system

Abstract

We provide the system. [Solution] Methods for collecting product information data from web pages, A generative information processing device means for detecting anomalies in text information based on the aforementioned product information data, An image analysis device means for detecting anomalies in image information based on the aforementioned product information data, A warning device means that generates and transmits notification information when an abnormality is detected, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In an online sales platform, it is difficult to accurately manage a large number of product information. In particular, incorrect information registration due to human error may bring disadvantages to both sellers and buyers. Also, since the risk of incorrect registration during price changes or information updates related to sales is high, a system that can prevent such problems and improve business efficiency is required.

Means for Solving the Problems

[0005] This invention provides a system for monitoring listing information overall by detecting anomalies in text information using a generative information processing device and further detecting anomalies in image information using an image analysis device, based on product information collected from web pages. When an anomaly is detected, this system immediately generates notification information using a warning device and sends it to the relevant parties, enabling the rapid correction of incorrectly registered information and achieving efficient and accurate listing management.

[0006] A "web page" is a document published on the internet, written in HTML format, and is a unit of information that can be viewed using a web browser.

[0007] "Product information data" refers to information such as the product name, price, description, and images displayed on a webpage.

[0008] A "generative information processing device" is a device that uses artificial intelligence technology to analyze input text data and has the function of detecting anomalies.

[0009] An "image analysis device" is a device that uses machine learning models to analyze input image data and detects deviations from expected criteria as anomalies.

[0010] "Notification information" refers to information sent from the system to relevant parties when an anomaly is detected, and includes details of the anomaly and any parts that need correction.

[0011] A "warning device means" is a part of a system that has the function of promptly generating notification information and transmitting it to the relevant parties when an anomaly is detected. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This embodiment of the present invention relates to a product information management system for an online sales platform, and in particular, to preventing human error and ensuring the accuracy of information using anomaly detection and notification functions. The components of the present invention and their operation are described in detail below.

[0034] The system consists of a server, terminals, and users. The server is primarily responsible for backend processing and is tasked with collecting product information data from web pages. The server retrieves HTML data from specific URLs and uses an analysis program to extract information such as product names, prices, descriptions, and image URLs. Subsequently, the server uses a generative information processing device to determine, based on natural language processing technology, whether there are any anomalies in the product names and descriptions.

[0035] Furthermore, the server uses an image analysis device to analyze product images obtained from image URLs and employs machine learning modeling techniques to evaluate whether the images meet expectations. This reduces the risk of incorrect or inappropriate images being registered.

[0036] If an anomaly is detected, the server immediately activates the warning system and generates notification information. The generated notification information is sent to the user's terminal, allowing the user to quickly correct the error based on that information.

[0037] As a concrete example, consider a case where a user lists a new product on an e-commerce site. The user enters the product page URL into the system, and the server sets that page as a target for monitoring. The server periodically retrieves information from this URL and analyzes the text and images. If, one day, there is an error in the pricing information, for example, if a 90% discount is incorrectly applied, the server detects the anomaly and issues a notification. The user can check this notification on their device and quickly make the necessary corrections.

[0038] In this way, the present invention provides a system that streamlines the management of listing information on e-commerce sites and prevents errors and inconsistencies.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server sends an HTTP request to the URL of the product page specified by the user, retrieving the HTML content from the web. This prepares the server to collect necessary data such as the product name, price, description, and image URLs.

[0042] Step 2:

[0043] The server launches an analysis program to parse the retrieved HTML content. Specifically, it analyzes the HTML structure and extracts the product name, price, description, and image URL using a specific selector. This ensures that important product information is managed within the system.

[0044] Step 3:

[0045] The server uses a generative information processing device to perform natural language processing on product names and descriptions. This detects whether the text data contains inappropriate or abnormal patterns. This anomaly detection is an important measure to prevent incorrect listing information.

[0046] Step 4:

[0047] The server analyzes product images using an image analysis device. It retrieves image data based on the image URL and evaluates the image through a machine learning model. In particular, it analyzes whether the image deviates from specific product characteristics or criteria and determines whether there is an anomaly.

[0048] Step 5:

[0049] Based on whether or not an anomaly is detected, the server aggregates the results. If an anomaly is detected in the text or image, the warning system is activated, and a process is initiated to generate notification information containing details of the anomaly.

[0050] Step 6:

[0051] The server sends the generated notification information to the user's device. The user receives the notification in real time through their device and can check the product information where an anomaly was reported. Based on this feedback, the user can correct the listing information.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] On online sales platforms, errors and inconsistencies in product information can damage consumer trust, and detecting and correcting them places a significant burden on users. Traditional methods primarily rely on manual verification, which has limitations in efficiency and accuracy.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes a medium for acquiring product data from a web page, a generative data processing medium for applying natural language processing technology to the product data and detecting anomalies in the text information, and an image analysis medium for using a machine learning model on the image information of the product data and analyzing anomalies in the images. This makes it possible to quickly and automatically detect anomalies in product information and send appropriate notifications to the user.

[0057] A "web page" refers to a collection of digital documents accessible via the internet, primarily informational content written in HTML format.

[0058] "Product data" refers to a dataset containing detailed product information provided on an online sales platform, including product name, price, description, image links, etc.

[0059] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language, and is used in text analysis and language generation.

[0060] A "generative data processing medium" refers to an information processing device or software that uses generative AI models to analyze data and detect specific patterns or anomalies.

[0061] "Image analysis medium" refers to an information processing device or software that uses machine learning models to analyze image data and evaluate its content.

[0062] A "machine learning model" refers to mathematical algorithms and methods that allow computers to automatically learn from large amounts of data and perform data analysis and prediction.

[0063] "Notification data" refers to information generated when an anomaly in product information is detected, and includes error messages and warning messages presented to the user.

[0064] The present invention is a system for highly sophisticated management of product information on an online sales platform, and includes a function to efficiently analyze product data on the web and detect anomalies. Specific embodiments of this system are described below.

[0065] First, the server retrieves product data from a webpage by specifying its URL. This utilizes common internet communication protocols and web crawler technology, specifically using the Python requests library to periodically access the webpage and retrieve the latest information. As a result, product names, prices, descriptions, image links, and other information are collected.

[0066] Subsequently, the server uses a generative AI model to analyze the text information of the product data. Applying natural language processing techniques, it employs models such as GPT and BERT to detect errors and inconsistencies in the text data. As a concrete example of a prompt, the generative model is input with the sentence, "Point out any errors in the following product descriptions," to detect anomalies.

[0067] Next, the server uses an image analysis medium to analyze the image information of the product data. Here, machine learning models, particularly convolutional neural networks (CNNs), are used to verify that the image content is as expected. For example, it verifies that no inappropriate images are included and that images of new products are displayed correctly.

[0068] Furthermore, if the server detects an anomaly through these procedures, it immediately generates notification data and notifies the user via the terminal. This allows the user to quickly correct errors in product information.

[0069] This system enables efficient management of errors in product information and improves reliability on online sales platforms. In this way, the embodiment of the present invention achieves accurate information management and rapid response to anomalies.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server receives the URL of the specified product's webpage as input and uses a web crawler to retrieve the page's HTML data. This process involves sending HTTP requests using the Python requests library to collect the latest data. The output provides structured information such as the product name, price, description, and image links.

[0073] Step 2:

[0074] The server extracts product information from the acquired HTML data and uses it as input for text analysis. It utilizes a generative AI model to detect anomalies and errors in product names and descriptions. Specifically, it uses GPT to generate prompts such as "Check if there are any deficiencies in the description." This analysis outputs text information containing inconsistencies and anomalous patterns.

[0075] Step 3:

[0076] The server takes the image links extracted in the previous step as input and performs image analysis. It downloads the image data and automatically analyzes the image content using machine learning models, particularly convolutional neural networks (CNNs). The output is an evaluation result that identifies inappropriate or unexpected images.

[0077] Step 4:

[0078] If the server detects an anomaly based on the analysis results of text and images, it uses this as input to generate a warning message. The generated notification data includes the details of the anomaly and the items that need correction. This is then output, and a notification is issued.

[0079] Step 5:

[0080] The server sends the generated notification data to the device. This can be done by sending an email using the SMTP protocol or by sending a push notification via APNs or Firebase. The device receives this and displays it to the user.

[0081] Step 6:

[0082] Users receive notifications displayed on their devices as input and correct errors by accessing the e-commerce site's administration screen. This process allows for the correction of inaccuracies in product data and keeps the information up-to-date and accurate.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] There is a need to prevent misregistration and human error in product information on online sales platforms and to ensure the accuracy of product information. In particular, a system is needed that allows sellers and administrators to efficiently manage information and quickly correct errors.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes a function to acquire product information from web resources, a generative data processing function to detect abnormalities in text information based on the product information, an image analysis function to detect abnormalities in image information based on the product information, a warning function to generate and distribute notifications when abnormalities are detected, and a function for users to receive notifications through display on a portable electronic device. This makes it possible to quickly detect and efficiently correct errors and inconsistencies when registering product information.

[0088] "Web resources" refer to a collection of data and information that exists on the internet, and in this context, they refer to web pages containing product information.

[0089] "Product information" refers to data that represents the details of a product, and includes components such as product name, price, description, and image information.

[0090] A "generative data processing device" is a device equipped with technology that analyzes the textual information of product information and automatically detects anomalies.

[0091] An "image analysis device" is a device that has the technology to analyze the content of product images and detect anomalies in light of expected standards.

[0092] The "warning function" is a feature that generates notifications when an anomaly is detected within the system, informing sellers and administrators of that information.

[0093] "Portable electronic devices" refer to electronic devices carried by individuals, such as smartphones and smart glasses, that are capable of displaying and operating information.

[0094] The system used to implement this application primarily consists of a server, a terminal, and a user. The server runs a program that automatically retrieves product information from web resources on the internet. It uses Python to perform scraping and collect data including product names, prices, descriptions, and image information.

[0095] Next, the server uses a generative data processing device to utilize natural language processing technology. This allows it to detect anomalies in the collected textual information. For example, it is used to check whether product names or descriptions deviate from normal expressions, or whether there are errors in price information.

[0096] In image analysis, the server uses a learning model built with TENSORFLOW® to verify product images. It analyzes whether the images match the product descriptions and whether any incorrect images are included.

[0097] When an anomaly is detected, the server generates an alert and sends a notification to the user's mobile electronic device via Firebase Cloud Messaging. This notification is delivered to sellers and administrators in real time, enabling a quick response.

[0098] A practical use case would be when a user lists a new product and the system detects a significant error in the pricing information. In this case, the server immediately pushes a message to the user's smartphone saying, "There is an error in the pricing information. Please check again," allowing the user to correct it on the spot.

[0099] An example of a prompt to the generative AI model would be: "Is there an error in the product description on this e-commerce site? Please check using a natural language processing model."

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

[0101] Step 1:

[0102] The server collects product information data from web resources on the internet. The input is a specific URL, and the output is a dataset containing product names, prices, descriptions, and image URLs. This process involves running a web scraping program using Python to extract the necessary information from the HTML data.

[0103] Step 2:

[0104] The server uses a generative data processing device to analyze the textual information of the collected product data. The input is the dataset from the previous stage, and the output is a flag indicating whether or not it is abnormal. Natural language processing techniques are used to detect semantic and grammatical anomalies in the text. Specifically, it individually analyzes whether there are any inappropriate values ​​or terms in the price or product name.

[0105] Step 3:

[0106] The server uses an image analysis device to detect anomalies in product images. The input is the image URL, and the output is an evaluation value indicating whether the image is as expected. A TensorFlow-based learning model analyzes the image content to check if any incorrect images have been registered. It checks whether the image content matches the description and whether there are any inappropriate images.

[0107] Step 4:

[0108] The server generates an alert and sends a notification to the user's mobile electronic device if an anomaly is detected. Inputs are an anomaly flag and evaluation value, and output is an alert message. Firebase Cloud Messaging is used to notify sellers and administrators of the anomaly in real time. Specifically, it generates an alert message and prepares to send a push notification to smartphones and smart glasses.

