Information processing methods, devices, electronic equipment and storage media

Abstract

This disclosure provides information processing methods, apparatus, electronic devices, and storage media. This disclosure relates to the field of computer technology, and particularly to the fields of big data, intelligent search, and intelligent recommendation. The specific solution is as follows: in response to receiving an operation to access a first URL, extracting the content of a first page of the first URL; in response to detecting an operation targeting a target object in the first page of the first URL, extracting the content of a second page of the first URL; determining the content of a target page based on the content of the first page and the content of the second page; and establishing a first correspondence between the first URL and the content of the target page. According to the solution of this disclosure, extracting web page content through a terminal not only greatly saves server computing and storage resources, but also extracts richer web page content, thereby helping to improve the accuracy of intelligent recommendations.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of big data, intelligent search, and intelligent recommendation. Background Technology

[0002] In related technologies, intelligent recommendation mainly takes two forms: First, the server crawls webpages to extract and store the content in a structured manner, then performs intelligent recommendations based on this stored content. Second, the server renders webpage content using a Uniform Resource Locator (URL), extracts and stores the content in a structured manner, and then performs intelligent recommendations based on this stored content. However, intelligent recommendations based on webpages crawled by web crawlers have certain timeliness issues and require significant server storage and computing resources; intelligent recommendations based on server-rendered webpage content also require significant server computing and storage resources. Summary of the Invention

[0003] This disclosure provides an information processing method, apparatus, electronic device, and storage medium.

[0004] According to a first aspect of this disclosure, an information processing method is provided, applied to a first terminal, comprising:

[0005] In response to receiving an access to the first URL, extract the content of the first page of the first URL;

[0006] In response to detecting an operation targeting a target object in the first page of the first URL, extract the content of the second page of the first URL;

[0007] The content of the target page is determined based on the content of the first page and the content of the second page.

[0008] Establish the first correspondence between the first URL and the content of the target page.

[0009] According to a second aspect of this disclosure, an information processing method is provided, applied to a server, comprising:

[0010] Receive a first correspondence relationship sent by a first terminal; wherein, the first correspondence relationship is the relationship between a first URL and target page content established by the first terminal, the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation targeting the target object in the first page of the first URL;

[0011] The third URL is determined based on the first correspondence, and the relevance of the third URL to the content of the target page satisfies the second preset condition.

[0012] Send a second recommended resource to the first terminal, which includes a link corresponding to a third URL.

[0013] According to a third aspect of this disclosure, an information processing apparatus is provided, applied to a first terminal, comprising:

[0014] The first extraction module is used to extract the content of the first page of the first URL in response to receiving an operation to access the first URL;

[0015] The second extraction module is used to extract the content of the second page of the first URL in response to detecting an operation targeting a target object in the first page of the first URL.

[0016] The first determining module is used to determine the content of the target page based on the content of the first page and the content of the second page.

[0017] The first module is used to establish the first correspondence between the first URL and the content of the target page.

[0018] According to a fourth aspect of this disclosure, an information processing apparatus is provided, applied to a server, comprising:

[0019] The second receiving module is used to receive the first correspondence relationship sent by the first terminal; wherein, the first correspondence relationship is the relationship between the first URL and the target page content established by the first terminal, the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation on the target object in the first page of the first URL;

[0020] The third determining module is used to determine the third URL based on the first correspondence relationship, wherein the relevance between the third URL and the content of the target page meets the second preset condition.

[0021] The second sending module is used to send a second recommended resource to the first terminal, which includes a link corresponding to a third URL.

[0022] According to a fifth aspect of this disclosure, an electronic device is provided, comprising: at least one processor; a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform an information processing method provided in the first aspect for a first terminal and / or an information processing method provided in the second aspect for a server.

[0023] According to a sixth aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to perform an information processing method provided in the first aspect for use on a first terminal and / or an information processing method provided in the second aspect for use on a server.

[0024] According to a seventh aspect of this disclosure, a computer program product is provided, comprising a computer program stored on a storage medium, which, when executed by a processor, implements the information processing method provided in the first aspect for use on a first terminal and / or the information processing method provided in the second aspect for use on a server.

[0025] According to the technical solution disclosed herein, extracting web page content through a terminal can not only greatly save server computing and storage resources, but also extract richer web page content, thereby helping to improve the accuracy of intelligent recommendations.

[0026] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of this application will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0027] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0028] Figure 1 This is a schematic diagram illustrating intelligent recommendation based on web page content crawled by a web crawler according to an embodiment of this disclosure;

[0029] Figure 2 This is a schematic diagram illustrating intelligent recommendation based on webpage content extracted from a server according to an embodiment of this disclosure;

[0030] Figure 3 This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. Figure 1 ;

[0031] Figure 4 This is a schematic diagram of information processing applications according to embodiments of the present disclosure;

[0032] Figure 5 This is a schematic diagram of the intelligent recommendation architecture according to embodiments of the present disclosure. Figure 1 ;

[0033] Figure 6 This is a schematic diagram of the process for intelligent summarizing and recommending web page content according to an embodiment of this disclosure. Figure 1 ;

[0034] Figure 7 This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. Figure 2 ;

[0035] Figure 8 This is a schematic diagram of the intelligent recommendation architecture according to embodiments of the present disclosure. Figure 2 ;

[0036] Figure 9 This is a schematic diagram of the process for intelligent summarizing and recommending web page content according to an embodiment of this disclosure. Figure 2 ;

[0037] Figure 10 This is a flowchart illustrating an extended application of intelligent summarization and recommendation of web page content based on embodiments of this disclosure.

[0038] Figure 11 This is a schematic diagram of the structure of an information processing apparatus according to an embodiment of the present disclosure. Figure 1 ;

[0039] Figure 12 This is a schematic diagram of the structure of an information processing apparatus according to an embodiment of the present disclosure. Figure 2 ;

[0040] Figure 13 This is a scenario illustration of an information processing method according to an embodiment of the present disclosure. Figure 1 ;

[0041] Figure 14 This is a scenario illustration of an information processing method according to an embodiment of the present disclosure. Figure 2 ;

[0042] Figure 15 This is a schematic diagram of the structure of an electronic device used to implement the information processing method of the embodiments of this disclosure. Detailed Implementation

[0043] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0044] The terms "first," "second," and "third," etc., used in the embodiments, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or units. A method, system, product, or apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0045] Figure 1 This diagram illustrates intelligent recommendations based on webpage content retrieved by a web crawler; such as... Figure 1 As shown, firstly, a web crawler retrieves the website URL and its corresponding webpage content, extracting structured data from the webpage content corresponding to the URL; the webpage content is then mapped and persistently stored based on the URL. Secondly, when a user accesses the website URL, the system queries the structured data of the webpage content based on the current URL. If structured data is found, a Natural Language Processing (NLP) model is used to intelligently summarize and recommend content; if no structured data is found, no intelligent summary or recommendation is provided. Here, the NLP model can include large language models, small language models, and other artificial intelligence models or algorithms.

[0046] However, using web crawlers to retrieve web page content for intelligent recommendations has the following drawbacks: 1. It relies excessively on the web crawler's advance crawling; intelligent recommendations can only be made based on the crawled results, leading to timeliness issues. 2. It consumes significant server storage and crawler resources. 3. The resources stored by the crawler may not be the same resources accessed by users, resulting in a low hit rate for intelligent recommendations.

[0047] Figure 2 This diagram illustrates intelligent recommendations based on webpage content retrieved from a server, such as... Figure 2 As shown, when a user accesses a website URL, the server queries the webpage content for structured data based on that URL. If structured data is found, it is used to intelligently summarize and recommend content using an NLP model. If no structured data is found, the server loads and renders the URL in real time to extract structured data, and the extracted webpage content and the URL are persistently stored. Intelligent summarization and recommendation are then performed based on the structured data using an NLP model. Here, the NLP model can include large language models, small language models, and other artificial intelligence models or algorithms.

