A picture derivation method, related apparatus and storage medium

Abstract

The application discloses a picture export method, which comprises the following steps: when a picture viewing instruction for a to-be-recognized page is acquired, displaying M pictures contained in the to-be-recognized page through a picture viewer; sending target text identification to a server, so that the server determines target picture set identification information according to the target text identification; if the target picture set identification information meets picture export conditions, displaying a picture set export interface on the picture viewer according to a picture set export request sent by the server; and when an operation on the picture set export interface is detected, exporting N pictures in the to-be-recognized page into a file in a target format. The application also provides related devices. The application can intelligently determine whether the pictures in the page can be exported, thereby increasing the rationality of data export and improving the efficiency of picture export.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a method, related apparatus and storage medium for image export. Background Technology

[0002] With the rapid development of the internet, online information is becoming increasingly abundant, and browsers are becoming more and more diverse. Browser pages not only include text but also a large number of images. Because images can intuitively display the information, they are highly favored by users. Therefore, images occupy a very important position in web page information.

[0003] Currently, the method for exporting images from a webpage is as follows: the user first selects the image to be exported on the webpage, then long-presses or clicks the image, a dialog box will pop up, and then the user can click the option to save the image in the dialog box. The browser responds to the user's selection and saves the image locally on the terminal device.

[0004] However, there are often many images on the page. If users want to save these images, they need to perform the above operation for each image individually, which is a cumbersome process and results in low efficiency in image export. Summary of the Invention

[0005] This application provides a method, related apparatus, and storage medium for image export. Based on target image set recognition information, it intelligently decides whether images on a page can be exported, thereby increasing the rationality of data export. If it is determined that the image set can be exported, a one-click export method is used to export the images on the page as files corresponding to the target format, thereby improving the efficiency of image export.

[0006] In view of this, this application provides a method for exporting images, including:

[0007] When an image viewing instruction is received for the page to be identified, the M images contained in the page to be identified are displayed through the image viewer. The image viewing instruction carries a target text identifier, which is used to indicate the target text contained in the page to be identified. M is an integer greater than or equal to 1.

[0008] Send the target text identifier to the server so that the server can determine the target atlas identification information based on the target text identifier;

[0009] If the target image set recognition information meets the image export conditions, then according to the image set export request sent by the server, the image set export interface is displayed on the image viewer. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0010] When an operation targeting the image atlas export interface is detected, N images from the page to be identified will be exported as files corresponding to the target format.

[0011] This application also provides a method for exporting images, including:

[0012] The receiving terminal device sends a target text identifier for the page to be identified, wherein the target text identifier is used to indicate the target text included in the page to be identified, and the page to be identified contains M images, where M is an integer greater than or equal to 1;

[0013] Determine the target image set identification information based on the target text identifier;

[0014] If the target image set recognition information meets the image export conditions, an image set export request is sent to the terminal device so that the terminal device can display the image set export interface on the image viewer according to the image set export request sent by the server. When the terminal device detects the operation on the image set export interface, it exports N images in the page to be recognized as files corresponding to the target format. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0015] This application also provides an image exporting device, comprising:

[0016] The display module is used to display M images contained in the page to be identified through an image viewer when an image viewing instruction for the page to be identified is received. The image viewing instruction carries a target text identifier, which is used to indicate the target text contained in the page to be identified. M is an integer greater than or equal to 1.

[0017] The sending module is used to send the target text identifier to the server so that the server can determine the target image set identification information based on the target text identifier.

[0018] The display module is also used to display the image set export interface on the image viewer according to the image set export request sent by the server if the target image set recognition information meets the image export conditions. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0019] The export module is used to export N images from the page to be recognized into files corresponding to the target format when an operation targeting the image export interface is detected.

[0020] In one possible design, in another implementation of the embodiments of this application,

[0021] The export module is specifically used to display the first export interface and the second export interface when an operation targeting the atlas export interface is detected.

[0022] If an operation targeting the first export interface is detected, then the N images on the page to be identified will be exported as files corresponding to the image format.

[0023] If an operation targeting the second export interface is detected, the N images on the page to be identified will be exported as files corresponding to the portable document format PDF.

[0024] In one possible design, in another implementation of another aspect of the embodiments of this application, N is an integer greater than 1;

[0025] The export module is specifically used to receive the image sorting results for N images sent by the server when an operation targeting the image atlas export interface is detected.

[0026] Based on the image sorting results, export the sorted N images into files corresponding to the image format.

[0027] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0028] The display module is also used to display N images through an image viewer if the target image set recognition information meets the image export conditions;

[0029] The export module is also used to export the K images on the page to be identified as files in the target format when an operation on K images is detected. The K images are contained in N images, and K is an integer greater than or equal to 1 and less than or equal to K.

[0030] This application also provides an image exporting device, comprising:

[0031] The receiving module is used to receive the target text identifier for the page to be identified sent by the terminal device. The target text identifier is used to indicate the target text included in the page to be identified. The page to be identified contains M images, where M is an integer greater than or equal to 1.

[0032] The determination module is used to determine the target image set recognition information based on the target text identifier;

[0033] The sending module is used to send an image set export request to the terminal device if the target image set recognition information meets the image export conditions. This allows the terminal device to display the image set export interface on the image viewer based on the image set export request sent by the server. When the terminal device detects an operation on the image set export interface, it exports N images from the page to be recognized as files corresponding to the target format. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0034] In one possible design, in another implementation of the embodiments of this application,

[0035] The determination module is specifically used to obtain target image set recognition information if the target text identifier matches the text identifier library. The target image set recognition information includes the image recognition information corresponding to each of the M images, and the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0036] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0037] The determination module is specifically used to obtain M images if the target text identifier does not match the text identifier library;

[0038] The target image set recognition information is obtained by recognizing M images, which includes the image recognition information corresponding to each of the M images.

[0039] The target text identifier and target image set recognition information are stored in a text identifier library, wherein the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0040] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0041] The determination module is specifically used to obtain the image recognition information corresponding to each of the M images through an object recognition model. The image recognition information includes at least one of the following: object category, object name, and keywords.

[0042] Based on the image recognition information corresponding to each of the M images, obtain the target image set recognition information.

[0043] In one possible design, in another implementation of another aspect of the embodiments of this application, the target image set identification information includes the image identification information corresponding to each of the M images;

[0044] The determination module is also used to determine the target image set recognition information after determining the target image set recognition information based on the target text identifier. If the correlation between the image recognition information of N images and the target text meets the image-text matching condition, and the image recognition information of N images meets the information security condition, then the target image set recognition information meets the image export condition. Here, N images are contained in M ​​images.

[0045] or,

[0046] After determining the target image set recognition information based on the target text identifier, if the correlation between the image recognition information of N images and the target text meets the image-text matching condition, then the target image set recognition information meets the image export condition.

[0047] or,

[0048] After determining the target image set recognition information based on the target text identifier, if the image recognition information of N images meets the information security conditions, then the target image set recognition information meets the image export conditions.

[0049] In one possible design, in another implementation of another aspect of the embodiments of this application, N is an integer greater than 1;

[0050] The image export device also includes a processing module;

[0051] The processing module is used to determine the target image set recognition information based on the target text identifier. If the target image set recognition information meets the image export conditions, the module performs clustering processing on the N images based on the image recognition information corresponding to each image in the N images to obtain the clustered N images.

[0052] The determination module is also used to determine the correlation between each image and the target text based on the target text and the image recognition information corresponding to each image in the N images;

[0053] The processing module is also used to sort the clustered N images in descending order of their relevance to obtain the image sorting result;

[0054] The sending module is also used to send the image sorting results to the terminal device, so that when the terminal device detects an operation on the image set export interface, it can export the sorted N images as files corresponding to the image format according to the image sorting results.

[0055] This application also provides a terminal device, including: a memory, a transceiver, a processor, and a bus system;

[0056] The memory is used to store programs;

[0057] The processor is used to execute programs in memory, and the processor is used to execute the methods mentioned above according to the instructions in the program code;

[0058] Bus systems are used to connect memory and processor to enable communication between them.

[0059] This application also provides a server, including: a memory, a transceiver, a processor, and a bus system;

[0060] The memory is used to store programs;

[0061] The processor is used to execute programs in memory, and the processor is used to execute the methods mentioned above according to the instructions in the program code;

[0062] Bus systems are used to connect memory and processor to enable communication between them.

[0063] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0064] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided by the various alternative implementations of the above aspects.

[0065] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0066] This application provides a method for exporting images. When an image viewing instruction is received for a page to be recognized, the terminal device displays M images contained in the page through an image viewer and sends a target text identifier to the server. The server then determines the target image set recognition information based on the target text identifier. If the target image set recognition information meets the image export conditions, the terminal device displays an image set export interface on the image viewer. When an operation targeting the image set export interface is detected, the terminal device exports N images from the page to be recognized as files corresponding to the target format. This method intelligently decides whether images on the page can be exported based on the target image set recognition information, thereby increasing the rationality of data export. When it is determined that the image set can be exported, a one-click export method is used to directly export the images on the page as files corresponding to the target format, eliminating the need for the user to save each image on the page, thus improving the efficiency of image export. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of the architecture of the image export system in an embodiment of this application;

[0068] Figure 2 This is a schematic diagram of an interactive process of the image export method in an embodiment of this application;

[0069] Figure 3 This is a schematic diagram of one embodiment of the image export method in this application;

[0070] Figure 4 This is a schematic diagram of an interface of the page to be identified in an embodiment of this application;

[0071] Figure 5 This is a schematic diagram of entering an image viewer through a page to be identified in an embodiment of this application;

[0072] Figure 6 This is a schematic diagram of an image viewer that meets the image export conditions in an embodiment of this application.