[0109] Step 5:

[0110] Based on the notification received, the user corrects the information on the system. The input is a warning message, and the output is the corrected product information. The user reviews the notification, manually corrects the errors in the product information, and uploads it back to the server. Specifically, this involves checking and correcting the information of the relevant product on a smartphone.

[0111] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0112] This invention aims to improve the user experience by combining emotion recognition functionality with a product information management system on an online sales platform. This system consists of a server, terminals, and users, and specifically performs anomaly detection, emotion recognition, and notification feedback based on these functions. The components of this invention and their operation are described below in detail.

[0113] The server collects information from the URL of the product page specified by the user. Specifically, it retrieves HTML data from the webpage and analyzes information such as the product name, price, description, and image URL. This information is important for ensuring the accuracy of the listing.

[0114] Next, the server uses a generative information processing device and an image analysis device to detect anomalies in the collected product information. The generative information processing device analyzes text information using natural language processing technology, and the image analysis device analyzes image information using machine learning models, thereby quickly finding errors and inconsistencies.

[0115] Even more important is the addition of an emotion engine. This emotion engine analyzes the user's text input and behavior logs to estimate the user's emotions. The user's emotional state is taken into consideration when generating and sending notification information, and is fed back to the user in the most optimal way.

[0116] For example, if a user registers a new product and an error is detected, the server analyzes the information and uses an emotion engine to adjust the content of the notification the user receives. If the emotion engine estimates that the user is particularly stressed, the notification text can be made gentler, more specific, and more supportive.

[0117] Thus, this invention goes beyond simply monitoring listing information; it improves the user experience by optimizing notification methods according to user emotions. The aim is to make e-commerce site management more comfortable and effective.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The server sends an HTTP request to the URL of the product page specified by the user and retrieves HTML data from the web page. This retrieved data is used as input data for analyzing the product information.

[0121] Step 2:

[0122] The server extracts the product name, price, description, and image URL from the HTML data obtained using an analysis program. This ensures that the necessary product information is managed within the system.

[0123] Step 3:

[0124] The server uses a generative information processing device to apply natural language processing techniques to the extracted product names and descriptions to detect anomalies in the text information. Specifically, it prevents the registration of incorrect information by identifying the use of unusual words and inappropriate expressions.

[0125] Step 4:

[0126] The server analyzes product images using an image analysis device. The image data is input into a machine learning model, and deviations from the standard are detected to verify the accuracy of the product images. During this process, it determines whether inappropriate images are being used.

[0127] Step 5:

[0128] The server activates the emotion engine and analyzes the user's emotional state based on the user's actions within the system and the text data they input. This analysis allows the server to estimate the user's current emotional state.

[0129] Step 6:

[0130] Based on the user's emotional state, the server adjusts the content and format of notification information. For example, if the user is feeling stressed, the notification will use gentle language and be delivered in a way that does not burden the user.

[0131] Step 7:

[0132] The server generates notification information and sends it to the user via the terminal. The user receives this notification and can check and correct the listing information based on the reported anomaly.

[0133] (Example 2)

[0134] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0135] While detecting inconsistencies and errors in product information is crucial for online sales platforms, it can degrade the user experience. In particular, sending error notifications without considering the user's emotional state can cause excessive stress, ultimately reducing their willingness to continue using the service. The objective of this invention is to provide a new system that improves the user experience while maintaining the accuracy of product information.

[0136] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0137] In this invention, the server includes means for collecting information, information processing means for detecting anomalies in text information, analysis means for detecting anomalies in image information, emotion engine means for analyzing user input and behavior logs and estimating the user's emotional state, and means for optimizing notification content based on the emotional state. This makes it possible to efficiently detect product inconsistencies while providing appropriate notifications that correspond to the user's emotions.

[0138] "Means of collecting information" refers to devices or programs that automatically acquire product and target data from web pages and related data sources.

[0139] "Information processing device" refers to a device or mechanism that analyzes collected text information and detects anomalies or inconsistencies using natural language processing technology.

[0140] "Analysis device means" refers to a device or system that analyzes image information using a machine learning model to identify anomalies or inconsistencies in the image information.

[0141] "Emotional engine means" refers to algorithms and programs that estimate a user's emotional state based on user input and behavioral logs.

[0142] "Means for optimizing notification content" refers to processes and methods for generating notifications with appropriate content, taking into account the user's emotional state, in response to detected anomalies in the information.

[0143] This invention combines emotion recognition functionality with a product information management system for an online sales platform. Specifically, the server, terminal, and user work together to perform functions such as product information collection, anomaly detection, and emotion feedback.

[0144] The server automatically retrieves HTML data from a specified product page on the web, for example using the Python requests library. Then, it extracts detailed information such as the product name, price, description, and image URL using libraries like BeautifulSoup. This information is used for subsequent data analysis.

[0145] To detect anomalies, the server utilizes a generative information processing system and an image analysis system. The generative information processing system analyzes text information using natural language processing techniques (e.g., the BERT model) to identify errors and inconsistencies in the text. The image analysis system uses machine learning models, such as TensorFlow, to detect anomalies in image data. High accuracy is achieved by comparing the image data with previously collected product information.

[0146] Furthermore, the server estimates the user's emotional state through an emotion engine. This engine analyzes user input text (such as product reviews and questions) and behavioral logs (such as product viewing time and click patterns) to identify emotions such as positive, negative, or neutral. Natural language processing and behavioral analysis algorithms are used for the analysis.

[0147] The content of notifications sent to users is optimized based on the estimation results of the emotion engine. Using a generative AI model (for example, OpenAI®'s GPT model), the system takes the prompt "Create an appropriate notification message for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." as input and generates an appropriate notification message.

[0148] In this way, the server can provide appropriate feedback along with accurate product information, while taking user emotions into consideration. This system aims to improve the user experience on e-commerce sites and support the streamlining of administrative tasks.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The server receives the URL of the product page specified by the user as input and begins collecting information. Specifically, the server uses the Python requests library to access the web resource and retrieve HTML data. This HTML data includes product information such as product name, price, description, and image URL. This information becomes the input for the next analysis step.

[0152] Step 2:

[0153] The server analyzes the collected HTML data as input. Text information is analyzed using a generative information processing device and natural language processing techniques (e.g., the BERT model). In this process, errors and inconsistencies in product names and descriptions are detected and output along with suggested corrections. Image information is analyzed using a machine learning model based on TensorFlow to diagnose image integrity and appropriateness. The results of this analysis become the input for the next sentiment estimation step.

[0154] Step 3:

[0155] The server estimates the emotional state using the analysis results and user input or behavior logs. The emotion engine receives text data entered by the user (e.g., reviews or inquiries) and the user's operation history as input. In this process, it uses natural language processing and behavioral analysis algorithms to estimate the user's emotional state (positive, negative, neutral, etc.) and outputs the result.

[0156] Step 4:

[0157] The server generates an appropriate notification for the user based on the output of the emotion engine. It utilizes a generative AI model (for example, OpenAI's GPT model) and takes emotion-appropriate prompt text as input. An example of a prompt text would be, "Please create an appropriate notification text for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." The generated notification content is then output.

[0158] Step 5:

[0159] The device provides users with notifications sent from the server. These notifications are supportive, taking into account the user's feelings, and include details of malfunctions or anomalies, as well as solutions. Users can receive these notifications and take actions such as correcting product information based on the output. This allows for appropriate feedback and improves the user experience.

[0160] (Application Example 2)

[0161] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0162] Online sales platforms face the problem of significantly degrading the user experience due to errors and inconsistencies in product information. Furthermore, the stress and discomfort users experience when these errors are pointed out poses an additional challenge. It is necessary to resolve these issues and achieve a comfortable and efficient management of product information for users.

[0163] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0164] In this invention, the server includes means for collecting product information data from web pages, generative information processing means for detecting anomalies in text information based on the product information data, image analysis means for detecting anomalies in image information based on the product information data, emotion recognition means for estimating emotions based on user input data and behavioral history, and notification means for generating optimized notification information based on anomalies and emotion estimation results and transmitting it via a communication device. This makes it possible to improve the user experience by providing appropriate notification content that takes the user's emotions into consideration.

[0165] "Product information data" refers to detailed information about a product on an online sales platform, including data such as product name, price, description, and image URL.

[0166] A "generative information processing device" is a device that uses natural language processing technology to detect anomalies in text data.

[0167] An "image analysis device" is a device that uses machine learning models to detect anomalies in image data.

[0168] "Emotion recognition means" refers to a technology or device for estimating a user's emotions based on the user's input data and behavioral history.

[0169] "Notification device means" refers to a device or system for transmitting notification information generated based on anomaly detection results and emotion estimation results to a user.

[0170] A "communication device" is a device used to send and receive data and information to and from external systems or user devices.

[0171] This invention is a system for efficiently managing product information on an online sales platform and improving the user experience. The system mainly consists of a server, terminals, and users.

[0172] First, the server collects product information data from the web page. This data includes the product name, price, description, and image URL. It then analyzes the HTML data of the web page, extracts the necessary information, and stores it in the database.

[0173] Next, the server uses a generative information processing device to detect text anomalies based on product information data. It utilizes natural language processing technology to check for errors or inconsistencies in product descriptions and names.

[0174] Furthermore, using an image analysis device, a machine learning model is used to evaluate whether the product images contain inaccuracies or abnormalities.

[0175] To take the user's emotional state into consideration, an emotion recognition mechanism is used. Based on user input data and behavioral history collected from the device, the emotion engine estimates the user's current emotions. If the user is experiencing any stress, the notification content is adjusted accordingly.

[0176] The notification device generates optimal notification information based on the results of the anomaly detection and emotion estimation described above. The generated information is transmitted to the user's smartphone via a communication device. The notification content is designed to reduce the user's psychological burden by gently informing them of the location of the error and possible solutions.

[0177] For example, if a user accidentally forgets to enter a product price, the system will notify the user with a friendly message such as, "It appears the price has not been entered, please enter it." Furthermore, by utilizing a generative AI model, the system adjusts the notification content using an example prompt message such as, "If the user's emotion is frustration, please generate a friendly notification message."

[0178] Thus, this system not only maintains the accuracy of product information but also considers user emotions and provides appropriate feedback, thereby realizing a better user experience.

[0179] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0180] Step 1:

[0181] The server collects product information data from the URLs of web pages on online sales platforms. As input, it retrieves the HTML data of the web page and extracts the product name, price, description, and image URL. The output is product information data containing these elements.

[0182] Step 2:

[0183] The server uses a generative information processing device to detect anomalies in the text information of product data. The input consists of text elements from the product data. Natural language processing techniques are applied to analyze for errors and inconsistencies. The result indicates whether or not anomalies are present.

[0184] Step 3:

[0185] The server uses an image analysis device to detect any anomalies in the image information within the product data. It analyzes the product images provided as input using a machine learning model to detect inconsistencies within the images. The output indicates whether or not there are anomalies in the image information.

[0186] Step 4:

[0187] The terminal sends user input data and behavioral history to the server. Input includes user text input and click history. Based on this, the server performs emotion recognition and estimates the user's emotions using an emotion engine. The output is the estimated emotional state.

[0188] Step 5:

[0189] The server generates optimal notification information using a notification device based on the anomaly detection results and emotion estimation results. The input is the anomaly information and emotion state obtained in the previous step. The notification text is created using a generation AI model. The output is the notification content to be sent to the user.

[0190] Step 6:

[0191] The server sends the generated notification information to the user's smartphone via a communication device. The input is the notification information created in step 5. It is output as a notification received by the user, providing the user with appropriate and engaging feedback.

[0192] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0193] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0198] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0199] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0200] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0202] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0203] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0206] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0207] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0208] This embodiment of the present invention relates to a product information management system for an online sales platform, and in particular, to preventing human error and ensuring the accuracy of information using anomaly detection and notification functions. The components of the present invention and their operation are described in detail below.