[0048] However, intelligent recommendations based on server-rendered webpage content have at least the following drawbacks: 1. Real-time rendering by the server is required to extract the webpage content viewed by the user. With a massive number of mobile devices, this consumes significant server computing and storage resources. 2. Extraction is only possible from the URLs accessed by the user. If the webpage corresponding to that URL triggers a dynamic content update, the server cannot obtain the updated webpage content or the content rendered during a secondary redirect.

[0049] To at least partially address one or more of the aforementioned problems and other potential issues, this disclosure proposes a decentralized web page content extraction method. Compared to a server handling the extraction of web page content from a massive number of mobile terminals, having each mobile terminal extract web page content independently not only significantly saves server computing and storage resources, but also allows each mobile terminal to extract richer web page content, thereby improving the accuracy of intelligent recommendations and increasing the hit rate of recommended resources.

[0050] Before introducing the technical solutions of the embodiments of this disclosure, the technical terms that may be used in this disclosure will be further explained:

[0051] Decentralization: Decentralization is a form of social relationship and content production that has emerged during the development of the internet. It is a new type of network content production process relative to "centralization." In a decentralized system, any node can become a center, and no center is permanent but rather temporary. No center has any coercive power over any node.

[0052] This disclosure provides an information processing method applied to a first terminal. Figure 3 This is a schematic flowchart of an information processing method according to an embodiment of the present disclosure. This information processing method can be applied to an information processing device. The information processing device is located in an electronic device. The electronic device includes, but is not limited to, a mobile terminal. For example, a mobile terminal includes, but is not limited to, a mobile phone, a tablet computer, and an in-vehicle terminal. In some possible implementations, the information processing method can also be implemented by a processor calling computer-readable instructions stored in memory. Figure 3 As shown, the information processing method includes:

[0053] S301: In response to receiving an operation to access the first URL, extract the content of the first page of the first URL;

[0054] S302: In response to detecting an operation targeting a target object in the first page of the first URL, extract the content of the second page of the first URL;

[0055] S303: Determine the target page content based on the content of the first page and the content of the second page;

[0056] S304: Establish the first correspondence between the first URL and the content of the target page.

[0057] In this embodiment of the disclosure, the first URL may be a webpage address accessed by the user on the first terminal.

[0058] In this embodiment of the disclosure, the first URL can be obtained through an application (APP), or through other channels such as links in SMS or MMS messages, or through search terms entered by the user on a third-party search website. The above is merely an illustrative example and is not intended to limit all possible methods of obtaining the first URL; it is simply not an exhaustive list.

[0059] In this embodiment, the first page content is the page content displayed at the first moment after the first URL is triggered. The first page content may include a title, body text, author, time, paragraphs, images, videos, media resources, and layout. In some implementations, obtaining the first page content may include: inputting the first URL into a local content extraction model to obtain the first page content output by the content extraction model. In other implementations, obtaining the first page content may include: loading and rendering the first URL using a Webview container to obtain the first page content of the first URL. The above are merely illustrative examples and are not intended to limit all possible methods of obtaining the first page content; they are simply not exhaustive.

[0060] In this embodiment, the target object is a triggerable object. Specifically, the target object can be a function button, function entry point, or floating layer on the first page. For example, the function button can be a zoom-in button, a next page button, a previous page button, a return to the table of contents button, or a font size increase button. The function entry point can be a video playback entry point, an image viewing entry point, or a music playback entry point. The above are merely illustrative examples and are not intended to limit the scope of all possible objects included in the target object; an exhaustive list is not provided here.

[0061] In this embodiment of the disclosure, the operation on the target object in the first page of the first URL can be a shortcut key operation on the mobile terminal, such as brightening the screen, increasing the volume, or zooming in on an image. It can also be an operation by the user clicking on a function button or function entry on the first page, or an operation by entering a floating page under the first page.

[0062] For example, when a user enters the keyword "loofah sponge" in the search bar of an app, a first URL is retrieved based on this keyword. The first page is then accessed based on this first URL; for instance, this first page might be an article about the "benefits of loofah sponge" and multiple functional entry points, including purchase links, preparation methods, and usage instructions. In response to detecting that the user clicks on the "preparation method" entry point, a second page based on the first URL, titled "How to Make Loofah Sponge," is displayed. It should be noted that the entry resources corresponding to purchase links, preparation methods, and usage instructions include, but are not limited to, articles, images, videos, and audio.

[0063] In this embodiment, the second page content is the page content presented at a second moment after the first URL is triggered, where the second moment is later than the first moment. Specifically, the second page content is the page content presented after a target object on the first page of the first URL is triggered. The first page may include multiple target objects, and the second page content is the page content presented after one or more target objects on the first page of the first URL are triggered. The second page content may include a title, body text, author, time, paragraphs, images, videos, media resources, and layout information. In some embodiments, obtaining the second page content may include: determining the difference layout features between the second layout features and the first layout features; and extracting the second page content based on the content corresponding to the difference layout features. In other embodiments, obtaining the second page content may include: reloading and rendering the first URL using a page view container to obtain the second page of the first URL; and extracting the second page content based on the second layout features of the second page. The above are merely illustrative examples and are not intended to limit all possible methods of obtaining the second page content; they are not exhaustive.

[0064] In this embodiment, the target page content is obtained based on the first page content and the second page content. In some implementations, the target page content can be obtained by extracting keywords from the first and second page content. In other implementations, the first and second page content can be compared to identify identical and different content; the target page content is then obtained based on this identical and different content. In still other implementations, feature extraction can be performed on the first and second page content to obtain a first target feature and a second target feature; these features are then input into a natural language model to obtain the target page content, where the natural language model is a pre-trained model. The above are merely illustrative examples and are not intended to limit the scope of all possible methods for determining the target page content; an exhaustive list is not provided here.

[0065] In this embodiment of the disclosure, the first correspondence can be used to express a summary of the content of multiple pages under a first URL. The first correspondence can exist in list form, such as a list including the values ​​of multiple items corresponding to the first URL. These multiple items include, but are not limited to, title, body text, author, time, paragraph, image, video, media resources, and layout. The first correspondence can also exist in key-value pair form, or in a graphic / text format. The above is merely illustrative and does not constitute a limitation on all possible representations of the first correspondence; an exhaustive list is not provided here.

[0066] Here, the content of the target page is obtained based on at least two pages under the same URL.

[0067] The technical solution of this disclosure embodiment, in response to receiving an operation to access a first URL, extracts the content of a first page of the first URL; in response to detecting an operation targeting a target object in the first page of the first URL, extracts the content of a second page of the first URL; determines the content of a target page based on the content of the first page and the content of the second page; and establishes a first correspondence between the first URL and the content of the target page. Thus, by extracting webpage content through a mobile terminal and establishing the relationship between the first URL and the content of the target page on the mobile terminal side, compared to a server handling the extraction of webpage content from a massive number of mobile terminals, having each mobile terminal extract webpage content independently significantly saves server computing and storage resources. Since the content of the target page is obtained from at least two pages under the same URL, each mobile terminal can extract richer page content, thereby improving the accuracy of intelligent recommendations and increasing the hit rate of recommended resources. Furthermore, extracting webpage content on the mobile terminal side helps improve the real-time nature of webpage content summarization and resource recommendations, thereby increasing the click-through rate of recommended resources.

[0068] In some embodiments, extracting the content of a first page from a first URL includes: inputting the first URL into a local content extraction model; and obtaining the content of the first page output by the content extraction model; wherein the content extraction model is a model pre-trained based on a first training sample.

