1425] software

[1426] Python: A programming language used for data processing and implementing artificial intelligence models.

[1427] scikit-learn: A machine learning library for learning user behavior patterns.

[1428] Custom Sentiment Engine: Software for analyzing user sentiment in real time.

[1429] Custom Ad Recommendation Engine: Software for generating optimal ads based on user sentiment and behavioral patterns.

[1430] Data processing and calculation

[1431] Collecting and learning from access logs

[1432] The server collects access logs when users visit the advertiser's site. These access logs include page browsing history, click information, and time spent on the site. The collected data is analyzed using machine learning algorithms such as clustering and classification using scikit-learn.

[1433] Emotion recognition

[1434] The device's built-in camera and microphone capture the user's facial expressions and tone of voice in real time, and this data is analyzed by a custom sentiment engine to estimate the user's emotional state.

[1435] Generate the next action

[1436] The server combines the user's behavioral patterns learned from the access log with the emotional data recognized by the emotion engine to generate the next ad to be displayed. This process uses a custom ad recommendation engine. The generated ad is personalized according to the user's emotional state and is displayed at the optimal time.

[1437] Specific examples

[1438] For example, if the emotion engine detects a user's excitement while browsing a page for "Product A," it will then highlight an ad for "Product B." In this way, it is possible to provide optimal ads based on the user's behavioral patterns and emotions.

[1439] Prompt Sentence Examples

[1440] When a user is browsing a product page, if the emotion engine detects the user's excitement, generate the next ad to display. Recommend the most appropriate ad by taking into account the user's access log and emotion data.

[1441] In this way, it becomes possible to serve personalized advertisements based on the user's behavioral patterns and emotions.

[1442] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1443] Step 1:

[1444] The server collects access logs when users visit the advertiser's site. As input, it receives data such as the user's page browsing history, click information, and time spent on the site, and stores this data in a database. As output, it obtains the collected access log data.

[1445] Step 2:

[1446] The server learns user behavior patterns using the collected access log data. It receives the access log data as input and applies machine learning algorithms such as clustering and classification using scikit-learn. The output is a model that shows user behavior patterns.

[1447] Step 3:

[1448] The device uses a camera and microphone to capture facial expressions and tone of voice to recognize the user's emotions in real time. As input, it receives the user's facial expression data and voice data and sends them to a custom emotion engine (SentimentEngine). As output, it obtains the user's emotional state.

[1449] Step 4:

[1450] The server combines the emotion data recognized by the emotion engine with the behavioral pattern model to generate the next action. As input, it receives the user's emotion data and behavioral pattern model, and generates the optimal advertisement using a custom ad recommendation engine. The output is a personalized advertisement.

[1451] Step 5:

[1452] The device displays the generated personalized advertisement to the user. As input, it receives the advertisement data sent from the server and displays it on the user's screen. As output, the advertisement optimized for the user is displayed.

[1453] Step 6:

[1454] When a user takes action on a displayed ad (click, purchase, etc.), the user's behavior data is collected as input and sent back to the server. New access log data is obtained as output.

[1455] Step 7:

[1456] The server updates the behavioral pattern model using newly collected access log data. It receives the new access log data as input and performs additional learning on the existing model. The updated behavioral pattern model is obtained as output.

[1457] In this way, it is possible to provide personalized advertising based on user behavior patterns and emotions, dynamically modifying the user experience on the site.

[1458] 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.

[1459] 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> ) 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.

[1460] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1461] 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.

[1462] [Third embodiment]

[1463] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1464] 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.

[1465] 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).

[1466] 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.

[1467] 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.

[1468] 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).

[1469] 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.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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.

[1474] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1475] "Example 1"

[1476] The system of the present invention builds an AI (UX generation AI) that learns from the access logs of advertiser sites. This AI generates and suggests next actions that will lead to a sale based on the initial actions of users who visit the advertiser site. Specifically, based on the initial actions taken by users when they visit the site (e.g., accessing a specific product page, searching for specific keywords, etc.), it generates actions such as which page to direct users to next or which product to recommend.

[1477] "Example 2"

[1478] The generated action is reflected on the advertiser's site, dynamically changing the site's UX. Specifically, when a user visits the site, the content displayed changes based on the generated action. For example, if an action recommending a specific product is generated, information about that product will be displayed preferentially when the user visits the site. This makes it possible to provide an optimal UX for each user and improve conversion rates.

[1479] "Example 3"

[1480] The system of the present invention understands user behavior patterns by studying the access logs of advertiser sites and generates optimal actions based on those patterns. Specifically, the system learns user behavior patterns from past access logs and generates the next action based on those patterns. For example, if the system learns a pattern that users who visit a specific product page have a high probability of purchasing another specific product, it generates the next action based on that pattern.

[1481] The processing flow of each embodiment will be described below.

[1482] "Example 1"

[1483] Step 1: Collect access logs from the advertiser's website, including the initial actions users take when visiting the website (e.g., accessing a specific product page, searching for a specific keyword, etc.).