[0209] The system consists of a server, terminals, and users. The server is primarily responsible for backend processing and is tasked with collecting product information data from web pages. The server retrieves HTML data from specific URLs and uses an analysis program to extract information such as product names, prices, descriptions, and image URLs. Subsequently, the server uses a generative information processing device to determine, based on natural language processing technology, whether there are any anomalies in the product names and descriptions.

[0210] Furthermore, the server uses an image analysis device to analyze product images obtained from image URLs and employs machine learning modeling techniques to evaluate whether the images meet expectations. This reduces the risk of incorrect or inappropriate images being registered.

[0211] If an anomaly is detected, the server immediately activates the warning system and generates notification information. The generated notification information is sent to the user's terminal, allowing the user to quickly correct the error based on that information.

[0212] As a concrete example, consider a case where a user lists a new product on an e-commerce site. The user enters the product page URL into the system, and the server sets that page as a target for monitoring. The server periodically retrieves information from this URL and analyzes the text and images. If, one day, there is an error in the pricing information, for example, if a 90% discount is incorrectly applied, the server detects the anomaly and issues a notification. The user can check this notification on their device and quickly make the necessary corrections.

[0213] In this way, the present invention provides a system that streamlines the management of listing information on e-commerce sites and prevents errors and inconsistencies.

[0214] The following describes the processing flow.

[0215] Step 1:

[0216] The server sends an HTTP request to the URL of the product page specified by the user, retrieving the HTML content from the web. This prepares the server to collect necessary data such as the product name, price, description, and image URLs.

[0217] Step 2:

[0218] The server launches an analysis program to parse the retrieved HTML content. Specifically, it analyzes the HTML structure and extracts the product name, price, description, and image URL using a specific selector. This ensures that important product information is managed within the system.

[0219] Step 3:

[0220] The server uses a generative information processing device to perform natural language processing on product names and descriptions. This detects whether the text data contains inappropriate or abnormal patterns. This anomaly detection is an important measure to prevent incorrect listing information.

[0221] Step 4:

[0222] The server analyzes product images using an image analysis device. It retrieves image data based on the image URL and evaluates the image through a machine learning model. In particular, it analyzes whether the image deviates from specific product characteristics or criteria and determines whether there is an anomaly.

[0223] Step 5:

[0224] Based on whether or not an anomaly is detected, the server aggregates the results. If an anomaly is detected in the text or image, the warning system is activated, and a process is initiated to generate notification information containing details of the anomaly.

[0225] Step 6:

[0226] The server sends the generated notification information to the user's device. The user receives the notification in real time through their device and can check the product information where an anomaly was reported. Based on this feedback, the user can correct the listing information.

[0227] (Example 1)

[0228] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0229] On online sales platforms, errors and inconsistencies in product information can damage consumer trust, and detecting and correcting them places a significant burden on users. Traditional methods primarily rely on manual verification, which has limitations in efficiency and accuracy.

[0230] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0231] In this invention, the server includes a medium for acquiring product data from a web page, a generative data processing medium for applying natural language processing technology to the product data and detecting anomalies in the text information, and an image analysis medium for using a machine learning model on the image information of the product data and analyzing anomalies in the images. This makes it possible to quickly and automatically detect anomalies in product information and send appropriate notifications to the user.

[0232] A "web page" refers to a collection of digital documents accessible via the internet, primarily informational content written in HTML format.

[0233] "Product data" refers to a dataset containing detailed product information provided on an online sales platform, including product name, price, description, image links, etc.

[0234] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language, and is used in text analysis and language generation.

[0235] A "generative data processing medium" refers to an information processing device or software that uses generative AI models to analyze data and detect specific patterns or anomalies.

[0236] "Image analysis medium" refers to an information processing device or software that uses machine learning models to analyze image data and evaluate its content.

[0237] A "machine learning model" refers to mathematical algorithms and methods that allow computers to automatically learn from large amounts of data and perform data analysis and prediction.

[0238] "Notification data" refers to information generated when an anomaly in product information is detected, and includes error messages and warning messages presented to the user.

[0239] The present invention is a system for highly sophisticated management of product information on an online sales platform, and includes a function to efficiently analyze product data on the web and detect anomalies. Specific embodiments of this system are described below.

[0240] First, the server retrieves product data from a webpage by specifying its URL. This utilizes common internet communication protocols and web crawler technology, specifically using the Python requests library to periodically access the webpage and retrieve the latest information. As a result, product names, prices, descriptions, image links, and other information are collected.

[0241] Subsequently, the server uses a generative AI model to analyze the text information of the product data. Applying natural language processing techniques, it employs models such as GPT and BERT to detect errors and inconsistencies in the text data. As a concrete example of a prompt, the generative model is input with the sentence, "Point out any errors in the following product descriptions," to detect anomalies.

[0242] Next, the server uses an image analysis medium to analyze the image information of the product data. Here, machine learning models, particularly convolutional neural networks (CNNs), are used to verify that the image content is as expected. For example, it verifies that no inappropriate images are included and that images of new products are displayed correctly.

[0243] Furthermore, if the server detects an anomaly through these procedures, it immediately generates notification data and notifies the user via the terminal. This allows the user to quickly correct errors in product information.

[0244] This system enables efficient management of errors in product information and improves reliability on online sales platforms. In this way, the embodiment of the present invention achieves accurate information management and rapid response to anomalies.

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

[0246] Step 1:

[0247] The server receives the URL of the specified product's webpage as input and uses a web crawler to retrieve the page's HTML data. This process involves sending HTTP requests using the Python requests library to collect the latest data. The output provides structured information such as the product name, price, description, and image links.

[0248] Step 2:

[0249] The server extracts product information from the acquired HTML data and uses it as input for text analysis. It utilizes a generative AI model to detect anomalies and errors in product names and descriptions. Specifically, it uses GPT to generate prompts such as "Check if there are any deficiencies in the description." This analysis outputs text information containing inconsistencies and anomalous patterns.

[0250] Step 3:

[0251] The server takes the image links extracted in the previous step as input and performs image analysis. It downloads the image data and automatically analyzes the image content using machine learning models, particularly convolutional neural networks (CNNs). The output is an evaluation result that identifies inappropriate or unexpected images.

[0252] Step 4:

[0253] If the server detects an anomaly based on the analysis results of text and images, it uses this as input to generate a warning message. The generated notification data includes the details of the anomaly and the items that need correction. This is then output, and a notification is issued.

[0254] Step 5:

[0255] The server sends the generated notification data to the device. This can be done by sending an email using the SMTP protocol or by sending a push notification via APNs or Firebase. The device receives this and displays it to the user.

[0256] Step 6:

[0257] Users receive notifications displayed on their devices as input and correct errors by accessing the e-commerce site's administration screen. This process allows for the correction of inaccuracies in product data and keeps the information up-to-date and accurate.

[0258] (Application Example 1)

[0259] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0260] There is a need to prevent misregistration and human error in product information on online sales platforms and to ensure the accuracy of product information. In particular, a system is needed that allows sellers and administrators to efficiently manage information and quickly correct errors.

[0261] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0262] In this invention, the server includes a function to acquire product information from web resources, a generative data processing function to detect abnormalities in text information based on the product information, an image analysis function to detect abnormalities in image information based on the product information, a warning function to generate and distribute notifications when abnormalities are detected, and a function for users to receive notifications through display on a portable electronic device. This makes it possible to quickly detect and efficiently correct errors and inconsistencies when registering product information.

[0263] "Web resources" refer to a collection of data and information that exists on the internet, and in this context, they refer to web pages containing product information.

[0264] "Product information" refers to data that represents the details of a product, and includes components such as product name, price, description, and image information.

[0265] A "generative data processing device" is a device equipped with technology that analyzes the textual information of product information and automatically detects anomalies.

[0266] An "image analysis device" is a device that has the technology to analyze the content of product images and detect anomalies in light of expected standards.

[0267] The "warning function" is a feature that generates notifications when an anomaly is detected within the system, informing sellers and administrators of that information.

[0268] "Portable electronic devices" refer to electronic devices carried by individuals, such as smartphones and smart glasses, that are capable of displaying and operating information.

[0269] The system used to implement this application primarily consists of a server, a terminal, and a user. The server runs a program that automatically retrieves product information from web resources on the internet. It uses Python to perform scraping and collect data including product names, prices, descriptions, and image information.

[0270] Next, the server uses a generative data processing device to utilize natural language processing technology. This allows it to detect anomalies in the collected textual information. For example, it is used to check whether product names or descriptions deviate from normal expressions, or whether there are errors in price information.

[0271] In image analysis, the server uses a trained model built with TensorFlow to verify product images. It analyzes whether the images match the product descriptions and whether any incorrect images are included.

[0272] When an anomaly is detected, the server generates an alert and sends a notification to the user's mobile electronic device via Firebase Cloud Messaging. This notification is delivered to sellers and administrators in real time, enabling a quick response.

[0273] A practical use case would be when a user lists a new product and the system detects a significant error in the pricing information. In this case, the server immediately pushes a message to the user's smartphone saying, "There is an error in the pricing information. Please check again," allowing the user to correct it on the spot.

[0274] An example of a prompt to the generative AI model would be: "Is there an error in the product description on this e-commerce site? Please check using a natural language processing model."

[0275] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0276] Step 1:

[0277] The server collects product information data from web resources on the internet. The input is a specific URL, and the output is a dataset containing product names, prices, descriptions, and image URLs. This process involves running a web scraping program using Python to extract the necessary information from the HTML data.

[0278] Step 2:

[0279] The server uses a generative data processing device to analyze the textual information of the collected product data. The input is the dataset from the previous stage, and the output is a flag indicating whether or not it is abnormal. Natural language processing techniques are used to detect semantic and grammatical anomalies in the text. Specifically, it individually analyzes whether there are any inappropriate values ​​or terms in the price or product name.

[0280] Step 3:

[0281] The server uses an image analysis device to detect anomalies in product images. The input is the image URL, and the output is an evaluation value indicating whether the image is as expected. A TensorFlow-based learning model analyzes the image content to check if any incorrect images have been registered. It checks whether the image content matches the description and whether there are any inappropriate images.

[0282] Step 4:

[0283] When an abnormality is detected in the server, it generates a warning and sends a notification to the user's mobile electronic device. The inputs are an abnormality flag and an evaluation value, and the output is a warning message. Firebase Cloud Messaging is used to notify the publisher and administrator of the abnormality in real time. As a specific operation, it prepares to generate a warning message and send a push notification to a smartphone or smart glasses.

[0284] Step 5:

[0285] Based on the received notification, the user modifies the information on the system. The input is the warning message, and the output is the modified product information. The user checks the notification, manually corrects the error in the product information, and uploads it to the server again. As a specific operation, it includes an operation of checking and correcting the information of the corresponding product on the smartphone.

[0286] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0287] The present invention aims to improve the user experience by further combining an emotion recognition function with a product information management system in an online sales platform. This system is composed of a server, a terminal, and a user, and particularly performs abnormality detection, emotion recognition, and notification feedback based on them. Hereinafter, the components and operations of the present invention will be described in sequence.

[0288] The server collects information from the URL of the product page specified by the user. Specifically, it acquires HTML data from the web page and analyzes information such as the product name, price, description, and image URL. This information is important for ensuring the accuracy of the product listing.

[0289] Next, the server uses a generative information processing device and an image analysis device to detect anomalies in the collected product information. The generative information processing device analyzes text information using natural language processing technology, and the image analysis device analyzes image information using machine learning models, thereby quickly finding errors and inconsistencies.

[0290] Even more important is the addition of an emotion engine. This emotion engine analyzes the user's text input and behavior logs to estimate the user's emotions. The user's emotional state is taken into consideration when generating and sending notification information, and is fed back to the user in the most optimal way.

[0291] For example, if a user registers a new product and an error is detected, the server analyzes the information and uses an emotion engine to adjust the content of the notification the user receives. If the emotion engine estimates that the user is particularly stressed, the notification text can be made gentler, more specific, and more supportive.