[0069] In this embodiment of the disclosure, the first training sample includes URL samples and webpage content samples corresponding to the URL samples. It should be noted that this disclosure does not limit the source of the first training sample.

[0070] In this embodiment, the training process of the content extraction model may include: obtaining a first training sample, which includes multiple URL samples; inputting the first training sample into a first model to be trained to obtain page content prediction values ​​corresponding to the multiple URL samples; obtaining ground truth values ​​of page content corresponding to the multiple URL samples; constructing a first objective loss function based on the ground truth values ​​and the predicted page content values; and training the first model to be trained based on the first objective loss function to obtain the content extraction model. The content extraction model is used to extract page content corresponding to URLs. The page content may include titles, body text, authors, timestamps, paragraphs, images, videos, media resources, and layout, etc. The content extraction model can be a lightweight model or a large model that can be deployed on mobile terminals.

[0071] In the embodiments of this disclosure, the content of the first page may include a title, body text, author, time, paragraphs, images, videos, media resources, and layout, etc. For example, the content of the first page is: title "How to Make Yogurt", time "2023.09.25", and image "Yogurt Making Guide".

[0072] The technical solution of this disclosure involves inputting a first URL into a local content extraction model and obtaining the first page content output by the content extraction model. This eliminates the need to upload the first URL accessed by the first terminal to a server, thus improving network information security. Compared to extracting webpage content from a server, obtaining the first page content through the mobile terminal's local model saves time spent sending the first URL to the server, improving the page content extraction speed and consequently, the speed of resource recommendation and page content summarization.

[0073] In some embodiments, extracting the content of the first page of the first URL includes: loading and rendering the first URL using a page view container to obtain the first page of the first URL; and extracting the content of the first page based on the first layout features of the first page.

[0074] In this embodiment of the disclosure, the first page may include multiple elements, such as: title, body text, author, time, paragraphs, images, videos, media resources, and layout. The first layout feature may include the positional information of each element on the first page, such as the title "How to Cultivate Orchids" in the center of the first page, the time "2022.05.06" in the lower left corner of the first page, and "Orchid Cultivation Diagram" in the middle of the first page. The first layout feature may also include the positional information of each functional entry point on the first page.

[0075] In this embodiment of the disclosure, the first page content is the page content on the first page of the first URL that is displayed at the first moment after the first URL is triggered. The first page may include page content from multiple sections, multiple clickable function entries, multiple floating layers, etc. In this embodiment of the disclosure, extracting the first page content may include: extracting the first page content based on a first layout feature of the first page. The first layout feature may include the location of webpage content such as Hyper Text Markup Language (HTML) tags, Cascading Style Sheets (CSC) samples, text, and attribute features.

[0076] In this embodiment of the disclosure, if the first terminal detects that the user has clicked on the first URL, then the first URL is rendered and loaded.

[0077] The technical solution of this disclosure embodiment uses a page view container to load and render a first URL to obtain a first page of the first URL; based on the first layout features of the first page, the content of the first page is extracted. In this way, the content of the first page corresponding to the first URL can be extracted on the mobile terminal. Each mobile terminal no longer relies on the real-time computing and storage resources of the server, achieving decentralized page content extraction and improving the security of data on the mobile terminal side.

[0078] In some embodiments, extracting the content of a second page of a first URL includes: loading and rendering the first URL using a page view container to obtain a second page of the first URL; and extracting the content of the second page based on the second layout features of the second page.

[0079] In this embodiment of the disclosure, the second webpage content is the page content displayed at a second moment after the first URL is triggered. Specifically, the second page content is the page content displayed after the target object on the first page of the first URL is triggered. The second page may include page content of multiple sections, multiple clickable function entries, multiple floating layers, etc. The second page content may include secondary rendering content of the target object on the first page content, jump content of the target object on the first page content, or update content of the target object on the first page content.

[0080] In this embodiment, the second page may include multiple elements, such as: title, body text, author, time, paragraphs, images, videos, media resources, and layout. The second layout features may include the positional information of each element on the second page, such as the title "Introduction to Noodles" in the center of the second page, the time "2022.06.02" in the lower left corner, and the video "Steamed Bun Making Video" in the middle. The second layout features may also include the positional information of each functional entry point on the second page.

[0081] In this embodiment of the disclosure, extracting the content of the second webpage includes: extracting the content of the second webpage based on the second layout features of the second page. The second layout features may include the positions of elements such as HTML tags, CCS styles, text, and attribute features on the page.

[0082] The technical solution of this disclosure embodiment uses a page view container to load and render a first URL to obtain a second page of the first URL; based on the second layout features of the second page, the content of the second page is extracted. Thus, in response to detecting an operation on a target object in the display interface of the first URL, the content of the second page corresponding to the first URL can be extracted on the mobile terminal. This second page content is unavailable when the server extracts page content based on the first URL. By extracting the second page content of the first URL on the mobile terminal, richer content information can be obtained based on the user's entire operation process on the first URL, thereby enriching the extracted target page content of the first URL. This provides richer data support for subsequent extended recommendations based on the target page content and also helps to improve the click-through rate of recommended resources.

[0083] In some embodiments, extracting the content of the second page based on the second layout features of the second page includes: determining the difference layout features between the second layout features and the first layout features; and extracting the content of the second page based on the content corresponding to the difference layout features.

[0084] In this embodiment, the first page and the second page are similar or related. For example, they may have the same title and author, but different images or text content. If the first page and the second page are obtained by loading and rendering the same URL, then the content of the second page is at least partially the same as the content of the first page.

[0085] For example, after the first terminal loads and renders the first URL at a first moment, it obtains the first page; after loading and rendering the first URL at a second moment, it obtains the second page, which is the next page after the first page. For example, taking the link corresponding to the first URL as "How to make steamed buns" as an example, the first page includes the title "How to make steamed buns", "Step 1: Material preparation" and specific material content; the first page also displays a "Next Page" trigger button; after the user clicks the "Next Page" button, the first terminal loads and renders the second page, which displays "Step 2: Add yeast to flour, knead into a dough of medium softness, and let it ferment in a warm place" and other information. Figure 1 The second page also displays "Next Page" and "Previous Page" buttons. After the user clicks the "Next Page" button, the first terminal loads and renders a new second page, which displays "Step 3: Deflate the fermented dough, knead it until smooth, divide it into equal portions, roll them into small balls, and knead the small balls until smooth to form steamed buns," along with accompanying instructions. Figure 2 The second page also displays "Next Page" and "Previous Page" buttons. After the user clicks the "Next Page" button, the first terminal loads and renders the new second page, which displays "Step 4: Put the steamed buns in cold water, steam for 20 minutes after the steam rises, turn off the heat, and let them sit for another 5 minutes before opening the lid," along with accompanying instructions. Figure 3 The second page also displays a "Previous Page" button and a link to "How to Make Twisted Dough Sticks". Clearly, the text content and images on the first and second pages can differ.

[0086] In this embodiment of the disclosure, a first URL is loaded and rendered to obtain a first page and a second page; structured content is extracted from the first page to obtain a first layout feature; structured content is extracted from the second page to obtain a second layout feature; a difference layout feature between the first layout feature and the second layout feature is determined, and the content of the second page is extracted based on the content corresponding to the difference layout feature.

[0087] The technical solution of this disclosure, by determining the difference layout features between the second layout features and the first layout features, and extracting the content of the second page based on the content corresponding to the difference layout features, can determine the content of the second page based on the difference layout features between the first page and the second page in advance. This helps to obtain the second page content that is different from the content of the first page in a targeted manner, improves the distinguishability between the content of the second page and the content of the first page, and thus helps to quickly obtain the target page content of the first URL based on the content of the first page and the content of the second page.