[1484] Step 2: The collected access logs are trained by AI (UX generation AI). The AI ​​learns user behavior patterns and generates the next action based on them.

[1485] Step 3: The generated action is reflected on the advertiser's site. Specifically, when a user visits the site, the content displayed is changed based on the generated action.

[1486] "Example 2"

[1487] Step 1: Collect initial user actions when visiting your site.

[1488] Step 2: Based on the collected initial behavior, AI (UX generation AI) generates the next action that leads to a successful conclusion.

[1489] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[1490] "Example 3"

[1491] Step 1: Collect access logs from the advertiser's site to understand user behavior patterns.

[1492] Step 2: Learn user behavior patterns from the collected access logs and generate the next action based on those patterns.

[1493] Step 3: Reflect the generated actions on the advertiser's site, dynamically changing the site's UX.

[1494] Example 1

[1495] Next, a description will be given of Example 1 of Form 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."

[1496] Conventional advertiser sites lacked the means to effectively utilize user behavior data to improve conversion rates. In particular, it was difficult to appropriately suggest the next action based on the user's initial behavior and dynamically change the user experience on the site. This meant that it was not possible to make suggestions that were in line with the user's interests and concerns, making it difficult to improve conversion rates.

[1497] 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.

[1498] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for training a generative AI model using the preprocessed data, means for generating and suggesting a next action based on a user's initial behavior, means for sending the generated next action to the user's terminal, and means for dynamically changing the user experience on the site based on the suggestion. This makes it possible to effectively utilize user behavior data and improve the conversion rate.

[1499] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[1500] An "access log" is a record of behavioral data when a user accesses a website, and includes information such as the pages viewed, search keywords, and the date and time of the visit.

[1501] "Database" means a system for storing collected access logs, enabling efficient management and retrieval of data.

[1502] "Preprocessing" refers to processes such as cleaning and normalizing collected data to make it easier to analyze.

[1503] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn user behavior patterns and generate the next action.

[1504] "User initial actions" are the first actions a user takes when accessing a website, including viewing a specific product page or searching for a specific keyword.

[1505] "Next Actions" are suggestions for what a user should do next based on their initial behavior, and can include directing them to a specific page or recommending a product.

[1506] "User experience" refers to the overall experience a user has when using a website, including the ease of use of the site and the quality of the information provided.

[1507] "Dynamic changes" refers to changing the content and structure of a website in real time based on user behavior data.

[1508] MODE FOR CARRYING OUT THE INVENTION

[1509] System Overview

[1510] The system of the present invention collects access logs from advertiser sites and builds a generative AI model that learns user behavior patterns based on these logs. This AI model generates and suggests next actions based on the user's initial behavior. Specifically, based on the user's initial behavior when visiting a site (e.g., accessing a specific product page, searching for a specific keyword, etc.), it generates actions such as which page to direct the user to next or which product to recommend.

[1511] Hardware and software used

[1512] The server collects, stores, and preprocesses access logs, trains the AI ​​model, and generates the next action. Specifically, it uses the following hardware and software:

[1513] Hardware: High-performance servers (CPU, GPU, memory, storage)

[1514] Software: Database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, PyTorch)

[1515] The device records the user's behavior data and sends it to the server, and also receives suggestions for next actions sent from the server and displays them to the user.

[1516] Hardware: User's device (e.g. smartphone, computer)

[1517] Software: web browser, mobile application

[1518] Specific operation of the system

[1519] 1. Collection of access logs

[1520] The server collects real-time behavioral data of users who visit the advertiser's site, specifically recording information such as which pages users viewed and which keywords they searched for.

[1521] 2. Data storage

[1522] The server stores the collected access logs in a database, including user IDs, visit dates and times, viewed pages, and search keywords.

[1523] 3. Data Preprocessing

[1524] The server preprocesses the stored data, specifically cleaning the data (filling in missing values ​​and removing outliers) and normalizing (scaling) the data.

[1525] 4. Training the AI ​​model

[1526] The server uses the preprocessed data to train a generative AI model using machine learning libraries such as TensorFlow and PyTorch.

[1527] 5. Generate the next action

[1528] The server uses the trained AI model to generate the next action based on the user's initial behavior, specifically predicting which page the user should be directed to next and which product to recommend.

[1529] 6. Submit your proposal

[1530] The server then sends the generated next action to the user's device, which then suggests appropriate pages and products to the user.

[1531] Specific examples

[1532] Suppose a user visits an advertiser's website and views a page for a specific smartphone model. The device records this behavior and sends it to the server. The server stores this data in a database, preprocesses it, and trains a generative AI model. The trained AI model determines that the user should next be directed to a page for smartphone accessories and related products, and sends this suggestion to the device. The device displays the suggestion to the user, who then views the suggested page.

[1533] Prompt Sentence Examples

[1534] "When a user visits an advertiser's website and views a specific product page, please build an AI model that will determine which page to direct them to next and which product to recommend. Specifically, this is a system that will suggest the next action that will lead to a sale based on the user's initial behavioral data."

