system

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing a filtering condition set by a user and excluding a page including an unpleasant content from a search result in order to exclude the unpleasant content; search processing means for receiving a search request and acquiring the search result from the Internet; analyzing means for analyzing a web page of the search result and extracting a URL of an image or a text content; filtering means for collating the extracted image or text content with the filtering condition and determining a page matching the condition; and display means for transmitting and displaying the filtered search result to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional Internet search services, when a user searches for a specific keyword, unpleasant images or text content may be displayed. The display of such unpleasant content can cause psychological stress for users and make it difficult for them to conduct searches with peace of mind. Furthermore, existing filtering systems often lack precision and flexibility, making it difficult for them to properly filter content based on user-specified criteria. The present invention aims to resolve this problem and provide an environment in which users can conduct searches with peace of mind. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a search system that removes offensive content from search results based on filtering conditions set by a user. Specifically, the system includes a search processing unit that receives a search request and retrieves search results from the Internet, and an analysis unit that analyzes the web pages in the search results and extracts image URLs and text content. The system further includes a filtering unit that compares the extracted image and text content with the filtering conditions and identifies pages that match the conditions. The system also provides a display unit that transmits the filtered search results to a user terminal and displays them. The system also includes a unit that analyzes the extracted image content using image analysis means, determines whether the analyzed image contains offensive content, and, if determined to contain offensive content, removes the page or assigns a warning label to it. The system further includes a unit that analyzes the extracted text content using natural language processing, determines whether it contains offensive keywords or phrases, and, if determined to contain offensive content, removes the page or assigns a warning label to it. In this way, users can perform comfortable and safe searches while avoiding offensive content.

[0006] "Offensive content" generally refers to the content of a web page, including images or text that cause psychological distress or discomfort to the viewer.

[0007] "Filtering conditions" are criteria for determining objectionable content based on specific criteria or rules set by the user, such as specific keywords or image characteristics.

[0008] The "search processing means" is a means having the function of receiving a search request from a user and retrieving related search results via the Internet.

[0009] The "analysis means" is a means having the function of analyzing the content of the web pages of the obtained search results and extracting image URLs and text content.

[0010] The "filtering means" is a means for checking extracted images and text content against filtering conditions set by the user to determine whether or not the extracted images and text content meet the conditions.

[0011] "Image analysis means" means means capable of analyzing image content extracted from a web page and determining whether the image contains objectionable material.

[0012] "Text analysis means" means means having the function of analyzing text content extracted from a web page and determining whether it contains offensive keywords or phrases.

[0013] The "display means" is a means having a function for transmitting the filtered search results to the user terminal and displaying them on the screen. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0036] overview

[0037] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. Its main components include a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0038] User operations

[0039] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0040] Processing search requests (server)

[0041] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0042] Analysis method (server)

[0043] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0044] Filtering method (server)

[0045] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0046] Warn or Exclude (Server)

[0047] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0048] Displaying the results (terminal)

[0049] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0050] Specific examples

[0051] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the server analyzes the content of each web page to check whether it contains any images or text of insects. If it does, the page is removed from the list or a warning label is attached. Finally, the filtered search results are displayed to the user, allowing them to browse the search results with peace of mind without seeing any unpleasant insect images.

[0052] In this way, the system of the present invention can provide a comfortable and secure search experience for the user.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user inputs search keywords and presses the search button. The user's device receives this input and creates a search request.

[0056] Step 2:

[0057] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0058] Step 3:

[0059] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0060] Step 4:

[0061] The server calls an external search engine API based on the search keywords and retrieves search results.

[0062] Search results include the title, URL, and snippet of the relevant web page.

[0063] Step 5:

[0064] The server analyzes each web page in the search results and extracts image URLs and text content.

[0065] Scraping technology is used to analyze HTML source code.

[0066] Step 6:

[0067] The server analyzes the URL of the extracted image using an image analysis means, which uses an image analysis library.

[0068] For example, determining if an image contains insects and checking for objectionable content.

[0069] Step 7:

[0070] The server uses text analysis means to analyze the extracted text content with a natural language processing library.

[0071] Check for the presence of certain offensive keywords or phrases.

[0072] Step 8:

[0073] Based on the analysis results, the server determines which pages contain objectionable content.

[0074] If the filtering conditions are met, the page will be excluded from the search results list or marked with a warning label.

[0075] Step 9:

[0076] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0077] Step 10:

[0078] The terminal analyzes the filtered search results received from the server and displays them on the user's screen.

[0079] For search results with warning labels, an appropriate warning message will be displayed to the user.

[0080] Through the above processing steps, the CleanSearch system provides users with search results that do not contain offensive content, ensuring a safe browsing environment.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] When searching the Internet, users may encounter objectionable content. For this reason, it is necessary to provide an environment where users can safely view search results. In particular, if the content of images or text contains objectionable content, it is necessary to improve the user experience by filtering or warning users in advance.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from a network, analysis means for analyzing web pages in the search results and extracting image paths and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that meet the conditions, and display means for transmitting the filtered search results to a user terminal and displaying them, thereby enabling users to view search results while avoiding offensive content.

[0086] "Filtering conditions" are specific criteria or rules that a user sets to avoid objectionable content.

[0087] A "search processing means" is a mechanism for receiving a search request and retrieving related information over a network.

[0088] The "analysis means" is a function for analyzing the acquired search results and extracting image paths and text content.

[0089] The "filtering means" is a function that checks the extracted content against the filtering conditions set by the user to determine whether or not it contains offensive content.

[0090] The "display means" is a mechanism for transmitting the filtered search results to the user terminal and presenting them to the user.

[0091] The "image analysis means" is a function for analyzing extracted image content and determining whether it contains offensive content.

[0092] The "text analysis means" is a mechanism for analyzing the extracted text content and identifying offensive keywords and phrases.

[0093] A "warning label" is a warning message or mark that is added to search results that contain offensive content.

[0094] "Network" refers to an information and communication network such as the Internet, which is the infrastructure for sending and receiving data.

[0095] A "user terminal" is a device such as a computer, smartphone, or tablet that is operated by an individual.

[0096] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0097] overview

[0098] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. The system includes a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0099] User operations

[0100] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0101] Processing a search request

[0102] The terminal sends a search request to the server. The server receives this request and performs a search on the network using the specified keywords. In this process, it uses an external search engine API to obtain a list of related web pages. Specifically, a search engine API is used as an example of an external search engine API.

[0103] Analysis means

[0104] The server begins parsing the search results. The parser analyzes the HTML content of each web page to extract image paths and text content. An HTML parsing library, such as BeautifulSoup, is used for the analysis.

[0105] Filtering Methods

[0106] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains offensive material. Image analysis is performed using an image processing library, such as OpenCV. Text analysis is performed using a text processing library, such as NLTK.

[0107] Warnings or Exclusions

[0108] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0109] Displaying the results

[0110] After filtering, the search results are sent from the server to the device. The device displays the filtered results on the user's screen. For search results with warning labels, an appropriate warning message is displayed to the user. For example, a warning such as "This page contains images of insects" is displayed.

[0111] Specific examples

[0112] For example, when a user enters the search keyword "insect control" and presses the search button, the server uses the keywords to retrieve a list of related web pages from an external search engine API. Next, it uses BeautifulSoup to analyze the content of each web page and checks whether it contains insect images or text. OpenCV is used to detect whether the page contains insect images, and NLTK is used to check the text for offensive content. If it contains insect images, the page is either excluded from the list or a warning label is added. Finally, the filtered search results are displayed to the user, allowing them to safely browse the search results while avoiding any offensive insect images.

[0113] Usage example (example of prompt sentence for generative AI model)

[0114] An example prompt might look like this:

[0115] A user searches for "insect prevention" and sets the filtering criteria to "Do not display images of insects." The server retrieves related web pages using an external search engine API, analyzes them with BeautifulSoup, and extracts image paths and text. OpenCV performs image analysis, and NLTK analyzes the text. Any objectionable content is removed from the results, and the final filtered search results are displayed to the user.

[0116] In this way, the system of the present invention provides a comfortable and secure search experience for the user.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] The user enters a keyword in the search field and presses the search button. For example, the user enters "insect control" and sets the filtering condition to "do not display images of insects." The input in this case is the keyword and the filtering condition. The output is a search request, which is generated by the terminal.

[0120] Step 2:

[0121] The terminal sends the search request entered by the user to the server. Specifically, the terminal sends the generated search request, i.e., a data packet containing keywords and filtering conditions, to the server via the network. The input is the search request, and the output is the transmission of the data packet to the server.

[0122] Step 3:

[0123] Based on the received search request, the server performs a network search using the specified keywords. At this time, it uses an external search engine API to obtain a list of related web pages. Specifically, the server sends an HTTP request to the API and receives an HTTP response containing the search results. The input is the search request, and the output is the list of retrieved web pages.

[0124] Step 4:

[0125] The server analyzes the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image paths and text content. Specifically, it uses an HTML analysis library called BeautifulSoup to analyze the HTML and extract image URLs and text. The input is a list of retrieved web pages, and the output is the extracted image URLs and text content.

[0126] Step 5:

[0127] The server compares the extracted images and text content with the filtering criteria set by the user. This comparison is performed using image analysis tools and involves necessary image processing. Specifically, it analyzes images using OpenCV to determine whether they contain offensive content. For example, it uses computer vision techniques based on a specific labeled image dataset. The input is the image URL, and the output is the filtering result.

[0128] Step 6:

[0129] The server analyzes the extracted text content using text analysis tools. Specifically, it uses the NLTK library to tokenize the text and detect offensive keywords and phrases. The input is the extracted text content, and the output is the text filtering decision.

[0130] Step 7:

[0131] If the server determines that a web page contains objectionable content, it either removes the web page from the search results or adds a warning label. Specifically, the server either removes the web page from the list or adds a warning message based on the result of the determination. The input is the filtering result, and the output is the final filtered search result list.

[0132] Step 8:

[0133] After filtering is complete, the search results are sent from the server to the terminal. The terminal displays the filtered results on the user's screen. Specifically, the server sends the filtered search results as data packets to the terminal, and the terminal parses the received data appropriately and displays it in a GUI. For search results with warning labels, a message such as "This page contains images of insects" is displayed. The input is the final filtered search result list, and the output is the search results displayed on the user's screen.

[0134] (Application example 1)

[0135] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0136] Conventional search systems often lack sufficient filtering capabilities to avoid offensive content. In particular, it has been difficult for video streaming services to proactively filter out content that users find offensive. This has led to the risk of users accidentally encountering unpleasant video content, making it difficult for them to enjoy content safely. Furthermore, existing filtering systems often lack the precision of image and text analysis, resulting in inaccurate filtering.

[0137] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0138] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from information sources, analysis means for analyzing digital information in the search results and extracting image addresses and text information, filtering means for comparing the extracted image and text information with the filtering conditions and determining pages that match the conditions, display means for transmitting the filtered search results to a user interface and displaying them, and video analysis means for analyzing video thumbnail images and descriptive text and excluding videos that match the user's filtering conditions. This allows users to use content distribution services with peace of mind without viewing offensive content.

[0139] "Filtering conditions" are criteria that a user sets to avoid objectionable content.

[0140] The "search processing means" is a function that receives a user's search request and retrieves relevant search results from information sources.

[0141] The "analysis means" is a function that analyzes the digital information contained in the obtained search results and extracts image addresses and text information.

[0142] The "filtering means" is a function that checks extracted image and text information against the filtering conditions set by the user and determines which pages match.

[0143] The "display means" is a function that transmits the filtered search results to the user interface and displays them.

[0144] The "video analysis means" is a function that analyzes the thumbnail images and description text of videos and eliminates videos that match the user's filtering conditions.

[0145] The system embodying the present invention is a search system that eliminates objectionable content based on filtering conditions set by a user. A specific embodiment of this system will be described below.

[0146] System Overview

[0147] The system includes a search processing unit, an analysis unit, a filtering unit, a display unit, and a video analysis unit, and can prevent users from viewing objectionable content, particularly in video distribution services.

[0148] Hardware and Software

[0149] The following hardware and software are used to implement this system:

[0150] Hardware: Smartphone, server, camera (for image analysis)

[0151] Software: OpenCV (image analysis), TextBlob (text analysis)

[0152] Process Overview

[0153] The server receives the user's filtering criteria, analyzes the search results based on them, and filters out or warns of offensive content, as detailed below.

[0154] Search processing means

[0155] When a user enters a search request on a terminal, the request is sent to the server, which retrieves relevant search results from the information source.

[0156] Analysis means

[0157] Analyze and extract the digital information (image addresses and text information) from the search results. Specifically, analyze the HTML content to extract the necessary information.

[0158] Filtering Methods

[0159] The extracted images and text information are compared with the filtering criteria set by the user to determine which pages or videos match. If there is a match, the page is either excluded or marked with a warning label.

[0160] Display means

[0161] The filtered search results are sent from the server to the terminal and displayed on the user interface.

[0162] Video analysis methods

[0163] Analyzes video thumbnail images and description text, and filters out content that matches the user's filtering criteria. Image analysis is performed using OpenCV, and text analysis is performed using TextBlob.

[0164] Specific examples

[0165] For example, consider a situation where a user has set a preference to "not display horror movies." When the user opens a video streaming app and searches for a specific keyword, the server receives the request and retrieves relevant videos from the source. The server then analyzes the video's thumbnail image and description text to determine whether it matches the user's filtering criteria of "horror movies." If it does, the video is removed from the viewing list or a warning label is added.

[0166] Prompt Sentence Examples

[0167] If a user searches for "horror movies" in a video streaming app, the following prompt will be generated:

[0168] text

[0169] The filter condition "Horror Movies" is set. Based on this requirement, perform image and text analysis to filter out horror movies.

[0170] In this way, the system of the present invention can provide users with a comfortable and safe video viewing experience.

[0171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0172] Step 1:

[0173] A user inputs a search request from a device. For example, a user sets a filtering condition such as "do not display horror movies" and operates a video streaming app to search for "latest movies." In this case, the specific action is to enter "latest movies" into the search field on the device and press the search button.

[0174] Step 2:

[0175] The terminal sends a search request (input: user's search keywords and filtering conditions) to the server. The data processing performed here is to generate request data including the search keywords and filtering conditions and send it to the server via the network. The output is the request data sent to the server.

[0176] Step 3:

[0177] The server processes the received search request and retrieves search results from the information source (e.g., calling an external search engine API). The server retrieves a list of related videos on the Internet based on the user's search keywords. At this time, an appropriate API call is made as data calculation, and the video list as search results is obtained as text data. The output is the retrieved video list.

[0178] Step 4:

[0179] The server analyzes the search results and extracts the addresses of the video thumbnail images and description text. The specific operation performed here is to parse the HTML content of each video and extract the necessary information (thumbnail URL and description text). The input is the list of videos in the search results, and the output is a list of extracted thumbnail URLs and description text.

[0180] Step 5:

[0181] The server compares the extracted thumbnail images and description text with the user's filtering criteria and filters them. For example, to check whether a movie is a horror movie, the server analyzes the thumbnail images with OpenCV and the description text with TextBlob. The input is the extracted thumbnail URL and description text, and the data calculation is the image and text analysis process. The output is a filtered list of movies.

[0182] Step 6:

[0183] Based on the filtered video list, the server removes videos determined to contain objectionable content from the list or assigns warning labels to them. Specifically, the server updates the video list according to the analysis results. The input is the filtered video list, and the output is the final display list (including videos with warning labels).

[0184] Step 7:

[0185] The server sends the final display list to the terminal. The server then transfers the updated video list to the terminal via the network. At this time, the server converts the list into the required format as data processing before sending it. The input is the final display list, and the output is the display list sent to the terminal.

[0186] Step 8:

[0187] The terminal displays the received final display list on the user interface. Specifically, the terminal updates the user interface to show the safe video list to the user. The input is the display list sent from the server, and the output is a screen display that the user can visually confirm.

[0188] By following the above steps, users can watch a filtered list of safe videos with peace of mind.

[0189] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0190] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0191] overview

[0192] In addition to search processing means, analysis means, filtering means, and display means, this system is equipped with an emotion engine that recognizes user emotions in real time and dynamically updates filtering conditions, allowing users to receive appropriate search results in response to changes in their emotions, providing a comfortable and secure search experience.

[0193] User operations

[0194] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition is set to "Do not display images of insects."