[0088] In some embodiments, the information processing method may further include: determining a second URL based on a first URL, wherein the relevance of the second URL to the content of a target page satisfies a first preset condition; and, in response to receiving a preset operation, outputting a first recommended resource for a first terminal, wherein the first recommended resource includes a link corresponding to the second URL, and the preset operation is used to instruct intelligent recommendation.

[0089] Here, the second URL and the first URL can belong to the same website or app, or they can belong to different websites or apps.

[0090] In this embodiment of the disclosure, the first preset condition can be expressed as a numerical point, such as a correlation of 0.8. The first preset condition can also be expressed as a numerical range, such as a correlation of 0.6 to 0.9. In practical applications, the first preset condition can be set or adjusted according to requirements.

[0091] In this embodiment, the preset operation can be a trigger operation for a preset button on the display page of the first URL, or it can be a trigger operation for the preset button using voice. The preset operation can be a pre-set operation, such as double-tapping the screen; it can also be clicking a target area, such as clicking the lower left corner button of the current page. When the first terminal detects the preset operation, it obtains a second URL that meets the first preset condition.

[0092] In this embodiment of the disclosure, the first recommended resource may include any resource such as text, images, videos, shopping links, and audio. The first recommended resource may be displayed on the display page as a link, or it may be displayed in a small window, which may display partial information about the first recommended resource, such as its title and summary.

[0093] The technical solution of this disclosure involves determining a second URL whose relevance to the target page content meets a first preset condition; and outputting a first recommended resource for the first terminal in response to receiving a preset operation. This provides users with a second URL that is highly relevant to the currently viewed page, helping to increase the click-through rate of the first recommended resource. Furthermore, the first recommended resource is output only when a preset operation is received; otherwise, it is not output. This allows for more reasonable and timely recommendations of the first recommended resource, enhancing the rationality and timeliness of the recommendations, thereby improving the user's search experience.

[0094] In some embodiments, outputting a first recommended resource for a first terminal includes: outputting a link corresponding to a second URL in a jumpable link manner.

[0095] In this embodiment of the disclosure, outputting the link corresponding to the second URL in a jumpable link manner may include: in response to receiving a preset operation, embedding the link corresponding to the second URL at a preset position on the target interface.

[0096] Here, the target interface can be the current interface of the mobile terminal, or it can be the interface displayed after the mobile terminal opens an application.

[0097] The technical solution of this disclosure can be flexibly embedded with the first recommended resource, which helps to improve the diversity of intelligent recommendations, facilitates users to browse recommended resources, and increases the click-through rate of recommended resources.

[0098] In some embodiments, outputting a first recommended resource for a first terminal includes:

[0099] Output at least a portion of the page content corresponding to the second URL using intelligent dialogue.

[0100] In this embodiment of the disclosure, outputting at least a portion of the page content corresponding to the second URL in an intelligent dialogue manner may include: generating multiple sets of questions and answers based on the page content of the second URL; outputting multiple questions according to a preset priority; and, in response to receiving a trigger operation for the first question among the multiple questions, outputting a first answer that matches the first question.

[0101] Here, at least part of the page content can be the original content of the page corresponding to the second URL, or it can be content that has been summarized, refined or analyzed based on the original content.

[0102] Figure 4 A schematic diagram of an information processing application is shown, such as... Figure 4As shown, the current page is the page after the user clicks the first URL (link 0), specifically the article "Tips for Taking Great Photos." Upon receiving the user's click of the "Smart Recommendation Button" on this page, recommended resources are displayed, including the second URL (link 1) "How to Take Personal Portraits" and its related "Ask a Question" button 1, the second URL (link 2) "How to Take Landscape Photos" and its related "Ask a Question" button 2, and the second URL (link 3) "How to Take Everyday Photos" and its related "Ask a Question" button 3. If the user clicks the "Ask a Question" button 1 related to "How to Take Personal Portraits," the entire overview of taking personal portraits is displayed directly on the current page. If the user clicks the "Ask a Question" button 2 related to "How to Take Landscape Photos," the relevant content on taking landscape photos is displayed word by word on the current page, and a "Stop Answering" button is displayed. During the word-by-word display of the relevant content on taking landscape photos, if the user clicks the "Stop Answering" button, the display of the remaining content on taking landscape photos stops. If the user clicks the "Ask a Question" button 3 related to "How to Take Lifestyle Photos", a video of the lifestyle photo will be displayed in a small window on the current page, along with a "Stop Playback" button. If the user clicks the "Stop Playback" button, the video playback will pause in the small window.

[0103] Here, the second URL can be one or more. When there are multiple second URLs, they can be sorted according to their relevance values. When outputting, if only one second URL needs to be output, the second URL with the highest relevance value will be output first. If only a certain number of second URLs need to be output, a certain number of second URLs with the highest relevance values ​​will be output first.

[0104] The technical solution of this disclosure can flexibly output at least part of the page content of the second URL, which helps to improve the flexibility of intelligent recommendation, thereby providing users with multiple recommendation methods and improving the user's search experience.

[0105] In some embodiments, the information processing method further includes: sending a first correspondence to a server; receiving a third URL returned by the server based on the first correspondence, wherein the relevance of the third URL to the target page content satisfies a second preset condition; and, in response to receiving a preset operation, outputting a second recommended resource for a first terminal, wherein the second recommended resource includes a link corresponding to the third URL, and the preset operation is used to instruct intelligent recommendation.

[0106] In this embodiment of the disclosure, the first correspondence is generated on the first terminal. The first terminal sends the first correspondence to the server; the server receives the first correspondence sent by the first terminal; the server performs a retrieval based on the first correspondence to obtain a third URL, which is a URL whose relevance to the target page content meets a second preset condition.

[0107] In this embodiment of the disclosure, the second preset condition can be expressed as a numerical point, such as: correlation = 0.6. The second preset condition can also be expressed as a numerical range, such as: correlation = 0.4 to 0.7. In practical applications, the second preset condition can be set or adjusted according to requirements.

[0108] In this embodiment of the disclosure, there is no limit to the number of third URLs. There can be one third URL, multiple third URLs, or a pre-set number of third URLs.

[0109] In this embodiment of the disclosure, the second recommended resource may include any resource such as text, images, videos, shopping links, and audio. The second recommended resource may be displayed on the display page as a link, or it may be displayed in a small window, which may display a portion of the second recommended resource's content, such as a title or summary.

[0110] Here, the third URL is provided by the server, and the second recommended resource is also provided by the server.

[0111] The technical solution of this disclosure embodiment sends a first correspondence relationship to the server; receives a third URL returned by the server based on the first correspondence relationship; and outputs a second recommended resource for the first terminal in response to receiving a preset operation. This can utilize the powerful resources of the server to recommend the second recommended resource for the first terminal, which helps to improve the diversity and timeliness of resources for the first terminal, thereby helping to improve the user's search experience.

[0112] In some embodiments, the information processing method further includes: storing a first correspondence locally; and / or sending the first correspondence to a server so that the server stores the first correspondence.

[0113] In this embodiment of the disclosure, the first correspondence can be persistently stored locally on the first terminal.

[0114] In this embodiment of the disclosure, a first correspondence relationship may be sent to a server so that the server can persistently store the first correspondence relationship.

[0115] In this embodiment of the disclosure, the first terminal locally persists and stores the first correspondence relationship, and sends the first correspondence relationship to the server so that the server persists and stores the first correspondence relationship.

[0116] Here, the first correspondence is generated on the first terminal, but the first correspondence can be stored locally or on the server.

[0117] The technical solution of this disclosure can flexibly choose to store the first correspondence on the first terminal or on the server. If it is continuously stored on the first terminal, it can be used for intelligent summarization and recommendation in non-browsing scenarios. If it is continuously stored on the server, it can be used as training and testing data to continuously improve the effect of the artificial intelligence model used for intelligent summarization and recommendation.