[1535] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1536] Step 1:

[1537] Collection of access logs

[1538] The server collects real-time behavioral data of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavioral data, and the output is the collected access log.

[1539] Step 2:

[1540] Data storage

[1541] The server stores the collected access logs in a database. The stored data includes the user ID, visit date and time, viewed pages, search keywords, etc. The collected access logs are the input, and the access logs stored in the database are the output.

[1542] Step 3:

[1543] Data Preprocessing

[1544] The server preprocesses the stored data. Specifically, it cleans the data (fills in missing values ​​and removes outliers), normalizes the data (scales it), etc. The input is the access log stored in the database, and the output is the preprocessed data.

[1545] Step 4:

[1546] Training an AI model

[1547] The server uses the preprocessed data to train a generative AI model. For training, it uses machine learning libraries such as TensorFlow and PyTorch. The input is the preprocessed data, and the output is a trained generative AI model.

[1548] Step 5:

[1549] Generate the next action

[1550] The server uses the trained AI model to generate the next action based on the user's initial behavior. Specifically, it predicts which page the user should be directed to next and which product should be recommended. The input is the user's initial behavior data, and the output is the generated next action.

[1551] Step 6:

[1552] Submit a proposal

[1553] The server sends the generated next action to the user's device, which then suggests appropriate pages or products to the user. The input is the generated next action, and the output is the suggestion sent to the user's device.

[1554] Step 7:

[1555] Receiving and Viewing Suggestions

[1556] The terminal receives the next action suggestions sent from the server and displays them to the user. The input is the suggestion sent from the server, and the output is the suggestion displayed to the user.

[1557] Step 8:

[1558] User Behavior

[1559] The user accepts the suggestion displayed on the device and performs the next action, such as viewing the suggested product page or purchasing the recommended product. The input is the suggestion displayed on the device, and the output is new behavioral data of the user.

[1560] (Application example 1)

[1561] Next, a description will be given of Application Example 1 of Form 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."

[1562] On conventional advertiser sites, it was difficult to appropriately suggest the next action that would lead to a sale based on the user's initial behavior. As a result, it was not possible to stimulate the user's desire to purchase, and it was not possible to expect an improvement in the sale rate. In addition, it was not possible to provide an optimized site user experience for each user, which meant it was not possible to improve user satisfaction.

[1563] 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.

[1564] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial actions of users who visit the advertiser's site, means for dynamically changing the site user experience based on the suggestions, and means for analyzing the user's initial actions and suggesting in real time which product to view next and which page to proceed to. This makes it possible to appropriately suggest next actions that lead to a contract based on the user's initial actions, which is expected to improve the contract rate and user satisfaction.

[1565] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[1566] An "access log" is data that records the behavioral history of users when they access a website, and includes information such as page views and search keywords.

[1567] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, giving them the ability to perform specific tasks automatically.

[1568] "User initial actions" are the first actions a user takes when visiting a website, such as accessing a specific product page or searching for a specific keyword.

[1569] "Conclusion" refers to a user purchasing a product or service on the website, meaning that the transaction is concluded.

[1570] "Next Action" refers to the next action a user should take on a website, suggesting actions that are more likely to lead to a sale.

[1571] "Site user experience" refers to the overall experience a user has when using a website, including ease of use and satisfaction.

[1572] "Dynamic change" refers to changing the content and structure of a website in real time in response to user behavior and circumstances.

[1573] "Real-time suggestions" refers to instantly analyzing user behavior and immediately suggesting the next action based on the results.

[1574] The system for implementing this invention constructs an artificial intelligence that learns from the access logs of advertiser sites and generates user actions that lead to sales. A specific embodiment of this system will be described below.

[1575] System configuration

[1576] The system consists of the following main components:

[1577] 1. Server: Collects access logs from advertiser sites and stores them as learning data.

[1578] 2. Artificial Intelligence (AI): Generates and suggests next actions based on the user's initial behavior.

[1579] 3. User Device: The device through which a user accesses an advertiser's site (e.g., smartphone, tablet, PC).

[1580] 4. Database: Data storage for storing access logs and user behavior data.

[1581] Program processing

[1582] Data collection and learning

[1583] The server collects access logs of users who visit the advertiser's site. These access logs include information such as which pages users viewed and what keywords they searched for. The collected data is stored in a database and used by the AI ​​as learning data.

[1584] User behavior analysis

[1585] The AI ​​analyzes the collected access logs and learns the initial behavioral patterns of users, generating a model that predicts what actions users should take to close a deal.

[1586] Suggested next actions

[1587] When a user visits an advertiser's website, AI analyzes the user's initial behavior in real time and suggests which products to view next and which pages to go to. These suggestions are displayed on the user's device to guide the user's actions.