[0195] Processing search requests (server)

[0196] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0197] Analysis method (server)

[0198] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0199] Filtering method (server)

[0200] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0201] Emotion engine function (server)

[0202] In parallel with the search process, the server analyzes emotions in real time based on the user's search behavior and feedback. The emotion engine monitors the user's facial expressions and click behavior while searching, and dynamically updates the filtering conditions if unpleasant emotions are recognized.

[0203] Warn or Exclude (Server)

[0204] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0205] Displaying the results (terminal)

[0206] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0207] Specific examples

[0208] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images or text of insects. If it does contain any images of insects, the page is removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated accordingly. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0209] In this way, the system of the present invention can provide users with a comfortable and secure search experience. By combining it with an emotion engine, appropriate filtering according to the user's emotions becomes possible, further improving user satisfaction.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] The user enters keywords into the search field and presses the search button. The user's device receives this input and creates a search request.

[0213] Step 2:

[0214] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0215] Step 3:

[0216] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0217] Step 4:

[0218] The server calls external search engine APIs based on the search keywords to retrieve search results, which include the titles, URLs, and snippets of relevant web pages.

[0219] Step 5:

[0220] The server analyzes each web page in the search results and extracts image URLs and text content, using scraping technology to analyze the HTML source code.

[0221] Step 6:

[0222] The server analyzes the extracted image URLs using image analysis techniques, such as using an image analysis library, to determine if the image contains insects or other objectionable content.

[0223] Step 7:

[0224] The server then uses text analysis tools to analyze the extracted text content using natural language processing libraries to check whether it contains certain offensive keywords or phrases.

[0225] Step 8:

[0226] Based on the analysis results, the server determines whether the page contains objectionable content and, if it meets the filtering criteria, removes the page from the search results list or adds a warning label.

[0227] Step 9:

[0228] The server runs an emotion engine based on the user's search behavior and feedback. The emotion engine uses facial recognition technology to detect emotions from the user's facial expressions in real time and analyzes their reactions to search results.

[0229] Step 10:

[0230] The server automatically and dynamically updates the filtering conditions when the user indicates unpleasant emotions, and applies the new filtering conditions to re-filter the search results.

[0231] Step 11:

[0232] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0233] Step 12:

[0234] The terminal analyzes the filtered search results received from the server and displays them on the user's screen. For search results with warning labels, the terminal displays an appropriate warning message to the user.

[0235] Through these processing steps, the CleanSearch system provides users with search results that do not contain offensive content, and the emotion engine also enables dynamic filtering based on user emotions, allowing users to enjoy a safe and enjoyable search experience.

[0236] Example 2

[0237] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] In conventional search systems, users often experience stress when checking search results due to the risk of encountering unpleasant content. Furthermore, they lack dynamic filtering that matches the user's emotions and preferences, making it difficult to provide optimal search results for each individual user. For this reason, there was a demand for a search system that could recognize user emotions in real time and dynamically update filtering conditions.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0240] In this invention, the server includes means for filtering out offensive content based on filtering conditions set by the user, search processing means for receiving search requests and retrieving search results from a global network, analysis means for analyzing web pages in the search results and extracting image data and text data, filtering means for comparing the extracted image data and text data with the filtering conditions and determining pages that meet the conditions, emotion analysis means for recognizing the user's emotions in real time and dynamically updating the filtering conditions, and display means for transmitting the filtered search results to the user terminal and displaying them. This allows users to enjoy a comfortable search experience tailored to their emotions and preferences without seeing offensive content during searches.

[0241] "User" refers to an individual who utilizes a search system to enter keywords to retrieve information and review search results.

[0242] A "terminal" is a device used by a user to access the search system and display search results, and includes a personal computer, smartphone, etc.

[0243] "Server" refers to the back-end computer system that receives search requests, retrieves search results from the Internet, and analyzes and filters the data.

[0244] "Filtering conditions" refer to criteria set by a user to filter out objectionable content, and may include specific keywords or image characteristics.

[0245] The term "search processing means" refers to a function that searches for related web pages using a global network based on a search request received from a user.

[0246] "Analysis means" refers to the function of analyzing the content of web pages included in search results and extracting image data and text data.

[0247] "Filtering means" refers to the function of comparing extracted image data and text data with filtering conditions and identifying pages that meet the criteria.

[0248] "Emotion analysis means" refers to the function of analyzing users' search behavior and facial expression data in real time and dynamically updating filtering conditions.

[0249] "Display means" refers to the function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0250] "Image analysis means" refers to a function that analyzes extracted image data and determines whether the content contains objectionable content.

[0251] "Text analysis means" refers to a function that analyzes extracted text data and determines whether the content contains offensive keywords or phrases.

[0252] "Warning label" refers to a message displayed to users to inform them that their search results contain objectionable content.

[0253] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0254] First, the user enters a keyword into the search field on the device and presses the search button. For example, they enter "insect control."

[0255] The device then sends the user's input search request to the server, which receives the request and uses an external search engine API (e.g., Google Custom Search API) to retrieve a list of related web pages.

[0256] The server analyzes the HTML content of the search results and extracts image and text data using Beautiful Soup or a similar library. The extracted image data is analyzed using image analysis software such as OpenCV, and the text data is analyzed using a natural language processing library such as NLTK.

[0257] The server then compares the extracted data with the filtering criteria set by the user. For example, an image analysis unit may determine whether the data contains images of insects, and if so, reject the objectionable content according to the filtering criteria. Similarly, a text analysis unit may analyze the text data to determine whether it contains objectionable keywords or phrases.

[0258] In parallel, the server analyzes users' search behavior and feedback in real time using an emotion engine, which uses machine learning models such as TensorFlow to monitor users' facial expression data and click behavior, dynamically updating filtering criteria if unpleasant emotions are recognized.

[0259] For example, if a user expresses displeasure when viewing a search result page, the emotion engine analyzes that data and reconfigures its filtering criteria to ensure the user does not encounter similar displeasure again.

[0260] Finally, the server sends the filtered search results to the device, which displays them on the user's screen and adds warning labels if necessary. For example, a page containing images of insects will display a warning message saying, "This page contains images of insects."

[0261] As a concrete example, suppose a user enters "insect control" as a search keyword and presses the search button. The server uses this keyword to call the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images of insects. If it does, the page is either removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated appropriately. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0262] An example of a prompt might be:

[0263] "When you enter a search keyword and press a button, the search is performed using an external search engine API, and objectionable content is filtered out based on the filtering conditions set by the user in advance. In addition, an emotion engine analyzes the user's emotions and dynamically updates the filtering conditions. A warning may also be displayed in the search results."

[0264] The system allows users to avoid objectionable content while searching, providing a comfortable and safe search experience with dynamic filtering that takes sentiment into account in real time.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1:

[0267] The user enters a keyword into the search field on the device and presses the search button. Specifically, the keyword "insect control" is entered. This input generates a search request. The output is this search request.

[0268] Step 2:

[0269] The terminal sends the generated search request to the server. Specifically, it generates an HTTP POST request and sends it to the server in a format that includes the search keywords. The input is the keyword entered by the user, and the output is the search request sent to the server.

[0270] Step 3:

[0271] The server parses the received search request and retrieves a list of relevant web pages using an external search engine API, specifically by calling the Google Custom Search API to retrieve the search results. The input is the received search request and the output is the list of retrieved search results.

[0272] Step 4:

[0273] The server analyzes the HTML content of the search results and extracts image data and text data. Specifically, it uses Beautiful Soup to extract image URLs and text from the HTML of each web page. The input is the HTML content of the search results, and the output is the extracted image data and text data.

[0274] Step 5:

[0275] The server compares the extracted image data and text data with the filtering conditions set by the user. Specifically, it performs image analysis using OpenCV and text analysis using NLTK. The input is the extracted image data or text data and the filtering conditions, and the output is a judgment result on whether the filtering conditions are met.

[0276] Step 6:

[0277] If the server determines that the extracted data contains offensive content, it will either exclude the page from the search results or add a warning label. For example, if the page contains an image of an insect, it will either exclude the page or add a warning message. The input is the result of the determination, and the output is an updated list of search results.

[0278] Step 7:

[0279] The server's emotion engine monitors users' search behavior and feedback and analyzes their emotions in real time. Specifically, it captures the user's facial expression data and analyzes it using TensorFlow. The input is the user's facial expression data, and the output is the analyzed emotion data.

[0280] Step 8:

[0281] The server dynamically updates the filtering conditions based on the emotion data. For example, if the user shows an unpleasant facial expression, it strengthens the related filtering conditions. The input is the emotion analysis result, and the output is the updated filtering conditions.

[0282] Step 9:

[0283] Finally, the server sends the filtered search results to the terminal. Specifically, it generates an HTTP response and sends it to the terminal including the search results. The input is the processed search result list, and the output is the final search results displayed on the user's terminal.

[0284] Step 10:

[0285] The terminal displays the filtered search results on the user's screen, for example displaying a warning message saying "This page contains images of insects." The input is the search results sent by the server, and the output is the search results visually presented to the user.

[0286] (Application example 2)

[0287] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0288] When searching the Internet, users may encounter unpleasant content, which can impair the search experience. Especially on online shopping sites, users may feel uneasy about making purchases if product information or images containing unpleasant content are displayed. Furthermore, there is a lack of a mechanism to dynamically change filtering conditions according to user emotions, which makes it difficult to respond flexibly.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0290] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from the Internet, analysis means for analyzing web pages in the search results and extracting image URLs and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that match the conditions, emotion recognition means for analyzing the user's search behavior and facial expressions in real time and recognizing emotions, means for dynamically updating the filtering conditions based on the user's emotions recognized by the emotion recognition means, and display means for transmitting the filtered search results to a user terminal and displaying them. This enables users to avoid offensive content and perform flexible filtering according to emotions.

[0291] "User-defined filtering conditions" refers to criteria for filtering out objectionable content by a user setting specific conditions.

[0292] The "search processing means" is a means having the function of receiving a search request from a user and retrieving related search results from the Internet.

[0293] "Analysis means" refers to a means that has the function of analyzing web pages in search results and extracting image URLs and text content.

[0294] The "filtering means" is a means having the function of checking extracted images and text content against the filtering conditions set by the user and determining which pages match those conditions.

[0295] The "emotion recognition means" is a means having a function of analyzing the user's search behavior and facial expressions in real time and recognizing the user's emotions.

[0296] The "dynamic update means" is a means having a function of changing or adjusting the filtering conditions in real time based on the user's emotion recognized by the emotion recognition means.

[0297] The "display means" is a means having a function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0298] MODE FOR CARRYING OUT THE INVENTION

[0299] The system that realizes this application example is a search system that eliminates unpleasant content from search results based on filtering conditions set by the user, and also performs dynamic filtering according to the user's emotions using emotion recognition means. This system is composed of both a server and a user terminal, and requires specific hardware and software to realize each function.

[0300] System Configuration

[0301] Hardware

[0302] Server: A computer system for performing search processing, analysis, filtering, and emotion recognition.

[0303] User device: A device used to input search keywords and display search results. This includes smartphones, tablets, and PCs.

[0304] Webcam: Hardware for capturing a user's facial expressions.

[0305] Microphone: Hardware used to capture the user's voice.

[0306] software

[0307] Search engine API: Software that uses external search engine services to obtain information on the Internet.

[0308] Image analysis module: Software for analyzing the acquired image content (e.g. OpenCV).

[0309] Text analysis module: Software for analyzing the captured text content (e.g., NLTK).

[0310] Emotion recognition model: Software for recognizing emotions from a user's facial expressions and voice in real time (e.g., Facial Expression Recognition model).

[0311] Filtering module: Software that matches the filtering criteria set by the user and filters out objectionable content.

[0312] Processing flow

[0313] 1. Submit a search request

[0314] The user enters keywords into the terminal and presses the search button.

[0315] The terminal sends a search request to the server.

[0316] 2. Obtaining search results

[0317] The server uses a search engine API to retrieve search results based on the specified keywords from the Internet.

[0318] 3. Content Analysis

[0319] Using the analysis means, the server analyzes the web pages of the retrieved search results and extracts image URLs and text content.

[0320] An image analysis module analyzes the extracted image content to determine if it contains objectionable material.

[0321] The text analysis module analyzes the extracted text content to determine whether it contains offensive keywords or phrases.

[0322] 4. Emotional Recognition

[0323] The server monitors the user's search behavior and facial expressions in real time via a webcam and microphone, and analyzes the user's emotions using an emotion recognition model.

[0324] 5. Filtering

[0325] The filtering module matches the extracted content with filtering criteria set by the user and dynamically updates the criteria based on the user's emotional state according to an emotion recognition model.

[0326] Exclude pages or add warning labels if they contain objectionable content.

[0327] 6. Displaying the results

[0328] The filtered search results are sent from the server to the user terminal and displayed.

[0329] Specific examples

[0330] For example, if a user searches for "stuffed toys," the server uses a search engine API to obtain a list of related web pages. Then, it uses analytics to analyze the content of each web page and detects offensive content from images and text. If it determines that the user dislikes spiders, spider images and related text are filtered out. Furthermore, the system analyzes the user's facial expressions and voice in real time, and if any unpleasant emotions are recognized, the filtering criteria are dynamically updated. Finally, the filtered search results are displayed on the device, allowing the user to choose their purchase with confidence.

[0331] Prompt Sentence Examples

[0332] Sentiment Analysis Prompt: "Analyze the user's emotions based on their facial expressions and voice to determine what content they find offensive."

[0333] Content Analysis prompt: "Identify content in your search results that users may find offensive and explain why."

[0334] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0335] Step 1:

[0336] User enters keyword

[0337] Users input search keywords using devices such as smartphones or PCs. This generates a search request. The input data is the keywords, and the output data is the search request.

[0338] Step 2:

[0339] Submitting a search request

[0340] The terminal sends the search request entered by the user to the server. The input data is the search request, and the output data is a request packet sent to the server. Specifically, the request is sent to the server using the HTTP protocol.

[0341] Step 3:

[0342] Getting search results

[0343] When the server receives a search request, it uses an external search engine API to retrieve relevant search results from the Internet. The input data is the search request, and the output data is a list of the retrieved search results. The data is processed by passing the search keywords to the search engine API and executing the search.

[0344] Step 4:

[0345] Content Analysis

[0346] The server analyzes the web pages of the search results it retrieves and extracts image URLs and text content. The input data is a list of search results, and the output data is the extracted image URLs and text content. Specifically, it performs HTML parsing to extract image URLs and text content.

[0347] Step 5:

[0348] User Emotion Recognition

[0349] The server captures the user's facial expressions and voice through a webcam and microphone. It then analyzes the user's emotions using an emotion recognition model. The input data are the captured facial expression images and voice data, and the output data is the analyzed emotional state. Image recognition algorithms and voice analysis algorithms are used for data processing.

[0350] Step 6:

[0351] Dynamic filtering condition updates

[0352] The server dynamically updates the filtering conditions based on the recognized user emotion. The input data is the analyzed emotional state, and the output data is the updated filtering conditions. Specific operations include executing logic to change the filtering criteria accordingly.

[0353] Step 7:

[0354] Content Filtering

[0355] The server uses analytical tools to match the extracted content with filtering criteria and exclude or label pages containing objectionable content. The input data are the extracted image URLs and text content and the filtering criteria, and the output data are the filtered search results. Specifically, the server evaluates the content using a criteria matching algorithm.

[0356] Step 8:

[0357] Submitting filtered search results

[0358] The server sends the filtered search results to the user terminal. The input data is the filtered search results, and the output data is a data packet sent to the user terminal. Specifically, the server sends back the results using the HTTP protocol.

[0359] Step 9:

[0360] Displaying search results

[0361] The user terminal receives the filtered search results and displays them on the user's screen. The input data are the search results sent from the server, and the output data are the search results displayed on the user's screen. Specifically, the received data is rendered on the screen in an appropriate format.

[0362] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0364] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0368] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0369] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0370] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0371] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0372] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0373] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0374] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0375] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0376] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0377] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0378] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0379] overview

[0380] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. Its main components include a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0381] User operations

[0382] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0383] Processing search requests (server)

[0384] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0385] Analysis method (server)

[0386] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0387] Filtering method (server)

[0388] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0389] Warn or Exclude (Server)

[0390] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0391] Displaying the results (terminal)

[0392] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0393] Specific examples

[0394] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the server analyzes the content of each web page to check whether it contains any images or text of insects. If it does, the page is removed from the list or a warning label is attached. Finally, the filtered search results are displayed to the user, allowing them to browse the search results with peace of mind without seeing any unpleasant insect images.