[0073] Figure 7 This is a schematic diagram of an image viewer interface that does not meet the image export conditions in this application embodiment;

[0074] Figure 8 This is a schematic diagram illustrating the first export interface and the second export interface in an embodiment of this application;

[0075] Figure 9 This is a schematic diagram illustrating the export of the file as an image format in an embodiment of this application;

[0076] Figure 10 This is a schematic diagram illustrating the export of a portable document format file in an embodiment of this application;

[0077] Figure 11 This is a schematic diagram illustrating the sequential export of images carrying document format files in an embodiment of this application.

[0078] Figure 12 This is a schematic diagram of manually selecting an exported image in an embodiment of this application;

[0079] Figure 13 This is a schematic diagram of another embodiment of the image export method in this application;

[0080] Figure 14 This is a flowchart illustrating a process for determining whether an image set meets the image export conditions in an embodiment of this application.

[0081] Figure 15 This is a schematic diagram of a process for sorting the atlas in an embodiment of this application;

[0082] Figure 16 This is a schematic diagram of one embodiment of the image exporting device in this application.

[0083] Figure 17 This is a schematic diagram of another embodiment of the image exporting device in this application;

[0084] Figure 18 This is a schematic diagram of the structure of a terminal device in an embodiment of this application;

[0085] Figure 19 This is a schematic diagram of the server structure in an embodiment of this application. Detailed Implementation

[0086] This application provides an image export method, apparatus, device, and storage medium based on Artificial Intelligence (AI). It intelligently decides whether images on a page can be exported based on target image set recognition information, thereby increasing the rationality of data export. If it is determined that the image set can be exported, a one-click export method is used to export the images on the page as files corresponding to the target format, thereby improving the efficiency of image export.

[0087] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “corresponding to,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0088] Whether on a browser page or a mini-program page, content is usually displayed in a combination of text and images. These images can be saved locally on the terminal device for later use and viewing. However, some pages display a large number of images, requiring users to save each image individually, making the entire process cumbersome. The image export method provided in this application effectively addresses this scenario. For example, if a browser page contains 20 images, the user can trigger the one-click export function to directly export all images on the page as files in a specified format. Furthermore, considering that the images on the page may contain discrepancies between the text and images or other sensitive information, these images need to be filtered before exporting. Even further, the exported images can be intelligently sorted, saving users time in classifying and sorting images.

[0089] This application proposes an AI-based image export method, which is applied to... Figure 1 The image export system shown in the figure includes a server and terminal devices, with the client deployed on the terminal devices. Specifically, the client in this application can be a browser or a mini-program, etc., without limitation. The server in this application can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and AI platforms. The terminal devices can be smartphones, tablets, laptops, PDAs, personal computers, smart TVs, and smartwatches, but are not limited to these. The terminal devices and servers can be connected directly or indirectly through wired or wireless communication, without limitation. The number of servers and terminal devices is also not limited.

[0090] based on Figure 1 Please refer to the image export system shown. Figure 2 , Figure 2 This is a schematic diagram of an interactive process for the image export method in an embodiment of this application. As shown in the figure, taking a browser installed on a terminal device as an example, specifically:

[0091] In step S1, the terminal device obtains image viewing instructions for the page to be identified through a browser.

[0092] In step S2, the terminal device responds to the image viewing command by launching the image viewer integrated in the browser and displaying the image on the page to be identified through the image viewer.

[0093] In step S3, when a user opens the image viewer, it indicates that the user is interested in the image on the page to be recognized and may want to export the image. Therefore, the terminal device will also send an image viewing command to the server to trigger the server to recognize and process the image.

[0094] In step S4, based on the image viewing instruction, the server first determines whether the page to be identified has been identified before. If it has been identified, the server directly obtains the target image set recognition information corresponding to the page. If it has not been identified before, steps S41, S42, and S43 are executed. Specifically, in step S41, the server uses AI technology to recognize each image and obtains the image recognition result for each image. In step S42, the server checks whether each image is suitable for export; images involving sensitive content cannot be exported. In step S43, the images allowed to be exported are sorted.

[0095] In step S5, if the server determines that the target image set recognition information meets the image export conditions, it sends an image set export request to the terminal device.

[0096] In step S6, the terminal device displays the image atlas export interface in the image viewer according to the image atlas export request.

[0097] In step S7, the user can export the images on the page to be recognized as files corresponding to the target format by clicking the image set export interface.

[0098] Understandably, this application involves AI technology. AI refers to the theories, methods, technologies, and application systems that utilize digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine capable of reacting in a manner similar to human intelligence. AI essentially studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0099] AI technology is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0100] Computer Vision (CV) technology is required in image recognition. CV is a science that studies how to enable machines to "see." More specifically, it refers to using cameras and computers to replace human eyes for target recognition, measurement, and other machine vision tasks, and then performing image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, CV studies related theories and technologies, attempting to build AI systems capable of extracting information from images or multidimensional data. CV technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0101] The process of identifying target documents (such as titles and body text on a page) requires the use of Natural Language Processing (NLP) technology. NLP is an important area within computer science and AI. It studies various theories and methods that enable effective communication between humans and computers using natural language. NLP is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field involves natural language—the language people use in daily life—and thus it has a close connection with linguistic research. NLP technologies typically include text processing, semantic understanding, machine translation, question answering, and knowledge graphs.

[0102] With the research and advancement of AI technology, AI is being studied and applied in various fields, such as smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, robots, smart healthcare, and smart customer service. It is believed that with the development of technology, AI will be applied in more fields and play an increasingly important role.

[0103] Based on the above description, the solutions provided in this application involve AI-based CV and NLP technologies. The following section will describe the AI-based image export method from the perspective of a terminal device. Please refer to [link to relevant documentation]. Figure 3 One embodiment of the AI-based image export method in this application includes:

[0104] 101. When an image viewing instruction is received for the page to be identified, the terminal device displays M images contained in the page to be identified through an image viewer. The image viewing instruction carries a target text identifier, which is used to indicate the target text contained in the page to be identified. M is an integer greater than or equal to 1.

[0105] In this embodiment, the page to be identified is displayed on the browser or other client of the terminal device. For ease of explanation, please refer to [link to documentation]. Figure 4 , Figure 4 This is a schematic diagram of an interface of the page to be identified in an embodiment of this application. As shown in the figure, the page to be identified displays target text and images. The target text may include a title and body text, and the number of images is M, where M is an integer greater than or equal to 1.

[0106] The image viewer can load all images on the page to be identified. Please refer to [link / reference]. Figure 5 , Figure 5 Figure (A) illustrates an example of accessing an image viewer via a page to be identified in this application. As shown in Figure (A), the user can view images on the page to be identified. If the user is interested in a particular image, they can long-press or double-click it, thus triggering an image viewing command. The terminal device responds to the image viewing command by launching the image viewer in the client, i.e., entering the image viewer interface as shown in Figure (B). The image viewer can display M images from the page to be identified, or only N images from the page to be identified that are allowed to be exported. The image selected by the user can be enlarged and displayed in the image viewer, while other images are displayed as thumbnails. Of course, the way the image viewer displays images can be flexibly configured. Figure 5 Figure (B) is for illustrative purposes only and should not be construed as limiting the scope of this application.

[0107] 102. The terminal device sends a target text identifier to the server so that the server can determine the target image set identification information based on the target text identifier;

[0108] In this embodiment, after receiving the image viewing instruction, the terminal device can also send a target text identifier to the server. The image viewing instruction carries the target text identifier corresponding to the target text, and the target text and the target text identifier have a unique correspondence. For the server, after receiving the image viewing instruction, it can parse it to obtain the target text identifier.

[0109] The server can first look up the target image set recognition information based on the target text identifier. This target image set recognition information can be a recognition information for all images on the page to be recognized.

[0110] For example, a target image set identification information of "1" indicates that the M images on the page to be identified meet the image export conditions and can be exported in full. Alternatively, a target image set identification information of "0" indicates that the M images on the page to be identified do not meet the image export conditions and cannot be exported. The above example judges the M images as a whole; therefore, the target image set identification information is only "1" or "0".

[0111] For example, the target image set recognition information may also include image recognition information corresponding to each of the M images. Assuming M is 20, the target image set recognition information includes 20 image recognition pieces. In one case, each image recognition piece can be represented as "1" or "0", where "1" indicates that the image can be exported, and "0" indicates that the image cannot be exported. In another case, each image recognition piece can include features of different dimensions, such as at least one of the image's object category, object name, and keywords.

[0112] 103. If the target image set recognition information meets the image export conditions, the terminal device will display the image set export interface on the image viewer according to the image set export request sent by the server. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0113] In this embodiment, based on the above description, after obtaining the target image set recognition information, the server needs to determine whether the target image set recognition information meets the image export conditions. If the image export conditions are met, the server will send an image set export request to the terminal device. The image set export request indicates that the terminal device is allowed to export the images on the page to be recognized. The terminal device then responds to the image set export request and displays the image set export interface on the image viewer. Conversely, if the image export request is not met, the server can send an image set export failure message to the terminal device. The terminal device can display messages such as "Images on this page cannot be exported" or "Illegal content exists on this page, cannot be exported."

[0114] For example, if the target image set identification information is "1", meaning the image export conditions are met, the server can send an image set export request to the terminal device. The image set export request indicates that N images can be exported, where N=M. If the target image set identification information is "0", meaning the image export conditions are not met, the server can send an image set export failure message to the terminal device.

[0115] For example, if the target image set identification information determines that N images have identification information of "1", meaning the image export condition is met, then the server can send an image set export request to the terminal device. The image set export request indicates that N images can be exported, where N ≤ M. If the target image set identification information determines that M images have identification information of "0", meaning the image export condition is not met, then the server can send an image set export failure message to the terminal device.

[0116] It is understood that the above method for determining whether the target image set recognition information meets the image export conditions is only an illustration. In actual practice, other methods can also be used for judgment, which will be explained in subsequent embodiments.

[0117] 104. When an operation targeting the image atlas export interface is detected, the terminal device will export N images from the page to be recognized as files corresponding to the target format.