[1588] Hardware and software used

[1589] Hardware: Servers, user devices (smartphones, tablets, PCs)

[1590] Software: Python, Pandas, Scikit-learn, database management system (e.g., MySQL)

[1591] Specific examples

[1592] For example, if a user views "Product A page" on an advertiser's website, gets 5 page views, and searches for "special price," AI will suggest that the user should next view "Product B page." This suggestion increases the user's desire to purchase and contributes to improving the conversion rate.

[1593] Prompt Sentence Examples

[1594] If a user views Product A's page, has 5 page views, and their search keyword is "Special Offer," predict which page they will view next.

[1595] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[1596] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1597] Step 1:

[1598] The server collects access logs of users who visit the advertiser's site. Specifically, it records information such as which pages users viewed and which keywords they searched for. The input is user behavior data, and the output is access log data.

[1599] Step 2:

[1600] The server saves the collected access log data in a database. The input is the access log data, and the output is the log data saved in the database. Specifically, the data is stored using a database management system (e.g., MySQL).

[1601] Step 3:

[1602] The server provides the access log data stored in the database to the artificial intelligence to use as training data. The input is the access log data obtained from the database, and the output is a trained artificial intelligence model. Specifically, the data is preprocessed using Python's Pandas library, and the model is trained using the Scikit-learn library.

[1603] Step 4:

[1604] When a user accesses an advertiser's website, the device sends the user's initial behavior data to the server. The input is the user's initial behavior data, and the output is the data sent to the server. Specifically, the device captures the user's behavior in real time and sends it to the server.

[1605] Step 5:

[1606] The server inputs the received initial behavior data into the AI ​​to predict the next action. The input is the user's initial behavior data, and the output is a proposal for the next action. Specifically, the data is input into a trained AI model to obtain a prediction result.

[1607] Step 6:

[1608] The server sends the predicted next action to the user's device. The input is the prediction result, and the output is a suggestion to be displayed on the user's device. Specifically, the server formats the prediction result and sends it to the user's device.

[1609] Step 7:

[1610] The user's device displays the received proposal to the user. The input is the proposal sent from the server, and the output is the information displayed to the user. Specifically, the proposal content is displayed in the user interface.

[1611] In this way, it becomes possible to appropriately suggest the next action that will lead to a successful sale based on the user's initial behavior, which is expected to improve the success rate and user satisfaction.

[1612] Example 2

[1613] Next, a description will be given of Example 2 of Form 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."

[1614] On conventional advertiser sites, it was difficult to effectively utilize user behavior data to provide an optimized user experience (UX) for each individual user. As a result, there was an issue of insufficient improvement in conversion rates. In particular, it was not possible to dynamically change the content displayed on the site based on the user's initial behavior, making it difficult to respond to the different needs of each user.

[1615] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1616] In this invention, the server includes a means for learning the access log of the advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, and a means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visited the advertiser's site. This enables a system that includes a means for collecting user behavior data and saving the generated actions in a database, and a means for acquiring the generated actions when the user visits the site again and dynamically changing the display content. This makes it possible to provide an optimized UX for each user and improve the conversion rate.

[1617] An "advertiser site" is a website that displays advertisements and that users can access to obtain information about products and services.

[1618] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as page views, clicks, and length of stay.

[1619] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and is particularly used to analyze user behavior data and generate optimal actions.

[1620] "User action" refers to a specific operation or action a user takes on a website, such as clicking on an item, adding it to a cart, or purchasing it.

[1621] "User experience (UX)" refers to the overall experience and satisfaction a user feels when using a website, and is influenced by factors such as the site's ease of use, design, and the quality of the information provided.

[1622] "Dynamic change" refers to changing the content and functionality of a website in real time in order to provide optimal information according to the user's behavior and situation.

[1623] "Behavioral data" refers to data about a series of actions or behaviors a user performs on a website, including browsing history, click patterns, purchase history, etc.

[1624] A "database" is a system for efficiently storing, managing, and retrieving data, and is used to store generated action and user behavior data.

[1625] "Generated actions" refers to the next optimal action or suggestion generated by artificial intelligence after analyzing user behavioral data.

[1626] "Displayed Content" refers to the information and content displayed to users on a website, including text, images, videos, links, etc.

[1627] The present invention is a system for dynamically optimizing the user experience (UX) of an advertiser's site. A specific embodiment of this system will be described below.

[1628] System Overview

[1629] This system consists of three main elements: a server, a device, and a user. The server collects user behavior data and generates optimal actions using a generative AI model. When a user visits a site, the device obtains the actions generated by the server and dynamically changes the displayed content. By visiting the site, the user experiences an optimized UX.

[1630] Hardware and software used

[1631] Server: Use a high-performance server machine (e.g., AWS EC2 instance).

[1632] Database: Use a relational database such as MySQL or PostgreSQL.

[1633] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[1634] Analytics tools: Use user behavior analytics tools such as Google Analytics and Mixpanel.

[1635] Data processing and calculation

[1636] The server collects user behavior data (e.g., browsing history, click patterns, purchase history, etc.) in real time. The collected data is stored in a database. The server then inputs prompt statements into a generative AI model to generate optimal actions. The generated actions are stored in the database, and when the user visits the site again, the device retrieves them and dynamically changes the displayed content.