[0118] In some embodiments, the information processing method may further include: acquiring user characteristics of a first terminal; establishing a second correspondence between target page content and user characteristics; and storing the second correspondence locally.

[0119] Furthermore, the information processing method may also include: sending the second correspondence to the server so that the server stores the second correspondence.

[0120] In this embodiment, the user characteristic can be obtained based on data such as the user's search terms, browsed pages, and clicked pages. Specifically, the user characteristic is a user self-portrait obtained from the user's page browsing data. By establishing a second correspondence between user characteristics and target page content, the accuracy of intelligent recommendations can be improved, thereby enhancing the user's search experience.

[0121] In some embodiments, after determining a second URL whose relevance to the target page content meets a first preset condition, the method further includes: determining a target second URL from a plurality of second URLs that meet the first preset condition based on a known second correspondence relationship, wherein the target second URL is the second URL ultimately recommended to the first terminal.

[0122] The technical solution of this disclosure, by acquiring user characteristics of a first terminal and establishing a second correspondence between target page content and user characteristics, can intelligently summarize the target page content of the first URL, facilitating subsequent intelligent recommendations based on the second correspondence, thereby further improving the accuracy of intelligent recommendations and increasing the click-through rate of recommended resources.

[0123] Figure 5 This illustrates the architecture of intelligent recommendation. Figure 1 ,like Figure 5As shown, the mobile terminal loads the URL accessed by the user and renders it on the mobile terminal interface; based on HTML tags, CSC samples, text, and attribute information, a structured extraction is performed to obtain the page content document tree (Document Tree); based on this page content document tree, the mobile terminal uses artificial intelligence algorithms to perform intelligent summarization and intelligent recommendations, which are available for consumption by the user. The intelligent summary is used to summarize the relevant content corresponding to the URL, and the intelligent recommendation is used to recommend resources related to the webpage content corresponding to the current URL.

[0124] Figure 6 This is a schematic diagram of the process for intelligent summarizing and recommending web page content according to an embodiment of this disclosure. Figure 1 ,like Figure 6 As shown, the process includes:

[0125] S601: Users access URLs provided in any form;

[0126] S602: The mobile terminal queries the database to see if there is structured data related to the URL; if it exists, proceed to S603; if it does not exist, proceed to S604; wherein, the database stores the correspondence between multiple known URLs and their target page content;

[0127] S603: The mobile terminal makes intelligent recommendations based on the database, obtains recommended resources, and then executes S605;

[0128] S604: The mobile terminal obtains recommended resources using a preset method, and then executes S605;

[0129] Here, the preset method may include: the mobile terminal sending a resource recommendation request to the server so that the server can make intelligent recommendations for the mobile terminal; the preset method may also include: the mobile terminal generating recommended resources for the mobile terminal based on user characteristics.

[0130] S605: Mobile terminals display recommended resources.

[0131] Therefore, by extracting webpage content from mobile devices and establishing the relationship between the first URL and the target page content, compared to a server handling the extraction of webpage content from massive numbers of mobile devices, having each mobile device extract content independently significantly saves server computing and storage resources. This helps improve the speed of intelligent recommendations and the display speed of recommended resources. Furthermore, extracting webpage content on the mobile device side helps improve the real-time nature of webpage content summarization and resource recommendations, thereby increasing the click-through rate of recommended resources.

[0132] This disclosure provides an information processing method applied to a server. Figure 7This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. This information processing method can be applied to an information processing device. It can also be applied to an electronic device. The electronic device includes, but is not limited to, a server, which can be a cloud server or a regular server. In some possible implementations, the information processing method can also be implemented by a processor calling computer-readable instructions stored in memory. For example... Figure 7 As shown, the information processing method includes:

[0133] S701: Receive the first correspondence relationship sent by the first terminal; wherein, the first correspondence relationship is the relationship between the first URL and the target page content established by the first terminal, the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation on the target object in the first page of the first URL;

[0134] S702: Determine a third URL based on the first correspondence relationship, wherein the relevance of the third URL to the content of the target page satisfies the second preset condition;

[0135] S703: Send a second recommended resource to the first terminal, the second recommended resource including a link corresponding to the third URL.

[0136] In this embodiment, the server receives a first correspondence relationship sent by a first terminal; analyzes the first correspondence relationship to obtain target page content; performs a search based on the target page content to obtain multiple third URLs that meet a second preset condition; sorts the multiple third URLs based on relevance to obtain the top N third URLs in terms of relevance; and sends a second recommended resource to the first terminal, the second recommended resource including links corresponding to the top N third URLs. Here, the value of N can be set and adjusted according to requirements.

[0137] Figure 8 This illustrates the architecture of intelligent recommendation. Figure 2 ,like Figure 8 As shown, the mobile terminal loads the URL accessed by the user and renders it onto the mobile terminal interface; based on HTML tags, CSC samples, text, and attribute information, a structured extraction is performed to obtain the page content document tree; the server performs intelligent summarization and intelligent recommendation based on this page content document tree.

[0138] Here, when storing structured data, the server can use artificial intelligence models to achieve intelligent summarization and recommendations.

[0139] Figure 9 This is a schematic diagram of the process for intelligent summarizing and recommending web page content according to an embodiment of this disclosure. Figure 2 ,like Figure 9 As shown, the process includes:

[0140] S901: The URL of the website accessed by the user;

[0141] S902: The mobile terminal loads and renders the URL;

[0142] S903: Mobile terminal extracts page content;

[0143] S904: The server receives a resource recommendation request sent by the mobile terminal, which carries page content.

[0144] S905: The server makes intelligent recommendations based on the resource recommendation request and obtains recommended resources;

[0145] S906: Send recommended resources to the mobile terminal;

[0146] S907: The recommended resource is displayed on the mobile terminal.

[0147] In this way, by extracting webpage content through mobile terminals and establishing the relationship between the first URL and the target page content, compared to the server being responsible for extracting webpage content from a massive number of mobile terminals, having each mobile terminal extract webpage content independently can greatly save the server's computing and storage resources; intelligent recommendation by the server can improve the speed of resource recommendation, thereby increasing the click-through rate of recommended resources.

[0148] Figure 10 The diagram illustrates an extended application of intelligent summarization and recommendation of web page content, such as... Figure 10 As shown, the process includes:

[0149] S1001: The user accesses a URL provided in any form;

[0150] S1002: The mobile terminal extracts page content and stores the correspondence between multiple known URLs and their target page content in the database;

[0151] S1003: The mobile terminal uses this database to train and evaluate the model, and obtains a usable model;

[0152] Here, the models include, but are not limited to, content extraction models and resource recommendation models.

[0153] S1004: Mobile terminals perform intelligent summarization and intelligent recommendation based on available models.

[0154] The server can persistently store the URLs and corresponding structured content extracted from the mobile terminal, which can be used to retrieve the structured content of the same URL in other scenarios. It can also be used for intelligent summarization and recommendation in non-browsing scenarios, and as training and testing data to continuously improve the performance of the AI ​​model for intelligent summarization and recommendation. This further enhances the model's intelligent summarization and recommendation capabilities.

[0155] The technical solution of this disclosure embodiment involves a server receiving a first correspondence relationship sent by a first terminal; determining a third URL based on the first correspondence relationship; and sending a second recommended resource for the first terminal to the first terminal. In this way, by sending the first correspondence relationship of the mobile terminal to the server, the server can perform intelligent recommendations based on the first correspondence relationship, improving the comprehensiveness of intelligent recommendations and helping to enhance the user's search experience.

[0156] In this embodiment of the disclosure, determining the third URL based on the first correspondence includes: inputting the first URL included in the first correspondence and the target page content into a resource recommendation model; obtaining the third URL output by the resource recommendation model; wherein the resource recommendation model is a model pre-trained based on the second training samples.