[0118] In this embodiment, if the target image set recognition information meets the image export conditions, the terminal device will export the image set according to the image set export request sent by the server. For ease of explanation, please refer to [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of an image viewer interface that meets the image export conditions in this embodiment of the application. As shown in the figure, K1 indicates the image set export interface. When the user triggers an operation on the image set export interface (e.g., single click, double click, or long press), the terminal device can respond to the user's operation and export N images from the page to be recognized as files corresponding to the target format. It should be noted that the target format includes, but is not limited to, image formats, portable document formats (PDF), spreadsheet formats (Excel), word processing formats (Word), and video formats.

[0119] If the target image set recognition information does not meet the image export conditions, the image set export interface will not be displayed in the image viewer, meaning the user cannot export the images from the page to be recognized. For a clearer explanation, please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of an image viewer interface in an embodiment of this application where the image export conditions are not met. As shown in the figure, only M images on the page to be identified are displayed on the image viewer, but these images cannot be exported.

[0120] This application provides an AI-based image export method. When an image viewing instruction is received for a page to be recognized, the terminal device displays M images contained in the page through an image viewer and sends a target text identifier to the server. The server then determines the target image set recognition information based on the target text identifier. If the target image set recognition information meets the image export conditions, the terminal device displays an image set export interface on the image viewer. When an operation targeting the image set export interface is detected, the terminal device exports N images from the page to be recognized as files corresponding to the target format. This method intelligently decides whether images on the page can be exported based on the target image set recognition information, thereby increasing the rationality of data export. When it is determined that the image set can be exported, a one-click export method is used to directly export the images on the page as files corresponding to the target format, eliminating the need for the user to save each image on the page, thus improving the efficiency of image export.

[0121] Optionally, in the above Figure 3 Based on the corresponding embodiments, in an optional embodiment provided by this application, when an operation targeting the image atlas export interface is detected, the terminal device exports N images from the page to be recognized as files corresponding to the target format, specifically including the following steps:

[0122] When an operation targeting the atlas export interface is detected, the terminal device displays the first export interface and the second export interface;

[0123] If an operation targeting the first export interface is detected, the terminal device will export the N images on the page to be identified as files corresponding to the image format.

[0124] If an operation targeting the second export interface is detected, the terminal device will export the N images on the page to be identified as files corresponding to the portable document format PDF.

[0125] This embodiment introduces a method for exporting images to different file formats. To improve the convenience of images for users, the images of the target text can be exported and saved to PDF or image files, making it easier for users to find images under the target text.

[0126] Specifically, when a user triggers an operation on the atlas export interface (e.g., a single click, double click, or long press), the terminal device responds to the user's action and then displays the first export interface and the second export interface. For easier understanding, please refer to [link to relevant documentation]. Figure 8 , Figure 8This is a schematic diagram illustrating the first and second export interfaces in an embodiment of this application. As shown in the figure, K2 indicates the first export interface. When a user triggers an operation through the first export interface, the terminal device can export N images from the page to be recognized as files corresponding to the image format. K3 indicates the second export interface. When a user triggers an operation through the second export interface, the terminal device can export N images from the page to be recognized as files corresponding to the PDF format. K4 indicates the "Save" button. After clicking the "Save" button, the user can save the image format file or the PDF format file. K5 indicates the "Share" button. After clicking the "Share" button, the user can share the image format file or the PDF format file with their friends or share it on other social media platforms. K6 indicates the "Cancel" button. After clicking the "Cancel" button, the user can cancel the image export operation, exit the image viewer, and return to the browser interface (or the interface of other clients).

[0127] Please see Figure 9 , Figure 9 This is a schematic diagram illustrating the export of images as image files in an embodiment of this application. As shown in the figure, N images can be stored in the local photo album of the terminal device, and the user can view the exported images in the album. Image formats include, but are not limited to, bitmap (BMP) format, graphics interchange format (GIF), joint photographic expert group (JPEG) format, and portable network graphics (PNG) format, etc., and are not limited here.

[0128] Please see Figure 10 , Figure 10 This is a schematic diagram illustrating the export of images into a portable document format file in an embodiment of this application. As shown in the figure, N images can be exported as a PDF file. After opening the PDF file, the images can be viewed, and page turning or scaling operations can be performed.

[0129] Secondly, this application provides a method for exporting images to different file formats. Using this method, users can choose the export format based on their needs. For example, if a user wants to export a single image, they can choose to export it as an image format, making it convenient to view and use a single image later. Alternatively, if a user wants to view and use images collectively, they can choose to export them as a PDF, allowing them to easily access or view images all at once, thus improving the flexibility of image processing.

[0130] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, N is an integer greater than 1;

[0131] When an operation targeting the image atlas export interface is detected, the terminal device exports N images from the page to be recognized as files corresponding to the target format, specifically including the following steps:

[0132] When an operation targeting the image atlas export interface is detected, the terminal device receives the image sorting results for N images sent by the server.

[0133] The terminal device exports the sorted N images into files corresponding to the image format based on the image sorting results.

[0134] This embodiment introduces a method for exporting images in sequence, where the exported file can display the N exported images in a certain order. When N equals 1, it is not necessary to aggregate and sort one image. Therefore, this embodiment will use the case where N is greater than 1 as an example for explanation. When the server determines that the target image set recognition information meets the image export conditions, the N images can be sorted.

[0135] Specifically, assume there are 12 images on the page to be identified, i.e., M=12. After determining that the target image set recognition information meets the image export conditions, the number of exportable images can be further determined. Assume there are 8 exportable images, i.e., N=8. Each image has corresponding image recognition information, and each image has an image identifier. For clarity, please refer to Table 1, which illustrates the relationship between images and image identifiers.

[0136] Table 1

[0137] Image A 0000 Transportation Image B 0001 plant Image C 0010 animal Image D 0011 plant Image E 0100 Transportation Image F 0101 plant Image G 0110 Transportation Image H 0111 animal

[0138] As shown in Table 1, the image recognition information can be object categories. These eight images are sorted based on their object categories, grouping images of the same category together. The image identifiers are then output to the terminal device sequentially, which exports the corresponding images according to these identifiers. For clarity, please refer to Table 2, which illustrates the image sorting results generated based on the image recognition information shown in Table 1.

[0139] Table 2

[0140] First picture Image A 0000 Transportation Second picture Image E 0100 Transportation The third one Image G 0110 Transportation Fourth Image B 0001 plant Fifth Image D 0011 plant Sixth Image F 0101 plant Seventh Image C 0010 animal Eighth Image H 0111 animal

[0141] Based on this, the terminal device displays N images in the order of their identifiers: "0000", "0100", "0110", "0001", "0011", "0101", "0010", and "0111". Figure 11 For example, Figure 11 This is a schematic diagram of the sequential export of images from a portable document format file in an embodiment of this application. As shown in the figure, the images presented on the PDF file are three images related to "vehicles".

[0142] Secondly, this application provides a method for exporting images in sequence. Through the above method, during the image export process, images can be intelligently aggregated and sorted according to the image recognition results of each image. This is reflected in the exported file by grouping images of the same category and with higher relevance together, making it easier for users to find the corresponding images in the file, thereby improving the flexibility and practicality of image export.

[0143] Optionally, in the above Figure 3 Based on the corresponding embodiments, another optional embodiment provided in this application further includes the following steps:

[0144] If the target image set recognition information meets the image export conditions, the terminal device will display N images through the image viewer;

[0145] When an operation targeting K images is detected, the terminal device exports the K images from the page to be identified into a file corresponding to the target format. The K images are contained within N images, and K is an integer greater than or equal to 1 and less than or equal to K.

[0146] This embodiment introduces a method for manually selecting several images to be exported. The image viewer can display M images from the page to be identified, or only N images from the page to be identified that are allowed to be exported. Since N is a value less than or equal to M, it is understandable that when the terminal device displays N images through the image viewer, it can also display the remaining (MN) images. The remaining (MN) images can be displayed in grayscale, highlighted in other ways, or displayed in a way indistinguishable from the N images; no limitation is made here.

[0147] Specifically, if the target image set recognition information meets the image export conditions, then the terminal device displays N images through an image viewer. For clarity, please refer to [link to relevant documentation]. Figure 12 , Figure 12Figure (A) illustrates a manual selection of images for export in an embodiment of this application. K7 indicates a selection box. If a user clicks the selection box below an image, it means that the user has selected to export that image. For example, if the user selects the first and second images but not the third, the exported PDF file will display the first and second images, but not the third. In other words, even if the third image can be exported, the user's actual selection will be prioritized.

[0148] Secondly, this application embodiment provides a method for manually selecting several images to be exported. Through the above method, users can also select K images as the objects to be exported in the image viewer, thereby increasing the flexibility and freedom of image export and better meeting the user's needs for image export.

[0149] Based on the above introduction, the AI-based image export method in this application will be described from the server's perspective below. Please refer to [link / reference]. Figure 13 Another embodiment of the AI-based image export method in this application includes:

[0150] 201. The server receives a target text identifier for the page to be identified sent by the terminal device. The target text identifier is used to indicate the target text included in the page to be identified. The page to be identified contains M images, where M is an integer greater than or equal to 1.

[0151] In this embodiment, the page to be identified is displayed on a browser or other client on the terminal device. Specifically, taking a browser installed on the terminal device as an example, the browser can display the target text and images on the page to be identified. The target text may include a title and body text, and the number of images is M, where M is an integer greater than or equal to 1. The target files in the browser are crawled from third-party web pages and stored in a database on the server.

[0152] Users can view images on the page to be recognized. If a user is interested in a particular image, they can long-press or double-tap it to trigger an image viewing command. The terminal device responds to the image viewing command by launching the image viewer in the client. The image viewer can display M images from the page to be recognized, or only N images from the page that are allowed to be exported. The selected image can be enlarged in the image viewer, while other images are displayed as thumbnails.