[0292] Thus, this invention goes beyond simply monitoring listing information; it improves the user experience by optimizing notification methods according to user emotions. The aim is to make e-commerce site management more comfortable and effective.

[0293] The following describes the processing flow.

[0294] Step 1:

[0295] The server sends an HTTP request to the URL of the product page specified by the user and retrieves HTML data from the web page. This retrieved data is used as input data for analyzing the product information.

[0296] Step 2:

[0297] The server extracts the product name, price, description, and image URL from the HTML data obtained using an analysis program. This ensures that the necessary product information is managed within the system.

[0298] Step 3:

[0299] The server uses a generative information processing device to apply natural language processing techniques to the extracted product names and descriptions to detect anomalies in the text information. Specifically, it prevents the registration of incorrect information by identifying the use of unusual words and inappropriate expressions.

[0300] Step 4:

[0301] The server analyzes product images using an image analysis device. The image data is input into a machine learning model, and deviations from the standard are detected to verify the accuracy of the product images. During this process, it determines whether inappropriate images are being used.

[0302] Step 5:

[0303] The server activates the emotion engine and analyzes the user's emotional state based on the user's actions within the system and the text data they input. This analysis allows the server to estimate the user's current emotional state.

[0304] Step 6:

[0305] Based on the user's emotional state, the server adjusts the content and format of notification information. For example, if the user is feeling stressed, the notification will use gentle language and be delivered in a way that does not burden the user.

[0306] Step 7:

[0307] The server generates notification information and sends it to the user via the terminal. The user receives this notification and can check and correct the listing information based on the reported anomaly.

[0308] (Example 2)

[0309] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0310] In an online sales platform, it is important to detect inconsistencies and errors in product information, but it may cause a decline in the user experience. In particular, when notifications for errors are sent without considering the user's emotional state, there is a risk of giving the user excessive stress. As a result, the user's willingness to continue using the service is diminished. The problem of the present invention is to provide a new system that improves the user experience while maintaining the accuracy of product information.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0312] In this invention, the server includes means for collecting information, information processing device means for detecting abnormalities in text information, analysis device means for detecting abnormalities in image information, emotion engine means for analyzing the user's input and action logs and estimating the user's emotional state, and means for optimizing the notification content based on the emotional state. Thereby, while efficiently detecting product inconsistencies, it becomes possible to give an appropriate notification according to the user's emotion.

[0313] The "means for collecting information" refers to a device or program for automatically acquiring products and target data from web pages and related data sources.

[0314] The "information processing device means" refers to a device or mechanism that analyzes the collected text information and detects abnormalities and inconsistencies using natural language processing technology.

[0315] The "analysis device means" refers to a device or mechanism that analyzes image information using a machine learning model and identifies abnormalities and inconsistencies in the image information.

[0316] "Emotional engine means" refers to algorithms and programs that estimate a user's emotional state based on user input and behavioral logs.

[0317] "Means for optimizing notification content" refers to processes and methods for generating notifications with appropriate content, taking into account the user's emotional state, in response to detected anomalies in the information.

[0318] This invention combines emotion recognition functionality with a product information management system for an online sales platform. Specifically, the server, terminal, and user work together to perform functions such as product information collection, anomaly detection, and emotion feedback.

[0319] The server automatically retrieves HTML data from a specified product page on the web, for example using the Python requests library. Then, it extracts detailed information such as the product name, price, description, and image URL using libraries like BeautifulSoup. This information is used for subsequent data analysis.

[0320] To detect anomalies, the server utilizes a generative information processing system and an image analysis system. The generative information processing system analyzes text information using natural language processing techniques (e.g., the BERT model) to identify errors and inconsistencies in the text. The image analysis system uses machine learning models, such as TensorFlow, to detect anomalies in image data. High accuracy is achieved by comparing the image data with previously collected product information.

[0321] Furthermore, the server estimates the user's emotional state through an emotion engine. This engine analyzes user input text (such as product reviews and questions) and behavioral logs (such as product viewing time and click patterns) to identify emotions such as positive, negative, or neutral. Natural language processing and behavioral analysis algorithms are used for the analysis.

[0322] The content of notifications sent to the user is optimized based on the sentiment engine's estimation results. Using a generative AI model (for example, OpenAI's GPT model), the prompt "Create an appropriate notification message for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." is input, and an appropriate notification message is generated.

[0323] In this way, the server can provide appropriate feedback along with accurate product information, while taking user emotions into consideration. This system aims to improve the user experience on e-commerce sites and support the streamlining of administrative tasks.

[0324] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0325] Step 1:

[0326] The server receives the URL of the product page specified by the user as input and begins collecting information. Specifically, the server uses the Python requests library to access the web resource and retrieve HTML data. This HTML data includes product information such as product name, price, description, and image URL. This information becomes the input for the next analysis step.

[0327] Step 2:

[0328] The server analyzes the collected HTML data as input. Text information is analyzed using a generative information processing device and natural language processing techniques (e.g., the BERT model). In this process, errors and inconsistencies in product names and descriptions are detected and output along with suggested corrections. Image information is analyzed using a machine learning model based on TensorFlow to diagnose image integrity and appropriateness. The results of this analysis become the input for the next sentiment estimation step.

[0329] Step 3:

[0330] The server estimates the emotional state using the analysis results and user input or behavior logs. The emotion engine receives text data entered by the user (e.g., reviews or inquiries) and the user's operation history as input. In this process, it uses natural language processing and behavioral analysis algorithms to estimate the user's emotional state (positive, negative, neutral, etc.) and outputs the result.

[0331] Step 4:

[0332] The server generates an appropriate notification for the user based on the output of the emotion engine. It utilizes a generative AI model (for example, OpenAI's GPT model) and takes emotion-appropriate prompt text as input. An example of a prompt text would be, "Please create an appropriate notification text for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." The generated notification content is then output.

[0333] Step 5:

[0334] The device provides users with notifications sent from the server. These notifications are supportive, taking into account the user's feelings, and include details of malfunctions or anomalies, as well as solutions. Users can receive these notifications and take actions such as correcting product information based on the output. This allows for appropriate feedback and improves the user experience.

[0335] (Application Example 2)

[0336] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0337] Online sales platforms face the problem of significantly degrading the user experience due to errors and inconsistencies in product information. Furthermore, the stress and discomfort users experience when these errors are pointed out poses an additional challenge. It is necessary to resolve these issues and achieve a comfortable and efficient management of product information for users.

[0338] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0339] In this invention, the server includes means for collecting product information data from web pages, generative information processing means for detecting anomalies in text information based on the product information data, image analysis means for detecting anomalies in image information based on the product information data, emotion recognition means for estimating emotions based on user input data and behavioral history, and notification means for generating optimized notification information based on anomalies and emotion estimation results and transmitting it via a communication device. This makes it possible to improve the user experience by providing appropriate notification content that takes the user's emotions into consideration.

[0340] "Product information data" refers to detailed information about a product on an online sales platform, including data such as product name, price, description, and image URL.

[0341] A "generative information processing device" is a device that uses natural language processing technology to detect anomalies in text data.

[0342] An "image analysis device" is a device that uses machine learning models to detect anomalies in image data.

[0343] "Emotion recognition means" refers to a technology or device for estimating a user's emotions based on the user's input data and behavioral history.

[0344] "Notification device means" refers to a device or system for transmitting notification information generated based on anomaly detection results and emotion estimation results to a user.

[0345] A "communication device" is a device used to send and receive data and information to and from external systems or user devices.

[0346] This invention is a system for efficiently managing product information on an online sales platform and improving the user experience. The system mainly consists of a server, terminals, and users.

[0347] First, the server collects product information data from the web page. This data includes the product name, price, description, and image URL. It then analyzes the HTML data of the web page, extracts the necessary information, and stores it in the database.

[0348] Next, the server uses a generative information processing device to detect text anomalies based on product information data. It utilizes natural language processing technology to check for errors or inconsistencies in product descriptions and names.

[0349] Furthermore, using an image analysis device, a machine learning model is used to evaluate whether the product images contain inaccuracies or abnormalities.

[0350] To take the user's emotional state into consideration, an emotion recognition mechanism is used. Based on user input data and behavioral history collected from the device, the emotion engine estimates the user's current emotions. If the user is experiencing any stress, the notification content is adjusted accordingly.

[0351] The notification device generates optimal notification information based on the results of the anomaly detection and emotion estimation described above. The generated information is transmitted to the user's smartphone via a communication device. The notification content is designed to reduce the user's psychological burden by gently informing them of the location of the error and possible solutions.

[0352] For example, if a user accidentally forgets to enter a product price, the system will notify the user with a friendly message such as, "It appears the price has not been entered, please enter it." Furthermore, by utilizing a generative AI model, the system adjusts the notification content using an example prompt message such as, "If the user's emotion is frustration, please generate a friendly notification message."

[0353] Thus, this system not only maintains the accuracy of product information but also considers user emotions and provides appropriate feedback, thereby realizing a better user experience.

[0354] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0355] Step 1:

[0356] The server collects product information data from the URLs of web pages on online sales platforms. As input, it retrieves the HTML data of the web page and extracts the product name, price, description, and image URL. The output is product information data containing these elements.

[0357] Step 2:

[0358] The server uses a generative information processing device to detect anomalies in the text information of product data. The input consists of text elements from the product data. Natural language processing techniques are applied to analyze for errors and inconsistencies. The result indicates whether or not anomalies are present.

[0359] Step 3:

[0360] The server uses an image analysis device to detect any anomalies in the image information within the product data. It analyzes the product images provided as input using a machine learning model to detect inconsistencies within the images. The output indicates whether or not there are anomalies in the image information.

[0361] Step 4:

[0362] The terminal sends user input data and behavioral history to the server. Input includes user text input and click history. Based on this, the server performs emotion recognition and estimates the user's emotions using an emotion engine. The output is the estimated emotional state.

[0363] Step 5:

[0364] The server generates optimal notification information using a notification device based on the anomaly detection results and emotion estimation results. The input is the anomaly information and emotion state obtained in the previous step. The notification text is created using a generation AI model. The output is the notification content to be sent to the user.

[0365] Step 6:

[0366] The server sends the generated notification information to the user's smartphone via a communication device. The input is the notification information created in step 5. It is output as a notification received by the user, providing the user with appropriate and engaging feedback.

[0367] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0368] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0369] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0370] [Third Embodiment]

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

[0372] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0373] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0374] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0375] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0376] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0377] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0378] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0379] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0380] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0381] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0382] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0383] This embodiment of the present invention relates to a product information management system for an online sales platform, and in particular, to preventing human error and ensuring the accuracy of information using anomaly detection and notification functions. The components of the present invention and their operation are described in detail below.

[0384] The system consists of a server, terminals, and users. The server is primarily responsible for backend processing and is tasked with collecting product information data from web pages. The server retrieves HTML data from specific URLs and uses an analysis program to extract information such as product names, prices, descriptions, and image URLs. Subsequently, the server uses a generative information processing device to determine, based on natural language processing technology, whether there are any anomalies in the product names and descriptions.

[0385] Furthermore, the server uses an image analysis device to analyze product images obtained from image URLs and employs machine learning modeling techniques to evaluate whether the images meet expectations. This reduces the risk of incorrect or inappropriate images being registered.

[0386] If an anomaly is detected, the server immediately activates the warning system and generates notification information. The generated notification information is sent to the user's terminal, allowing the user to quickly correct the error based on that information.

[0387] As a concrete example, consider a case where a user lists a new product on an e-commerce site. The user enters the product page URL into the system, and the server sets that page as a target for monitoring. The server periodically retrieves information from this URL and analyzes the text and images. If, one day, there is an error in the pricing information, for example, if a 90% discount is incorrectly applied, the server detects the anomaly and issues a notification. The user can check this notification on their device and quickly make the necessary corrections.

[0388] In this way, the present invention provides a system that streamlines the management of listing information on e-commerce sites and prevents errors and inconsistencies.