[1637] Specific examples

[1638] For example, if a user visits an online shopping site and frequently browses pages about sporting goods, the server might input the following prompts into the generative AI model:

[1639] Recommend the best product for this user.

[1640] The generative AI model analyzes the input data and generates an action, "recommend sporting goods." The server stores this action in a database, and the device retrieves it when the user visits the site again. The device then displays a banner for sporting goods on the homepage based on the retrieved action.

[1641] In this way, we can provide an optimized UX for each user and improve conversion rates.

[1642] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1643] Step 1:

[1644] A user visits the site.

[1645] Input: The user opens a browser and enters the URL of the advertiser's site.

[1646] Output: A user visits the site and some initial behavioral data is generated.

[1647] Specific behavior: A user visits an online shopping site and the homepage is displayed.

[1648] Step 2:

[1649] The server collects user behavior data.

[1650] Input: Behavioral data such as user browsing history, click patterns, and purchase history.

[1651] Output: Collected behavioral data is stored in a database.

[1652] Specific operation: The server uses analytical tools such as Google Analytics and Mixpanel to collect user behavior data in real time and store it in a database.

[1653] Step 3:

[1654] The server inputs prompt statements into the generative AI model and generates the optimal action.

[1655] Input: Collected behavioral data and a prompt (e.g., "Recommend the best product for this user").

[1656] Output: The optimal action obtained from the generative AI model.

[1657] Specific operation: Based on the collected behavioral data, the server inputs a prompt statement such as "Recommend the best product for this user" into the generative AI model (e.g., GPT-4) and generates the optimal action.

[1658] Step 4:

[1659] The server saves the generated action in the database.

[1660] Input: The optimal action obtained from the generative AI model.

[1661] Output: Actions stored in the database.

[1662] Specific operation: The server stores the generated actions in a database such as MySQL or PostgreSQL.

[1663] Step 5:

[1664] The terminal acquires the generated action from the server when the user visits.

[1665] Input: The request when the user returns to the site.

[1666] Output: The generated actions retrieved from the server.

[1667] Specific operation: When the user visits the site again, the device sends a request to the server and retrieves the generated action.

[1668] Step 6:

[1669] Dynamically change the display content based on the actions taken by the device.

[1670] Input: The generated action retrieved from the server.

[1671] Output: The dynamically changed display content.

[1672] Specific behavior: The device dynamically changes the content displayed based on the action taken, such as displaying a sports goods banner on the home page.

[1673] Step 7:

[1674] Users experience an optimized UX.

[1675] Input: Dynamically changed display content.

[1676] Output: Improved user satisfaction and higher conversion rates.

[1677] What it does: By simply visiting the site, users experience a personalized UX, with sporting goods information displayed first.

[1678] (Application example 2)

[1679] Next, a description will be given of Application Example 2 of Form 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."

[1680] On traditional advertiser sites, it was difficult to provide an optimal user experience for each user, making it difficult to improve conversion rates. Furthermore, there was a lack of effective ways to utilize users' past purchase and browsing histories, making it impossible to recommend appropriate products to users. This resulted in a failure to attract users' interest, resulting in a lower conversion rate.

[1681] 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.

[1682] In this invention, the server includes means for learning the access log of the advertiser's site, means for building artificial intelligence that generates user actions that lead to a contract, means for generating and suggesting next actions that lead to a contract based on the initial behavior of users who visit the advertiser's site, means for dynamically changing the user experience of the site based on the suggestions, and means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions. This makes it possible to provide an optimal user experience for each user and improve the conversion rate.

[1683] "Advertiser Site" means a website that displays advertisements and an online platform that users can visit to view and purchase products and services.

[1684] An "access log" is data that records the behavioral history of a user when they visit a website, and includes information such as the date and time of the visit, the pages viewed, and the links clicked.

[1685] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn, reason, and make decisions, particularly with the ability to analyze user behavior patterns and generate the next action.

[1686] "User experience" refers to the overall experience a user has when using a website or application, and includes factors such as ease of use, satisfaction, and convenience.

[1687] "Purchase history" is a record of products and services purchased by a user in the past, and includes information such as the purchase date and time, product name, and price.

[1688] "Browsing history" refers to a record of the pages and products a user has viewed on a website, including the date and time of the viewing, the pages viewed, and information about the products viewed.

[1689] "Dynamic change" refers to changing the content and functions of a website in real time according to the user's behavior and situation, and flexibly changing from a fixed display.

[1690] The "conversion rate" is an indicator that shows the percentage of users who actually purchase products or services among those who visit a website, and is an important indicator for measuring the effectiveness of marketing and sales.

[1691] A system for implementing this invention includes a means for learning the access log of an advertiser's site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that will lead to a contract based on the initial behavior of a user who visits the advertiser's site, a means for dynamically changing the user experience of the site based on the suggestions, and a means for acquiring the user's past purchase history and browsing history and dynamically changing the display content based on the generated actions.