[0395] In this way, the system of the present invention can provide a comfortable and secure search experience for the user.

[0396] The processing flow will be explained below.

[0397] Step 1:

[0398] The user inputs search keywords and presses the search button. The user's device receives this input and creates a search request.

[0399] Step 2:

[0400] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0401] Step 3:

[0402] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0403] Step 4:

[0404] The server calls an external search engine API based on the search keywords and retrieves search results.

[0405] Search results include the title, URL, and snippet of the relevant web page.

[0406] Step 5:

[0407] The server analyzes each web page in the search results and extracts image URLs and text content.

[0408] Scraping technology is used to analyze HTML source code.

[0409] Step 6:

[0410] The server analyzes the URL of the extracted image using an image analysis means, which uses an image analysis library.

[0411] For example, determining if an image contains insects and checking for objectionable content.

[0412] Step 7:

[0413] The server uses text analysis means to analyze the extracted text content with a natural language processing library.

[0414] Check for the presence of certain offensive keywords or phrases.

[0415] Step 8:

[0416] Based on the analysis results, the server determines which pages contain objectionable content.

[0417] If the filtering conditions are met, the page will be excluded from the search results list or marked with a warning label.

[0418] Step 9:

[0419] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0420] Step 10:

[0421] The terminal analyzes the filtered search results received from the server and displays them on the user's screen.

[0422] For search results with warning labels, an appropriate warning message will be displayed to the user.

[0423] Through the above processing steps, the CleanSearch system provides users with search results that do not contain offensive content, ensuring a safe browsing environment.

[0424] Example 1

[0425] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0426] When searching the Internet, users may encounter objectionable content. For this reason, it is necessary to provide an environment where users can safely view search results. In particular, if the content of images or text contains objectionable content, it is necessary to improve the user experience by filtering or warning users in advance.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0428] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from a network, analysis means for analyzing web pages in the search results and extracting image paths and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that meet the conditions, and display means for transmitting the filtered search results to a user terminal and displaying them, thereby enabling users to view search results while avoiding offensive content.

[0429] "Filtering conditions" are specific criteria or rules that a user sets to avoid objectionable content.

[0430] A "search processing means" is a mechanism for receiving a search request and retrieving related information over a network.

[0431] The "analysis means" is a function for analyzing the acquired search results and extracting image paths and text content.

[0432] The "filtering means" is a function that checks the extracted content against the filtering conditions set by the user to determine whether or not it contains offensive content.

[0433] The "display means" is a mechanism for transmitting the filtered search results to the user terminal and presenting them to the user.

[0434] The "image analysis means" is a function for analyzing extracted image content and determining whether it contains offensive content.

[0435] The "text analysis means" is a mechanism for analyzing the extracted text content and identifying offensive keywords and phrases.

[0436] A "warning label" is a warning message or mark that is added to search results that contain offensive content.

[0437] "Network" refers to an information and communication network such as the Internet, which is the infrastructure for sending and receiving data.

[0438] A "user terminal" is a device such as a computer, smartphone, or tablet that is operated by an individual.

[0439] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0440] overview

[0441] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. The system includes a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0442] User operations

[0443] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0444] Processing a search request

[0445] The terminal sends a search request to the server. The server receives this request and performs a search on the network using the specified keywords. In this process, it uses an external search engine API to obtain a list of related web pages. Specifically, a search engine API is used as an example of an external search engine API.

[0446] Analysis means

[0447] The server begins parsing the search results. The parser analyzes the HTML content of each web page to extract image paths and text content. An HTML parsing library, such as BeautifulSoup, is used for the analysis.

[0448] Filtering Methods

[0449] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains offensive material. Image analysis is performed using an image processing library, such as OpenCV. Text analysis is performed using a text processing library, such as NLTK.

[0450] Warnings or Exclusions

[0451] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0452] Displaying the results

[0453] After filtering, the search results are sent from the server to the device. The device displays the filtered results on the user's screen. For search results with warning labels, an appropriate warning message is displayed to the user. For example, a warning such as "This page contains images of insects" is displayed.

[0454] Specific examples

[0455] For example, when a user enters the search keyword "insect control" and presses the search button, the server uses the keywords to retrieve a list of related web pages from an external search engine API. Next, it uses BeautifulSoup to analyze the content of each web page and checks whether it contains insect images or text. OpenCV is used to detect whether the page contains insect images, and NLTK is used to check the text for offensive content. If it contains insect images, the page is either excluded from the list or a warning label is added. Finally, the filtered search results are displayed to the user, allowing them to safely browse the search results while avoiding any offensive insect images.

[0456] Usage example (example of prompt sentence for generative AI model)

[0457] An example prompt might look like this:

[0458] A user searches for "insect prevention" and sets the filtering criteria to "Do not display images of insects." The server retrieves related web pages using an external search engine API, analyzes them with BeautifulSoup, and extracts image paths and text. OpenCV performs image analysis, and NLTK analyzes the text. Any objectionable content is removed from the results, and the final filtered search results are displayed to the user.

[0459] In this way, the system of the present invention provides a comfortable and secure search experience for the user.

[0460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0461] Step 1:

[0462] The user enters a keyword in the search field and presses the search button. For example, the user enters "insect control" and sets the filtering condition to "do not display images of insects." The input in this case is the keyword and the filtering condition. The output is a search request, which is generated by the terminal.

[0463] Step 2:

[0464] The terminal sends the search request entered by the user to the server. Specifically, the terminal sends the generated search request, i.e., a data packet containing keywords and filtering conditions, to the server via the network. The input is the search request, and the output is the transmission of the data packet to the server.

[0465] Step 3:

[0466] Based on the received search request, the server performs a network search using the specified keywords. At this time, it uses an external search engine API to obtain a list of related web pages. Specifically, the server sends an HTTP request to the API and receives an HTTP response containing the search results. The input is the search request, and the output is the list of retrieved web pages.

[0467] Step 4:

[0468] The server analyzes the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image paths and text content. Specifically, it uses an HTML analysis library called BeautifulSoup to analyze the HTML and extract image URLs and text. The input is a list of retrieved web pages, and the output is the extracted image URLs and text content.

[0469] Step 5:

[0470] The server compares the extracted images and text content with the filtering criteria set by the user. This comparison is performed using image analysis tools and involves necessary image processing. Specifically, it analyzes images using OpenCV to determine whether they contain offensive content. For example, it uses computer vision techniques based on a specific labeled image dataset. The input is the image URL, and the output is the filtering result.

[0471] Step 6:

[0472] The server analyzes the extracted text content using text analysis tools. Specifically, it uses the NLTK library to tokenize the text and detect offensive keywords and phrases. The input is the extracted text content, and the output is the text filtering decision.

[0473] Step 7:

[0474] If the server determines that a web page contains objectionable content, it either removes the web page from the search results or adds a warning label. Specifically, the server either removes the web page from the list or adds a warning message based on the result of the determination. The input is the filtering result, and the output is the final filtered search result list.

[0475] Step 8:

[0476] After filtering is complete, the search results are sent from the server to the terminal. The terminal displays the filtered results on the user's screen. Specifically, the server sends the filtered search results as data packets to the terminal, and the terminal parses the received data appropriately and displays it in a GUI. For search results with warning labels, a message such as "This page contains images of insects" is displayed. The input is the final filtered search result list, and the output is the search results displayed on the user's screen.

[0477] (Application example 1)

[0478] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0479] Conventional search systems often lack sufficient filtering capabilities to avoid offensive content. In particular, it has been difficult for video streaming services to proactively filter out content that users find offensive. This has led to the risk of users accidentally encountering unpleasant video content, making it difficult for them to enjoy content safely. Furthermore, existing filtering systems often lack the precision of image and text analysis, resulting in inaccurate filtering.

[0480] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0481] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from information sources, analysis means for analyzing digital information in the search results and extracting image addresses and text information, filtering means for comparing the extracted image and text information with the filtering conditions and determining pages that match the conditions, display means for transmitting the filtered search results to a user interface and displaying them, and video analysis means for analyzing video thumbnail images and descriptive text and excluding videos that match the user's filtering conditions. This allows users to use content distribution services with peace of mind without viewing offensive content.

[0482] "Filtering conditions" are criteria that a user sets to avoid objectionable content.

[0483] The "search processing means" is a function that receives a user's search request and retrieves relevant search results from information sources.

[0484] The "analysis means" is a function that analyzes the digital information contained in the obtained search results and extracts image addresses and text information.

[0485] The "filtering means" is a function that checks extracted image and text information against the filtering conditions set by the user and determines which pages match.

[0486] The "display means" is a function that transmits the filtered search results to the user interface and displays them.

[0487] The "video analysis means" is a function that analyzes the thumbnail images and description text of videos and eliminates videos that match the user's filtering conditions.

[0488] The system embodying the present invention is a search system that eliminates objectionable content based on filtering conditions set by a user. A specific embodiment of this system will be described below.

[0489] System Overview

[0490] The system includes a search processing unit, an analysis unit, a filtering unit, a display unit, and a video analysis unit, and can prevent users from viewing objectionable content, particularly in video distribution services.

[0491] Hardware and Software

[0492] The following hardware and software are used to implement this system:

[0493] Hardware: Smartphone, server, camera (for image analysis)

[0494] Software: OpenCV (image analysis), TextBlob (text analysis)

[0495] Process Overview

[0496] The server receives the user's filtering criteria, analyzes the search results based on them, and filters out or warns of offensive content, as detailed below.

[0497] Search processing means

[0498] When a user enters a search request on a terminal, the request is sent to the server, which retrieves relevant search results from the information source.

[0499] Analysis means

[0500] Analyze and extract the digital information (image addresses and text information) from the search results. Specifically, analyze the HTML content to extract the necessary information.

[0501] Filtering Methods

[0502] The extracted images and text information are compared with the filtering criteria set by the user to determine which pages or videos match. If there is a match, the page is either excluded or marked with a warning label.

[0503] Display means

[0504] The filtered search results are sent from the server to the terminal and displayed on the user interface.

[0505] Video analysis methods

[0506] Analyzes video thumbnail images and description text, and filters out content that matches the user's filtering criteria. Image analysis is performed using OpenCV, and text analysis is performed using TextBlob.

[0507] Specific examples

[0508] For example, consider a situation where a user has set a preference to "not display horror movies." When the user opens a video streaming app and searches for a specific keyword, the server receives the request and retrieves relevant videos from the source. The server then analyzes the video's thumbnail image and description text to determine whether it matches the user's filtering criteria of "horror movies." If it does, the video is removed from the viewing list or a warning label is added.

[0509] Prompt Sentence Examples

[0510] If a user searches for "horror movies" in a video streaming app, the following prompt will be generated:

[0511] text

[0512] The filter condition "Horror Movies" is set. Based on this requirement, perform image and text analysis to filter out horror movies.

[0513] In this way, the system of the present invention can provide users with a comfortable and safe video viewing experience.

[0514] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0515] Step 1:

[0516] A user inputs a search request from a device. For example, a user sets a filtering condition such as "do not display horror movies" and operates a video streaming app to search for "latest movies." In this case, the specific action is to enter "latest movies" into the search field on the device and press the search button.

[0517] Step 2:

[0518] The terminal sends a search request (input: user's search keywords and filtering conditions) to the server. The data processing performed here is to generate request data including the search keywords and filtering conditions and send it to the server via the network. The output is the request data sent to the server.

[0519] Step 3:

[0520] The server processes the received search request and retrieves search results from the information source (e.g., calling an external search engine API). The server retrieves a list of related videos on the Internet based on the user's search keywords. At this time, an appropriate API call is made as data calculation, and the video list as search results is obtained as text data. The output is the retrieved video list.

[0521] Step 4:

[0522] The server analyzes the search results and extracts the addresses of the video thumbnail images and description text. The specific operation performed here is to parse the HTML content of each video and extract the necessary information (thumbnail URL and description text). The input is the list of videos in the search results, and the output is a list of extracted thumbnail URLs and description text.

[0523] Step 5:

[0524] The server compares the extracted thumbnail images and description text with the user's filtering criteria and filters them. For example, to check whether a movie is a horror movie, the server analyzes the thumbnail images with OpenCV and the description text with TextBlob. The input is the extracted thumbnail URL and description text, and the data calculation is the image and text analysis process. The output is a filtered list of movies.

[0525] Step 6:

[0526] Based on the filtered video list, the server removes videos determined to contain objectionable content from the list or assigns warning labels to them. Specifically, the server updates the video list according to the analysis results. The input is the filtered video list, and the output is the final display list (including videos with warning labels).

[0527] Step 7:

[0528] The server sends the final display list to the terminal. The server then transfers the updated video list to the terminal via the network. At this time, the server converts the list into the required format as data processing before sending it. The input is the final display list, and the output is the display list sent to the terminal.

[0529] Step 8:

[0530] The terminal displays the received final display list on the user interface. Specifically, the terminal updates the user interface to show the safe video list to the user. The input is the display list sent from the server, and the output is a screen display that the user can visually confirm.

[0531] By following the above steps, users can watch a filtered list of safe videos with peace of mind.

[0532] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0533] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0534] overview

[0535] In addition to search processing means, analysis means, filtering means, and display means, this system is equipped with an emotion engine that recognizes user emotions in real time and dynamically updates filtering conditions, allowing users to receive appropriate search results in response to changes in their emotions, providing a comfortable and secure search experience.

[0536] User operations

[0537] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition is set to "Do not display images of insects."

[0538] Processing search requests (server)

[0539] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0540] Analysis method (server)

[0541] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0542] Filtering method (server)

[0543] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0544] Emotion engine function (server)

[0545] In parallel with the search process, the server analyzes emotions in real time based on the user's search behavior and feedback. The emotion engine monitors the user's facial expressions and click behavior while searching, and dynamically updates the filtering conditions if unpleasant emotions are recognized.

[0546] Warn or Exclude (Server)

[0547] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0548] Displaying the results (terminal)

[0549] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0550] Specific examples

[0551] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images or text of insects. If it does contain any images of insects, the page is removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated accordingly. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0552] In this way, the system of the present invention can provide users with a comfortable and secure search experience. By combining it with an emotion engine, appropriate filtering according to the user's emotions becomes possible, further improving user satisfaction.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] The user enters keywords into the search field and presses the search button. The user's device receives this input and creates a search request.

[0556] Step 2:

[0557] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0558] Step 3:

[0559] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0560] Step 4:

[0561] The server calls external search engine APIs based on the search keywords to retrieve search results, which include the titles, URLs, and snippets of relevant web pages.

[0562] Step 5:

[0563] The server analyzes each web page in the search results and extracts image URLs and text content, using scraping technology to analyze the HTML source code.

[0564] Step 6:

[0565] The server analyzes the extracted image URLs using image analysis techniques, such as using an image analysis library, to determine if the image contains insects or other objectionable content.

[0566] Step 7:

[0567] The server then uses text analysis tools to analyze the extracted text content using natural language processing libraries to check whether it contains certain offensive keywords or phrases.

[0568] Step 8:

[0569] Based on the analysis results, the server determines whether the page contains objectionable content and, if it meets the filtering criteria, removes the page from the search results list or adds a warning label.

[0570] Step 9:

[0571] The server runs an emotion engine based on the user's search behavior and feedback. The emotion engine uses facial recognition technology to detect emotions from the user's facial expressions in real time and analyzes their reactions to search results.

[0572] Step 10:

[0573] The server automatically and dynamically updates the filtering conditions when the user indicates unpleasant emotions, and applies the new filtering conditions to re-filter the search results.

[0574] Step 11:

[0575] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0576] Step 12:

[0577] The terminal analyzes the filtered search results received from the server and displays them on the user's screen. For search results with warning labels, the terminal displays an appropriate warning message to the user.

[0578] Through these processing steps, the CleanSearch system provides users with search results that do not contain offensive content, and the emotion engine also enables dynamic filtering based on user emotions, allowing users to enjoy a safe and enjoyable search experience.

[0579] Example 2

[0580] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] In conventional search systems, users often experience stress when checking search results due to the risk of encountering unpleasant content. Furthermore, they lack dynamic filtering that matches the user's emotions and preferences, making it difficult to provide optimal search results for each individual user. For this reason, there was a demand for a search system that could recognize user emotions in real time and dynamically update filtering conditions.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0583] In this invention, the server includes means for filtering out offensive content based on filtering conditions set by the user, search processing means for receiving search requests and retrieving search results from a global network, analysis means for analyzing web pages in the search results and extracting image data and text data, filtering means for comparing the extracted image data and text data with the filtering conditions and determining pages that meet the conditions, emotion analysis means for recognizing the user's emotions in real time and dynamically updating the filtering conditions, and display means for transmitting the filtered search results to the user terminal and displaying them. This allows users to enjoy a comfortable search experience tailored to their emotions and preferences without seeing offensive content during searches.