[0389] The following describes the processing flow.

[0390] Step 1:

[0391] The server sends an HTTP request to the URL of the product page specified by the user, retrieving the HTML content from the web. This prepares the server to collect necessary data such as the product name, price, description, and image URLs.

[0392] Step 2:

[0393] The server launches an analysis program to parse the retrieved HTML content. Specifically, it analyzes the HTML structure and extracts the product name, price, description, and image URL using a specific selector. This ensures that important product information is managed within the system.

[0394] Step 3:

[0395] The server uses a generative information processing device to perform natural language processing on product names and descriptions. This detects whether the text data contains inappropriate or abnormal patterns. This anomaly detection is an important measure to prevent incorrect listing information.

[0396] Step 4:

[0397] The server analyzes product images using an image analysis device. It retrieves image data based on the image URL and evaluates the image through a machine learning model. In particular, it analyzes whether the image deviates from specific product characteristics or criteria and determines whether there is an anomaly.

[0398] Step 5:

[0399] Based on whether or not an anomaly is detected, the server aggregates the results. If an anomaly is detected in the text or image, the warning system is activated, and a process is initiated to generate notification information containing details of the anomaly.

[0400] Step 6:

[0401] The server sends the generated notification information to the user's device. The user receives the notification in real time through their device and can check the product information where an anomaly was reported. Based on this feedback, the user can correct the listing information.

[0402] (Example 1)

[0403] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0404] On online sales platforms, errors and inconsistencies in product information can damage consumer trust, and detecting and correcting them places a significant burden on users. Traditional methods primarily rely on manual verification, which has limitations in efficiency and accuracy.

[0405] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0406] In this invention, the server includes a medium for acquiring product data from a web page, a generative data processing medium for applying natural language processing technology to the product data and detecting anomalies in the text information, and an image analysis medium for using a machine learning model on the image information of the product data and analyzing anomalies in the images. This makes it possible to quickly and automatically detect anomalies in product information and send appropriate notifications to the user.

[0407] A "web page" refers to a collection of digital documents accessible via the internet, primarily informational content written in HTML format.

[0408] "Product data" refers to a dataset containing detailed product information provided on an online sales platform, including product name, price, description, image links, etc.

[0409] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language, and is used in text analysis and language generation.

[0410] A "generative data processing medium" refers to an information processing device or software that uses generative AI models to analyze data and detect specific patterns or anomalies.

[0411] "Image analysis medium" refers to an information processing device or software that uses machine learning models to analyze image data and evaluate its content.

[0412] A "machine learning model" refers to mathematical algorithms and methods that allow computers to automatically learn from large amounts of data and perform data analysis and prediction.

[0413] "Notification data" refers to information generated when an anomaly in product information is detected, and includes error messages and warning messages presented to the user.

[0414] The present invention is a system for highly sophisticated management of product information on an online sales platform, and includes a function to efficiently analyze product data on the web and detect anomalies. Specific embodiments of this system are described below.

[0415] First, the server retrieves product data from a webpage by specifying its URL. This utilizes common internet communication protocols and web crawler technology, specifically using the Python requests library to periodically access the webpage and retrieve the latest information. As a result, product names, prices, descriptions, image links, and other information are collected.

[0416] Subsequently, the server uses a generative AI model to analyze the text information of the product data. Applying natural language processing techniques, it employs models such as GPT and BERT to detect errors and inconsistencies in the text data. As a concrete example of a prompt, the generative model is input with the sentence, "Point out any errors in the following product descriptions," to detect anomalies.

[0417] Next, the server uses an image analysis medium to analyze the image information of the product data. Here, machine learning models, particularly convolutional neural networks (CNNs), are used to verify that the image content is as expected. For example, it verifies that no inappropriate images are included and that images of new products are displayed correctly.

[0418] Furthermore, if the server detects an anomaly through these procedures, it immediately generates notification data and notifies the user via the terminal. This allows the user to quickly correct errors in product information.

[0419] This system enables efficient management of errors in product information and improves reliability on online sales platforms. In this way, the embodiment of the present invention achieves accurate information management and rapid response to anomalies.

[0420] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0421] Step 1:

[0422] The server receives the URL of the specified product's webpage as input and uses a web crawler to retrieve the page's HTML data. This process involves sending HTTP requests using the Python requests library to collect the latest data. The output provides structured information such as the product name, price, description, and image links.

[0423] Step 2:

[0424] The server extracts product information from the acquired HTML data and uses it as input for text analysis. It utilizes a generative AI model to detect anomalies and errors in product names and descriptions. Specifically, it uses GPT to generate prompts such as "Check if there are any deficiencies in the description." This analysis outputs text information containing inconsistencies and anomalous patterns.

[0425] Step 3:

[0426] The server takes the image links extracted in the previous step as input and performs image analysis. It downloads the image data and automatically analyzes the image content using machine learning models, particularly convolutional neural networks (CNNs). The output is an evaluation result that identifies inappropriate or unexpected images.

[0427] Step 4:

[0428] If the server detects an anomaly based on the analysis results of text and images, it uses this as input to generate a warning message. The generated notification data includes the details of the anomaly and the items that need correction. This is then output, and a notification is issued.

[0429] Step 5:

[0430] The server sends the generated notification data to the device. This can be done by sending an email using the SMTP protocol or by sending a push notification via APNs or Firebase. The device receives this and displays it to the user.

[0431] Step 6:

[0432] Users receive notifications displayed on their devices as input and correct errors by accessing the e-commerce site's administration screen. This process allows for the correction of inaccuracies in product data and keeps the information up-to-date and accurate.

[0433] (Application Example 1)

[0434] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0435] There is a need to prevent misregistration and human error in product information on online sales platforms and to ensure the accuracy of product information. In particular, a system is needed that allows sellers and administrators to efficiently manage information and quickly correct errors.

[0436] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0437] In this invention, the server includes a function to acquire product information from web resources, a generative data processing function to detect abnormalities in text information based on the product information, an image analysis function to detect abnormalities in image information based on the product information, a warning function to generate and distribute notifications when abnormalities are detected, and a function for users to receive notifications through display on a portable electronic device. This makes it possible to quickly detect and efficiently correct errors and inconsistencies when registering product information.

[0438] "Web resources" refer to a collection of data and information that exists on the internet, and in this context, they refer to web pages containing product information.

[0439] "Product information" refers to data that represents the details of a product, and includes components such as product name, price, description, and image information.

[0440] A "generative data processing device" is a device equipped with technology that analyzes the textual information of product information and automatically detects anomalies.

[0441] An "image analysis device" is a device that has the technology to analyze the content of product images and detect anomalies in light of expected standards.

[0442] The "warning function" is a feature that generates notifications when an anomaly is detected within the system, informing sellers and administrators of that information.

[0443] "Portable electronic devices" refer to electronic devices carried by individuals, such as smartphones and smart glasses, that are capable of displaying and operating information.

[0444] The system used to implement this application primarily consists of a server, a terminal, and a user. The server runs a program that automatically retrieves product information from web resources on the internet. It uses Python to perform scraping and collect data including product names, prices, descriptions, and image information.

[0445] Next, the server uses a generative data processing device to utilize natural language processing technology. This allows it to detect anomalies in the collected textual information. For example, it is used to check whether product names or descriptions deviate from normal expressions, or whether there are errors in price information.

[0446] In image analysis, the server uses a trained model built with TensorFlow to verify product images. It analyzes whether the images match the product descriptions and whether any incorrect images are included.

[0447] When an anomaly is detected, the server generates an alert and sends a notification to the user's mobile electronic device via Firebase Cloud Messaging. This notification is delivered to sellers and administrators in real time, enabling a quick response.

[0448] A practical use case would be when a user lists a new product and the system detects a significant error in the pricing information. In this case, the server immediately pushes a message to the user's smartphone saying, "There is an error in the pricing information. Please check again," allowing the user to correct it on the spot.

[0449] An example of a prompt to the generative AI model would be: "Is there an error in the product description on this e-commerce site? Please check using a natural language processing model."

[0450] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0451] Step 1:

[0452] The server collects product information data from web resources on the internet. The input is a specific URL, and the output is a dataset containing product names, prices, descriptions, and image URLs. This process involves running a web scraping program using Python to extract the necessary information from the HTML data.

[0453] Step 2:

[0454] The server uses a generative data processing device to analyze the textual information of the collected product data. The input is the dataset from the previous stage, and the output is a flag indicating whether or not it is abnormal. Natural language processing techniques are used to detect semantic and grammatical anomalies in the text. Specifically, it individually analyzes whether there are any inappropriate values ​​or terms in the price or product name.

[0455] Step 3:

[0456] The server uses an image analysis device to detect anomalies in product images. The input is the image URL, and the output is an evaluation value indicating whether the image is as expected. A TensorFlow-based learning model analyzes the image content to check if any incorrect images have been registered. It checks whether the image content matches the description and whether there are any inappropriate images.

[0457] Step 4:

[0458] The server generates an alert and sends a notification to the user's mobile electronic device if an anomaly is detected. Inputs are an anomaly flag and evaluation value, and output is an alert message. Firebase Cloud Messaging is used to notify sellers and administrators of the anomaly in real time. Specifically, it generates an alert message and prepares to send a push notification to smartphones and smart glasses.

[0459] Step 5:

[0460] Based on the notification received, the user corrects the information on the system. The input is a warning message, and the output is the corrected product information. The user reviews the notification, manually corrects the errors in the product information, and uploads it back to the server. Specifically, this involves checking and correcting the information of the relevant product on a smartphone.

[0461] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0462] This invention aims to improve the user experience by combining emotion recognition functionality with a product information management system on an online sales platform. This system consists of a server, terminals, and users, and specifically performs anomaly detection, emotion recognition, and notification feedback based on these functions. The components of this invention and their operation are described below in detail.

[0463] The server collects information from the URL of the product page specified by the user. Specifically, it retrieves HTML data from the webpage and analyzes information such as the product name, price, description, and image URL. This information is important for ensuring the accuracy of the listing.

[0464] Next, the server uses a generative information processing device and an image analysis device to detect anomalies in the collected product information. The generative information processing device analyzes text information using natural language processing technology, and the image analysis device analyzes image information using machine learning models, thereby quickly finding errors and inconsistencies.

[0465] Even more important is the addition of an emotion engine. This emotion engine analyzes the user's text input and behavior logs to estimate the user's emotions. The user's emotional state is taken into consideration when generating and sending notification information, and is fed back to the user in the most optimal way.

[0466] For example, if a user registers a new product and an error is detected, the server analyzes the information and uses an emotion engine to adjust the content of the notification the user receives. If the emotion engine estimates that the user is particularly stressed, the notification text can be made gentler, more specific, and more supportive.

[0467] Thus, this invention goes beyond simply monitoring listing information; it improves the user experience by optimizing notification methods according to user emotions. The aim is to make e-commerce site management more comfortable and effective.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] The server sends an HTTP request to the URL of the product page specified by the user and retrieves HTML data from the web page. This retrieved data is used as input data for analyzing the product information.

[0471] Step 2:

[0472] The server extracts the product name, price, description, and image URL from the HTML data obtained using an analysis program. This ensures that the necessary product information is managed within the system.

[0473] Step 3:

[0474] The server uses a generative information processing device to apply natural language processing techniques to the extracted product names and descriptions to detect anomalies in the text information. Specifically, it prevents the registration of incorrect information by identifying the use of unusual words and inappropriate expressions.

[0475] Step 4:

[0476] The server analyzes product images using an image analysis device. The image data is input into a machine learning model, and deviations from the standard are detected to verify the accuracy of the product images. During this process, it determines whether inappropriate images are being used.

[0477] Step 5:

[0478] The server activates the emotion engine and analyzes the user's emotional state based on the user's actions within the system and the text data they input. This analysis allows the server to estimate the user's current emotional state.

[0479] Step 6:

[0480] Based on the user's emotional state, the server adjusts the content and format of notification information. For example, if the user is feeling stressed, the notification will use gentle language and be delivered in a way that does not burden the user.