[0157] Here, the resource recommendation model is a lightweight model or a large model deployed on the server side.

[0158] In this embodiment of the disclosure, the second training sample includes a page content sample and a URL sample corresponding to the page content sample. It should be noted that this disclosure does not limit the source of the second training sample.

[0159] In this embodiment of the disclosure, the training process of the resource recommendation model may include: obtaining a second training sample, which includes multiple page content samples; inputting the second training sample into a second training model to obtain URL prediction values ​​corresponding to the multiple page contents respectively; obtaining the URL ground truth values ​​corresponding to the multiple page content samples respectively; constructing a second objective loss function based on the URL ground truth values ​​and URL prediction values; and training the second training model based on the second objective loss function to obtain the resource recommendation model.

[0160] The technical solution of this disclosure, through a resource recommendation model deployed on a server, can obtain more comprehensive and accurate recommended resources, thereby helping to improve the accuracy of recommended resources.

[0161] In some embodiments, the information processing method further includes: obtaining access information for a third URL sent by a first terminal; based on the differences and / or related content of the target page content corresponding to the first URL and the unaccessed third URL respectively; and updating the resource recommendation model based on the differences and / or related content.

[0162] In some embodiments, the information processing method further includes: obtaining access information for the third URL sent by the first terminal; determining, based on the access information, first difference content and / or first related content of the target page content corresponding to the first URL and the unaccessed third URL respectively; and updating the resource recommendation model based on the first difference content and / or the first related content.

[0163] The technical solution of this disclosure can use the access status of a third URL as training data or test data to update the resource recommendation model, which helps to improve the accuracy of the resource recommendation model in recommending resources.

[0164] In some embodiments, the information processing method further includes: obtaining access information for a third URL sent by a first terminal; determining second difference content and / or second related content of the target page content corresponding to the first URL and the accessed third URL respectively based on the access information; and updating the resource recommendation model based on the second difference content and / or second related content.

[0165] In this embodiment of the disclosure, the access information may include the number of accesses, access duration, access time, etc.

[0166] The technical solution of this disclosure can use the access status of a third URL as training data or test data to update the resource recommendation model, which helps to improve the accuracy of the resource recommendation model in recommending resources.

[0167] In some embodiments, the information processing method further includes: a server receiving a second correspondence sent by a first terminal; wherein the second correspondence is the relationship between the target page content of a first URL established by the first terminal and the user characteristics of the first terminal; and storing the second correspondence.

[0168] In this embodiment of the disclosure, if a user browses the content of the first page and then clicks to browse the content of the second page, it can be concluded that the user is more interested in the content of the second page.

[0169] Different users have different preferences; for example, some users focus on products, some on articles, and some on videos. Sending the user characteristics generated by this mobile terminal to the server can provide data support for the server's intelligent recommendations.

[0170] In this embodiment of the disclosure, the second correspondence is persistently stored in the server, which can be used to retrieve structured content of the same URL in other scenarios, as well as for intelligent summarization and recommendation in non-browsing scenarios, and can also be used as training and testing data to continuously improve the accuracy of artificial intelligence models.

[0171] The technical solution of this disclosure embodiment, by persistently storing the second correspondence, can make full use of the data included in the second correspondence to provide training data for intelligent summarization and recommendation.

[0172] In some embodiments, the information processing method may further include: in response to detecting that a first correspondence from a second terminal is stored locally, determining common user characteristics of the first terminal and the second terminal; and establishing a third correspondence between the common user characteristics and the content of a target page.

[0173] In some embodiments, obtaining common user characteristics may include: obtaining user characteristics of a first terminal and user characteristics of a second terminal, wherein there may be one or more common user characteristics; and persistently storing the common user characteristics in the second terminal.

[0174] The technical solution of this disclosure, in response to detecting a first correspondence from a second terminal in local storage, determines common user features between the first and second terminals; and establishes a third correspondence between the common user features and the content of the target page. In this way, a knowledge graph can be generated based on the persistently stored correspondence, effectively reflecting the complex relationship between URLs and user features, thereby better understanding and analyzing data, and providing strong data support for intelligent summarization and intelligent recommendation.

[0175] It should be understood that Figure 1 , Figure 2 , Figure 4 , Figure 5 , Figure 6 , Figure 8 , Figure 9 and Figure 10 The schematic diagrams shown are merely illustrative and not limiting, and are scalable; those skilled in the art can use them as a basis. Figure 1 , Figure 2 , Figure 4 , Figure 5 , Figure 6 , Figure 8 , Figure 9 and Figure 10 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0176] This disclosure provides an information processing device applied to a first terminal, such as... Figure 11As shown, the information processing device includes: a first extraction module 1101, configured to extract the content of a first page of the first URL in response to receiving an operation to access the first URL; a second extraction module 1102, configured to extract the content of a second page of the first URL in response to detecting an operation targeting a target object in the first page of the first URL; a first determination module 1103, configured to determine the content of a target page based on the content of the first page and the content of the second page; and a first establishment module 1104, configured to establish a first correspondence between the first URL and the content of the target page.

[0177] In some embodiments, the first extraction module 1101 includes: a first input submodule for inputting a first URL into a local content extraction model; and a first acquisition submodule for acquiring the first page content output by the content extraction model; wherein the content extraction model is a model pre-trained based on training samples.

[0178] In some embodiments, the first extraction module 1101 includes: a second acquisition submodule, configured to load and render a first URL using a page view container to obtain a first page of the first URL; and a first extraction submodule, configured to extract the content of the first page based on a first layout feature of the first page.

[0179] In some embodiments, the second extraction module 1102 includes: a third acquisition submodule, configured to load and render a first URL using a page view container to obtain a second page of the first URL; and a second extraction submodule, configured to extract the content of the second page based on the second layout features of the second page.

[0180] In some embodiments, the second extraction submodule is used to: determine the difference layout features between the second layout features and the first layout features; and extract the content of the second page based on the content corresponding to the difference layout features.

[0181] In some embodiments, the information processing apparatus further includes: a second determining module ( Figure 11 (not shown in the image), used to determine a second URL whose relevance to the target page content meets a first preset condition; the first output module ( Figure 11 (not shown in the image) is used to respond to receiving a preset operation and output a first recommended resource for the first terminal. The first recommended resource includes a link corresponding to a second URL. The preset operation is used to instruct intelligent recommendation.

[0182] In some embodiments, the first output module ( Figure 11 (Not shown in the image) is used to: output the link corresponding to the second URL in a jumpable link manner.

[0183] In some embodiments, the first output module ( Figure 11(Not shown in the image) is used to: output at least a portion of the page content corresponding to the second URL in an intelligent dialogue manner.

[0184] In some embodiments, the information processing apparatus further includes: a first transmitting module ( Figure 11 (Not shown in the image), used to send the first correspondence relationship to the server; the first receiving module ( Figure 11 (Not shown in the image), used to receive a third URL returned by the server based on a first correspondence, wherein the relevance between the third URL and the content of the target page meets a second preset condition; the second output module ( Figure 11 (Not shown in the image) is used to respond to receiving a preset operation and output a second recommended resource for the first terminal. The second recommended resource includes a link corresponding to a third URL. The preset operation is used to instruct intelligent recommendation.

[0185] In some embodiments, the information processing apparatus further includes: a first acquisition module ( Figure 11 (Not shown in the image), used to obtain user characteristics of the first terminal; the second establishment module ( Figure 11 (not shown in the image), used to establish a second correspondence between the target page content and user characteristics; first storage module ( Figure 11 (not shown in the image), used to store the second correspondence locally or send the second correspondence to the server so that the server can store the second correspondence.