[0153] After receiving an image viewing instruction, the terminal device can also send the image viewing instruction to the server. The image viewing instruction carries the target text identifier corresponding to the target text. There is a unique correspondence between the target text and the target text identifier. For the server, after receiving the image viewing instruction, it can parse it to obtain the target text identifier.

[0154] 202. The server determines the target image set recognition information based on the target text identifier;

[0155] In this embodiment, the server can search for target image set identification information based on the target text identifier. The target image set identification information can be identification information for all images on the page to be identified.

[0156] For example, a target image set identification information of "1" indicates that the M images on the page to be identified meet the image export conditions and can be exported in full. Alternatively, a target image set identification information of "0" indicates that the M images on the page to be identified do not meet the image export conditions and cannot be exported. The above example judges the M images as a whole; therefore, the target image set identification information is only "1" or "0".

[0157] For example, the target image set recognition information may also include image recognition information corresponding to each of the M images. Assuming M is 20, the target image set recognition information includes 20 image recognition pieces. In one case, each image recognition piece can be represented as "1" or "0", where "1" indicates that the image can be exported, and "0" indicates that the image cannot be exported. In another case, each image recognition piece can include features of different dimensions, such as at least one of the image's object category, object name, and keywords.

[0158] 203. If the target image set recognition information meets the image export conditions, the server sends an image set export request to the terminal device, so that the terminal device displays the image set export interface on the image viewer according to the image set export request sent by the server. When the terminal device detects the operation for the image set export interface, it exports N images in the page to be recognized as files corresponding to the target format. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0159] In this embodiment, based on the above description, after obtaining the target image set recognition information, the server needs to determine whether the target image set recognition information meets the image export conditions. If the image export conditions are met, the server will send an image set export request to the terminal device. The image set export request indicates that the terminal device is allowed to export the images on the page to be recognized. The terminal device then responds to the image set export request and displays the image set export interface on the image viewer. Conversely, if the image export request is not met, the server can send an image set export failure message to the terminal device. The terminal device can display messages such as "Images on this page cannot be exported" or "Illegal content exists on this page, cannot be exported."

[0160] For example, if the target image set identification information is "1", meaning the image export condition is met, the server can send an image set export request to the terminal device. This request indicates that N images can be exported, where N = M. If the target image set identification information is "0", meaning the image export condition is not met, the server can send an image set export failure message to the terminal device. For example, if, based on the target image set identification information, N images have identification information of "1", meaning the image export condition is met, the server can send an image set export request to the terminal device. This request indicates that N images can be exported, where N ≤ M. If, based on the target image set identification information, M images have identification information of "0", meaning the image export condition is not met, the server can send an image set export failure message to the terminal device.

[0161] It is understood that the above method for determining whether the target image set recognition information meets the image export conditions is only an illustration. In actual practice, other methods can also be used for judgment, which will be explained in subsequent embodiments.

[0162] If the target image set recognition information meets the image export conditions, the terminal device will respond to the user's operation (e.g., single click, double click, or long press) when the user triggers an operation on the image set export interface, based on the image set export request sent by the server, and export the N images from the page to be recognized as files corresponding to the target format. It should be noted that the target format includes, but is not limited to, image formats, PDF, Excel, Word, and video formats.

[0163] This application provides an AI-based image export method. The server receives a target text identifier for a page to be recognized from a terminal device. Then, it determines target image set recognition information based on the target text identifier. If the target image set recognition information meets the image export conditions, the server sends an image set export request to the terminal device. The terminal device then displays an image set export interface on an image viewer based on the server's request. When the terminal device detects an operation on the image set export interface, it exports N images from the page to be recognized as files corresponding to the target format. This method intelligently decides whether images on a page can be exported based on the target image set recognition information, thereby increasing the rationality of data export. When it is determined that the image set can be exported, a one-click export method is used to directly export the images on the page as files corresponding to the target format, eliminating the need for the user to save each image on the page, thus improving the efficiency of image export.

[0164] Optionally, in the above Figure 13 Based on the corresponding embodiments, in an optional embodiment provided by this application, the server determines the target image set identification information according to the target text identifier, specifically including the following steps:

[0165] If the target text identifier matches the text identifier library, the server obtains the target image set recognition information, which includes the image recognition information corresponding to each of the M images. The text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0166] This embodiment introduces a method for obtaining target image set recognition information based on target text identifiers. Specifically, the server maintains a text identifier library, which stores text identifiers and their corresponding image set recognition information in key-value pairs. Image set recognition information that has already been recognized on a page is directly stored on the server, indexed by the text identifier corresponding to the text on that page.

[0167] Specifically, for ease of explanation, please refer to Table 3, which is a schematic diagram of storing text identifiers and image recognition information based on a text identifier library.

[0168] Table 3

[0169] 1 Image A is "Animals"; Image B is "Animals"; Image C is "Vehicles"; Image D is "Plants"; 2 Image E is "animal"; Image F is "animal"; Image G is "animal"; Image H is "animal"; Image I is "animal"; Image J is "animal"; 3 Image K represents "vehicles"; Image L represents "plants"; Image M represents "vehicles". 4 Image N is "Plant"; Image O is "Animal"; Image P is "Plant"; Image Q is "Plant"; Image R is "Plant"; Image S is "Animal"; Image T is "Plant"; Image U is "Plant"; Image V is "Plant";

[0170] As shown in Table 3, the image recognition information includes the image recognition information for each image on the page. Table 3 uses the example of image recognition information being an object category for illustration. In practice, image recognition information can also include other information, such as object names and keywords. This is only an illustration and should not be construed as a limitation of this application. Here, the key is represented by text, and the value is the image recognition information.

[0171] Based on Table 3, assuming the target text identifier is "3", the text identifier library is hit, and the server can directly obtain the target image set recognition information. This target image set recognition information includes the image recognition information corresponding to each of the M images. At this time, M=3, and the target image set recognition information includes the image recognition information of image K, image L, and image M.

[0172] Secondly, this application provides a method for obtaining target image set recognition information based on target text identifiers. In this method, the server can prioritize matching the target text identifier with text identifiers in the text identifier library. If the match is successful, the image set recognition information corresponding to the text identifier can be directly used as the target image set recognition information. The server does not need to detect each image again. The server can store the image set recognition information locally because the text on the page does not change. After processing once, the next user request can be directly returned, thereby improving processing efficiency and saving processing resources.

[0173] Optionally, in the above Figure 13 Based on the corresponding embodiments, in an optional embodiment provided by this application, the server determines the target image set identification information according to the target text identifier, specifically including the following steps:

[0174] If the target text identifier does not match the text identifier library, the server retrieves M images;

[0175] The server identifies M images to obtain target image set identification information, which includes the image identification information corresponding to each of the M images.

[0176] The server stores the target text identifier and the target image set recognition information into a text identifier library, wherein the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0177] This embodiment introduces a method for storing target image set recognition information in a text tag library. Specifically, the server maintains a text tag library that stores text tags and their corresponding image set recognition information in a key-value format. Image set recognition information that has already been recognized on a page is directly stored on the server, indexed by the text tag corresponding to the text on that page.

[0178] Specifically, taking Table 3 above as an example, assuming the target text identifier is "5", there is no match in the text identifier library. Therefore, the server needs to identify the M images on the page to be identified, obtain the image recognition information corresponding to each image, and use this image recognition information as the target image set recognition information. Then, the server adds the target image set recognition information and the corresponding target text identifier to the text identifier library. For ease of explanation, please refer to Table 4, which is an illustration of the text identifier library obtained after adding the target text identifier and the target image set recognition information.

[0179] Table 4

[0180] 1 Image A is "Animals"; Image B is "Animals"; Image C is "Vehicles"; Image D is "Plants"; 2 Image E is "animal"; Image F is "animal"; Image G is "animal"; Image H is "animal"; Image I is "animal"; Image J is "animal"; 3 Image K represents "vehicles"; Image L represents "plants"; Image M represents "vehicles". 4 Image N is "Plant"; Image O is "Animal"; Image P is "Plant"; Image Q is "Plant"; Image R is "Plant"; Image S is "Animal"; Image T is "Plant"; Image U is "Plant"; Image V is "Plant"; 5 Image W represents "vehicle"; Image X represents "vehicle"; Image Y represents "vehicle"; Image Z represents "vehicle".

[0181] As shown in Table 4, the image recognition information includes the image recognition information for each image on the page. Table 4 uses the example of image recognition information being an object category. In practice, image recognition information can also include other information, such as object names and keywords. This is only an illustration and should not be construed as a limitation of this application. Here, "key" represents the text representation, and "value" represents the image recognition information. Based on Table 4, the image recognition information corresponding to the target text identifier "5" has been added to the text identifier library. If any subsequent terminal device requests the image recognition result on this page, it can directly obtain the image recognition result without secondary recognition.

[0182] Secondly, this application embodiment provides a method for storing target image set recognition information in a text identifier library. Using this method, if the server does not detect the target text identifier in the text identifier library, it is necessary to recognize the image on the page to be recognized to obtain the target image set recognition information. Then, the target image set recognition information and the corresponding target text identifier are stored locally. Because the text on the page does not change, after one processing step, the next user request can be directly returned, thereby improving processing efficiency and saving processing resources.

[0183] Optionally, in the above Figure 13 Based on the corresponding embodiments, in an optional embodiment provided by this application, the server identifies M images to obtain target image set identification information, specifically including the following steps:

[0184] For each of the M images, the server uses an object recognition model to obtain the corresponding image recognition information, which includes at least one of the following: object category, object name, and keywords.

[0185] The server obtains the target image set recognition information based on the image recognition information corresponding to each of the M images.

[0186] This embodiment introduces a method for image recognition. The following will take any one of the M images as an example to illustrate how to obtain the image recognition information of that image. It is understood that the image recognition information of other images is obtained in a similar way, which will not be elaborated here.