[0481] Step 7:

[0482] The server generates notification information and sends it to the user via the terminal. The user receives this notification and can check and correct the listing information based on the reported anomaly.

[0483] (Example 2)

[0484] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0485] While detecting inconsistencies and errors in product information is crucial for online sales platforms, it can degrade the user experience. In particular, sending error notifications without considering the user's emotional state can cause excessive stress, ultimately reducing their willingness to continue using the service. The objective of this invention is to provide a new system that improves the user experience while maintaining the accuracy of product information.

[0486] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0487] In this invention, the server includes means for collecting information, information processing means for detecting anomalies in text information, analysis means for detecting anomalies in image information, emotion engine means for analyzing user input and behavior logs and estimating the user's emotional state, and means for optimizing notification content based on the emotional state. This makes it possible to efficiently detect product inconsistencies while providing appropriate notifications that correspond to the user's emotions.

[0488] "Means of collecting information" refers to devices or programs that automatically acquire product and target data from web pages and related data sources.

[0489] "Information processing device" refers to a device or mechanism that analyzes collected text information and detects anomalies or inconsistencies using natural language processing technology.

[0490] "Analysis device means" refers to a device or system that analyzes image information using a machine learning model to identify anomalies or inconsistencies in the image information.

[0491] "Emotional engine means" refers to algorithms and programs that estimate a user's emotional state based on user input and behavioral logs.

[0492] "Means for optimizing notification content" refers to processes and methods for generating notifications with appropriate content, taking into account the user's emotional state, in response to detected anomalies in the information.

[0493] This invention combines emotion recognition functionality with a product information management system for an online sales platform. Specifically, the server, terminal, and user work together to perform functions such as product information collection, anomaly detection, and emotion feedback.

[0494] The server automatically retrieves HTML data from a specified product page on the web, for example using the Python requests library. Then, it extracts detailed information such as the product name, price, description, and image URL using libraries like BeautifulSoup. This information is used for subsequent data analysis.

[0495] To detect anomalies, the server utilizes a generative information processing system and an image analysis system. The generative information processing system analyzes text information using natural language processing techniques (e.g., the BERT model) to identify errors and inconsistencies in the text. The image analysis system uses machine learning models, such as TensorFlow, to detect anomalies in image data. High accuracy is achieved by comparing the image data with previously collected product information.

[0496] Furthermore, the server estimates the user's emotional state through an emotion engine. This engine analyzes user input text (such as product reviews and questions) and behavioral logs (such as product viewing time and click patterns) to identify emotions such as positive, negative, or neutral. Natural language processing and behavioral analysis algorithms are used for the analysis.

[0497] The content of notifications sent to the user is optimized based on the sentiment engine's estimation results. Using a generative AI model (for example, OpenAI's GPT model), the prompt "Create an appropriate notification message for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." is input, and an appropriate notification message is generated.

[0498] In this way, the server can provide appropriate feedback along with accurate product information, while taking user emotions into consideration. This system aims to improve the user experience on e-commerce sites and support the streamlining of administrative tasks.

[0499] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0500] Step 1:

[0501] The server receives the URL of the product page specified by the user as input and begins collecting information. Specifically, the server uses the Python requests library to access the web resource and retrieve HTML data. This HTML data includes product information such as product name, price, description, and image URL. This information becomes the input for the next analysis step.

[0502] Step 2:

[0503] The server analyzes the collected HTML data as input. Text information is analyzed using a generative information processing device and natural language processing techniques (e.g., the BERT model). In this process, errors and inconsistencies in product names and descriptions are detected and output along with suggested corrections. Image information is analyzed using a machine learning model based on TensorFlow to diagnose image integrity and appropriateness. The results of this analysis become the input for the next sentiment estimation step.

[0504] Step 3:

[0505] The server estimates the emotional state using the analysis results and user input or behavior logs. The emotion engine receives text data entered by the user (e.g., reviews or inquiries) and the user's operation history as input. In this process, it uses natural language processing and behavioral analysis algorithms to estimate the user's emotional state (positive, negative, neutral, etc.) and outputs the result.

[0506] Step 4:

[0507] The server generates an appropriate notification for the user based on the output of the emotion engine. It utilizes a generative AI model (for example, OpenAI's GPT model) and takes emotion-appropriate prompt text as input. An example of a prompt text would be, "Please create an appropriate notification text for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." The generated notification content is then output.

[0508] Step 5:

[0509] The device provides users with notifications sent from the server. These notifications are supportive, taking into account the user's feelings, and include details of malfunctions or anomalies, as well as solutions. Users can receive these notifications and take actions such as correcting product information based on the output. This allows for appropriate feedback and improves the user experience.

[0510] (Application Example 2)

[0511] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0512] Online sales platforms face the problem of significantly degrading the user experience due to errors and inconsistencies in product information. Furthermore, the stress and discomfort users experience when these errors are pointed out poses an additional challenge. It is necessary to resolve these issues and achieve a comfortable and efficient management of product information for users.

[0513] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0514] In this invention, the server includes means for collecting product information data from web pages, generative information processing means for detecting anomalies in text information based on the product information data, image analysis means for detecting anomalies in image information based on the product information data, emotion recognition means for estimating emotions based on user input data and behavioral history, and notification means for generating optimized notification information based on anomalies and emotion estimation results and transmitting it via a communication device. This makes it possible to improve the user experience by providing appropriate notification content that takes the user's emotions into consideration.

[0515] "Product information data" refers to detailed information about a product on an online sales platform, including data such as product name, price, description, and image URL.

[0516] A "generative information processing device" is a device that uses natural language processing technology to detect anomalies in text data.

[0517] An "image analysis device" is a device that uses machine learning models to detect anomalies in image data.

[0518] "Emotion recognition means" refers to a technology or device for estimating a user's emotions based on the user's input data and behavioral history.

[0519] "Notification device means" refers to a device or system for transmitting notification information generated based on anomaly detection results and emotion estimation results to a user.

[0520] A "communication device" is a device used to send and receive data and information to and from external systems or user devices.

[0521] This invention is a system for efficiently managing product information on an online sales platform and improving the user experience. The system mainly consists of a server, terminals, and users.

[0522] First, the server collects product information data from the web page. This data includes the product name, price, description, and image URL. It then analyzes the HTML data of the web page, extracts the necessary information, and stores it in the database.

[0523] Next, the server uses a generative information processing device to detect text anomalies based on product information data. It utilizes natural language processing technology to check for errors or inconsistencies in product descriptions and names.

[0524] Furthermore, using an image analysis device, a machine learning model is used to evaluate whether the product images contain inaccuracies or abnormalities.

[0525] To take the user's emotional state into consideration, an emotion recognition mechanism is used. Based on user input data and behavioral history collected from the device, the emotion engine estimates the user's current emotions. If the user is experiencing any stress, the notification content is adjusted accordingly.

[0526] The notification device generates optimal notification information based on the results of the anomaly detection and emotion estimation described above. The generated information is transmitted to the user's smartphone via a communication device. The notification content is designed to reduce the user's psychological burden by gently informing them of the location of the error and possible solutions.

[0527] For example, if a user accidentally forgets to enter a product price, the system will notify the user with a friendly message such as, "It appears the price has not been entered, please enter it." Furthermore, by utilizing a generative AI model, the system adjusts the notification content using an example prompt message such as, "If the user's emotion is frustration, please generate a friendly notification message."

[0528] Thus, this system not only maintains the accuracy of product information but also considers user emotions and provides appropriate feedback, thereby realizing a better user experience.

[0529] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0530] Step 1:

[0531] The server collects product information data from the URLs of web pages on online sales platforms. As input, it retrieves the HTML data of the web page and extracts the product name, price, description, and image URL. The output is product information data containing these elements.

[0532] Step 2:

[0533] The server uses a generative information processing device to detect anomalies in the text information of product data. The input consists of text elements from the product data. Natural language processing techniques are applied to analyze for errors and inconsistencies. The result indicates whether or not anomalies are present.

[0534] Step 3:

[0535] The server uses an image analysis device to detect any anomalies in the image information within the product data. It analyzes the product images provided as input using a machine learning model to detect inconsistencies within the images. The output indicates whether or not there are anomalies in the image information.

[0536] Step 4:

[0537] The terminal sends user input data and behavioral history to the server. Input includes user text input and click history. Based on this, the server performs emotion recognition and estimates the user's emotions using an emotion engine. The output is the estimated emotional state.

[0538] Step 5:

[0539] The server generates optimal notification information using a notification device based on the anomaly detection results and emotion estimation results. The input is the anomaly information and emotion state obtained in the previous step. The notification text is created using a generation AI model. The output is the notification content to be sent to the user.

[0540] Step 6:

[0541] The server sends the generated notification information to the user's smartphone via a communication device. The input is the notification information created in step 5. It is output as a notification received by the user, providing the user with appropriate and engaging feedback.

[0542] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0543] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0544] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0545] [Fourth Embodiment]

[0546] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0547] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0548] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0550] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0552] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0553] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0554] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0555] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0556] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0557] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0558] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0559] This embodiment of the present invention relates to a product information management system for an online sales platform, and in particular, to preventing human error and ensuring the accuracy of information using anomaly detection and notification functions. The components of the present invention and their operation are described in detail below.

[0560] The system consists of a server, terminals, and users. The server is primarily responsible for backend processing and is tasked with collecting product information data from web pages. The server retrieves HTML data from specific URLs and uses an analysis program to extract information such as product names, prices, descriptions, and image URLs. Subsequently, the server uses a generative information processing device to determine, based on natural language processing technology, whether there are any anomalies in the product names and descriptions.

[0561] Furthermore, the server uses an image analysis device to analyze product images obtained from image URLs and employs machine learning modeling techniques to evaluate whether the images meet expectations. This reduces the risk of incorrect or inappropriate images being registered.

[0562] If an anomaly is detected, the server immediately activates the warning system and generates notification information. The generated notification information is sent to the user's terminal, allowing the user to quickly correct the error based on that information.

[0563] As a concrete example, consider a case where a user lists a new product on an e-commerce site. The user enters the product page URL into the system, and the server sets that page as a target for monitoring. The server periodically retrieves information from this URL and analyzes the text and images. If, one day, there is an error in the pricing information, for example, if a 90% discount is incorrectly applied, the server detects the anomaly and issues a notification. The user can check this notification on their device and quickly make the necessary corrections.

[0564] In this way, the present invention provides a system that streamlines the management of listing information on e-commerce sites and prevents errors and inconsistencies.

[0565] The following describes the processing flow.

[0566] Step 1:

[0567] The server sends an HTTP request to the URL of the product page specified by the user, retrieving the HTML content from the web. This prepares the server to collect necessary data such as the product name, price, description, and image URLs.

[0568] Step 2:

[0569] The server launches an analysis program to parse the retrieved HTML content. Specifically, it analyzes the HTML structure and extracts the product name, price, description, and image URL using a specific selector. This ensures that important product information is managed within the system.

[0570] Step 3:

[0571] The server uses a generative information processing device to perform natural language processing on product names and descriptions. This detects whether the text data contains inappropriate or abnormal patterns. This anomaly detection is an important measure to prevent incorrect listing information.

[0572] Step 4:

[0573] The server analyzes product images using an image analysis device. It retrieves image data based on the image URL and evaluates the image through a machine learning model. In particular, it analyzes whether the image deviates from specific product characteristics or criteria and determines whether there is an anomaly.

[0574] Step 5:

[0575] Based on whether or not an anomaly is detected, the server aggregates the results. If an anomaly is detected in the text or image, the warning system is activated, and a process is initiated to generate notification information containing details of the anomaly.

[0576] Step 6:

[0577] The server sends the generated notification information to the user's device. The user receives the notification in real time through their device and can check the product information where an anomaly was reported. Based on this feedback, the user can correct the listing information.