[1692] System configuration

[1693] The server uses the following hardware and software:

[1694] Hardware: A server with a powerful processor, sufficient memory, and storage

[1695] Software: Python, API request library (requests), API for generative AI models

[1696] Data processing and calculation

[1697] 1. Obtaining user information: When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history using an API request.

[1698] 2. Sending prompts to the generative AI model: The server sends the acquired user information as prompts to the generative AI model, which then generates the optimal action for the user (such as recommended products).

[1699] 3. Dynamically changing the site content: The server dynamically changes the site content based on the generated action. Specifically, the recommended products are reflected in the site content.

[1700] Specific examples

[1701] For example, if a user has previously purchased "smartphone accessories" and recently browsed "smartwatches," the generative AI model will generate an action that recommends "smartwatch accessories."

[1702] Prompt Sentence Examples

[1703] User's past purchase history: Smartphone accessories, browsing history: Smartwatch

[1704] By sending this prompt to a generative AI model, the most appropriate product recommendation for each user is made, providing an optimal user experience and improving conversion rates.

[1705] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1706] Step 1:

[1707] When a user visits an advertiser's site, the server obtains the user's past purchase history and browsing history.

[1708] Input: User ID

[1709] Data processing: Use API requests to retrieve user purchase and browsing history.

[1710] Output: User purchase and browsing history data

[1711] Step 2:

[1712] The server sends the acquired user information to the generative AI model as a prompt.

[1713] Input: User purchase and browsing history data

[1714] Data calculation: Convert user information into a text prompt and send it to the API of the generative AI model.

[1715] Output: Recommended actions from the generative AI model (e.g., recommended products)

[1716] Step 3:

[1717] The server dynamically changes the content displayed on the site based on the generated actions.

[1718] Input: Recommended actions from a generative AI model

[1719] Data processing: Obtain site content data and update it to prioritize the display of recommended products.

[1720] Output: Updated site content data

[1721] Step 4:

[1722] When a user visits a site, the user views dynamically changed display content.

[1723] Input: Updated site content data

[1724] Data Calculation: Display the updated content in the user's browser.

[1725] Output: User-optimized display

[1726] Step 5:

[1727] The server records the user's new behavior data in the access log.

[1728] Input: User behavior data (e.g. clicks, pages viewed)

[1729] Data processing: Add new behavioral data to the access log.

[1730] Output: Updated access log

[1731] Example 3

[1732] Next, a third embodiment of the third embodiment will be described. 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."

[1733] On conventional advertiser sites, it was difficult to fully understand users' behavioral patterns and propose optimal actions. As a result, there were problems with low conversion rates and insufficient advertising effectiveness. Furthermore, it was not possible to make proposals optimized for each user, making it difficult to meet the needs of individual users.

[1734] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1735] In this invention, the server includes means for collecting access logs of advertiser sites, means for saving the collected access logs in a database, means for preprocessing the saved access logs, means for building a generative AI model that learns user behavior patterns using the preprocessed data, means for generating a next action based on the learned behavior pattern, means for sending the generated action to the terminal, means for the user to take action based on the action displayed on the terminal, and means for recording the action again as an access log. This makes it possible to accurately understand user behavior patterns and propose actions optimized for each user.

[1736] An "advertiser site" is a website that displays advertisements and that users can visit to obtain information about products and services.

[1737] An "access log" is data that records the behavioral history of users when they visit a website, including actions such as page views, clicks, and purchases.

[1738] A "database" is a system for storing collected access logs, and includes relational databases, NoSQL databases, etc.

[1739] "Preprocessing" refers to the process of preparing the collected access logs in a format that is easy to analyze, and includes data cleaning and normalization.

[1740] A "generative AI model" is a model that uses machine learning algorithms to learn user behavior patterns and predict their next actions.

[1741] An "action" is what the user should do next, such as purchasing a particular product or visiting a particular page.

[1742] "Terminal" refers to a device used by a user, including a PC, smartphone, tablet, etc.

[1743] "Behavioral patterns" refer to the tendency of a series of actions that a user takes on a website, and are learned from past access logs.

[1744] "Suggestion" refers to the next action that the generative AI model suggests to the user based on the behavioral patterns it has learned.

[1745] "Conversion rate" refers to the percentage of users who take a suggested action and actually achieve their goal, such as purchasing a product.

[1746] This invention is a system that collects access logs from advertiser sites, learns user behavior patterns, and then generates and suggests optimal next actions to users. Specific embodiments of this system are described below.

[1747] Server Processing

[1748] The server collects access logs for the advertiser's website. The access logs include information such as the pages visited by users, the links clicked, and the products purchased. This data is collected using web server logs such as Apache and Nginx.

[1749] The server then stores the collected access logs in a relational database such as MySQL or PostgreSQL, and the stored data includes user IDs, visited pages, and action timestamps.