[0187] Specifically, the image is input into the object recognition model, which, based on AI recognition algorithms, can identify the object category in the image, such as "plant," "animal," or "vehicle." If the object recognition model is also trained for a specific object category, it can also identify the object name within that category. For example, if the object category is "plant," the identified object name could be "rose," "tulip," "poplar," "willow," or "weed." Similarly, if the object category is "animal," the identified object name could be "dog," "cat," "pig," "chicken," or "elephant." Furthermore, if the object recognition model incorporates keyword recognition during training, it can reflect the keywords in the image. Therefore, image recognition information includes at least one of the following: object category, object name, and keyword. More specifically, this information is represented by a triple: (object type, object name [optional], keyword [optional]).

[0188] For ease of explanation, please refer to Table 5, which is a schematic diagram of target atlas identification information.

[0189] Table 5

[0190] Image W Transportation bus Coin Image X Transportation taxi Payment Image Y Transportation truck pass Image Z Transportation bus platform

[0191] As shown in Table 5, taking four images as an example, the target image set recognition information includes the image recognition information corresponding to each of the four images, and each image recognition information is represented as a triplet.

[0192] It should be noted that the network structure of the object recognition model can be Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), or Support Vector Machines (SVM), etc., and there is no limitation here.

[0193] Furthermore, in this embodiment of the application, a method for recognizing images is provided. Through the above method, an object recognition model can be used to obtain image recognition information for each image. The image recognition information includes at least one of object category, object name, and keywords. The object category can intuitively reflect the content of the image, the object name can represent the concrete content of the image, and the keywords can represent the image as a concrete concept. Therefore, intelligent processing can be achieved based on the image recognition information.

[0194] Optionally, in the above Figure 13 Based on the corresponding embodiments, in an optional embodiment provided by this application, the target image set recognition information includes the image recognition information corresponding to each of the M images;

[0195] After the server determines the target image set recognition information based on the target text identifier, the following steps are also included:

[0196] If the correlation between the image recognition information of N images and the target text satisfies the image-text matching condition, and the image recognition information of N images satisfies the information security condition, then the server determines that the target image set recognition information satisfies the image export condition, wherein the N images are contained in the M images;

[0197] or,

[0198] If the correlation between the image recognition information of N images and the target text meets the image-text matching condition, then the server determines that the target image set recognition information meets the image export condition.

[0199] or,

[0200] If the image recognition information of N images meets the information security requirements, then the server determines that the image set recognition information meets the image export requirements.

[0201] This embodiment introduces a method for determining whether the target image set recognition information meets the image export conditions. Since in reality, images on a page may have discrepancies between the image and text or contain sensitive content, each image can be checked before exporting. Images that pass the check can be exported, while those that fail cannot. This application provides three methods for determining whether the target image set recognition information meets the image export conditions. It should be noted that if at least one (i.e., N) of the M images included in the page to be recognized can be exported, it indicates that the target image set recognition information meets the image export conditions. If none of the M images can be exported, it indicates that the target image set recognition information does not meet the image export conditions. Based on this, this application provides three methods to determine whether an image can be exported.

[0202] Method 1: Determine whether an image can be exported based solely on the correlation between the image and text.

[0203] For example, taking the target text and any image interspersed within the target text as an example, the target text can extract corresponding keywords when it is entered into the database. For example, these keywords can be keywords defined by the author of the target text, keywords marked by backend personnel, or keywords extracted using AI recognition technology. There are no limitations here.

[0204] Based on this, the server needs to determine the relevance between the keywords in the target text and the keywords in the image. Specifically, Pointwise Mutual Information (PMI) can be used to calculate the semantic similarity between words. The basic idea is to count the probability that two words appear simultaneously in the text. Assuming the keyword in the target text is word1 and the keyword in the image is word2, the PMI values ​​of word1 and word2 are calculated, thus obtaining PMI(word1&word2).

[0205] PMI (word1 & word2) > 0 indicates that the two keywords are related; the larger the value, the stronger the relevance.

[0206] PMI (word1&word2)=0 indicates that the two keywords are statistically independent, unrelated and not mutually exclusive.

[0207] PMI (word1&word2) < 0 indicates that the two keywords are unrelated and mutually exclusive.

[0208] If the PMI (word1 & word2) is less than a certain threshold, the image-text relevance is considered low, meaning the image does not meet the image-text matching criteria. Conversely, if the PMI (word1 & word2) is greater than or equal to a certain threshold, the image-text relevance is considered high, meaning the image meets the image-text matching criteria.

[0209] Method 2: Determine whether an image can be exported based solely on its sensitivity.

[0210] For example, taking target text and any image interspersed within the target text as an example, after obtaining the image recognition information of the image, it is analyzed whether the content of the image recognition information meets the information security conditions. If the image recognition information contains sensitive content, it does not meet the information security conditions.

[0211] If the object category included in the image recognition information is "laws", it may involve sensitive content, which means it does not meet the information security requirements.

[0212] If the object name included in the image recognition information is "a certain regulation", it may involve sensitive content, that is, it does not meet the information security requirements.

[0213] If the keyword included in the image recognition information is "policy", it may involve sensitive content, which means it does not meet the information security requirements.

[0214] Method 3: Consider both the relevance of the image and text, as well as the sensitivity of the image, to determine whether the image can be exported;

[0215] It is understandable that for considering the correlation between images and text, please refer to Method 1 above; for considering the sensitivity of images, please refer to Method 2 above. If both the image and text matching conditions and the information security conditions are met, it means that the image can be exported.

[0216] For clarity, the following example uses any one of the M images to illustrate how to determine if that image can be exported. It's understood that other images are determined using a similar method, which will not be elaborated upon here; please refer to [link to relevant documentation]. Figure 14 , Figure 14 This is a flowchart illustrating a process for determining whether an image set meets the image export conditions in an embodiment of this application. Specifically:

[0217] In step A1, the image recognition information corresponding to the image is obtained, which includes the object category, object name, and keywords;

[0218] In step A2, the security monitoring process is initiated, and the image recognition information of each image is detected using the method described in Method 2 above.

[0219] In step A3, the detection process includes determining whether the image recognition information involves sensitive content. If it does, the information security conditions are not met. If it does not involve sensitive content, the information security conditions are met.

[0220] In step A4, if the information security conditions are met, then the image can be exported;

[0221] In step A5, the keywords of the target text are obtained; the method of obtaining them will not be described in detail here.

[0222] In step A6, the relevance between the keywords of the image and the keywords of the target text is determined. If the relevance is high, the image-text matching condition is met; if the relevance is low, the image-text matching condition is not met.

[0223] In step A7, if the image and text matching conditions are met, it means that the image can be exported;

[0224] In step A8, once the server determines that N images out of the M images meet both the image-text matching condition and the information security condition, it can send an image set export request to the terminal device.

[0225] Furthermore, in this embodiment, a method is provided for determining whether the target image set identification information meets the image export conditions. This method better enables the intelligent image export function. Firstly, considering the correlation between the image and text, if the image and text are severely mismatched, the image can be considered not to meet the image export conditions and will not be exported, thus improving the reasonableness of the exported images. Secondly, considering sensitive content, non-compliant images are considered not to meet the image export conditions, which can effectively control the spread of illegal images and help maintain a healthy network environment.

[0226] Optionally, in the above Figure 13 Based on the corresponding embodiments, in an optional embodiment provided by this application, N is an integer greater than 1;

[0227] After the server determines the target image set recognition information based on the target text identifier, the following steps are also included:

[0228] If the target image set recognition information meets the image export conditions, the server will perform clustering processing on the N images based on the image recognition information corresponding to each image in the N images, and obtain the clustered N images.

[0229] The server determines the correlation between each image and the target text based on the target text and the image recognition information corresponding to each of the N images.

[0230] The server sorts the N clustered images in descending order of their relevance, thus obtaining the image sorting result;

[0231] The server sends the image sorting results to the terminal device so that when the terminal device detects an operation on the image set export interface, it can export the sorted N images into files corresponding to the image format based on the image sorting results.

[0232] This embodiment introduces a method for intelligently sorting images to be exported. First, the images can be clustered based on the object categories. Then, based on the keywords of the target text and the keywords of the images, the clustered results are sorted according to their relevance to the target text. The greater the relevance between the images and the target text, the higher they are ranked. After sorting, the images can also be aggregated according to the object names. Finally, the images are exported as files in the target format.

[0233] Specifically, the exported file can display these N exported images in a certain order. When N equals 1, it is not necessary to aggregate and sort one image. Therefore, this embodiment will be described using the case where N is greater than 1 as an example. When the server determines that the target image set recognition information meets the image export conditions, the N images can be sorted. Assume there are 12 images on the page to be recognized, i.e., M=12. When it is determined that the target image set recognition information meets the image export conditions, the number of exportable images can be further determined. Assume there are 8 exportable images, i.e., N=8. Each image has corresponding image recognition information, including object category, object name, and keywords, and each image has an image identifier. For ease of explanation, please refer to Table 6, which illustrates the association between images and image identifiers.

[0234] Table 6

[0235] Image A 0000 Transportation bus 0.2 Image B 0001 plant Rose 0.5 Image C 0010 animal sheep 0.6 Image D 0011 plant tulip 0.1 Image E 0100 Transportation truck 0.7 Image F 0101 plant tulip 0.4 Image G 0110 Transportation taxi 0.3 Image H 0111 animal dog 0.9

[0236] Based on Table 6, we first perform clustering on objects of the same category to obtain N clustered images. For easier understanding, please refer to Table 7, which is a schematic of the N clustered images.

[0237] Table 7

[0238] Image A 0000 Transportation bus 0.2 Image E 0100 Transportation truck 0.7 Image G 0110 Transportation taxi 0.3 Image B 0001 plant Rose 0.5 Image D 0011 plant tulip 0.1 Image F 0101 plant tulip 0.4 Image C 0010 animal sheep 0.6 Image H 0111 animal dog 0.9

[0239] Based on Table 7, the N clustered images are then sorted in descending order of correlation to obtain the image sorting results. Please refer to Table 8, which is an illustration of the image sorting results obtained after sorting.