[0186] Those skilled in the art should understand that the functions of each processing module in the information processing apparatus of this disclosure embodiment can be understood with reference to the relevant description of the foregoing information processing method. Each processing module in the information processing apparatus of this disclosure embodiment can be implemented by an analog circuit that implements the functions described in the embodiments of this disclosure, or by running software that performs the functions described in the embodiments of this disclosure on an electronic device.

[0187] The information processing apparatus of this disclosure can extract web page content through a terminal, which can not only greatly save the computing and storage resources of the server, but also extract richer web page content, thereby helping to improve the accuracy of intelligent recommendations.

[0188] This disclosure provides an information processing apparatus applied to a server, such as... Figure 12As shown, the information processing device includes: a second receiving module 1201, used to receive a first correspondence relationship sent by a first terminal; wherein the first correspondence relationship is the relationship between a first URL and target page content established by the first terminal, the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation targeting a target object in the first page of the first URL; a third determining module 1202, used to determine a third URL based on the first correspondence relationship, wherein the relevance between the third URL and the target page content satisfies a second preset condition; and a second sending module 1203, used to send a second recommended resource to the first terminal, the second recommended resource including a link corresponding to the third URL.

[0189] In some embodiments, the third determining module 1202 includes: a second input submodule, used to input the first URL and the target page content into the resource recommendation model; and a fourth obtaining submodule, used to obtain the third URL output by the resource recommendation model.

[0190] In some embodiments, the information processing apparatus further includes: a second acquisition module ( Figure 12 (not shown in the image), used to obtain access information to the third URL sent by the first terminal; the fourth determining module ( Figure 12 (Not shown in the image), used to determine the differences in target page content corresponding to the first URL and the third URL based on access information; the first update module ( Figure 12 (Not shown in the image), used for updating resource recommendation models based on differences.

[0191] In some embodiments, the information processing apparatus further includes: a third acquisition module ( Figure 12 (Not shown in the image), used to obtain access information for the third URL sent by the first terminal; the fifth determining module ( Figure 12 (not shown in the image), used to determine the second difference content and / or second related content of the target page content corresponding to the first URL and the accessed third URL based on the access situation; the second update module ( Figure 12 (not shown in the image) is used to update the resource recommendation model based on the differences in second-difference content and / or second-related content.

[0192] In some embodiments, the information processing apparatus further includes: a third receiving module ( Figure 12 (not shown in the image), used to receive a second correspondence relationship sent by the first terminal; wherein, the second correspondence relationship is the relationship between the target page content of the first URL established by the first terminal and the user characteristics of the first terminal; the second storage module ( Figure 12 (Not shown in the image), used to store the second correspondence.

[0193] In some embodiments, the information processing apparatus further includes: a sixth determining module ( Figure 12 (not shown in the image), used in response to detecting a first correspondence from the second terminal in local storage, to determine common user characteristics of the first terminal and the second terminal; the third establishment module ( Figure 12 (Not shown in the image), used to establish a third correspondence between common user characteristics and target page content.

[0194] Those skilled in the art should understand that the functions of each processing module in the information processing apparatus of this disclosure embodiment can be understood with reference to the relevant description of the foregoing information processing method. Each processing module in the information processing apparatus of this disclosure embodiment can be implemented by an analog circuit that implements the functions described in the embodiments of this disclosure, or by running software that performs the functions described in the embodiments of this disclosure on an electronic device.

[0195] The information processing apparatus of this disclosure can send a first correspondence relationship of a mobile terminal to a server, and the server makes intelligent recommendations based on the first correspondence relationship, thereby improving the comprehensiveness of the intelligent recommendations and helping to improve the user's search experience.

[0196] This disclosure provides a scenario illustration of an information processing method applied to a first terminal, such as... Figure 13 As shown. As previously described, the information processing method provided in this disclosure is applied to an electronic device. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0197] Specifically, the electronic device may perform the following operations:

[0198] In response to receiving an access to the first URL, extract the content of the first page of the first URL;

[0199] In response to detecting an operation targeting a target object in the first page of the first URL, extract the content of the second page of the first URL;

[0200] The content of the target page is determined based on the content of the first page and the content of the second page.

[0201] Establish the first correspondence between the first URL and the content of the target page.

[0202] The first URL can be obtained from the mobile device. The mobile device can be various forms of electronic devices, such as mobile phones, tablets, laptops, personal digital assistants, etc.

[0203] It should be understood that Figure 13 The scene diagrams shown are merely illustrative and not restrictive; those skilled in the art can interpret them based on... Figure 13 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0204] This disclosure also provides a scenario illustration of an information processing method applied to a server, such as... Figure 14 As shown. As previously described, the information processing method provided in this disclosure is applied to an electronic device. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0205] Specifically, the electronic device may perform the following operations:

[0206] Receive a first correspondence relationship sent by a first terminal; wherein, the first correspondence relationship is the relationship between a first URL and target page content established by the first terminal, the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation targeting the target object in the first page of the first URL;

[0207] The third URL is determined based on the first correspondence, and the relevance between the third URL and the content of the target page satisfies the second preset condition.

[0208] Send a second recommended resource to the first terminal. The second recommended resource includes a link corresponding to the third URL.

[0209] It should be understood that Figure 14 The scene diagrams shown are merely illustrative and not restrictive; those skilled in the art can interpret them based on... Figure 14 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0210] The acquisition, storage, and application of personal information of the target object involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0211] Figure 15 A schematic block diagram of an example electronic device 1500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0212] like Figure 15 As shown, device 1500 includes a computing unit 1501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 1502 or a computer program loaded from storage unit 1508 into random access memory (RAM) 1503. RAM 1503 may also store various programs and data required for the operation of device 1500. The computing unit 1501, ROM 1502, and RAM 1503 are interconnected via bus 1504. Input / output (I / O) interface 1505 is also connected to bus 1504.

[0213] Multiple components in device 1500 are connected to I / O interface 1505, including: input unit 1506, such as keyboard, mouse, etc.; output unit 1507, such as various types of monitors, speakers, etc.; storage unit 1508, such as disk, optical disk, etc.; and communication unit 1509, such as network card, modem, wireless transceiver, etc. Communication unit 1509 allows device 1500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0214] The computing unit 1501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 1501 performs the various methods and processes described above, such as information processing methods. For example, in some embodiments, the information processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1500 via ROM 1502 and / or communication unit 1509. When the computer program is loaded into RAM 1503 and executed by the computing unit 1501, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 1501 may be configured to perform an information processing method by any other suitable means (e.g., by means of firmware).

[0215] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0216] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0217] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0218] To provide interaction with a target object, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the target object; and a keyboard and pointing device (e.g., a mouse or trackball) through which the target object provides input to the computer. Other types of devices can also be used to provide interaction with the target object; for example, feedback provided to the target object can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the target object can be received in any form (including sound input, voice input, or tactile input).

[0219] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a target computer with a graphical user interface or web browser through which a target object can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

[0220] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0221] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0222] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information processing method, applied to a first terminal, comprising: In response to receiving an operation to access the first Uniform Resource Locator URL, extract the content of the first page of the first URL; In response to detecting an operation targeting a target object in a first page of the first URL, the content of a second page of the first URL is extracted; the target object includes function buttons, function entry points, and / or overlays in the first page; the content of the second page includes secondary rendered content for the target object and / or updated content for the target object; wherein, the operation of the target object includes clicking the function button, function entry point, or entering the overlay page; the content of the second page is the page content presented at a second moment after the first URL is triggered; The target page content is determined based on the content of the first page and the content of the second page; Establish a first correspondence between the first URL and the content of the target page; wherein, the first correspondence is used to represent a summary of the content of multiple target pages under the same first URL; The second URL is determined based on the first correspondence, and the relevance of the second URL to the content of the target page satisfies the first preset condition. In response to receiving a preset operation on a preset function button on the first page, a first recommended resource for the first terminal is output. The first recommended resource includes a link corresponding to a second URL. The preset operation is used to instruct intelligent recommendation. The step of extracting the content of the second page from the first URL includes: The first URL is loaded and rendered using a page view container to obtain the second page of the first URL; Based on the second layout features of the second page, extract the content of the second page; The step of extracting the content of the second page based on the second layout features of the second page includes: Determine the difference layout features between the second layout feature and the first layout feature, wherein the first layout feature is the layout feature of the first page of the first URL; Based on the content corresponding to the aforementioned differential layout features, the content of the second page is extracted.