[1750] The stored access logs are subjected to preprocessing such as data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This process is often performed using the Python Pandas library.

[1751] Using the preprocessed data, the server builds a generative AI model, which is built using machine learning frameworks such as TensorFlow and PyTorch. The model learns user behavior patterns from past access logs and predicts the next action to be taken.

[1752] Based on the learned behavioral patterns, the server generates the next optimal action for the user. For example, if a user visits a specific product page, it will suggest the next product they are likely to purchase. This suggestion is made in real time using a generative AI model.

[1753] The generated actions are sent to the terminal in JSON format via the REST API.

[1754] Terminal handling

[1755] The device receives the optimal action sent from the server and presents it to the user, for example, as a pop-up on a web page or by sending an email notification.

[1756] User Action

[1757] The user checks the next action displayed on the device and purchases the product if necessary. The user's response is also recorded as an access log and will be used for the next learning.

[1758] Specific examples

[1759] For example, suppose a user visits the "Smartphone A" page on an advertiser's website. The server studies past access logs and knows that users who visit "Smartphone A" are highly likely to purchase "Smartphone Case B." In this case, the server suggests to the user that they purchase "Smartphone Case B" as their next action.

[1760] Prompt Sentence Examples

[1761] "If a user visits the page on smartphone A, please suggest the next product they are likely to purchase."

[1762] In this way, a system is realized in which the server, the terminal, and the user work together to generate optimal actions based on the user's behavioral patterns and present them to the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1763] Step 1:

[1764] The server collects access logs for the advertiser's website, specifically recording actions taken by users on the website, such as page views, clicks, and purchases. The input includes user behavior data, and the output is stored in a log file.

[1765] Step 2:

[1766] The server stores the collected access logs in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input includes the collected access logs, and the output is structured data stored in the database.

[1767] Step 3:

[1768] The server preprocesses the stored access logs. Specifically, it performs data cleaning (filling in missing values ​​and removing outliers) and normalization (scaling the data). This processing is performed using the Python Pandas library. The input includes the raw data stored in the database, and the output is the preprocessed, clean data.

[1769] Step 4:

[1770] The server uses the preprocessed data to build a generative AI model that learns user behavior patterns. Specifically, it trains a neural network using a machine learning framework such as TensorFlow or PyTorch. The input includes the preprocessed data, and the output is a trained generative AI model.

[1771] Step 5:

[1772] The server generates the next action based on the learned behavioral patterns. Specifically, it uses a generative AI model to predict the next action the user should take. The inputs include the trained generative AI model and real-time user behavior data, and the output is the optimal next action.

[1773] Step 6:

[1774] The server sends the generated action to the device. Specifically, it sends data in JSON format via a REST API. The input contains the generated action, and the output is the action data sent to the device.

[1775] Step 7:

[1776] The device then presents the optimal action received from the server to the user, for example, by displaying it as a pop-up on a web page or by sending an email notification. The input includes the action data sent from the server, and the output is the action presented to the user.

[1777] Step 8:

[1778] The user checks the next action displayed on the terminal and purchases the product if necessary. Specifically, the user purchases the product on the website according to the presented action. The input includes the action displayed on the terminal, and the output is the user's purchasing behavior.

[1779] Step 9:

[1780] The server records the user's response again as an access log. Specifically, it saves the user's actions as a new access log. The input contains the user's behavior data, and the output is an updated access log.

[1781] (Application example 3)

[1782] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1783] Conventional ad delivery systems were unable to fully grasp user behavior patterns, making it difficult to display the right ad at the right time. As a result, they were unable to attract user interest and could not expect to improve conversion rates. In addition, because ads were not displayed in an optimized format for each user, there was a problem of reduced advertising effectiveness.

[1784] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for learning the access log of the advertiser site, a means for building artificial intelligence that generates user actions that lead to a contract, a means for generating and suggesting next actions that lead to a contract based on the initial behavior of a user who visited the advertiser site, a means for dynamically changing the site user experience based on the suggestions, and a means for learning the user's past website visit history and displaying advertisements that are likely to interest the user in real time. This makes it possible to grasp the user's behavioral patterns in detail and display appropriate advertisements at the optimal timing.

[1785] "Advertiser Site" means a website for displaying advertisements and an online platform intended for users to visit.

[1786] An "access log" is data that records the behavioral history of users when they visit a website, and includes information such as the pages visited and the length of time spent on the website.

[1787] "Artificial intelligence" is a technology that allows computer systems to imitate human intelligence to learn and reason, and has the ability to analyze user behavior patterns and generate the next action.

[1788] "User experience" refers to the experiences and feelings that users have when using a website or application, and affects the ease of use and satisfaction of the site.

[1789] "Dynamic change" means changing the content and layout of a website in real time according to the user's behavior and situation, providing an optimized display for each user.

[1790] "Website visit history" refers to a record of websites a user has visited in the past, including information such as pages visited, time spent there, and links clicked.

[1791] "Displaying in real time" means instantly displaying ads or content based on the user's current behavior and situation, providing information without delay.