[0584] "User" refers to an individual who utilizes a search system to enter keywords to retrieve information and review search results.

[0585] A "terminal" is a device used by a user to access the search system and display search results, and includes a personal computer, smartphone, etc.

[0586] "Server" refers to the back-end computer system that receives search requests, retrieves search results from the Internet, and analyzes and filters the data.

[0587] "Filtering conditions" refer to criteria set by a user to filter out objectionable content, and may include specific keywords or image characteristics.

[0588] The term "search processing means" refers to a function that searches for related web pages using a global network based on a search request received from a user.

[0589] "Analysis means" refers to the function of analyzing the content of web pages included in search results and extracting image data and text data.

[0590] "Filtering means" refers to the function of comparing extracted image data and text data with filtering conditions and identifying pages that meet the criteria.

[0591] "Emotion analysis means" refers to the function of analyzing users' search behavior and facial expression data in real time and dynamically updating filtering conditions.

[0592] "Display means" refers to the function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0593] "Image analysis means" refers to a function that analyzes extracted image data and determines whether the content contains objectionable content.

[0594] "Text analysis means" refers to a function that analyzes extracted text data and determines whether the content contains offensive keywords or phrases.

[0595] "Warning label" refers to a message displayed to users to inform them that their search results contain objectionable content.

[0596] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0597] First, the user enters a keyword into the search field on the device and presses the search button. For example, they enter "insect control."

[0598] The device then sends the user's input search request to the server, which receives the request and uses an external search engine API (e.g., Google Custom Search API) to retrieve a list of related web pages.

[0599] The server analyzes the HTML content of the search results and extracts image and text data using Beautiful Soup or a similar library. The extracted image data is analyzed using image analysis software such as OpenCV, and the text data is analyzed using a natural language processing library such as NLTK.

[0600] The server then compares the extracted data with the filtering criteria set by the user. For example, an image analysis unit may determine whether the data contains images of insects, and if so, reject the objectionable content according to the filtering criteria. Similarly, a text analysis unit may analyze the text data to determine whether it contains objectionable keywords or phrases.

[0601] In parallel, the server analyzes users' search behavior and feedback in real time using an emotion engine, which uses machine learning models such as TensorFlow to monitor users' facial expression data and click behavior, dynamically updating filtering criteria if unpleasant emotions are recognized.

[0602] For example, if a user expresses displeasure when viewing a search result page, the emotion engine analyzes that data and reconfigures its filtering criteria to ensure the user does not encounter similar displeasure again.

[0603] Finally, the server sends the filtered search results to the device, which displays them on the user's screen and adds warning labels if necessary. For example, a page containing images of insects will display a warning message saying, "This page contains images of insects."

[0604] As a concrete example, suppose a user enters "insect control" as a search keyword and presses the search button. The server uses this keyword to call the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images of insects. If it does, the page is either removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated appropriately. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0605] An example of a prompt might be:

[0606] "When you enter a search keyword and press a button, the search is performed using an external search engine API, and objectionable content is filtered out based on the filtering conditions set by the user in advance. In addition, an emotion engine analyzes the user's emotions and dynamically updates the filtering conditions. A warning may also be displayed in the search results."

[0607] The system allows users to avoid objectionable content while searching, providing a comfortable and safe search experience with dynamic filtering that takes sentiment into account in real time.

[0608] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0609] Step 1:

[0610] The user enters a keyword into the search field on the device and presses the search button. Specifically, the keyword "insect control" is entered. This input generates a search request. The output is this search request.

[0611] Step 2:

[0612] The terminal sends the generated search request to the server. Specifically, it generates an HTTP POST request and sends it to the server in a format that includes the search keywords. The input is the keyword entered by the user, and the output is the search request sent to the server.

[0613] Step 3:

[0614] The server parses the received search request and retrieves a list of relevant web pages using an external search engine API, specifically by calling the Google Custom Search API to retrieve the search results. The input is the received search request and the output is the list of retrieved search results.

[0615] Step 4:

[0616] The server analyzes the HTML content of the search results and extracts image data and text data. Specifically, it uses Beautiful Soup to extract image URLs and text from the HTML of each web page. The input is the HTML content of the search results, and the output is the extracted image data and text data.

[0617] Step 5:

[0618] The server compares the extracted image data and text data with the filtering conditions set by the user. Specifically, it performs image analysis using OpenCV and text analysis using NLTK. The input is the extracted image data or text data and the filtering conditions, and the output is a judgment result on whether the filtering conditions are met.

[0619] Step 6:

[0620] If the server determines that the extracted data contains offensive content, it will either exclude the page from the search results or add a warning label. For example, if the page contains an image of an insect, it will either exclude the page or add a warning message. The input is the result of the determination, and the output is an updated list of search results.

[0621] Step 7:

[0622] The server's emotion engine monitors users' search behavior and feedback and analyzes their emotions in real time. Specifically, it captures the user's facial expression data and analyzes it using TensorFlow. The input is the user's facial expression data, and the output is the analyzed emotion data.

[0623] Step 8:

[0624] The server dynamically updates the filtering conditions based on the emotion data. For example, if the user shows an unpleasant facial expression, it strengthens the related filtering conditions. The input is the emotion analysis result, and the output is the updated filtering conditions.

[0625] Step 9:

[0626] Finally, the server sends the filtered search results to the terminal. Specifically, it generates an HTTP response and sends it to the terminal including the search results. The input is the processed search result list, and the output is the final search results displayed on the user's terminal.

[0627] Step 10:

[0628] The terminal displays the filtered search results on the user's screen, for example displaying a warning message saying "This page contains images of insects." The input is the search results sent by the server, and the output is the search results visually presented to the user.

[0629] (Application example 2)

[0630] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0631] When searching the Internet, users may encounter unpleasant content, which can impair the search experience. Especially on online shopping sites, users may feel uneasy about making purchases if product information or images containing unpleasant content are displayed. Furthermore, there is a lack of a mechanism to dynamically change filtering conditions according to user emotions, which makes it difficult to respond flexibly.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0633] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from the Internet, analysis means for analyzing web pages in the search results and extracting image URLs and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that match the conditions, emotion recognition means for analyzing the user's search behavior and facial expressions in real time and recognizing emotions, means for dynamically updating the filtering conditions based on the user's emotions recognized by the emotion recognition means, and display means for transmitting the filtered search results to a user terminal and displaying them. This enables users to avoid offensive content and perform flexible filtering according to emotions.

[0634] "User-defined filtering conditions" refers to criteria for filtering out objectionable content by a user setting specific conditions.

[0635] The "search processing means" is a means having the function of receiving a search request from a user and retrieving related search results from the Internet.

[0636] "Analysis means" refers to a means that has the function of analyzing web pages in search results and extracting image URLs and text content.

[0637] The "filtering means" is a means having the function of checking extracted images and text content against the filtering conditions set by the user and determining which pages match those conditions.

[0638] The "emotion recognition means" is a means having a function of analyzing the user's search behavior and facial expressions in real time and recognizing the user's emotions.

[0639] The "dynamic update means" is a means having a function of changing or adjusting the filtering conditions in real time based on the user's emotion recognized by the emotion recognition means.

[0640] The "display means" is a means having a function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0641] MODE FOR CARRYING OUT THE INVENTION

[0642] The system that realizes this application example is a search system that eliminates unpleasant content from search results based on filtering conditions set by the user, and also performs dynamic filtering according to the user's emotions using emotion recognition means. This system is composed of both a server and a user terminal, and requires specific hardware and software to realize each function.

[0643] System Configuration

[0644] Hardware

[0645] Server: A computer system for performing search processing, analysis, filtering, and emotion recognition.

[0646] User device: A device used to input search keywords and display search results. This includes smartphones, tablets, and PCs.

[0647] Webcam: Hardware for capturing a user's facial expressions.

[0648] Microphone: Hardware used to capture the user's voice.

[0649] software

[0650] Search engine API: Software that uses external search engine services to obtain information on the Internet.

[0651] Image analysis module: Software for analyzing the acquired image content (e.g. OpenCV).

[0652] Text analysis module: Software for analyzing the captured text content (e.g., NLTK).

[0653] Emotion recognition model: Software for recognizing emotions from a user's facial expressions and voice in real time (e.g., Facial Expression Recognition model).

[0654] Filtering module: Software that matches the filtering criteria set by the user and filters out objectionable content.

[0655] Processing flow

[0656] 1. Submit a search request

[0657] The user enters keywords into the terminal and presses the search button.

[0658] The terminal sends a search request to the server.

[0659] 2. Obtaining search results

[0660] The server uses a search engine API to retrieve search results based on the specified keywords from the Internet.

[0661] 3. Content Analysis

[0662] Using the analysis means, the server analyzes the web pages of the retrieved search results and extracts image URLs and text content.

[0663] An image analysis module analyzes the extracted image content to determine if it contains objectionable material.

[0664] The text analysis module analyzes the extracted text content to determine whether it contains offensive keywords or phrases.

[0665] 4. Emotional Recognition

[0666] The server monitors the user's search behavior and facial expressions in real time via a webcam and microphone, and analyzes the user's emotions using an emotion recognition model.

[0667] 5. Filtering

[0668] The filtering module matches the extracted content with filtering criteria set by the user and dynamically updates the criteria based on the user's emotional state according to an emotion recognition model.

[0669] Exclude pages or add warning labels if they contain objectionable content.

[0670] 6. Displaying the results

[0671] The filtered search results are sent from the server to the user terminal and displayed.

[0672] Specific examples

[0673] For example, if a user searches for "stuffed toys," the server uses a search engine API to obtain a list of related web pages. Then, it uses analytics to analyze the content of each web page and detects offensive content from images and text. If it determines that the user dislikes spiders, spider images and related text are filtered out. Furthermore, the system analyzes the user's facial expressions and voice in real time, and if any unpleasant emotions are recognized, the filtering criteria are dynamically updated. Finally, the filtered search results are displayed on the device, allowing the user to choose their purchase with confidence.

[0674] Prompt Sentence Examples

[0675] Sentiment Analysis Prompt: "Analyze the user's emotions based on their facial expressions and voice to determine what content they find offensive."

[0676] Content Analysis prompt: "Identify content in your search results that users may find offensive and explain why."

[0677] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0678] Step 1:

[0679] User enters keyword

[0680] Users input search keywords using devices such as smartphones or PCs. This generates a search request. The input data is the keywords, and the output data is the search request.

[0681] Step 2:

[0682] Submitting a search request

[0683] The terminal sends the search request entered by the user to the server. The input data is the search request, and the output data is a request packet sent to the server. Specifically, the request is sent to the server using the HTTP protocol.

[0684] Step 3:

[0685] Getting search results

[0686] When the server receives a search request, it uses an external search engine API to retrieve relevant search results from the Internet. The input data is the search request, and the output data is a list of the retrieved search results. The data is processed by passing the search keywords to the search engine API and executing the search.

[0687] Step 4:

[0688] Content Analysis

[0689] The server analyzes the web pages of the search results it retrieves and extracts image URLs and text content. The input data is a list of search results, and the output data is the extracted image URLs and text content. Specifically, it performs HTML parsing to extract image URLs and text content.

[0690] Step 5:

[0691] User Emotion Recognition

[0692] The server captures the user's facial expressions and voice through a webcam and microphone. It then analyzes the user's emotions using an emotion recognition model. The input data are the captured facial expression images and voice data, and the output data is the analyzed emotional state. Image recognition algorithms and voice analysis algorithms are used for data processing.

[0693] Step 6:

[0694] Dynamic filtering condition updates

[0695] The server dynamically updates the filtering conditions based on the recognized user emotion. The input data is the analyzed emotional state, and the output data is the updated filtering conditions. Specific operations include executing logic to change the filtering criteria accordingly.

[0696] Step 7:

[0697] Content Filtering

[0698] The server uses analytical tools to match the extracted content with filtering criteria and exclude or label pages containing objectionable content. The input data are the extracted image URLs and text content and the filtering criteria, and the output data are the filtered search results. Specifically, the server evaluates the content using a criteria matching algorithm.

[0699] Step 8:

[0700] Submitting filtered search results

[0701] The server sends the filtered search results to the user terminal. The input data is the filtered search results, and the output data is a data packet sent to the user terminal. Specifically, the server sends back the results using the HTTP protocol.

[0702] Step 9:

[0703] Displaying search results

[0704] The user terminal receives the filtered search results and displays them on the user's screen. The input data are the search results sent from the server, and the output data are the search results displayed on the user's screen. Specifically, the received data is rendered on the screen in an appropriate format.

[0705] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0706] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0707] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0708] [Third embodiment]

[0709] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0710] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0711] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0712] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0713] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0714] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0715] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0716] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0717] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0718] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0719] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0720] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0721] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0722] overview

[0723] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. Its main components include a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0724] User operations

[0725] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0726] Processing search requests (server)

[0727] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0728] Analysis method (server)

[0729] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0730] Filtering method (server)

[0731] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0732] Warn or Exclude (Server)

[0733] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0734] Displaying the results (terminal)

[0735] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0736] Specific examples

[0737] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the server analyzes the content of each web page to check whether it contains any images or text of insects. If it does, the page is removed from the list or a warning label is attached. Finally, the filtered search results are displayed to the user, allowing them to browse the search results with peace of mind without seeing any unpleasant insect images.

[0738] In this way, the system of the present invention can provide a comfortable and secure search experience for the user.

[0739] The processing flow will be explained below.

[0740] Step 1:

[0741] The user inputs search keywords and presses the search button. The user's device receives this input and creates a search request.

[0742] Step 2:

[0743] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0744] Step 3:

[0745] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0746] Step 4:

[0747] The server calls an external search engine API based on the search keywords and retrieves search results.

[0748] Search results include the title, URL, and snippet of the relevant web page.

[0749] Step 5:

[0750] The server analyzes each web page in the search results and extracts image URLs and text content.

[0751] Scraping technology is used to analyze HTML source code.

[0752] Step 6:

[0753] The server analyzes the URL of the extracted image using an image analysis means, which uses an image analysis library.

[0754] For example, determining if an image contains insects and checking for objectionable content.

[0755] Step 7:

[0756] The server uses text analysis means to analyze the extracted text content with a natural language processing library.

[0757] Check for the presence of certain offensive keywords or phrases.

[0758] Step 8:

[0759] Based on the analysis results, the server determines which pages contain objectionable content.

[0760] If the filtering conditions are met, the page will be excluded from the search results list or marked with a warning label.

[0761] Step 9:

[0762] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0763] Step 10:

[0764] The terminal analyzes the filtered search results received from the server and displays them on the user's screen.

[0765] For search results with warning labels, an appropriate warning message will be displayed to the user.

[0766] Through the above processing steps, the CleanSearch system provides users with search results that do not contain offensive content, ensuring a safe browsing environment.

[0767] Example 1

[0768] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0769] When searching the Internet, users may encounter objectionable content. For this reason, it is necessary to provide an environment where users can safely view search results. In particular, if the content of images or text contains objectionable content, it is necessary to improve the user experience by filtering or warning users in advance.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0771] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from a network, analysis means for analyzing web pages in the search results and extracting image paths and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that meet the conditions, and display means for transmitting the filtered search results to a user terminal and displaying them, thereby enabling users to view search results while avoiding offensive content.

[0772] "Filtering conditions" are specific criteria or rules that a user sets to avoid objectionable content.

[0773] A "search processing means" is a mechanism for receiving a search request and retrieving related information over a network.

[0774] The "analysis means" is a function for analyzing the acquired search results and extracting image paths and text content.

[0775] The "filtering means" is a function that checks the extracted content against the filtering conditions set by the user to determine whether or not it contains offensive content.

[0776] The "display means" is a mechanism for transmitting the filtered search results to the user terminal and presenting them to the user.

[0777] The "image analysis means" is a function for analyzing extracted image content and determining whether it contains offensive content.

[0778] The "text analysis means" is a mechanism for analyzing the extracted text content and identifying offensive keywords and phrases.

[0779] A "warning label" is a warning message or mark that is added to search results that contain offensive content.