[0240] Table 8

[0241] Image E 0100 Transportation truck 0.7 Image G 0110 Transportation taxi 0.3 Image A 0000 Transportation bus 0.2 Image B 0001 plant Rose 0.5 Image F 0101 plant tulip 0.4 Image D 0011 plant tulip 0.1 Image H 0111 animal dog 0.9 Image C 0010 animal sheep 0.6

[0242] At this time, you can follow Figure 8 The image sorting results shown are used to export corresponding images. The terminal device displays N images in the order of image identifiers "0100", "0110", "0000", "0001", "0101", "0011", "0111", and "0010". Optionally, images with the same object name are further clustered. For example, images F and D are both "Tulips", so they can be grouped together.

[0243] For clarity, please refer to Figure 15 , Figure 15 This is a flowchart illustrating the sorting of the atlas in an embodiment of this application, as shown in the figure. Specifically:

[0244] In step B1, the image recognition information for each of the N images is first obtained;

[0245] In step B2, the images are clustered according to the object categories included in the image recognition information, thereby obtaining N clustered images;

[0246] In step B3, the correlation between each image and the target text is obtained, and then the N clustered images are sorted in descending order of correlation to obtain the image sorting result;

[0247] In step B4, images with the same object name can be grouped together to obtain the final image sorting result.

[0248] In step B5, the server sends the image sorting results back to the terminal device. When the terminal device detects an operation on the image set export interface, it exports the sorted N images into files corresponding to the image format based on the image sorting results.

[0249] Secondly, this application provides a method for intelligently sorting images to be exported. Through the above method, during the image export process, images can be intelligently aggregated and sorted according to the image recognition results of each image. This is reflected in the exported file by grouping images of the same category and with higher relevance together, making it easier for users to find the corresponding images in the file, thereby improving the flexibility and practicality of image export.

[0250] The following is a detailed description of an image exporting device in this application. Please refer to [link / reference]. Figure 16 , Figure 16 This is a schematic diagram of one embodiment of the image exporting device in this application. The image exporting device 30 includes:

[0251] The display module 301 is used to display M images contained in the page to be identified through an image viewer when an image viewing instruction for the page to be identified is obtained. The image viewing instruction carries a target text identifier, which is used to indicate the target text contained in the page to be identified. M is an integer greater than or equal to 1.

[0252] The sending module 302 is used to send a target text identifier to the server so that the server can determine the target image set identification information based on the target text identifier;

[0253] The display module 301 is also used to display the image set export interface on the image viewer according to the image set export request sent by the server if the target image set recognition information meets the image export conditions. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0254] The export module 303 is used to export N images from the page to be recognized as files corresponding to the target format when an operation targeting the image export interface is detected.

[0255] This application provides an AI-based image export device. Using this device, the system intelligently decides whether images on a page can be exported based on target image set recognition information, thereby increasing the rationality of data export. If it is determined that the image set can be exported, a one-click export method is used to directly export the images on the page as files corresponding to the target format, eliminating the need for the user to save each image on the page, thus improving the efficiency of image export.

[0256] Optionally, in the above Figure 16 Based on the corresponding embodiments, in another embodiment of the image exporting device 30 provided in this application,

[0257] The export module 303 is specifically used to display the first export interface and the second export interface when an operation targeting the atlas export interface is detected.

[0258] If an operation targeting the first export interface is detected, then the N images on the page to be identified will be exported as files corresponding to the image format.

[0259] If an operation targeting the second export interface is detected, the N images on the page to be identified will be exported as files corresponding to the portable document format PDF.

[0260] Secondly, this application provides an apparatus for exporting images into different file formats. Using this apparatus, users can choose the format of the exported images according to their needs. For example, if a user wants to export a single image, they can choose to export it as an image format, which facilitates subsequent viewing and use of individual images. Alternatively, if a user wants to view and use images collectively, they can choose to export them as PDFs, allowing for convenient one-time access or viewing of images, thereby improving the flexibility of image processing.

[0261] Optionally, in the above Figure 16 Based on the corresponding embodiments, in another embodiment of the image exporting device 30 provided in this application, N is an integer greater than 1;

[0262] The export module 303 is specifically used to receive the image sorting results for N images sent by the server when an operation on the image atlas export interface is detected.

[0263] Based on the image sorting results, export the sorted N images into files corresponding to the image format.

[0264] Secondly, this application provides a method for exporting images in sequence. Through the above method, during the image export process, images can be intelligently aggregated and sorted according to the image recognition results of each image. This is reflected in the exported file by grouping images of the same category and with higher relevance together, making it easier for users to find the corresponding images in the file, thereby improving the flexibility and practicality of image export.

[0265] Optionally, in the above Figure 16 Based on the corresponding embodiments, in another embodiment of the image exporting device 30 provided in this application,

[0266] The display module 301 is also used to display N images through an image viewer if the target image set recognition information meets the image export conditions;

[0267] The export module 303 is also used to export the K images in the page to be identified as a file corresponding to the target format when an operation on K images is detected. Here, the K images are contained in N images, and K is an integer greater than or equal to 1 and less than or equal to K.

[0268] Secondly, this application embodiment provides a method for manually selecting several images to be exported. Through the above method, users can also select K images as the objects to be exported in the image viewer, thereby increasing the flexibility and freedom of image export and better meeting the user's needs for image export.

[0269] The following is a detailed description of another image exporting device in this application. Please refer to [link / reference]. Figure 17 , Figure 17 This is a schematic diagram of another embodiment of the image exporting device in this application. The image exporting device 40 includes:

[0270] The receiving module 401 is used to receive the target text identifier for the page to be identified sent by the terminal device. The target text identifier is used to indicate the target text included in the page to be identified. The page to be identified contains M images, where M is an integer greater than or equal to 1.

[0271] The determination module 402 is used to determine the target image set recognition information based on the target text identifier;

[0272] The sending module 403 is used to send an image set export request to the terminal device if the target image set recognition information meets the image export conditions, so that the terminal device can display the image set export interface on the image viewer according to the image set export request sent by the server. When the terminal device detects the operation on the image set export interface, it exports N images in the page to be recognized as files corresponding to the target format. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0273] This application provides an AI-based image export device. Using this device, the system intelligently decides whether images on a page can be exported based on target image set recognition information, thereby increasing the rationality of data export. If it is determined that the image set can be exported, a one-click export method is used to directly export the images on the page as files corresponding to the target format, eliminating the need for the user to save each image on the page, thus improving the efficiency of image export.

[0274] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the image exporting device 40 provided in this application,

[0275] The determination module 402 is specifically used to obtain target image set recognition information if the target text identifier matches the text identifier library. The target image set recognition information includes the image recognition information corresponding to each of the M images, and the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0276] Secondly, in this application embodiment, a device for obtaining target image set recognition information based on target text identifier is provided. Using the above device, the server can preferentially use the target text identifier to match the text identifier in the text identifier library. If the match is successful, the image set recognition information corresponding to the text identifier can be directly used as the target image set recognition information. The server does not need to detect each image again. The server can store the image set recognition information locally because the text on the page does not change. After processing once, the next user request can be directly returned, thereby improving processing efficiency and saving processing resources.

[0277] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the image exporting device 40 provided in this application,

[0278] The determination module 402 is specifically used to obtain M images if the target text identifier does not match the text identifier library;

[0279] The target image set recognition information is obtained by recognizing M images, which includes the image recognition information corresponding to each of the M images.

[0280] The target text identifier and target image set recognition information are stored in a text identifier library, wherein the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

[0281] Secondly, in this embodiment, an apparatus for storing target image set recognition information in a text identifier library is provided. Using this apparatus, if the server does not detect the target text identifier in the text identifier library, it is necessary to recognize the image on the page to be recognized to obtain the target image set recognition information. The target image set recognition information and the corresponding target text identifier are then stored locally. Because the text on the page does not change, after one processing step, the next user request can be directly returned, thereby improving processing efficiency and saving processing resources.

[0282] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the image exporting device 40 provided in this application,

[0283] The determination module 402 is specifically used to obtain the image recognition information corresponding to each of the M images through an object recognition model. The image recognition information includes at least one of the following: object category, object name, and keywords.

[0284] Based on the image recognition information corresponding to each of the M images, obtain the target image set recognition information.

[0285] Furthermore, in this embodiment of the application, an apparatus for recognizing images is provided. Using the above apparatus, an object recognition model can be used to obtain image recognition information for each image. The image recognition information includes at least one of object category, object name, and keywords. The object category can intuitively reflect the content of the image, the object name can represent the concrete content of the image, and the keywords can represent the image as a concrete concept. Therefore, intelligent processing can be achieved based on the image recognition information.

[0286] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the image exporting device 40 provided in this application, the target image set recognition information includes the image recognition information corresponding to each of the M images;

[0287] The determination module 402 is further configured to determine the target image set recognition information after determining the target image set recognition information based on the target text identifier. If the correlation between the image recognition information of N images and the target text satisfies the image-text matching condition, and the image recognition information of N images satisfies the information security condition, then the target image set recognition information satisfies the image export condition, wherein the N images are contained in the M images.

[0288] or,

[0289] After determining the target image set recognition information based on the target text identifier, if the correlation between the image recognition information of N images and the target text meets the image-text matching condition, then the target image set recognition information meets the image export condition.

[0290] or,

[0291] After determining the target image set recognition information based on the target text identifier, if the image recognition information of N images meets the information security conditions, then the target image set recognition information meets the image export conditions.

[0292] Furthermore, in this embodiment of the application, a device is provided for determining whether the target image set identification information meets the image export conditions. Using this device, the function of intelligent image export can be better realized. On the one hand, considering the correlation between images and text, if the images and text are severely mismatched, the image can be considered not to meet the image export conditions and will not be exported, thus improving the rationality of the exported images. On the other hand, considering sensitive content, non-compliant images are considered not to meet the image export conditions, which can also effectively control the spread of illegal images and help maintain a good network environment.