[0578] (Example 1)

[0579] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0580] On online sales platforms, errors and inconsistencies in product information can damage consumer trust, and detecting and correcting them places a significant burden on users. Traditional methods primarily rely on manual verification, which has limitations in efficiency and accuracy.

[0581] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0582] In this invention, the server includes a medium for acquiring product data from a web page, a generative data processing medium for applying natural language processing technology to the product data and detecting anomalies in the text information, and an image analysis medium for using a machine learning model on the image information of the product data and analyzing anomalies in the images. This makes it possible to quickly and automatically detect anomalies in product information and send appropriate notifications to the user.

[0583] A "web page" refers to a collection of digital documents accessible via the internet, primarily informational content written in HTML format.

[0584] "Product data" refers to a dataset containing detailed product information provided on an online sales platform, including product name, price, description, image links, etc.

[0585] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language, and is used in text analysis and language generation.

[0586] A "generative data processing medium" refers to an information processing device or software that uses generative AI models to analyze data and detect specific patterns or anomalies.

[0587] "Image analysis medium" refers to an information processing device or software that uses machine learning models to analyze image data and evaluate its content.

[0588] A "machine learning model" refers to mathematical algorithms and methods that allow computers to automatically learn from large amounts of data and perform data analysis and prediction.

[0589] "Notification data" refers to information generated when an anomaly in product information is detected, and includes error messages and warning messages presented to the user.

[0590] The present invention is a system for highly sophisticated management of product information on an online sales platform, and includes a function to efficiently analyze product data on the web and detect anomalies. Specific embodiments of this system are described below.

[0591] First, the server retrieves product data from a webpage by specifying its URL. This utilizes common internet communication protocols and web crawler technology, specifically using the Python requests library to periodically access the webpage and retrieve the latest information. As a result, product names, prices, descriptions, image links, and other information are collected.

[0592] Subsequently, the server uses a generative AI model to analyze the text information of the product data. Applying natural language processing techniques, it employs models such as GPT and BERT to detect errors and inconsistencies in the text data. As a concrete example of a prompt, the generative model is input with the sentence, "Point out any errors in the following product descriptions," to detect anomalies.

[0593] Next, the server uses an image analysis medium to analyze the image information of the product data. Here, machine learning models, particularly convolutional neural networks (CNNs), are used to verify that the image content is as expected. For example, it verifies that no inappropriate images are included and that images of new products are displayed correctly.

[0594] Furthermore, if the server detects an anomaly through these procedures, it immediately generates notification data and notifies the user via the terminal. This allows the user to quickly correct errors in product information.

[0595] This system enables efficient management of errors in product information and improves reliability on online sales platforms. In this way, the embodiment of the present invention achieves accurate information management and rapid response to anomalies.

[0596] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0597] Step 1:

[0598] The server receives the URL of the specified product's webpage as input and uses a web crawler to retrieve the page's HTML data. This process involves sending HTTP requests using the Python requests library to collect the latest data. The output provides structured information such as the product name, price, description, and image links.

[0599] Step 2:

[0600] The server extracts product information from the acquired HTML data and uses it as input for text analysis. It utilizes a generative AI model to detect anomalies and errors in product names and descriptions. Specifically, it uses GPT to generate prompts such as "Check if there are any deficiencies in the description." This analysis outputs text information containing inconsistencies and anomalous patterns.

[0601] Step 3:

[0602] The server takes the image links extracted in the previous step as input and performs image analysis. It downloads the image data and automatically analyzes the image content using machine learning models, particularly convolutional neural networks (CNNs). The output is an evaluation result that identifies inappropriate or unexpected images.

[0603] Step 4:

[0604] If the server detects an anomaly based on the analysis results of text and images, it uses this as input to generate a warning message. The generated notification data includes the details of the anomaly and the items that need correction. This is then output, and a notification is issued.

[0605] Step 5:

[0606] The server sends the generated notification data to the device. This can be done by sending an email using the SMTP protocol or by sending a push notification via APNs or Firebase. The device receives this and displays it to the user.

[0607] Step 6:

[0608] Users receive notifications displayed on their devices as input and correct errors by accessing the e-commerce site's administration screen. This process allows for the correction of inaccuracies in product data and keeps the information up-to-date and accurate.

[0609] (Application Example 1)

[0610] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0611] There is a need to prevent misregistration and human error in product information on online sales platforms and to ensure the accuracy of product information. In particular, a system is needed that allows sellers and administrators to efficiently manage information and quickly correct errors.

[0612] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0613] In this invention, the server includes a function to acquire product information from web resources, a generative data processing function to detect abnormalities in text information based on the product information, an image analysis function to detect abnormalities in image information based on the product information, a warning function to generate and distribute notifications when abnormalities are detected, and a function for users to receive notifications through display on a portable electronic device. This makes it possible to quickly detect and efficiently correct errors and inconsistencies when registering product information.

[0614] "Web resources" refer to a collection of data and information that exists on the internet, and in this context, they refer to web pages containing product information.

[0615] "Product information" refers to data that represents the details of a product, and includes components such as product name, price, description, and image information.

[0616] A "generative data processing device" is a device equipped with technology that analyzes the textual information of product information and automatically detects anomalies.

[0617] An "image analysis device" is a device that has the technology to analyze the content of product images and detect anomalies in light of expected standards.

[0618] The "warning function" is a feature that generates notifications when an anomaly is detected within the system, informing sellers and administrators of that information.

[0619] "Portable electronic devices" refer to electronic devices carried by individuals, such as smartphones and smart glasses, that are capable of displaying and operating information.

[0620] The system used to implement this application primarily consists of a server, a terminal, and a user. The server runs a program that automatically retrieves product information from web resources on the internet. It uses Python to perform scraping and collect data including product names, prices, descriptions, and image information.

[0621] Next, the server uses a generative data processing device to utilize natural language processing technology. This allows it to detect anomalies in the collected textual information. For example, it is used to check whether product names or descriptions deviate from normal expressions, or whether there are errors in price information.

[0622] In image analysis, the server uses a trained model built with TensorFlow to verify product images. It analyzes whether the images match the product descriptions and whether any incorrect images are included.

[0623] When an anomaly is detected, the server generates an alert and sends a notification to the user's mobile electronic device via Firebase Cloud Messaging. This notification is delivered to sellers and administrators in real time, enabling a quick response.

[0624] A practical use case would be when a user lists a new product and the system detects a significant error in the pricing information. In this case, the server immediately pushes a message to the user's smartphone saying, "There is an error in the pricing information. Please check again," allowing the user to correct it on the spot.

[0625] An example of a prompt to the generative AI model would be: "Is there an error in the product description on this e-commerce site? Please check using a natural language processing model."

[0626] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0627] Step 1:

[0628] The server collects product information data from web resources on the internet. The input is a specific URL, and the output is a dataset containing product names, prices, descriptions, and image URLs. This process involves running a web scraping program using Python to extract the necessary information from the HTML data.

[0629] Step 2:

[0630] The server uses a generative data processing device to analyze the textual information of the collected product data. The input is the dataset from the previous stage, and the output is a flag indicating whether or not it is abnormal. Natural language processing techniques are used to detect semantic and grammatical anomalies in the text. Specifically, it individually analyzes whether there are any inappropriate values ​​or terms in the price or product name.

[0631] Step 3:

[0632] The server uses an image analysis device to detect anomalies in product images. The input is the image URL, and the output is an evaluation value indicating whether the image is as expected. A TensorFlow-based learning model analyzes the image content to check if any incorrect images have been registered. It checks whether the image content matches the description and whether there are any inappropriate images.

[0633] Step 4:

[0634] The server generates an alert and sends a notification to the user's mobile electronic device if an anomaly is detected. Inputs are an anomaly flag and evaluation value, and output is an alert message. Firebase Cloud Messaging is used to notify sellers and administrators of the anomaly in real time. Specifically, it generates an alert message and prepares to send a push notification to smartphones and smart glasses.

[0635] Step 5:

[0636] Based on the notification received, the user corrects the information on the system. The input is a warning message, and the output is the corrected product information. The user reviews the notification, manually corrects the errors in the product information, and uploads it back to the server. Specifically, this involves checking and correcting the information of the relevant product on a smartphone.

[0637] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0638] This invention aims to improve the user experience by combining emotion recognition functionality with a product information management system on an online sales platform. This system consists of a server, terminals, and users, and specifically performs anomaly detection, emotion recognition, and notification feedback based on these functions. The components of this invention and their operation are described below in detail.

[0639] The server collects information from the URL of the product page specified by the user. Specifically, it retrieves HTML data from the webpage and analyzes information such as the product name, price, description, and image URL. This information is important for ensuring the accuracy of the listing.

[0640] Next, the server uses a generative information processing device and an image analysis device to detect anomalies in the collected product information. The generative information processing device analyzes text information using natural language processing technology, and the image analysis device analyzes image information using machine learning models, thereby quickly finding errors and inconsistencies.

[0641] Even more important is the addition of an emotion engine. This emotion engine analyzes the user's text input and behavior logs to estimate the user's emotions. The user's emotional state is taken into consideration when generating and sending notification information, and is fed back to the user in the most optimal way.

[0642] For example, if a user registers a new product and an error is detected, the server analyzes the information and uses an emotion engine to adjust the content of the notification the user receives. If the emotion engine estimates that the user is particularly stressed, the notification text can be made gentler, more specific, and more supportive.

[0643] Thus, this invention goes beyond simply monitoring listing information; it improves the user experience by optimizing notification methods according to user emotions. The aim is to make e-commerce site management more comfortable and effective.

[0644] The following describes the processing flow.

[0645] Step 1:

[0646] The server sends an HTTP request to the URL of the product page specified by the user and retrieves HTML data from the web page. This retrieved data is used as input data for analyzing the product information.

[0647] Step 2:

[0648] The server extracts the product name, price, description, and image URL from the HTML data obtained using an analysis program. This ensures that the necessary product information is managed within the system.

[0649] Step 3:

[0650] The server uses a generative information processing device to apply natural language processing techniques to the extracted product names and descriptions to detect anomalies in the text information. Specifically, it prevents the registration of incorrect information by identifying the use of unusual words and inappropriate expressions.

[0651] Step 4:

[0652] The server analyzes product images using an image analysis device. The image data is input into a machine learning model, and deviations from the standard are detected to verify the accuracy of the product images. During this process, it determines whether inappropriate images are being used.

[0653] Step 5:

[0654] The server activates the emotion engine and analyzes the user's emotional state based on the user's actions within the system and the text data they input. This analysis allows the server to estimate the user's current emotional state.

[0655] Step 6:

[0656] Based on the user's emotional state, the server adjusts the content and format of notification information. For example, if the user is feeling stressed, the notification will use gentle language and be delivered in a way that does not burden the user.

[0657] Step 7:

[0658] The server generates notification information and sends it to the user via the terminal. The user receives this notification and can check and correct the listing information based on the reported anomaly.

[0659] (Example 2)

[0660] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] While detecting inconsistencies and errors in product information is crucial for online sales platforms, it can degrade the user experience. In particular, sending error notifications without considering the user's emotional state can cause excessive stress, ultimately reducing their willingness to continue using the service. The objective of this invention is to provide a new system that improves the user experience while maintaining the accuracy of product information.

[0662] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0663] In this invention, the server includes means for collecting information, information processing means for detecting anomalies in text information, analysis means for detecting anomalies in image information, emotion engine means for analyzing user input and behavior logs and estimating the user's emotional state, and means for optimizing notification content based on the emotional state. This makes it possible to efficiently detect product inconsistencies while providing appropriate notifications that correspond to the user's emotions.

[0664] "Means of collecting information" refers to devices or programs that automatically acquire product and target data from web pages and related data sources.

[0665] "Information processing device" refers to a device or mechanism that analyzes collected text information and detects anomalies or inconsistencies using natural language processing technology.

[0666] "Analysis device means" refers to a device or system that analyzes image information using a machine learning model to identify anomalies or inconsistencies in the image information.

[0667] "Emotional engine means" refers to algorithms and programs that estimate a user's emotional state based on user input and behavioral logs.