[0780] "Network" refers to an information and communication network such as the Internet, which is the infrastructure for sending and receiving data.

[0781] A "user terminal" is a device such as a computer, smartphone, or tablet that is operated by an individual.

[0782] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[0783] overview

[0784] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. The system includes a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[0785] User operations

[0786] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[0787] Processing a search request

[0788] The terminal sends a search request to the server. The server receives this request and performs a search on the network using the specified keywords. In this process, it uses an external search engine API to obtain a list of related web pages. Specifically, a search engine API is used as an example of an external search engine API.

[0789] Analysis means

[0790] The server begins parsing the search results. The parser analyzes the HTML content of each web page to extract image paths and text content. An HTML parsing library, such as BeautifulSoup, is used for the analysis.

[0791] Filtering Methods

[0792] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains offensive material. Image analysis is performed using an image processing library, such as OpenCV. Text analysis is performed using a text processing library, such as NLTK.

[0793] Warnings or Exclusions

[0794] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0795] Displaying the results

[0796] After filtering, the search results are sent from the server to the device. The device displays the filtered results on the user's screen. For search results with warning labels, an appropriate warning message is displayed to the user. For example, a warning such as "This page contains images of insects" is displayed.

[0797] Specific examples

[0798] For example, when a user enters the search keyword "insect control" and presses the search button, the server uses the keywords to retrieve a list of related web pages from an external search engine API. Next, it uses BeautifulSoup to analyze the content of each web page and checks whether it contains insect images or text. OpenCV is used to detect whether the page contains insect images, and NLTK is used to check the text for offensive content. If it contains insect images, the page is either excluded from the list or a warning label is added. Finally, the filtered search results are displayed to the user, allowing them to safely browse the search results while avoiding any offensive insect images.

[0799] Usage example (example of prompt sentence for generative AI model)

[0800] An example prompt might look like this:

[0801] A user searches for "insect prevention" and sets the filtering criteria to "Do not display images of insects." The server retrieves related web pages using an external search engine API, analyzes them with BeautifulSoup, and extracts image paths and text. OpenCV performs image analysis, and NLTK analyzes the text. Any objectionable content is removed from the results, and the final filtered search results are displayed to the user.

[0802] In this way, the system of the present invention provides a comfortable and secure search experience for the user.

[0803] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] The user enters a keyword in the search field and presses the search button. For example, the user enters "insect control" and sets the filtering condition to "do not display images of insects." The input in this case is the keyword and the filtering condition. The output is a search request, which is generated by the terminal.

[0806] Step 2:

[0807] The terminal sends the search request entered by the user to the server. Specifically, the terminal sends the generated search request, i.e., a data packet containing keywords and filtering conditions, to the server via the network. The input is the search request, and the output is the transmission of the data packet to the server.

[0808] Step 3:

[0809] Based on the received search request, the server performs a network search using the specified keywords. At this time, it uses an external search engine API to obtain a list of related web pages. Specifically, the server sends an HTTP request to the API and receives an HTTP response containing the search results. The input is the search request, and the output is the list of retrieved web pages.

[0810] Step 4:

[0811] The server analyzes the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image paths and text content. Specifically, it uses an HTML analysis library called BeautifulSoup to analyze the HTML and extract image URLs and text. The input is a list of retrieved web pages, and the output is the extracted image URLs and text content.

[0812] Step 5:

[0813] The server compares the extracted images and text content with the filtering criteria set by the user. This comparison is performed using image analysis tools and involves necessary image processing. Specifically, it analyzes images using OpenCV to determine whether they contain offensive content. For example, it uses computer vision techniques based on a specific labeled image dataset. The input is the image URL, and the output is the filtering result.

[0814] Step 6:

[0815] The server analyzes the extracted text content using text analysis tools. Specifically, it uses the NLTK library to tokenize the text and detect offensive keywords and phrases. The input is the extracted text content, and the output is the text filtering decision.

[0816] Step 7:

[0817] If the server determines that a web page contains objectionable content, it either removes the web page from the search results or adds a warning label. Specifically, the server either removes the web page from the list or adds a warning message based on the result of the determination. The input is the filtering result, and the output is the final filtered search result list.

[0818] Step 8:

[0819] After filtering is complete, the search results are sent from the server to the terminal. The terminal displays the filtered results on the user's screen. Specifically, the server sends the filtered search results as data packets to the terminal, and the terminal parses the received data appropriately and displays it in a GUI. For search results with warning labels, a message such as "This page contains images of insects" is displayed. The input is the final filtered search result list, and the output is the search results displayed on the user's screen.

[0820] (Application example 1)

[0821] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0822] Conventional search systems often lack sufficient filtering capabilities to avoid offensive content. In particular, it has been difficult for video streaming services to proactively filter out content that users find offensive. This has led to the risk of users accidentally encountering unpleasant video content, making it difficult for them to enjoy content safely. Furthermore, existing filtering systems often lack the precision of image and text analysis, resulting in inaccurate filtering.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0824] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from information sources, analysis means for analyzing digital information in the search results and extracting image addresses and text information, filtering means for comparing the extracted image and text information with the filtering conditions and determining pages that match the conditions, display means for transmitting the filtered search results to a user interface and displaying them, and video analysis means for analyzing video thumbnail images and descriptive text and excluding videos that match the user's filtering conditions. This allows users to use content distribution services with peace of mind without viewing offensive content.

[0825] "Filtering conditions" are criteria that a user sets to avoid objectionable content.

[0826] The "search processing means" is a function that receives a user's search request and retrieves relevant search results from information sources.

[0827] The "analysis means" is a function that analyzes the digital information contained in the obtained search results and extracts image addresses and text information.

[0828] The "filtering means" is a function that checks extracted image and text information against the filtering conditions set by the user and determines which pages match.

[0829] The "display means" is a function that transmits the filtered search results to the user interface and displays them.

[0830] The "video analysis means" is a function that analyzes the thumbnail images and description text of videos and eliminates videos that match the user's filtering conditions.

[0831] The system embodying the present invention is a search system that eliminates objectionable content based on filtering conditions set by a user. A specific embodiment of this system will be described below.

[0832] System Overview

[0833] The system includes a search processing unit, an analysis unit, a filtering unit, a display unit, and a video analysis unit, and can prevent users from viewing objectionable content, particularly in video distribution services.

[0834] Hardware and Software

[0835] The following hardware and software are used to implement this system:

[0836] Hardware: Smartphone, server, camera (for image analysis)

[0837] Software: OpenCV (image analysis), TextBlob (text analysis)

[0838] Process Overview

[0839] The server receives the user's filtering criteria, analyzes the search results based on them, and filters out or warns of offensive content, as detailed below.

[0840] Search processing means

[0841] When a user enters a search request on a terminal, the request is sent to the server, which retrieves relevant search results from the information source.

[0842] Analysis means

[0843] Analyze and extract the digital information (image addresses and text information) from the search results. Specifically, analyze the HTML content to extract the necessary information.

[0844] Filtering Methods

[0845] The extracted images and text information are compared with the filtering criteria set by the user to determine which pages or videos match. If there is a match, the page is either excluded or marked with a warning label.

[0846] Display means

[0847] The filtered search results are sent from the server to the terminal and displayed on the user interface.

[0848] Video analysis methods

[0849] Analyzes video thumbnail images and description text, and filters out content that matches the user's filtering criteria. Image analysis is performed using OpenCV, and text analysis is performed using TextBlob.

[0850] Specific examples

[0851] For example, consider a situation where a user has set a preference to "not display horror movies." When the user opens a video streaming app and searches for a specific keyword, the server receives the request and retrieves relevant videos from the source. The server then analyzes the video's thumbnail image and description text to determine whether it matches the user's filtering criteria of "horror movies." If it does, the video is removed from the viewing list or a warning label is added.

[0852] Prompt Sentence Examples

[0853] If a user searches for "horror movies" in a video streaming app, the following prompt will be generated:

[0854] text

[0855] The filter condition "Horror Movies" is set. Based on this requirement, perform image and text analysis to filter out horror movies.

[0856] In this way, the system of the present invention can provide users with a comfortable and safe video viewing experience.

[0857] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0858] Step 1:

[0859] A user inputs a search request from a device. For example, a user sets a filtering condition such as "do not display horror movies" and operates a video streaming app to search for "latest movies." In this case, the specific action is to enter "latest movies" into the search field on the device and press the search button.

[0860] Step 2:

[0861] The terminal sends a search request (input: user's search keywords and filtering conditions) to the server. The data processing performed here is to generate request data including the search keywords and filtering conditions and send it to the server via the network. The output is the request data sent to the server.

[0862] Step 3:

[0863] The server processes the received search request and retrieves search results from the information source (e.g., calling an external search engine API). The server retrieves a list of related videos on the Internet based on the user's search keywords. At this time, an appropriate API call is made as data calculation, and the video list as search results is obtained as text data. The output is the retrieved video list.

[0864] Step 4:

[0865] The server analyzes the search results and extracts the addresses of the video thumbnail images and description text. The specific operation performed here is to parse the HTML content of each video and extract the necessary information (thumbnail URL and description text). The input is the list of videos in the search results, and the output is a list of extracted thumbnail URLs and description text.

[0866] Step 5:

[0867] The server compares the extracted thumbnail images and description text with the user's filtering criteria and filters them. For example, to check whether a movie is a horror movie, the server analyzes the thumbnail images with OpenCV and the description text with TextBlob. The input is the extracted thumbnail URL and description text, and the data calculation is the image and text analysis process. The output is a filtered list of movies.

[0868] Step 6:

[0869] Based on the filtered video list, the server removes videos determined to contain objectionable content from the list or assigns warning labels to them. Specifically, the server updates the video list according to the analysis results. The input is the filtered video list, and the output is the final display list (including videos with warning labels).

[0870] Step 7:

[0871] The server sends the final display list to the terminal. The server then transfers the updated video list to the terminal via the network. At this time, the server converts the list into the required format as data processing before sending it. The input is the final display list, and the output is the display list sent to the terminal.

[0872] Step 8:

[0873] The terminal displays the received final display list on the user interface. Specifically, the terminal updates the user interface to show the safe video list to the user. The input is the display list sent from the server, and the output is a screen display that the user can visually confirm.

[0874] By following the above steps, users can watch a filtered list of safe videos with peace of mind.

[0875] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0876] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0877] overview

[0878] In addition to search processing means, analysis means, filtering means, and display means, this system is equipped with an emotion engine that recognizes user emotions in real time and dynamically updates filtering conditions, allowing users to receive appropriate search results in response to changes in their emotions, providing a comfortable and secure search experience.

[0879] User operations

[0880] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition is set to "Do not display images of insects."

[0881] Processing search requests (server)

[0882] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[0883] Analysis method (server)

[0884] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[0885] Filtering method (server)

[0886] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[0887] Emotion engine function (server)

[0888] In parallel with the search process, the server analyzes emotions in real time based on the user's search behavior and feedback. The emotion engine monitors the user's facial expressions and click behavior while searching, and dynamically updates the filtering conditions if unpleasant emotions are recognized.

[0889] Warn or Exclude (Server)

[0890] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[0891] Displaying the results (terminal)

[0892] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[0893] Specific examples

[0894] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images or text of insects. If it does contain any images of insects, the page is removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated accordingly. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0895] In this way, the system of the present invention can provide users with a comfortable and secure search experience. By combining it with an emotion engine, appropriate filtering according to the user's emotions becomes possible, further improving user satisfaction.

[0896] The processing flow will be explained below.

[0897] Step 1:

[0898] The user enters keywords into the search field and presses the search button. The user's device receives this input and creates a search request.

[0899] Step 2:

[0900] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[0901] Step 3:

[0902] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[0903] Step 4:

[0904] The server calls external search engine APIs based on the search keywords to retrieve search results, which include the titles, URLs, and snippets of relevant web pages.

[0905] Step 5:

[0906] The server analyzes each web page in the search results and extracts image URLs and text content, using scraping technology to analyze the HTML source code.

[0907] Step 6:

[0908] The server analyzes the extracted image URLs using image analysis techniques, such as using an image analysis library, to determine if the image contains insects or other objectionable content.

[0909] Step 7:

[0910] The server then uses text analysis tools to analyze the extracted text content using natural language processing libraries to check whether it contains certain offensive keywords or phrases.

[0911] Step 8:

[0912] Based on the analysis results, the server determines whether the page contains objectionable content and, if it meets the filtering criteria, removes the page from the search results list or adds a warning label.

[0913] Step 9:

[0914] The server runs an emotion engine based on the user's search behavior and feedback. The emotion engine uses facial recognition technology to detect emotions from the user's facial expressions in real time and analyzes their reactions to search results.

[0915] Step 10:

[0916] The server automatically and dynamically updates the filtering conditions when the user indicates unpleasant emotions, and applies the new filtering conditions to re-filter the search results.

[0917] Step 11:

[0918] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[0919] Step 12:

[0920] The terminal analyzes the filtered search results received from the server and displays them on the user's screen. For search results with warning labels, the terminal displays an appropriate warning message to the user.

[0921] Through these processing steps, the CleanSearch system provides users with search results that do not contain offensive content, and the emotion engine also enables dynamic filtering based on user emotions, allowing users to enjoy a safe and enjoyable search experience.

[0922] Example 2

[0923] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] In conventional search systems, users often experience stress when checking search results due to the risk of encountering unpleasant content. Furthermore, they lack dynamic filtering that matches the user's emotions and preferences, making it difficult to provide optimal search results for each individual user. For this reason, there was a demand for a search system that could recognize user emotions in real time and dynamically update filtering conditions.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0926] In this invention, the server includes means for filtering out offensive content based on filtering conditions set by the user, search processing means for receiving search requests and retrieving search results from a global network, analysis means for analyzing web pages in the search results and extracting image data and text data, filtering means for comparing the extracted image data and text data with the filtering conditions and determining pages that meet the conditions, emotion analysis means for recognizing the user's emotions in real time and dynamically updating the filtering conditions, and display means for transmitting the filtered search results to the user terminal and displaying them. This allows users to enjoy a comfortable search experience tailored to their emotions and preferences without seeing offensive content during searches.

[0927] "User" refers to an individual who utilizes a search system to enter keywords to retrieve information and review search results.

[0928] A "terminal" is a device used by a user to access the search system and display search results, and includes a personal computer, smartphone, etc.

[0929] "Server" refers to the back-end computer system that receives search requests, retrieves search results from the Internet, and analyzes and filters the data.

[0930] "Filtering conditions" refer to criteria set by a user to filter out objectionable content, and may include specific keywords or image characteristics.

[0931] The term "search processing means" refers to a function that searches for related web pages using a global network based on a search request received from a user.

[0932] "Analysis means" refers to the function of analyzing the content of web pages included in search results and extracting image data and text data.

[0933] "Filtering means" refers to the function of comparing extracted image data and text data with filtering conditions and identifying pages that meet the criteria.

[0934] "Emotion analysis means" refers to the function of analyzing users' search behavior and facial expression data in real time and dynamically updating filtering conditions.

[0935] "Display means" refers to the function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0936] "Image analysis means" refers to a function that analyzes extracted image data and determines whether the content contains objectionable content.

[0937] "Text analysis means" refers to a function that analyzes extracted text data and determines whether the content contains offensive keywords or phrases.

[0938] "Warning label" refers to a message displayed to users to inform them that their search results contain objectionable content.

[0939] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0940] First, the user enters a keyword into the search field on the device and presses the search button. For example, they enter "insect control."

[0941] The device then sends the user's input search request to the server, which receives the request and uses an external search engine API (e.g., Google Custom Search API) to retrieve a list of related web pages.

[0942] The server analyzes the HTML content of the search results and extracts image and text data using Beautiful Soup or a similar library. The extracted image data is analyzed using image analysis software such as OpenCV, and the text data is analyzed using a natural language processing library such as NLTK.

[0943] The server then compares the extracted data with the filtering criteria set by the user. For example, an image analysis unit may determine whether the data contains images of insects, and if so, reject the objectionable content according to the filtering criteria. Similarly, a text analysis unit may analyze the text data to determine whether it contains objectionable keywords or phrases.

[0944] In parallel, the server analyzes users' search behavior and feedback in real time using an emotion engine, which uses machine learning models such as TensorFlow to monitor users' facial expression data and click behavior, dynamically updating filtering criteria if unpleasant emotions are recognized.