[0293] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the image exporting device 40 provided in this application, N is an integer greater than 1;

[0294] The image exporting device 40 also includes a processing module 404;

[0295] The processing module 404 is used to determine the target image set recognition information based on the target text identifier. If the target image set recognition information meets the image export conditions, then the N images are clustered based on the image recognition information corresponding to each image in the N images to obtain the clustered N images.

[0296] The determination module 402 is also used to determine the correlation between each image and the target text based on the target text and the image recognition information corresponding to each image in the N images;

[0297] Processing module 404 is also used to sort the clustered N images in descending order of their correlation degree to obtain the image sorting result;

[0298] The sending module 403 is also used to send the image sorting results to the terminal device so that when the terminal device detects an operation on the image set export interface, it can export the sorted N images as files corresponding to the image format according to the image sorting results.

[0299] Secondly, this application provides an apparatus for intelligently sorting images to be exported. Using the above apparatus, during the image export process, images can be intelligently aggregated and sorted according to the image recognition results of each image. This is reflected in the exported file by grouping images of the same category and with higher relevance together, making it easier for users to find the corresponding images in the file, thereby improving the flexibility and practicality of image export.

[0300] This application also provides another image exporting device, such as... Figure 18 As shown, for ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. Taking a mobile phone as an example as the terminal device:

[0301] Figure 18 This diagram illustrates a partial structural representation of a mobile phone related to the terminal device provided in this embodiment. (Reference) Figure 18 The mobile phone includes components such as a radio frequency (RF) circuit 510, a memory 520, an input unit 530, a display unit 540, a sensor 550, an audio circuit 560, a wireless fidelity (WiFi) module 570, a processor 580, and a power supply 590. Those skilled in the art will understand that... Figure 18 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0302] The following is combined with Figure 18 A detailed introduction to each component of a mobile phone:

[0303] RF circuit 510 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with processor 580; additionally, it transmits uplink data to the base station. Typically, RF circuit 510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), and a duplexer. Furthermore, RF circuit 510 can also communicate wirelessly with networks and other devices. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Message Service (SMS).

[0304] The memory 520 can be used to store software programs and modules. The processor 580 executes various mobile phone functions and data processing by running the software programs and modules stored in the memory 520. The memory 520 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 520 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0305] The input unit 530 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 530 may include a touch panel 531 and other input devices 532. The touch panel 531, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 531), and drive the corresponding connected devices according to a pre-set program. Optionally, the touch panel 531 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 580, and can receive and execute commands sent by the processor 580. In addition, the touch panel 531 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 531, the input unit 530 may also include other input devices 532. Specifically, other input devices 532 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0306] The display unit 540 can be used to display information input by the user or information provided to the user, as well as various menus of the mobile phone. The display unit 540 may include a display panel 541, which may optionally be configured as a liquid crystal display (LCD), organic light-emitting diode (OLED), or similar form. Further, a touch panel 531 may cover the display panel 541. When the touch panel 531 detects a touch operation on or near it, it transmits the information to the processor 580 to determine the type of touch event. Subsequently, the processor 580 provides corresponding visual output on the display panel 541 according to the type of touch event. Although in Figure 18 In this embodiment, the touch panel 531 and the display panel 541 are two separate components to realize the input and output functions of the mobile phone. However, in some embodiments, the touch panel 531 and the display panel 541 can be integrated to realize the input and output functions of the mobile phone.

[0307] The mobile phone may also include at least one sensor 550, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 541 according to the ambient light level, and the proximity sensor can turn off the display panel 541 and / or backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0308] Audio circuit 560, speaker 561, and microphone 562 provide an audio interface between the user and the mobile phone. Audio circuit 560 converts received audio data into electrical signals and transmits them to speaker 561, where speaker 561 converts them into sound signals for output. On the other hand, microphone 562 converts collected sound signals into electrical signals, which are received by audio circuit 560, converted into audio data, and then output to processor 580 for processing. The audio data is then transmitted via RF circuit 510 to, for example, another mobile phone, or output to memory 520 for further processing.

[0309] WiFi is a short-range wireless transmission technology. Through the WiFi module 570, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 18 WiFi module 570 is shown, but it is understood that it is not an essential component of a mobile phone and can be omitted as needed without changing the essence of the invention.

[0310] The processor 580 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 520, and by calling data stored in the memory 520. Optionally, the processor 580 may include one or more processing units; optionally, the processor 580 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may also not be integrated into the processor 580.

[0311] The phone also includes a power supply 590 (such as a battery) that supplies power to various components. Optionally, the power supply can be logically connected to the processor 580 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0312] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0313] In this embodiment of the application, the processor 580 included in the terminal device also has the following functions:

[0314] When an image viewing instruction is received for the page to be identified, the M images contained in the page to be identified are displayed through the image viewer. The image viewing instruction carries a target text identifier, which is used to indicate the target text contained in the page to be identified. M is an integer greater than or equal to 1.

[0315] Send the target text identifier to the server so that the server can determine the target atlas identification information based on the target text identifier;

[0316] If the target image set recognition information meets the image export conditions, then according to the image set export request sent by the server, the image set export interface is displayed on the image viewer. The image set export interface is used to export N images out of M images, where N is an integer greater than or equal to 1 and less than or equal to M.

[0317] When an operation targeting the image atlas export interface is detected, N images from the page to be identified will be exported as files corresponding to the target format.

[0318] Figure 19 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 600 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 622 (e.g., one or more processors) and memory 632, and one or more storage media 630 (e.g., one or more mass storage devices) for storing application programs 642 or data 644. The memory 632 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the server. Furthermore, the CPU 622 may be configured to communicate with the storage media 630 and execute the series of instruction operations in the storage media 630 on the server 600.

[0319] Server 600 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input / output interfaces 658, and / or one or more operating systems 641, such as Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0320] The steps performed by the server in the above embodiments can be based on this Figure 19 The server structure shown.

[0321] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

[0322] This application also provides a computer program product including a program, which, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

[0323] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0324] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0325] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0326] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0327] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0328] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for exporting images, characterized in that, The method is applied to a terminal device, and the method includes: When an image viewing instruction is received for any image on the page to be identified, a target text identifier for the page to be identified is sent to the server. This allows the server to determine the target image set identification information through the target text identifier and return it to the terminal device. The terminal device is then triggered to display M images contained in the target image set identification information through an image viewer. The webpage to be identified displays target text and images. The target text includes a title and body text. The image viewing instruction is generated when the user views any image on the page to be identified on the user interface of the terminal device. M is an integer greater than or equal to 1. When an image set export request is received, an image set export interface is displayed on the image viewer. The image set export request is used to indicate that the images on the page to be identified that meet the image export conditions are allowed to be exported with one click. The image set export interface is used to export N images out of the M images with one click. N is an integer greater than or equal to 1 and less than or equal to M. The image export conditions include at least one of image-text matching conditions and information security conditions. When an operation targeting the image set export interface is detected, a first export interface and a second export interface are displayed. The first export interface is used to export the N images in the page to be identified as files corresponding to the image format, and the second export interface is used to export the N images in the page to be identified as files corresponding to the portable document format PDF. If an operation targeting the first export interface is detected, the N images in the page to be identified are exported as files corresponding to the image format. If an operation targeting the second export interface is detected, the N images in the page to be identified are exported as files corresponding to the portable document format PDF. The N images have been clustered according to object categories before being exported with one click, and are automatically sorted from largest to smallest according to their relevance to the target text, with images having the same object name arranged adjacently. When an operation targeting K images is detected, the K images on the page to be identified are exported as files corresponding to the target format, wherein the K images are contained in the N images, and K is an integer greater than or equal to 1 and less than or equal to N; After the server determines the target image set identification information through the target text identifier, the method further includes: If the target image set recognition information meets the image export conditions, then based on the image recognition information corresponding to each of the N images, the N images are clustered to obtain the clustered N images. Based on the target text and the image recognition information corresponding to each of the N images, determine the correlation between each image and the target text; The N clustered images are sorted in descending order of their relevance to obtain the image sorting result; The image sorting result is sent to the terminal device so that when the terminal device detects an operation on the image set export interface, it exports the sorted N images as files corresponding to the image format according to the image sorting result.

2. The method according to claim 1, characterized in that, N is an integer greater than 1; When an operation targeting the image atlas export interface is detected, exporting the N images from the page to be identified as files corresponding to the target format includes: When an operation targeting the atlas export interface is detected, the image sorting results for the N images sent by the server are received. Based on the image sorting results, export the sorted N images into files corresponding to the image format.

3. A method for exporting images, characterized in that, The method is applied to a server, and the method includes: The receiving terminal device sends a target text identifier for a page to be identified, wherein the page to be identified displays target text and images, the target text includes a title and body text, the target text identifier is used to indicate the target text included in the page to be identified, the page to be identified contains M images, where M is an integer greater than or equal to 1, the target text identifier is sent by the terminal device when it receives a viewing instruction for any image in the page to be identified, the image viewing instruction is generated when the user views any image in the page to be identified on the user interface of the terminal device; The target image set identification information is determined based on the target text identifier; If the target image set recognition information meets the image export conditions, an image set export request is sent to the terminal device. This allows the terminal device to display an image set export interface on the image viewer based on the server's request. When the terminal device detects an operation on the image set export interface, it exports the N images from the page to be recognized as files corresponding to the target format with a single click. When the terminal device detects an operation on K images, it exports the K images from the page to be recognized as files corresponding to the target format. The K images are included in the N images, where K is an integer greater than or equal to 1 and less than or equal to N. The image set export interface is used to export N images from the M images with a single click, where N is... The target format includes an image format and a portable document identifier. The image set export request is used to indicate that images on the page to be identified that meet the image export conditions are allowed to be exported with one click. The image set export interface includes a first export interface and a second export interface. The first export interface is used to export the N images on the page to be identified as files corresponding to the image format. The second export interface is used to export the N images on the page to be identified as files corresponding to the portable document format PDF. The N images have been clustered according to object categories before being exported with one click, and automatically sorted according to their relevance to the target text from largest to smallest. Images with the same object name are arranged adjacently. After determining the target image set recognition information based on the target text identifier, the method further includes: If the target image set recognition information meets the image export conditions, then based on the image recognition information corresponding to each of the N images, the N images are clustered to obtain the clustered N images. Based on the target text and the image recognition information corresponding to each of the N images, determine the correlation between each image and the target text; The N clustered images are sorted in descending order of their relevance to obtain the image sorting result; The image sorting result is sent to the terminal device so that when the terminal device detects an operation on the image set export interface, it exports the sorted N images as files corresponding to the image format according to the image sorting result.