[0668] "Means for optimizing notification content" refers to processes and methods for generating notifications with appropriate content, taking into account the user's emotional state, in response to detected anomalies in the information.

[0669] This invention combines emotion recognition functionality with a product information management system for an online sales platform. Specifically, the server, terminal, and user work together to perform functions such as product information collection, anomaly detection, and emotion feedback.

[0670] The server automatically retrieves HTML data from a specified product page on the web, for example using the Python requests library. Then, it extracts detailed information such as the product name, price, description, and image URL using libraries like BeautifulSoup. This information is used for subsequent data analysis.

[0671] To detect anomalies, the server utilizes a generative information processing system and an image analysis system. The generative information processing system analyzes text information using natural language processing techniques (e.g., the BERT model) to identify errors and inconsistencies in the text. The image analysis system uses machine learning models, such as TensorFlow, to detect anomalies in image data. High accuracy is achieved by comparing the image data with previously collected product information.

[0672] Furthermore, the server estimates the user's emotional state through an emotion engine. This engine analyzes user input text (such as product reviews and questions) and behavioral logs (such as product viewing time and click patterns) to identify emotions such as positive, negative, or neutral. Natural language processing and behavioral analysis algorithms are used for the analysis.

[0673] The content of notifications sent to the user is optimized based on the sentiment engine's estimation results. Using a generative AI model (for example, OpenAI's GPT model), the prompt "Create an appropriate notification message for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." is input, and an appropriate notification message is generated.

[0674] In this way, the server can provide appropriate feedback along with accurate product information, while taking user emotions into consideration. This system aims to improve the user experience on e-commerce sites and support the streamlining of administrative tasks.

[0675] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0676] Step 1:

[0677] The server receives the URL of the product page specified by the user as input and begins collecting information. Specifically, the server uses the Python requests library to access the web resource and retrieve HTML data. This HTML data includes product information such as product name, price, description, and image URL. This information becomes the input for the next analysis step.

[0678] Step 2:

[0679] The server analyzes the collected HTML data as input. Text information is analyzed using a generative information processing device and natural language processing techniques (e.g., the BERT model). In this process, errors and inconsistencies in product names and descriptions are detected and output along with suggested corrections. Image information is analyzed using a machine learning model based on TensorFlow to diagnose image integrity and appropriateness. The results of this analysis become the input for the next sentiment estimation step.

[0680] Step 3:

[0681] The server estimates the emotional state using the analysis results and user input or behavior logs. The emotion engine receives text data entered by the user (e.g., reviews or inquiries) and the user's operation history as input. In this process, it uses natural language processing and behavioral analysis algorithms to estimate the user's emotional state (positive, negative, neutral, etc.) and outputs the result.

[0682] Step 4:

[0683] The server generates an appropriate notification for the user based on the output of the emotion engine. It utilizes a generative AI model (for example, OpenAI's GPT model) and takes emotion-appropriate prompt text as input. An example of a prompt text would be, "Please create an appropriate notification text for when an anomaly is detected in the image of a product newly registered by the user. The user is feeling anxious." The generated notification content is then output.

[0684] Step 5:

[0685] The device provides users with notifications sent from the server. These notifications are supportive, taking into account the user's feelings, and include details of malfunctions or anomalies, as well as solutions. Users can receive these notifications and take actions such as correcting product information based on the output. This allows for appropriate feedback and improves the user experience.

[0686] (Application Example 2)

[0687] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] Online sales platforms face the problem of significantly degrading the user experience due to errors and inconsistencies in product information. Furthermore, the stress and discomfort users experience when these errors are pointed out poses an additional challenge. It is necessary to resolve these issues and achieve a comfortable and efficient management of product information for users.

[0689] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0690] In this invention, the server includes means for collecting product information data from web pages, generative information processing means for detecting anomalies in text information based on the product information data, image analysis means for detecting anomalies in image information based on the product information data, emotion recognition means for estimating emotions based on user input data and behavioral history, and notification means for generating optimized notification information based on anomalies and emotion estimation results and transmitting it via a communication device. This makes it possible to improve the user experience by providing appropriate notification content that takes the user's emotions into consideration.

[0691] "Product information data" refers to detailed information about a product on an online sales platform, including data such as product name, price, description, and image URL.

[0692] A "generative information processing device" is a device that uses natural language processing technology to detect anomalies in text data.

[0693] An "image analysis device" is a device that uses machine learning models to detect anomalies in image data.

[0694] "Emotion recognition means" refers to a technology or device for estimating a user's emotions based on the user's input data and behavioral history.

[0695] "Notification device means" refers to a device or system for transmitting notification information generated based on anomaly detection results and emotion estimation results to a user.

[0696] A "communication device" is a device used to send and receive data and information to and from external systems or user devices.

[0697] This invention is a system for efficiently managing product information on an online sales platform and improving the user experience. The system mainly consists of a server, terminals, and users.

[0698] First, the server collects product information data from the web page. This data includes the product name, price, description, and image URL. It then analyzes the HTML data of the web page, extracts the necessary information, and stores it in the database.

[0699] Next, the server uses a generative information processing device to detect text anomalies based on product information data. It utilizes natural language processing technology to check for errors or inconsistencies in product descriptions and names.

[0700] Furthermore, using an image analysis device, a machine learning model is used to evaluate whether the product images contain inaccuracies or abnormalities.

[0701] To take the user's emotional state into consideration, an emotion recognition mechanism is used. Based on user input data and behavioral history collected from the device, the emotion engine estimates the user's current emotions. If the user is experiencing any stress, the notification content is adjusted accordingly.

[0702] The notification device generates optimal notification information based on the results of the anomaly detection and emotion estimation described above. The generated information is transmitted to the user's smartphone via a communication device. The notification content is designed to reduce the user's psychological burden by gently informing them of the location of the error and possible solutions.

[0703] For example, if a user accidentally forgets to enter a product price, the system will notify the user with a friendly message such as, "It appears the price has not been entered, please enter it." Furthermore, by utilizing a generative AI model, the system adjusts the notification content using an example prompt message such as, "If the user's emotion is frustration, please generate a friendly notification message."

[0704] Thus, this system not only maintains the accuracy of product information but also considers user emotions and provides appropriate feedback, thereby realizing a better user experience.

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

[0706] Step 1:

[0707] The server collects product information data from the URLs of web pages on online sales platforms. As input, it retrieves the HTML data of the web page and extracts the product name, price, description, and image URL. The output is product information data containing these elements.

[0708] Step 2:

[0709] The server uses a generative information processing device to detect anomalies in the text information of product data. The input consists of text elements from the product data. Natural language processing techniques are applied to analyze for errors and inconsistencies. The result indicates whether or not anomalies are present.

[0710] Step 3:

[0711] The server uses an image analysis device to detect any anomalies in the image information within the product data. It analyzes the product images provided as input using a machine learning model to detect inconsistencies within the images. The output indicates whether or not there are anomalies in the image information.

[0712] Step 4:

[0713] The terminal sends user input data and behavioral history to the server. Input includes user text input and click history. Based on this, the server performs emotion recognition and estimates the user's emotions using an emotion engine. The output is the estimated emotional state.

[0714] Step 5:

[0715] The server generates optimal notification information using a notification device based on the anomaly detection results and emotion estimation results. The input is the anomaly information and emotion state obtained in the previous step. The notification text is created using a generation AI model. The output is the notification content to be sent to the user.

[0716] Step 6:

[0717] The server sends the generated notification information to the user's smartphone via a communication device. The input is the notification information created in step 5. It is output as a notification received by the user, providing the user with appropriate and engaging feedback.

[0718] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0719] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0721] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0722] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0723] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0724] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0725] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0726] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0727] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0728] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0729] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0730] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0731] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0732] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0733] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0734] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0735] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0736] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0737] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0738] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0739] The following is further disclosed regarding the embodiments described above.

[0740] (Claim 1)

[0741] Methods for collecting product information data from web pages,

[0742] A generative information processing device means for detecting anomalies in text information based on the aforementioned product information data,

[0743] An image analysis device means for detecting anomalies in image information based on the aforementioned product information data,

[0744] A warning device means that generates and transmits notification information when an abnormality is detected,

[0745] A system that includes this.

[0746] (Claim 2)

[0747] The system according to claim 1, wherein the generative information processing device that detects anomalies in the text information analyzes the text data using natural language processing technology.

[0748] (Claim 3)

[0749] The system according to claim 1, wherein the image analysis device analyzes image anomalies using a machine learning model.

[0750] "Example 1"

[0751] (Claim 1)

[0752] A medium for obtaining product data from a webpage,

[0753] A generative data processing medium that applies natural language processing technology to the aforementioned product data to detect anomalies in the text information,

[0754] An image analysis medium that uses a machine learning model on the image information of the aforementioned product data to analyze image anomalies,

[0755] A warning medium that generates and transmits notification data when an anomaly is detected,

[0756] A system that includes this.

[0757] (Claim 2)

[0758] The system according to claim 1, wherein the generative data processing medium analyzes text data using prompt statements.

[0759] (Claim 3)

[0760] The system according to claim 1, wherein the image analysis medium obtains image data from a URL specified by the image analysis medium and evaluates its contents.

[0761] "Application Example 1"

[0762] (Claim 1)

[0763] A function to retrieve product information from web resources,

[0764] Based on the aforementioned product information, a generative data processing device function detects anomalies in the text information,

[0765] Based on the aforementioned product information, the image analysis device has a function to detect anomalies in the image information,

[0766] A warning function that generates and distributes notifications when an anomaly is detected,

[0767] A function that allows users to receive notifications through display on their mobile electronic devices,

[0768] Information management device including

[0769] (Claim 2)

[0770] The information management device according to claim 1, wherein the generative data processing device that detects anomalies in the character information uses natural language processing technology to analyze the linguistic information.

[0771] (Claim 3)

[0772] The information management device according to claim 1, wherein the image analysis device uses a learning model to analyze image anomalies.

[0773] "Example 2 of combining an emotion engine"

[0774] (Claim 1)

[0775] Means of collecting information,

[0776] Information processing device means for detecting abnormalities in text information based on the aforementioned information,

[0777] Based on the aforementioned information, an analysis device means for detecting anomalies in image information,

[0778] A device means for generating and transmitting notification information when the aforementioned abnormality is detected,

[0779] An emotion engine means that analyzes user input and behavior logs to estimate the user's emotional state,

[0780] Means for optimizing notification content based on the aforementioned emotional state,

[0781] A system that includes this.

[0782] (Claim 2)

[0783] The system according to claim 1, wherein the information processing device analyzes text information using natural language processing technology.

[0784] (Claim 3)

[0785] The system according to claim 1, wherein the analysis device analyzes image information using a machine learning model.

[0786] "Application example 2 of combining emotional engines"

[0787] (Claim 1)

[0788] Methods for collecting product information data from web pages,

[0789] A generative information processing device means for detecting anomalies in text information based on the aforementioned product information data,

[0790] An image analysis device means for detecting anomalies in image information based on the aforementioned product information data,

[0791] An emotion recognition means for estimating emotions based on the user's input data and behavioral history,

[0792] A notification device means that generates optimized notification information based on abnormality and emotion estimation results and transmits it via a communication device,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, wherein the generative information processing device that detects anomalies in the text information analyzes the text data using natural language processing technology.

[0796] (Claim 3)

[0797] The system according to claim 1, wherein the image analysis device analyzes image anomalies using a machine learning model. [Explanation of Symbols]

[0798] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for collecting product information data from web pages, A generative information processing device means for detecting anomalies in text information based on the aforementioned product information data, An image analysis device means for detecting anomalies in image information based on the aforementioned product information data, A warning device means that generates and transmits notification information when an abnormality is detected, A system that includes this.

2. The system according to claim 1, wherein the generative information processing device that detects anomalies in the text information analyzes the text data using natural language processing technology.

3. The system according to claim 1, wherein the image analysis device analyzes image anomalies using a machine learning model.

Images