[0945] For example, if a user expresses displeasure when viewing a search result page, the emotion engine analyzes that data and reconfigures its filtering criteria to ensure the user does not encounter similar displeasure again.

[0946] Finally, the server sends the filtered search results to the device, which displays them on the user's screen and adds warning labels if necessary. For example, a page containing images of insects will display a warning message saying, "This page contains images of insects."

[0947] As a concrete example, suppose a user enters "insect control" as a search keyword and presses the search button. The server uses this keyword to call the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images of insects. If it does, the page is either removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated appropriately. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[0948] An example of a prompt might be:

[0949] "When you enter a search keyword and press a button, the search is performed using an external search engine API, and objectionable content is filtered out based on the filtering conditions set by the user in advance. In addition, an emotion engine analyzes the user's emotions and dynamically updates the filtering conditions. A warning may also be displayed in the search results."

[0950] The system allows users to avoid objectionable content while searching, providing a comfortable and safe search experience with dynamic filtering that takes sentiment into account in real time.

[0951] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0952] Step 1:

[0953] The user enters a keyword into the search field on the device and presses the search button. Specifically, the keyword "insect control" is entered. This input generates a search request. The output is this search request.

[0954] Step 2:

[0955] The terminal sends the generated search request to the server. Specifically, it generates an HTTP POST request and sends it to the server in a format that includes the search keywords. The input is the keyword entered by the user, and the output is the search request sent to the server.

[0956] Step 3:

[0957] The server parses the received search request and retrieves a list of relevant web pages using an external search engine API, specifically by calling the Google Custom Search API to retrieve the search results. The input is the received search request and the output is the list of retrieved search results.

[0958] Step 4:

[0959] The server analyzes the HTML content of the search results and extracts image data and text data. Specifically, it uses Beautiful Soup to extract image URLs and text from the HTML of each web page. The input is the HTML content of the search results, and the output is the extracted image data and text data.

[0960] Step 5:

[0961] The server compares the extracted image data and text data with the filtering conditions set by the user. Specifically, it performs image analysis using OpenCV and text analysis using NLTK. The input is the extracted image data or text data and the filtering conditions, and the output is a judgment result on whether the filtering conditions are met.

[0962] Step 6:

[0963] If the server determines that the extracted data contains offensive content, it will either exclude the page from the search results or add a warning label. For example, if the page contains an image of an insect, it will either exclude the page or add a warning message. The input is the result of the determination, and the output is an updated list of search results.

[0964] Step 7:

[0965] The server's emotion engine monitors users' search behavior and feedback and analyzes their emotions in real time. Specifically, it captures the user's facial expression data and analyzes it using TensorFlow. The input is the user's facial expression data, and the output is the analyzed emotion data.

[0966] Step 8:

[0967] The server dynamically updates the filtering conditions based on the emotion data. For example, if the user shows an unpleasant facial expression, it strengthens the related filtering conditions. The input is the emotion analysis result, and the output is the updated filtering conditions.

[0968] Step 9:

[0969] Finally, the server sends the filtered search results to the terminal. Specifically, it generates an HTTP response and sends it to the terminal including the search results. The input is the processed search result list, and the output is the final search results displayed on the user's terminal.

[0970] Step 10:

[0971] The terminal displays the filtered search results on the user's screen, for example displaying a warning message saying "This page contains images of insects." The input is the search results sent by the server, and the output is the search results visually presented to the user.

[0972] (Application example 2)

[0973] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0974] When searching the Internet, users may encounter unpleasant content, which can impair the search experience. Especially on online shopping sites, users may feel uneasy about making purchases if product information or images containing unpleasant content are displayed. Furthermore, there is a lack of a mechanism to dynamically change filtering conditions according to user emotions, which makes it difficult to respond flexibly.

[0975] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0976] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from the Internet, analysis means for analyzing web pages in the search results and extracting image URLs and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that match the conditions, emotion recognition means for analyzing the user's search behavior and facial expressions in real time and recognizing emotions, means for dynamically updating the filtering conditions based on the user's emotions recognized by the emotion recognition means, and display means for transmitting the filtered search results to a user terminal and displaying them. This enables users to avoid offensive content and perform flexible filtering according to emotions.

[0977] "User-defined filtering conditions" refers to criteria for filtering out objectionable content by a user setting specific conditions.

[0978] The "search processing means" is a means having the function of receiving a search request from a user and retrieving related search results from the Internet.

[0979] "Analysis means" refers to a means that has the function of analyzing web pages in search results and extracting image URLs and text content.

[0980] The "filtering means" is a means having the function of checking extracted images and text content against the filtering conditions set by the user and determining which pages match those conditions.

[0981] The "emotion recognition means" is a means having a function of analyzing the user's search behavior and facial expressions in real time and recognizing the user's emotions.

[0982] The "dynamic update means" is a means having a function of changing or adjusting the filtering conditions in real time based on the user's emotion recognized by the emotion recognition means.

[0983] The "display means" is a means having a function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[0984] MODE FOR CARRYING OUT THE INVENTION

[0985] The system that realizes this application example is a search system that eliminates unpleasant content from search results based on filtering conditions set by the user, and also performs dynamic filtering according to the user's emotions using emotion recognition means. This system is composed of both a server and a user terminal, and requires specific hardware and software to realize each function.

[0986] System Configuration

[0987] Hardware

[0988] Server: A computer system for performing search processing, analysis, filtering, and emotion recognition.

[0989] User device: A device used to input search keywords and display search results. This includes smartphones, tablets, and PCs.

[0990] Webcam: Hardware for capturing a user's facial expressions.

[0991] Microphone: Hardware used to capture the user's voice.

[0992] software

[0993] Search engine API: Software that uses external search engine services to obtain information on the Internet.

[0994] Image analysis module: Software for analyzing the acquired image content (e.g. OpenCV).

[0995] Text analysis module: Software for analyzing the captured text content (e.g., NLTK).

[0996] Emotion recognition model: Software for recognizing emotions from a user's facial expressions and voice in real time (e.g., Facial Expression Recognition model).

[0997] Filtering module: Software that matches the filtering criteria set by the user and filters out objectionable content.

[0998] Processing flow

[0999] 1. Submit a search request

[1000] The user enters keywords into the terminal and presses the search button.

[1001] The terminal sends a search request to the server.

[1002] 2. Obtaining search results

[1003] The server uses a search engine API to retrieve search results based on the specified keywords from the Internet.

[1004] 3. Content Analysis

[1005] Using the analysis means, the server analyzes the web pages of the retrieved search results and extracts image URLs and text content.

[1006] An image analysis module analyzes the extracted image content to determine if it contains objectionable material.

[1007] The text analysis module analyzes the extracted text content to determine whether it contains offensive keywords or phrases.

[1008] 4. Emotional Recognition

[1009] The server monitors the user's search behavior and facial expressions in real time via a webcam and microphone, and analyzes the user's emotions using an emotion recognition model.

[1010] 5. Filtering

[1011] The filtering module matches the extracted content with filtering criteria set by the user and dynamically updates the criteria based on the user's emotional state according to an emotion recognition model.

[1012] Exclude pages or add warning labels if they contain objectionable content.

[1013] 6. Displaying the results

[1014] The filtered search results are sent from the server to the user terminal and displayed.

[1015] Specific examples

[1016] For example, if a user searches for "stuffed toys," the server uses a search engine API to obtain a list of related web pages. Then, it uses analytics to analyze the content of each web page and detects offensive content from images and text. If it determines that the user dislikes spiders, spider images and related text are filtered out. Furthermore, the system analyzes the user's facial expressions and voice in real time, and if any unpleasant emotions are recognized, the filtering criteria are dynamically updated. Finally, the filtered search results are displayed on the device, allowing the user to choose their purchase with confidence.

[1017] Prompt Sentence Examples

[1018] Sentiment Analysis Prompt: "Analyze the user's emotions based on their facial expressions and voice to determine what content they find offensive."

[1019] Content Analysis prompt: "Identify content in your search results that users may find offensive and explain why."

[1020] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1021] Step 1:

[1022] User enters keyword

[1023] Users input search keywords using devices such as smartphones or PCs. This generates a search request. The input data is the keywords, and the output data is the search request.

[1024] Step 2:

[1025] Submitting a search request

[1026] The terminal sends the search request entered by the user to the server. The input data is the search request, and the output data is a request packet sent to the server. Specifically, the request is sent to the server using the HTTP protocol.

[1027] Step 3:

[1028] Getting search results

[1029] When the server receives a search request, it uses an external search engine API to retrieve relevant search results from the Internet. The input data is the search request, and the output data is a list of the retrieved search results. The data is processed by passing the search keywords to the search engine API and executing the search.

[1030] Step 4:

[1031] Content Analysis

[1032] The server analyzes the web pages of the search results it retrieves and extracts image URLs and text content. The input data is a list of search results, and the output data is the extracted image URLs and text content. Specifically, it performs HTML parsing to extract image URLs and text content.

[1033] Step 5:

[1034] User Emotion Recognition

[1035] The server captures the user's facial expressions and voice through a webcam and microphone. It then analyzes the user's emotions using an emotion recognition model. The input data are the captured facial expression images and voice data, and the output data is the analyzed emotional state. Image recognition algorithms and voice analysis algorithms are used for data processing.

[1036] Step 6:

[1037] Dynamic filtering condition updates

[1038] The server dynamically updates the filtering conditions based on the recognized user emotion. The input data is the analyzed emotional state, and the output data is the updated filtering conditions. Specific operations include executing logic to change the filtering criteria accordingly.

[1039] Step 7:

[1040] Content Filtering

[1041] The server uses analytical tools to match the extracted content with filtering criteria and exclude or label pages containing objectionable content. The input data are the extracted image URLs and text content and the filtering criteria, and the output data are the filtered search results. Specifically, the server evaluates the content using a criteria matching algorithm.

[1042] Step 8:

[1043] Submitting filtered search results

[1044] The server sends the filtered search results to the user terminal. The input data is the filtered search results, and the output data is a data packet sent to the user terminal. Specifically, the server sends back the results using the HTTP protocol.

[1045] Step 9:

[1046] Displaying search results

[1047] The user terminal receives the filtered search results and displays them on the user's screen. The input data are the search results sent from the server, and the output data are the search results displayed on the user's screen. Specifically, the received data is rendered on the screen in an appropriate format.

[1048] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1049] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1050] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1051] [Fourth embodiment]

[1052] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1053] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1054] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1055] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1056] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1057] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1058] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1059] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1060] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1061] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1062] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1063] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1064] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1065] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[1066] overview

[1067] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. Its main components include a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[1068] User operations

[1069] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[1070] Processing search requests (server)

[1071] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[1072] Analysis method (server)

[1073] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[1074] Filtering method (server)

[1075] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[1076] Warn or Exclude (Server)

[1077] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[1078] Displaying the results (terminal)

[1079] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[1080] Specific examples

[1081] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the server analyzes the content of each web page to check whether it contains any images or text of insects. If it does, the page is removed from the list or a warning label is attached. Finally, the filtered search results are displayed to the user, allowing them to browse the search results with peace of mind without seeing any unpleasant insect images.

[1082] In this way, the system of the present invention can provide a comfortable and secure search experience for the user.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] The user inputs search keywords and presses the search button. The user's device receives this input and creates a search request.

[1086] Step 2:

[1087] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[1088] Step 3:

[1089] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[1090] Step 4:

[1091] The server calls an external search engine API based on the search keywords and retrieves search results.

[1092] Search results include the title, URL, and snippet of the relevant web page.

[1093] Step 5:

[1094] The server analyzes each web page in the search results and extracts image URLs and text content.

[1095] Scraping technology is used to analyze HTML source code.

[1096] Step 6:

[1097] The server analyzes the URL of the extracted image using an image analysis means, which uses an image analysis library.

[1098] For example, determining if an image contains insects and checking for objectionable content.

[1099] Step 7:

[1100] The server uses text analysis means to analyze the extracted text content with a natural language processing library.

[1101] Check for the presence of certain offensive keywords or phrases.

[1102] Step 8:

[1103] Based on the analysis results, the server determines which pages contain objectionable content.

[1104] If the filtering conditions are met, the page will be excluded from the search results list or marked with a warning label.

[1105] Step 9:

[1106] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[1107] Step 10:

[1108] The terminal analyzes the filtered search results received from the server and displays them on the user's screen.

[1109] For search results with warning labels, an appropriate warning message will be displayed to the user.

[1110] Through the above processing steps, the CleanSearch system provides users with search results that do not contain offensive content, ensuring a safe browsing environment.

[1111] Example 1

[1112] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1113] When searching the Internet, users may encounter objectionable content. For this reason, it is necessary to provide an environment where users can safely view search results. In particular, if the content of images or text contains objectionable content, it is necessary to improve the user experience by filtering or warning users in advance.

[1114] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1115] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from a network, analysis means for analyzing web pages in the search results and extracting image paths and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that meet the conditions, and display means for transmitting the filtered search results to a user terminal and displaying them, thereby enabling users to view search results while avoiding offensive content.

[1116] "Filtering conditions" are specific criteria or rules that a user sets to avoid objectionable content.

[1117] A "search processing means" is a mechanism for receiving a search request and retrieving related information over a network.

[1118] The "analysis means" is a function for analyzing the acquired search results and extracting image paths and text content.

[1119] The "filtering means" is a function that checks the extracted content against the filtering conditions set by the user to determine whether or not it contains offensive content.

[1120] The "display means" is a mechanism for transmitting the filtered search results to the user terminal and presenting them to the user.

[1121] The "image analysis means" is a function for analyzing extracted image content and determining whether it contains offensive content.

[1122] The "text analysis means" is a mechanism for analyzing the extracted text content and identifying offensive keywords and phrases.

[1123] A "warning label" is a warning message or mark that is added to search results that contain offensive content.

[1124] "Network" refers to an information and communication network such as the Internet, which is the infrastructure for sending and receiving data.

[1125] A "user terminal" is a device such as a computer, smartphone, or tablet that is operated by an individual.

[1126] The present invention relates to a search system that eliminates objectionable content based on filtering conditions set by a user. Specific embodiments of this system are described below.

[1127] overview

[1128] This system removes or warns users of offensive content from search results to provide a safe and secure environment for users. The system includes a search processing means, an analysis means, a filtering means, and a display means. Furthermore, image analysis means and text analysis means are used to improve the accuracy of detecting offensive content.

[1129] User operations

[1130] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition may be set to "Do not display images of insects."

[1131] Processing a search request

[1132] The terminal sends a search request to the server. The server receives this request and performs a search on the network using the specified keywords. In this process, it uses an external search engine API to obtain a list of related web pages. Specifically, a search engine API is used as an example of an external search engine API.

[1133] Analysis means

[1134] The server begins parsing the search results. The parser analyzes the HTML content of each web page to extract image paths and text content. An HTML parsing library, such as BeautifulSoup, is used for the analysis.

[1135] Filtering Methods

[1136] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains offensive material. Image analysis is performed using an image processing library, such as OpenCV. Text analysis is performed using a text processing library, such as NLTK.

[1137] Warnings or Exclusions

[1138] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[1139] Displaying the results

[1140] After filtering, the search results are sent from the server to the device. The device displays the filtered results on the user's screen. For search results with warning labels, an appropriate warning message is displayed to the user. For example, a warning such as "This page contains images of insects" is displayed.

[1141] Specific examples

[1142] For example, when a user enters the search keyword "insect control" and presses the search button, the server uses the keywords to retrieve a list of related web pages from an external search engine API. Next, it uses BeautifulSoup to analyze the content of each web page and checks whether it contains insect images or text. OpenCV is used to detect whether the page contains insect images, and NLTK is used to check the text for offensive content. If it contains insect images, the page is either excluded from the list or a warning label is added. Finally, the filtered search results are displayed to the user, allowing them to safely browse the search results while avoiding any offensive insect images.

[1143] Usage example (example of prompt sentence for generative AI model)

[1144] An example prompt might look like this:

[1145] A user searches for "insect prevention" and sets the filtering criteria to "Do not display images of insects." The server retrieves related web pages using an external search engine API, analyzes them with BeautifulSoup, and extracts image paths and text. OpenCV performs image analysis, and NLTK analyzes the text. Any objectionable content is removed from the results, and the final filtered search results are displayed to the user.

[1146] In this way, the system of the present invention provides a comfortable and secure search experience for the user.

[1147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1148] Step 1:

[1149] The user enters a keyword in the search field and presses the search button. For example, the user enters "insect control" and sets the filtering condition to "do not display images of insects." The input in this case is the keyword and the filtering condition. The output is a search request, which is generated by the terminal.