4. The method according to claim 3, characterized in that, The step of determining the target image set recognition information based on the target text identifier includes: If the target text identifier matches the text identifier library, then the target image set recognition information is obtained, wherein the target image set recognition information includes the image recognition information corresponding to each of the M images, and the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

5. The method according to claim 3, characterized in that, The step of determining the target image set recognition information based on the target text identifier includes: If the target text identifier does not match the text identifier library, then obtain the M images; The M images are identified to obtain the target image set identification information, wherein the target image set identification information includes the image identification information corresponding to each of the M images; The target text identifier and the target image set recognition information are stored in the text identifier library, wherein the text identifier library includes at least one text identifier and image set recognition information corresponding to each text identifier.

6. The method according to claim 5, characterized in that, The process of identifying the M images to obtain the target image set identification information includes: For each of the M images, image recognition information corresponding to the image is obtained through an object recognition model, wherein the image recognition information includes at least one of object category, object name, and keywords; Based on the image recognition information corresponding to each of the M images, the target image set recognition information is obtained.

7. The method according to any one of claims 3 to 6, characterized in that, The target image set recognition information includes the image recognition information corresponding to each of the M images; After determining the target image set recognition information based on the target text identifier, the method further includes: If the correlation between the image recognition information of the N images and the target text satisfies the image-text matching condition, and the image recognition information of the N images satisfies the information security condition, then it is determined that the target image set recognition information satisfies the image export condition, wherein the N images are contained in the M images; or, If the correlation between the image recognition information of the N images and the target text satisfies the image-text matching condition, then it is determined that the target image set recognition information satisfies the image export condition. or, If the image recognition information of the N images meets the information security conditions, then the target image set recognition information is determined to meet the image export conditions.

8. An image exporting device, characterized in that, The device is used in a terminal device, and the device includes: The display module is used to send a target text identifier for the page to be identified to the server when an image viewing instruction is received for any image on the page to be identified. This allows the server to determine the target image set identification information through the target text identifier and return it to the terminal device. The terminal device is then triggered to display M images contained in the target image set identification information through an image viewer. The page to be identified displays target text and images. The target text includes a title and body text. The image viewing instruction is generated when the user views any image on the page to be identified on the user interface of the terminal device. M is an integer greater than or equal to 1. The display module is further configured to, upon receiving an image set export request, display an image set export interface on the image viewer according to the image set export request sent by the server. The image set export request is used to indicate that images that meet the image export conditions on the page to be identified can be exported with one click. The image set export interface is used to export N images out of the M images with one click. N is an integer greater than or equal to 1 and less than or equal to M. The image export conditions include at least one of image-text matching conditions and information security conditions. The export module is used to display a first export interface and a second export interface when an operation targeting the image set export interface is detected. The first export interface is used to export the N images on the page to be recognized as files corresponding to the image format, and the second export interface is used to export the N images on the page to be recognized as files corresponding to the portable document format PDF. If an operation targeting the first export interface is detected, the N images on the page to be recognized are exported as files corresponding to the image format; if an operation targeting the second export interface is detected, the N images on the page to be recognized are exported as files corresponding to the portable document format PDF. The N images have been clustered according to object categories before being exported with one click, and are automatically sorted from highest to lowest relevance to the target text, with images having the same object name arranged adjacently. When an operation targeting K images is detected, the K images on the page to be recognized are exported as files corresponding to the target format, where the K images are included in the N images, and K is an integer greater than or equal to 1 and less than or equal to N. After the server determines the target image set identification information through the target text identifier, the device further includes: If the target image set recognition information meets the image export conditions, then based on the image recognition information corresponding to each of the N images, the N images are clustered to obtain the clustered N images. Based on the target text and the image recognition information corresponding to each of the N images, determine the correlation between each image and the target text; The N clustered images are sorted in descending order of their relevance to obtain the image sorting result; The image sorting result is sent to the terminal device so that when the terminal device detects an operation on the image set export interface, it exports the sorted N images as files corresponding to the image format according to the image sorting result.

9. The image exporting device according to claim 8, characterized in that, The export module is specifically used to display the first export interface and the second export interface when an operation targeting the atlas export interface is detected. If an operation targeting the first export interface is detected, the N images in the page to be identified are exported as files corresponding to the image format. If an operation targeting the second export interface is detected, the N images in the page to be identified are exported as files corresponding to the portable document format PDF.

10. The image exporting device according to claim 8, characterized in that, N is an integer greater than 1; The export module is specifically used to receive the image sorting results for the N images sent by the server when an operation on the image set export interface is detected. Based on the image sorting results, export the sorted N images into files corresponding to the image format.

11. The image exporting device according to claim 8, characterized in that, The display module is further configured to display the N images through the image viewer if the target image set recognition information meets the image export conditions; The export module is further configured to export the K images in the page to be identified as files corresponding to the target format when an operation on K images is detected, wherein the K images are contained in the N images, and K is an integer greater than or equal to 1 and less than or equal to N.

12. An image exporting device, characterized in that, The device is used in a server, and the device includes: The receiving module is used to receive a target text identifier for a page to be identified sent by a terminal device. The page to be identified displays target text and images. The target text includes a title and body text. The target text identifier is used to indicate the target text included in the page to be identified. M is an integer greater than or equal to 1. The target text identifier is sent by the terminal device when it receives an image viewing instruction for any image in the page to be identified. The image viewing instruction is generated when the user views any image in the page to be identified on the user interface of the terminal device. The determination module is used to determine the target image set recognition information based on the target text identifier; The sending module is used to send an image set export request to the terminal device if the target image set recognition information meets the image export conditions. This allows the terminal device to display an image set export interface on the image viewer based on the export request sent by the server. When the terminal device detects an operation on the image set export interface, it exports the N images from the page to be recognized as files corresponding to the target format with one click. When the terminal device detects an operation on K images, it exports the K images from the page to be recognized as files corresponding to the target format. The K images are included in the N images, where K is an integer greater than or equal to 1 and less than or equal to N. The image set export interface is used to export N images from the M images with one click. N is an integer greater than or equal to 1 and less than or equal to M. The target format includes image format and portable document identifier. The image set export request is used to indicate that images on the page to be identified that meet the image export conditions are allowed to be exported with one click. The image set export interface includes a first export interface and a second export interface. The first export interface is used to export the N images on the page to be identified as files corresponding to the image format. The second export interface is used to export the N images on the page to be identified as files corresponding to the portable document format PDF. The N images have been clustered according to object category before being exported with one click, and automatically sorted according to the degree of relevance to the target text from large to small. Images with the same object name are arranged adjacently. The image exporting device also includes a processing module; The processing module is configured to perform clustering processing on the N images based on the image recognition information corresponding to each image in the N images if the target image set recognition information meets the image export conditions, so as to obtain N clustered images. The determining module is further configured to determine the correlation between each image and the target text based on the target text and the image recognition information corresponding to each image in the N images; The processing module is also used to sort the N clustered images in descending order of their correlation to obtain an image sorting result; The sending module is further configured to send the image sorting result to the terminal device, so that when the terminal device detects an operation on the image set export interface, it exports the sorted N images as files corresponding to the image format according to the image sorting result.

13. The image exporting device according to claim 12, characterized in that, The determining module is specifically used to obtain the target image set recognition information if the target text identifier matches the text identifier library. The target image set recognition information includes the image recognition information corresponding to each of the M images, and the text identifier library includes at least one text identifier and the image set recognition information corresponding to each text identifier.

14. The image exporting device according to claim 12, characterized in that, The determining module is specifically used to obtain the M images if the target text identifier does not match the text identifier library; The M images are identified to obtain the target image set identification information, wherein the target image set identification information includes the image identification information corresponding to each of the M images; The target text identifier and the target image set recognition information are stored in the text identifier library, wherein the text identifier library includes at least one text identifier and image set recognition information corresponding to each text identifier.

15. The image exporting device according to claim 14, characterized in that, The determining module is specifically used to obtain image recognition information corresponding to each of the M images through an object recognition model, wherein the image recognition information includes at least one of object category, object name, and keywords; Based on the image recognition information corresponding to each of the M images, the target image set recognition information is obtained.

16. The image exporting apparatus according to any one of claims 12-15, characterized in that, The target image set recognition information includes the image recognition information corresponding to each of the M images; The determining module is further configured to, after determining the target image set identification information based on the target text identifier, if the correlation between the image identification information of the N images and the target text satisfies the image-text matching condition, and the image identification information of the N images satisfies the information security condition, then determine that the target image set identification information satisfies the image export condition, wherein the N images are included in the M images; or, If the correlation between the image recognition information of the N images and the target text satisfies the image-text matching condition, then it is determined that the target image set recognition information satisfies the image export condition. or, If the image recognition information of the N images meets the information security conditions, then the target image set recognition information is determined to meet the image export conditions.

17. A terminal device, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, and the processor is configured to execute the method of any one of claims 1 to 2 according to the instructions in the program code; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

18. A server, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, and the processor is configured to execute the method of any one of claims 3 to 7 according to the instructions in the program code; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

19. A computer-readable storage medium comprising instructions, when executed on a computer, causing the computer to perform the method as claimed in any one of claims 1 to 2, or to perform the method as claimed in any one of claims 3 to 7.

Images