[1792] The system for carrying out this invention learns access logs of advertiser sites, analyzes user behavior patterns, and displays optimal advertisements in real time. A specific embodiment of this system will be described below.

[1793] The server first collects access logs from the advertiser's website and stores them in a database. These access logs include information such as the pages visited by users, the time spent there, and the links clicked. The server then uses these access logs to build an artificial intelligence model to learn user behavior patterns. This model is trained using Python libraries such as pandas and scikit-learn.

[1794] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time and generates the next optimal action to take. This action is to display an advertisement that the user is likely to be interested in. The server references the user's past website visit history and selects the most appropriate advertisement based on information such as the pages the user previously visited and the length of time they spent there.

[1795] For example, if a user previously visited a specific fashion brand's website and stayed on a specific product page for 120 seconds, the server would prioritize displaying new products and sales information from the same brand to that user. In this way, ads are displayed that are optimized for each user, which is expected to improve conversion rates.

[1796] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to generate advertisements based on user behavior patterns.

[1797] Example prompt sentence:

[1798] Predict the next ad to display based on the user's history of previously visited websites. For example, if a user visits the website of "Fashion Brand A" and stays on a specific product page for 120 seconds, display information about new products and sales from "Fashion Brand A" to that user.

[1799] This system makes it possible to grasp user behavior patterns in detail and display appropriate advertisements at the optimal time, which is expected to improve advertising effectiveness and conversion rates.

[1800] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1801] Step 1:

[1802] The server collects access logs for the advertiser's website and stores them in a database. It receives information such as the pages visited by the user, the time spent there, and the links clicked as input, and stores this data in the database. Specifically, the web server collects access logs in real time and stores them in a database management system (e.g., MySQL or PostgreSQL).

[1803] Step 2:

[1804] The server uses the collected access logs to build an AI model to learn user behavior patterns. As input, it uses the access logs stored in the database and processes the data to extract features (for example, number of page visits, average length of stay, etc.). As output, it generates a trained AI model. Specifically, it preprocesses the data using Python's pandas and trains the model using scikit-learn's RandomForestClassifier, etc.

[1805] Step 3:

[1806] When a user visits an advertiser's site, the server analyzes the user's initial behavior in real time. As input, it receives the user's current behavior data (pages visited, time spent, etc.) and inputs this into the artificial intelligence model that was previously constructed. As output, it generates the next optimal action to be taken (the advertisement to be displayed). Specifically, it inputs the data collected in real time into the model and obtains the predicted results.

[1807] Step 4:

[1808] The server references the user's past website visit history and selects advertisements that are likely to interest the user. The server uses the user's past visit history data as input and processes the data by analyzing past behavioral patterns. The output is the selection of the most suitable advertisement. Specifically, it retrieves past visit history from a database and analyzes it using an artificial intelligence model.

[1809] Step 5:

[1810] The server displays the selected advertisement to the user in real time. It uses the selected advertisement data as input and displays the advertisement on the user's screen as output. Specifically, it dynamically changes the content of the web page to insert the advertisement.

[1811] Step 6:

[1812] The server again collects user responses after the ad is displayed as an access log and stores it in a database. It receives user response data to the ad (clicks, time spent, etc.) as input and stores this in the database. Specifically, the web server collects user responses in real time and stores them in a database management system.

[1813] This series of processes allows for a detailed understanding of user behavior patterns and makes it possible to display appropriate advertisements at optimal times, which is expected to improve advertising effectiveness and conversion rates.

[1814] 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.

[1815] "Example 1"

[1816] One embodiment of the present invention is a system that incorporates an emotion engine. This system combines an AI (UX generation AI) that learns from the access logs of advertisers' websites and generates the next action that leads to a sale based on the user's initial behavior (UX generation AI), with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine infers the user's emotions from their actions and reactions when visiting the website, and the UX generation AI generates the next action based on those emotions. For example, if the emotion engine detects the user's excitement while browsing a product page, the UX generation AI takes that excitement into account and generates an action, such as highlighting the "Buy Now" button. This provides a personalized UX that reflects the user's emotions, contributing to an improved conversion rate.

[1817] "Example 2"

[1818] Another embodiment of the present invention is a system in which an emotion engine and a UX generation AI work t...

Claims

1. A means for collecting access logs of the advertiser's site; A means for storing the collected access logs in a database; means for performing pre-processing to clean and normalize the stored access log data; A means for constructing a generative AI model by learning a user's behavioral patterns using the preprocessed data; A means for generating a next action based on an initial action of a user who accessed the advertiser site using the learned generating AI model; means for dynamically modifying a user experience of the advertiser site based on the generated next action; A system including:

2. A means for collecting actions and reactions of the users who access the advertiser site in real time and estimating emotions using an emotion engine; generating the next action based on the estimated emotion and the initial behavior using the generative AI model; The system of claim 1 .

3. the user experience is optimized for the user; A system according to claim 1 or claim 2.

Images