[1150] Step 2:

[1151] The terminal sends the search request entered by the user to the server. Specifically, the terminal sends the generated search request, i.e., a data packet containing keywords and filtering conditions, to the server via the network. The input is the search request, and the output is the transmission of the data packet to the server.

[1152] Step 3:

[1153] Based on the received search request, the server performs a network search using the specified keywords. At this time, it uses an external search engine API to obtain a list of related web pages. Specifically, the server sends an HTTP request to the API and receives an HTTP response containing the search results. The input is the search request, and the output is the list of retrieved web pages.

[1154] Step 4:

[1155] The server analyzes the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image paths and text content. Specifically, it uses an HTML analysis library called BeautifulSoup to analyze the HTML and extract image URLs and text. The input is a list of retrieved web pages, and the output is the extracted image URLs and text content.

[1156] Step 5:

[1157] The server compares the extracted images and text content with the filtering criteria set by the user. This comparison is performed using image analysis tools and involves necessary image processing. Specifically, it analyzes images using OpenCV to determine whether they contain offensive content. For example, it uses computer vision techniques based on a specific labeled image dataset. The input is the image URL, and the output is the filtering result.

[1158] Step 6:

[1159] The server analyzes the extracted text content using text analysis tools. Specifically, it uses the NLTK library to tokenize the text and detect offensive keywords and phrases. The input is the extracted text content, and the output is the text filtering decision.

[1160] Step 7:

[1161] If the server determines that a web page contains objectionable content, it either removes the web page from the search results or adds a warning label. Specifically, the server either removes the web page from the list or adds a warning message based on the result of the determination. The input is the filtering result, and the output is the final filtered search result list.

[1162] Step 8:

[1163] After filtering is complete, the search results are sent from the server to the terminal. The terminal displays the filtered results on the user's screen. Specifically, the server sends the filtered search results as data packets to the terminal, and the terminal parses the received data appropriately and displays it in a GUI. For search results with warning labels, a message such as "This page contains images of insects" is displayed. The input is the final filtered search result list, and the output is the search results displayed on the user's screen.

[1164] (Application example 1)

[1165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1166] Conventional search systems often lack sufficient filtering capabilities to avoid offensive content. In particular, it has been difficult for video streaming services to proactively filter out content that users find offensive. This has led to the risk of users accidentally encountering unpleasant video content, making it difficult for them to enjoy content safely. Furthermore, existing filtering systems often lack the precision of image and text analysis, resulting in inaccurate filtering.

[1167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1168] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from information sources, analysis means for analyzing digital information in the search results and extracting image addresses and text information, filtering means for comparing the extracted image and text information with the filtering conditions and determining pages that match the conditions, display means for transmitting the filtered search results to a user interface and displaying them, and video analysis means for analyzing video thumbnail images and descriptive text and excluding videos that match the user's filtering conditions. This allows users to use content distribution services with peace of mind without viewing offensive content.

[1169] "Filtering conditions" are criteria that a user sets to avoid objectionable content.

[1170] The "search processing means" is a function that receives a user's search request and retrieves relevant search results from information sources.

[1171] The "analysis means" is a function that analyzes the digital information contained in the obtained search results and extracts image addresses and text information.

[1172] The "filtering means" is a function that checks extracted image and text information against the filtering conditions set by the user and determines which pages match.

[1173] The "display means" is a function that transmits the filtered search results to the user interface and displays them.

[1174] The "video analysis means" is a function that analyzes the thumbnail images and description text of videos and eliminates videos that match the user's filtering conditions.

[1175] The system embodying the present invention is a search system that eliminates objectionable content based on filtering conditions set by a user. A specific embodiment of this system will be described below.

[1176] System Overview

[1177] The system includes a search processing unit, an analysis unit, a filtering unit, a display unit, and a video analysis unit, and can prevent users from viewing objectionable content, particularly in video distribution services.

[1178] Hardware and Software

[1179] The following hardware and software are used to implement this system:

[1180] Hardware: Smartphone, server, camera (for image analysis)

[1181] Software: OpenCV (image analysis), TextBlob (text analysis)

[1182] Process Overview

[1183] The server receives the user's filtering criteria, analyzes the search results based on them, and filters out or warns of offensive content, as detailed below.

[1184] Search processing means

[1185] When a user enters a search request on a terminal, the request is sent to the server, which retrieves relevant search results from the information source.

[1186] Analysis means

[1187] Analyze and extract the digital information (image addresses and text information) from the search results. Specifically, analyze the HTML content to extract the necessary information.

[1188] Filtering Methods

[1189] The extracted images and text information are compared with the filtering criteria set by the user to determine which pages or videos match. If there is a match, the page is either excluded or marked with a warning label.

[1190] Display means

[1191] The filtered search results are sent from the server to the terminal and displayed on the user interface.

[1192] Video analysis methods

[1193] Analyzes video thumbnail images and description text, and filters out content that matches the user's filtering criteria. Image analysis is performed using OpenCV, and text analysis is performed using TextBlob.

[1194] Specific examples

[1195] For example, consider a situation where a user has set a preference to "not display horror movies." When the user opens a video streaming app and searches for a specific keyword, the server receives the request and retrieves relevant videos from the source. The server then analyzes the video's thumbnail image and description text to determine whether it matches the user's filtering criteria of "horror movies." If it does, the video is removed from the viewing list or a warning label is added.

[1196] Prompt Sentence Examples

[1197] If a user searches for "horror movies" in a video streaming app, the following prompt will be generated:

[1198] text

[1199] The filter condition "Horror Movies" is set. Based on this requirement, perform image and text analysis to filter out horror movies.

[1200] In this way, the system of the present invention can provide users with a comfortable and safe video viewing experience.

[1201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1202] Step 1:

[1203] A user inputs a search request from a device. For example, a user sets a filtering condition such as "do not display horror movies" and operates a video streaming app to search for "latest movies." In this case, the specific action is to enter "latest movies" into the search field on the device and press the search button.

[1204] Step 2:

[1205] The terminal sends a search request (input: user's search keywords and filtering conditions) to the server. The data processing performed here is to generate request data including the search keywords and filtering conditions and send it to the server via the network. The output is the request data sent to the server.

[1206] Step 3:

[1207] The server processes the received search request and retrieves search results from the information source (e.g., calling an external search engine API). The server retrieves a list of related videos on the Internet based on the user's search keywords. At this time, an appropriate API call is made as data calculation, and the video list as search results is obtained as text data. The output is the retrieved video list.

[1208] Step 4:

[1209] The server analyzes the search results and extracts the addresses of the video thumbnail images and description text. The specific operation performed here is to parse the HTML content of each video and extract the necessary information (thumbnail URL and description text). The input is the list of videos in the search results, and the output is a list of extracted thumbnail URLs and description text.

[1210] Step 5:

[1211] The server compares the extracted thumbnail images and description text with the user's filtering criteria and filters them. For example, to check whether a movie is a horror movie, the server analyzes the thumbnail images with OpenCV and the description text with TextBlob. The input is the extracted thumbnail URL and description text, and the data calculation is the image and text analysis process. The output is a filtered list of movies.

[1212] Step 6:

[1213] Based on the filtered video list, the server removes videos determined to contain objectionable content from the list or assigns warning labels to them. Specifically, the server updates the video list according to the analysis results. The input is the filtered video list, and the output is the final display list (including videos with warning labels).

[1214] Step 7:

[1215] The server sends the final display list to the terminal. The server then transfers the updated video list to the terminal via the network. At this time, the server converts the list into the required format as data processing before sending it. The input is the final display list, and the output is the display list sent to the terminal.

[1216] Step 8:

[1217] The terminal displays the received final display list on the user interface. Specifically, the terminal updates the user interface to show the safe video list to the user. The input is the display list sent from the server, and the output is a screen display that the user can visually confirm.

[1218] By following the above steps, users can watch a filtered list of safe videos with peace of mind.

[1219] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1220] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[1221] overview

[1222] In addition to search processing means, analysis means, filtering means, and display means, this system is equipped with an emotion engine that recognizes user emotions in real time and dynamically updates filtering conditions, allowing users to receive appropriate search results in response to changes in their emotions, providing a comfortable and secure search experience.

[1223] User operations

[1224] The user enters a keyword in the search field and presses the search button. For example, if the user enters "insect control," the filtering condition is set to "Do not display images of insects."

[1225] Processing search requests (server)

[1226] The device sends a search request to the server, which receives the request and performs an internet search using the specified keywords, using an external search engine API to retrieve a list of related web pages.

[1227] Analysis method (server)

[1228] The server begins to analyze the retrieved search results. The analysis means analyzes the HTML content of each web page and extracts image URLs and text content.

[1229] Filtering method (server)

[1230] The server compares the extracted image and text content with the filtering criteria set by the user. It uses image analysis tools to analyze the extracted image content and determine whether it contains objectionable content. For example, if an image of an insect is included, it meets the filtering criteria.

[1231] Emotion engine function (server)

[1232] In parallel with the search process, the server analyzes emotions in real time based on the user's search behavior and feedback. The emotion engine monitors the user's facial expressions and click behavior while searching, and dynamically updates the filtering conditions if unpleasant emotions are recognized.

[1233] Warn or Exclude (Server)

[1234] If the server determines that the web page contains offensive content, it will either exclude the web page from search results or add a warning label to it. The text analysis means will also analyze the text content of the web page to determine whether it contains offensive keywords or phrases.

[1235] Displaying the results (terminal)

[1236] After filtering, the server sends the search results to the device. The device then displays the filtered results on the user's screen. For search results with warning labels, the device displays an appropriate warning message to the user. For example, the device displays a warning such as "This page contains images of insects."

[1237] Specific examples

[1238] For example, suppose a user enters "insect control" as a search keyword and presses the search button. Based on this keyword, the server calls the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images or text of insects. If it does contain any images of insects, the page is removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated accordingly. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[1239] In this way, the system of the present invention can provide users with a comfortable and secure search experience. By combining it with an emotion engine, appropriate filtering according to the user's emotions becomes possible, further improving user satisfaction.

[1240] The processing flow will be explained below.

[1241] Step 1:

[1242] The user enters keywords into the search field and presses the search button. The user's device receives this input and creates a search request.

[1243] Step 2:

[1244] The terminal sends a search request (including search keywords and user filtering conditions) to the server.

[1245] Step 3:

[1246] The server analyzes the search request received from the terminal and extracts search keywords and filtering conditions.

[1247] Step 4:

[1248] The server calls external search engine APIs based on the search keywords to retrieve search results, which include the titles, URLs, and snippets of relevant web pages.

[1249] Step 5:

[1250] The server analyzes each web page in the search results and extracts image URLs and text content, using scraping technology to analyze the HTML source code.

[1251] Step 6:

[1252] The server analyzes the extracted image URLs using image analysis techniques, such as using an image analysis library, to determine if the image contains insects or other objectionable content.

[1253] Step 7:

[1254] The server then uses text analysis tools to analyze the extracted text content using natural language processing libraries to check whether it contains certain offensive keywords or phrases.

[1255] Step 8:

[1256] Based on the analysis results, the server determines whether the page contains objectionable content and, if it meets the filtering criteria, removes the page from the search results list or adds a warning label.

[1257] Step 9:

[1258] The server runs an emotion engine based on the user's search behavior and feedback. The emotion engine uses facial recognition technology to detect emotions from the user's facial expressions in real time and analyzes their reactions to search results.

[1259] Step 10:

[1260] The server automatically and dynamically updates the filtering conditions when the user indicates unpleasant emotions, and applies the new filtering conditions to re-filter the search results.

[1261] Step 11:

[1262] The server generates a list of search results after the filtering process is completed and transmits this to the terminal.

[1263] Step 12:

[1264] The terminal analyzes the filtered search results received from the server and displays them on the user's screen. For search results with warning labels, the terminal displays an appropriate warning message to the user.

[1265] Through these processing steps, the CleanSearch system provides users with search results that do not contain offensive content, and the emotion engine also enables dynamic filtering based on user emotions, allowing users to enjoy a safe and enjoyable search experience.

[1266] Example 2

[1267] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1268] In conventional search systems, users often experience stress when checking search results due to the risk of encountering unpleasant content. Furthermore, they lack dynamic filtering that matches the user's emotions and preferences, making it difficult to provide optimal search results for each individual user. For this reason, there was a demand for a search system that could recognize user emotions in real time and dynamically update filtering conditions.

[1269] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1270] In this invention, the server includes means for filtering out offensive content based on filtering conditions set by the user, search processing means for receiving search requests and retrieving search results from a global network, analysis means for analyzing web pages in the search results and extracting image data and text data, filtering means for comparing the extracted image data and text data with the filtering conditions and determining pages that meet the conditions, emotion analysis means for recognizing the user's emotions in real time and dynamically updating the filtering conditions, and display means for transmitting the filtered search results to the user terminal and displaying them. This allows users to enjoy a comfortable search experience tailored to their emotions and preferences without seeing offensive content during searches.

[1271] "User" refers to an individual who utilizes a search system to enter keywords to retrieve information and review search results.

[1272] A "terminal" is a device used by a user to access the search system and display search results, and includes a personal computer, smartphone, etc.

[1273] "Server" refers to the back-end computer system that receives search requests, retrieves search results from the Internet, and analyzes and filters the data.

[1274] "Filtering conditions" refer to criteria set by a user to filter out objectionable content, and may include specific keywords or image characteristics.

[1275] The term "search processing means" refers to a function that searches for related web pages using a global network based on a search request received from a user.

[1276] "Analysis means" refers to the function of analyzing the content of web pages included in search results and extracting image data and text data.

[1277] "Filtering means" refers to the function of comparing extracted image data and text data with filtering conditions and identifying pages that meet the criteria.

[1278] "Emotion analysis means" refers to the function of analyzing users' search behavior and facial expression data in real time and dynamically updating filtering conditions.

[1279] "Display means" refers to the function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[1280] "Image analysis means" refers to a function that analyzes extracted image data and determines whether the content contains objectionable content.

[1281] "Text analysis means" refers to a function that analyzes extracted text data and determines whether the content contains offensive keywords or phrases.

[1282] "Warning label" refers to a message displayed to users to inform them that their search results contain objectionable content.

[1283] The present invention relates to a system that provides a more sophisticated search experience by eliminating offensive content from search results based on filtering conditions set by the user and by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[1284] First, the user enters a keyword into the search field on the device and presses the search button. For example, they enter "insect control."

[1285] The device then sends the user's input search request to the server, which receives the request and uses an external search engine API (e.g., Google Custom Search API) to retrieve a list of related web pages.

[1286] The server analyzes the HTML content of the search results and extracts image and text data using Beautiful Soup or a similar library. The extracted image data is analyzed using image analysis software such as OpenCV, and the text data is analyzed using a natural language processing library such as NLTK.

[1287] The server then compares the extracted data with the filtering criteria set by the user. For example, an image analysis unit may determine whether the data contains images of insects, and if so, reject the objectionable content according to the filtering criteria. Similarly, a text analysis unit may analyze the text data to determine whether it contains objectionable keywords or phrases.

[1288] In parallel, the server analyzes users' search behavior and feedback in real time using an emotion engine, which uses machine learning models such as TensorFlow to monitor users' facial expression data and click behavior, dynamically updating filtering criteria if unpleasant emotions are recognized.

[1289] For example, if a user expresses displeasure when viewing a search result page, the emotion engine analyzes that data and reconfigures its filtering criteria to ensure the user does not encounter similar displeasure again.

[1290] Finally, the server sends the filtered search results to the device, which displays them on the user's screen and adds warning labels if necessary. For example, a page containing images of insects will display a warning message saying, "This page contains images of insects."

[1291] As a concrete example, suppose a user enters "insect control" as a search keyword and presses the search button. The server uses this keyword to call the search engine API to obtain a list of related web pages. Next, the content of each web page is analyzed to check whether it contains any images of insects. If it does, the page is either removed from the list or a warning label is attached. Furthermore, the emotion engine monitors the user's facial expressions and click behavior, and if any unpleasant emotions are recognized, the filtering conditions are updated appropriately. The final filtered search results are displayed to the user, allowing them to view the search results with peace of mind without seeing any unpleasant insect images.

[1292] An example of a prompt might be:

[1293] "When you enter a search keyword and press a button, the search is performed using an external search engine API, and objectionable content is filtered out based on the filtering conditions set by the user in advance. In addition, an emotion engine analyzes the user's emotions and dynamically updates the filtering conditions. A warning may also be displayed in the search results."

[1294] The system allows users to avoid objectionable content while searching, providing a comfortable and safe search experience with dynamic filtering that takes sentiment into account in real time.

[1295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1296] Step 1:

[1297] The user enters a keyword into the search field on the device and presses the search button. Specifically, the keyword "insect control" is entered. This input generates a search request. The output is this search request.

[1298] Step 2:

[1299] The terminal sends the generated search request to the server. Specifically, it generates an HTTP POST request and sends it to the server in a format that includes the search keywords. The input is the keyword entered by the user, and the output is the search request sent to the server.

[1300] Step 3:

[1301] The server parses the received search request and retrieves a list of relevant web pages using an external search engine API, specifically by calling the Google Custom Search API to retrieve the search results. The input is the received search request and the output is the list of retrieved search results.

[1302] Step 4:

[1303] The server analyzes the HTML content of the search results and extracts image data and text data. Specifically, it uses Beautiful Soup to extract image URLs and text from the HTML of each web page. The input is the HTML content of the search results, and the output is the extracted image data and text data.

[1304] Step 5:

[1305] The server compares the extracted image data and text data with the filtering conditions set by the user. Specifically, it performs image analysis using OpenCV and text analysis using NLTK. The input is the extracted image data or text data and the filtering conditions, and the output is a judgment result on whether the filtering conditions are met.

[1306] Step 6:

[1307] If the server determines that the extracted data contains offensive content, it will either exclude the page from the search results or add a warning label. For example, if the page contains an image of an insect, it will either exclude the page or add a warning message. The input is the result of the determination, and the output is an updated list of search results.

[1308] Step 7:

[1309] The server's emotion engine monitors users' search behavior and feedback and analyzes their emotions in real time. Specifically, it captures the user's facial expression data and analyzes it using TensorFlow. The input is the user's facial expression data, and the output is the analyzed emotion data.

[1310] Step 8:

[1311] The server dynamically updates the filtering conditions based on the emotion data. For example, if the user shows an unpleasant facial expression, it strengthens the related filtering conditions. The input is the emotion analysis result, and the output is the updated filtering conditions.

[1312] Step 9:

[1313] Finally, the server sends the filtered search results to the terminal. Specifically, it generates an HTTP response and sends it to the terminal including the search results. The input is the processed search result list, and the output is the final search results displayed on the user's terminal.

[1314] Step 10:

[1315] The terminal displays the filtered search results on the user's screen, for example displaying a warning message saying "This page contains images of insects." The input is the search results sent by the server, and the output is the search results visually presented to the user.

[1316] (Application example 2)

[1317] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] When searching the Internet, users may encounter unpleasant content, which can impair the search experience. Especially on online shopping sites, users may feel uneasy about making purchases if product information or images containing unpleasant content are displayed. Furthermore, there is a lack of a mechanism to dynamically change filtering conditions according to user emotions, which makes it difficult to respond flexibly.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1320] In this invention, the server includes means for analyzing filtering conditions set by a user and excluding pages containing offensive content from search results, search processing means for receiving a search request and retrieving search results from the Internet, analysis means for analyzing web pages in the search results and extracting image URLs and text content, filtering means for comparing the extracted images and text content with the filtering conditions and determining pages that match the conditions, emotion recognition means for analyzing the user's search behavior and facial expressions in real time and recognizing emotions, means for dynamically updating the filtering conditions based on the user's emotions recognized by the emotion recognition means, and display means for transmitting the filtered search results to a user terminal and displaying them. This enables users to avoid offensive content and perform flexible filtering according to emotions.

[1321] "User-defined filtering conditions" refers to criteria for filtering out objectionable content by a user setting specific conditions.

[1322] The "search processing means" is a means having the function of receiving a search request from a user and retrieving related search results from the Internet.

[1323] "Analysis means" refers to a means that has the function of analyzing web pages in search results and extracting image URLs and text content.

[1324] The "filtering means" is a means having the function of checking extracted images and text content against the filtering conditions set by the user and determining which pages match those conditions.

[1325] The "emotion recognition means" is a means having a function of analyzing the user's search behavior and facial expressions in real time and recognizing the user's emotions.

[1326] The "dynamic update means" is a means having a function of changing or adjusting the filtering conditions in real time based on the user's emotion recognized by the emotion recognition means.

[1327] The "display means" is a means having a function of transmitting the filtered search results to the user terminal and displaying them on the screen.

[1328] MODE FOR CARRYING OUT THE INVENTION

[1329] The system that realizes this application example is a search system that eliminates unpleasant content from search results based on filtering conditions set by the user, and also performs dynamic filtering according to the user's emotions using emotion recognition means. This system is composed of both a server and a user terminal, and requires specific hardware and software to realize each function.

[1330] System Configuration

[1331] Hardware

[1332] Server: A computer system for performing search processing, analysis, filtering, and emotion recognition.

[1333] User device: A device used to input search keywords and display search results. This includes smartphones, tablets, and PCs.

[1334] Webcam: Hardware for capturing a user's facial expressions.

[1335] Microphone: Hardware used to capture the user's voice.

[1336] software

[1337] Search engine API: Software that uses external search engine services to obtain information on the Internet.

[1338] Image analysis module: Software for analyzing the acquired image content (e.g. OpenCV).

[1339] Text analysis module: Software for analyzing the captured text content (e.g., NLTK).

[1340] Emotion recognition model: Software for recognizing emotions from a user's facial expressions and voice in real time (e.g., Facial Expression Recognition model).

[1341] Filtering module: Software that matches the filtering criteria set by the user and filters out objectionable content.

[1342] Processing flow

[1343] 1. Submit a search request

[1344] The user enters keywords into the terminal and presses the search button.

[1345] The terminal sends a search request to the server.

[1346] 2. Obtaining search results

[1347] The server uses a search engine API to retrieve search results based on the specified keywords from the Internet.

[1348] 3. Content Analysis

[1349] Using the analysis means, the server analyzes the web pages of the retrieved search results and extracts image URLs and text content.

[1350] An image analysis module analyzes the extracted image content to determine if it contains objectionable material.

[1351] The text analysis module analyzes the extracted text content to determine whether it contains offensive keywords or phrases.

[1352] 4. Emotional Recognition

[1353] The server monitors the user's search behavior and facial expressions in real time via a webcam and microphone, and analyzes the user's emotions using an emotion recognition model.

[1354] 5. Filtering

[1355] The filtering module matches the extracted content with filtering criteria set by the user and dynamically updates the criteria based on the user's emotional state according to an emotion recognition model.

[1356] Exclude pages or add warning labels if they contain objectionable content.

[1357] 6. Displaying the results

[1358] The filtered search results are sent from the server to the user terminal and displayed.

[1359] Specific examples

[1360] For example, if a user searches for "stuffed toys," the server uses a search engine API to obtain a list of related web pages. Then, it uses analytics to analyze the content of each web page and detects offensive content from images and text. If it determines that the user dislikes spiders, spider images and related text are filtered out. Furthermore, the system analyzes the user's facial expressions and voice in real time, and if any unpleasant emotions are recognized, the filtering criteria are dynamically updated. Finally, the filtered search results are displayed on the device, allowing the user to choose their purchase with confidence.

[1361] Prompt Sentence Examples

[1362] Sentiment Analysis Prompt: "Analyze the user's emotions based on their facial expressions and voice to determine what content they find offensive."

[1363] Content Analysis prompt: "Identify content in your search results that users may find offensive and explain why."

[1364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1365] Step 1:

[1366] User enters keyword

[1367] Users input search keywords using devices such as smartphones or PCs. This generates a search request. The input data is the keywords, and the output data is the search request.

[1368] Step 2:

[1369] Submitting a search request

[1370] The terminal sends the search request entered by the user to the server. The input data is the search request, and the output data is a request packet sent to the server. Specifically, the request is sent to the server using the HTTP protocol.

[1371] Step 3:

[1372] Getting search results

[1373] When the server receives a search request, it uses an external search engine API to retrieve relevant search results from the Internet. The input data is the search request, and the output data is a list of the retrieved search results. The data is processed by passing the search keywords to the search engine API and executing the search.

[1374] Step 4:

[1375] Content Analysis

[1376] The server analyzes the web pages of the search results it retrieves and extracts image URLs and text content. The input data is a list of search results, and the output data is the extracted image URLs and text content. Specifically, it performs HTML parsing to extract image URLs and text content.

[1377] Step 5:

[1378] User Emotion Recognition

[1379] The server captures the user's facial expressions and voice through a webcam and microphone. It then analyzes the user's emotions using an emotion recognition model. The input data are the captured facial expression images and voice data, and the output data is the analyzed emotional state. Image recognition algorithms and voice analysis algorithms are used for data processing.

[1380] Step 6:

[1381] Dynamic filtering condition updates

[1382] The server dynamically updates the filtering conditions based on the recognized user emotion. The input data is the analyzed emotional state, and the output data is the updated filtering conditions. Specific operations include executing logic to change the filtering criteria accordingly.

[1383] Step 7:

[1384] Content Filtering

[1385] The server uses analytical tools to match the extracted content with filtering criteria and exclude or label pages containing objectionable content. The input data are the extracted image URLs and text content and the filtering criteria, and the output data are the filtered search results. Specifically, the server evaluates the content using a criteria matching algorithm.

[1386] Step 8:

[1387] Submitting filtered search results

[1388] The server sends the filtered search results to the user terminal. The input data is the filtered search results, and the output data is a data packet sent to the user terminal. Specifically, the server sends back the results using the HTTP protocol.

[1389] Step 9:

[1390] Displaying search results

[1391] The user terminal receives the filtered search results and displays them on the user's screen. The input data are the search results sent from the server, and the output data are the search results displayed on the user's screen. Specifically, the received data is rendered on the screen in an appropriate format.

[1392] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1393] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1394] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1395] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1396] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1397] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1398] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1399] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1400] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1401] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1402] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1403] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1404] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1405] 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.

[1406] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1407] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1408] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1409] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1410] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1411] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1412] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1413] The following is further disclosed regarding the above embodiment.

[1414] (Claim 1)

[1415] a means for analysing filtering criteria set by a user to exclude offensive content from search results; and

[1416] a search processing means for receiving a search request and retrieving search results from the Internet;

[1417] an analysis means for analyzing the web pages of the search results and extracting image URLs and text content;

[1418] a filtering means for comparing the extracted image and text content with filtering conditions and determining pages that meet the conditions;

[1419] a display means for transmitting and displaying the filtered search results to a user terminal;

[1420] A system including:

[1421] (Claim 2)

[1422] image analysis means for analyzing the extracted image content;

[1423] means for determining whether the analyzed image contains objectionable content;

[1424] A means to remove or label pages that contain objectionable content; and

[1425] 2. The system of claim 1,

[1426] (Claim 3)

[1427] a text analysis means for analyzing the extracted text content;

[1428] means for determining whether the analyzed text contains offensive keywords or phrases;

[1429] A means to remove or label pages that contain objectionable content; and

[1430] 2. The system of claim 1,

[1431] "Example 1"

[1432] (Claim 1)

[1433] A means of analysing the filtering criteria set by the user and excluding pages containing objectionable content from the search results;

[1434] a search processing means for receiving a search request and retrieving search results from a network;

[1435] An analysis means for analyzing the web pages of the search results and extracting image paths and text content;

[1436] a filtering means for comparing the extracted image and text content with filtering conditions and determining pages that match the conditions;

[1437] a display means for transmitting and displaying the filtered search results to a user terminal;

[1438] A system including:

[1439] (Claim 2)

[1440] image analysis means for analyzing the extracted image content;

[1441] means for determining whether the analyzed image contains objectionable content;

[1442] A means to remove or label pages that contain objectionable content; and

[1443] To obtain search results, you can use an external search engine,

[1444] 2. The system of claim 1,

[1445] (Claim 3)

[1446] a text analysis means for analyzing the extracted text content;

[1447] means for determining whether the analyzed text contains offensive keywords or phrases;

[1448] A means to remove or label pages that contain objectionable content; and

[1449] a means for displaying the results including a warning message;

[1450] 2. The system of claim 1,

[1451] "Application Example 1"

[1452] (Claim 1)

[1453] A means of analysing the filtering criteria set by the user and excluding pages containing objectionable content from the search results;

[1454] search processing means for receiving a search request and retrieving search results from the information sources;

[1455] an analysis means for analyzing the digital information of the search results and extracting image addresses and text information;

[1456] a filtering means for comparing the extracted image and text information with filtering conditions and determining pages that match the conditions;

[1457] display means for transmitting and displaying the filtered search results to a user interface;

[1458] A video analysis means for analyzing thumbnail images and description text of videos and excluding videos that match the user's filtering conditions;

[1459] A system including:

[1460] (Claim 2)

[1461] image analysis means for analyzing the extracted image information;

[1462] means for determining whether the analyzed image contains objectionable content;

[1463] A means to remove or label pages that contain objectionable content; and

[1464] 2. The system of claim 1,

[1465] (Claim 3)

[1466] a text analysis means for analyzing the extracted text information;

[1467] means for determining whether the analyzed text contains offensive keywords or phrases;

[1468] A means to remove or label pages that contain objectionable content; and

[1469] means for filtering the video list based on a user's filtering criteria;

[1470] 2. The system of claim 1,

[1471] "Example 2: Combining Emotion Engines"

[1472] (Claim 1)

[1473] means for filtering out objectionable content based on filtering criteria set by the user;

[1474] a search processing means for receiving a search request and retrieving search results from a global network;

[1475] an analysis means for analyzing the web pages of the search results and extracting image data and text data;

[1476] a filtering means for comparing the extracted image data and text data with filtering conditions and determining pages that match the conditions;

[1477] An emotion analysis means for recognizing a user's emotion in real time and dynamically updating filtering conditions;

[1478] a display means for transmitting and displaying the filtered search results to a user terminal;

[1479] A system including:

[1480] (Claim 2)

[1481] image analysis means for analyzing image data;

[1482] means for determining whether the analyzed image contains objectionable content;

[1483] A means to remove or label pages that contain objectionable content; and

[1484] 2. The system of claim 1,

[1485] (Claim 3)

[1486] a text analysis means for analyzing text data;

[1487] means for determining whether the analyzed text contains offensive keywords or phrases;

[1488] A means to remove or label pages that contain objectionable content; and

[1489] 2. The system of claim 1,

[1490] "Application example 2 when combining emotion engines"

[1491] (Claim 1)

[1492] A means of analysing the filtering criteria set by the user and excluding pages containing objectionable content from the search results;

[1493] a search processing means for receiving a search request and retrieving search results from the Internet;

[1494] an analysis means for analyzing the web pages of the search results and extracting image URLs and text content;

[1495] a filtering means for comparing the extracted image and text content with filtering conditions and determining pages that meet the conditions;

[1496] emotion recognition means for analyzing a user's search behavior and facial expression in real time and recognizing emotions;

[1497] means for dynamically updating filtering conditions based on the user's emotion recognized by the emotion recognition means;

[1498] a display means for transmitting and displaying the filtered search results to a user terminal;

[1499] A system including:

[1500] (Claim 2)

[1501] image analysis means for analyzing the extracted image content;

[1502] means for determining whether the analyzed image contains objectionable content;

[1503] A means to remove or label pages that contain objectionable content; and

[1504] 2. The system of claim 1,

[1505] (Claim 3)

[1506] a text analysis means for analyzing the extracted text content;

[1507] means for determining whether the analyzed text contains offensive keywords or phrases;

[1508] A means to remove or label pages that contain objectionable content; and

[1509] 2. The system of claim 1, [Explanation of symbols]

[1510] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for analysing filtering criteria set by a user to exclude offensive content from search results; and a search processing means for receiving a search request and retrieving search results from the Internet; an analysis means for analyzing the web pages of the search results and extracting image URLs and text content; a filtering means for comparing the extracted image and text content with filtering conditions and determining pages that meet the conditions; a display means for transmitting and displaying the filtered search results to a user terminal; A system including:

2. image analysis means for analyzing the extracted image content; means for determining whether the analyzed image contains objectionable content; A means to remove or label pages that contain objectionable content; and 2. The system of claim 1, wherein:

3. a text analysis means for analyzing the extracted text content; means for determining whether the analyzed text contains offensive keywords or phrases; A means to remove or label pages that contain objectionable content; and 2. The system of claim 1, wherein:

Images