2. The method according to claim 1, wherein, The extraction of the first page content from the first URL includes: The content extraction model is obtained by inputting the first URL into the local database. Obtain the content of the first page output by the content extraction model; wherein, the content extraction model is a model pre-trained based on the first training sample.

3. The method according to claim 1, wherein, The extraction of the first page content from the first URL includes: The first URL is loaded and rendered using a page view container to obtain the first page of the first URL; Based on the first layout features of the first page, the content of the first page is extracted.

4. The method according to claim 1, wherein, The output of the first recommended resource for the first terminal includes: Output the link corresponding to the second URL as a jumpable link.

5. The method according to claim 1, wherein, The output of the first recommended resource for the first terminal includes: Output at least a portion of the page content corresponding to the second URL in an intelligent dialogue manner.

6. The method according to claim 1, further comprising: Send the first correspondence to the server; Receive the third URL returned by the server based on the first correspondence relationship, wherein the relevance between the third URL and the content of the target page satisfies the second preset condition; In response to receiving a preset operation, a second recommended resource is output to the first terminal. The second recommended resource includes a link corresponding to the third URL. The preset operation is used to instruct intelligent recommendation.

7. The method according to claim 1, further comprising: Obtain the user characteristics of the first terminal; Establish a second correspondence between the target page content and the user characteristics; Store the second correspondence locally; or The second correspondence is sent to the server so that the server can store the second correspondence.

8. An information processing method, applied to a server, comprising: The system receives a first correspondence relationship sent by a first terminal; wherein the first correspondence relationship is the relationship between a first URL and target page content established by the first terminal, and the first correspondence relationship is used to represent a summary of the content of multiple target pages under the same first URL; the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation on a target object in the first page of the first URL; the second page content is the page content presented at a second time after the first URL is triggered; A third URL is determined based on the first correspondence, and the relevance between the third URL and the content of the target page satisfies the second preset condition; Send a second recommended resource to the first terminal, the second recommended resource including the link corresponding to the third URL.

9. The method according to claim 8, wherein, Determining the third URL based on the first correspondence includes: Input the first URL and the content of the target page into the resource recommendation model; Obtain the third URL output by the resource recommendation model; wherein the resource recommendation model is a model pre-trained based on the second training samples.

10. The method of claim 9, further comprising: Obtain the access information sent by the first terminal to the third URL; Based on the access information, determine the first difference content and / or the first related content of the target page content corresponding to the first URL and the unaccessed third URL, respectively; The resource recommendation model is updated based on the first difference content and / or the first related content.

11. The method of claim 9, further comprising: Obtain the access information sent by the first terminal to the third URL; Based on the access information, determine the second difference content and / or the second related content of the target page content corresponding to the first URL and the accessed third URL, respectively; The resource recommendation model is updated based on the second difference content and / or the second related content.

12. The method according to claim 8, further comprising: Receive a second correspondence relationship sent by the first terminal; wherein the second correspondence relationship is the relationship between the target page content of the first URL established by the first terminal and the user characteristics of the first terminal; Store the second correspondence.

13. The method of claim 12, further comprising: In response to detecting that the first correspondence from the second terminal is stored locally, the common user characteristics of the first terminal and the second terminal are determined; Establish a third correspondence between the common user characteristics and the content of the target page.

14. An information processing apparatus, applied to a first terminal, comprising: The first extraction module is used to extract the content of the first page of the first URL in response to receiving an operation to access the first URL; The second extraction module is configured to extract the content of a second page of the first URL in response to detecting an operation on a target object in a first page of the first URL; the target object includes function buttons, function entry points, and / or overlays in the first page; the content of the second page includes secondary rendered content and / or updated content for the target object; wherein, the operation on the target object includes clicking the function button, function entry point, or entering the overlay page; the content of the second page is the page content presented at a second moment after the first URL is triggered; The first determining module is used to determine the target page content based on the first page content and the second page content; A first establishment module is used to establish a first correspondence between the first URL and the content of the target page; wherein, the first correspondence is used to represent a summary of the content of multiple target pages under the same first URL; The second determining module is used to determine the second URL based on the first correspondence relationship, wherein the relevance between the second URL and the content of the target page satisfies the first preset condition; The first output module is configured to respond to receiving a preset operation on a preset function button on the first page and output a first recommended resource for the first terminal. The first recommended resource includes a link corresponding to a second URL. The preset operation is used to instruct intelligent recommendation. The second extraction module includes: The third acquisition submodule is used to load and render the first URL using a page view container to obtain the second page of the first URL; The second extraction submodule is used to extract the content of the second page based on the second layout features of the second page; The second extraction submodule is used for: Determine the difference layout features between the second layout feature and the first layout feature, wherein the first layout feature is the layout feature of the first page of the first URL; Based on the content corresponding to the aforementioned differential layout features, the content of the second page is extracted.

15. The apparatus according to claim 14, wherein, The first extraction module includes: The first input submodule is used to extract the content model from the first URL input locally. The first acquisition submodule is used to acquire the content of the first page output by the content extraction model; wherein the content extraction model is a model pre-trained based on the first training samples.

16. The apparatus according to claim 14, wherein, The first extraction module includes: The second acquisition submodule is used to load and render the first URL using a page view container to obtain the first page of the first URL; The first extraction submodule is used to extract the content of the first page based on the first layout features of the first page.

17. The apparatus according to claim 14, wherein, The first output module is used for: Output the link corresponding to the second URL as a jumpable link.

18. The apparatus according to claim 14, wherein, The first output module is used for: Output at least a portion of the page content corresponding to the second URL in an intelligent dialogue manner.

19. The apparatus of claim 14, further comprising: The first sending module is used to send the first correspondence relationship to the server; The first receiving module is used to receive the third URL returned by the server based on the first correspondence relationship, wherein the relevance between the third URL and the content of the target page satisfies the second preset condition. The second output module is used to respond to receiving a preset operation and output a second recommended resource for the first terminal. The second recommended resource includes a link corresponding to the third URL. The preset operation is used to instruct intelligent recommendation.

20. The apparatus of claim 14, further comprising: The first acquisition module is used to acquire user characteristics of the first terminal; The second module is used to establish a second correspondence between the target page content and the user characteristics; The first storage module is used to store the second correspondence locally or send the second correspondence to the server so that the server can store the second correspondence.

21. An information processing apparatus, applied to a server, comprising: The second receiving module is used to receive a first correspondence relationship sent by the first terminal; wherein, the first correspondence relationship is the relationship between a first URL and target page content established by the first terminal, and the first correspondence relationship is used to represent a summary of multiple target page contents under the same first URL; the target page content is determined by the first terminal based on the first page content and the second page content of the first URL, the first page content is extracted when the first terminal receives an operation to access the first URL, and the second page content is extracted when the first terminal detects an operation on a target object in the first page of the first URL; the second page content is the page content presented at a second time after the first URL is triggered; The third determining module is used to determine a third URL based on the first correspondence relationship, wherein the relevance between the third URL and the content of the target page satisfies a second preset condition; The second sending module is used to send a second recommended resource to the first terminal, the second recommended resource including the link corresponding to the third URL.

22. The apparatus according to claim 21, wherein, The third determining module includes: The second input submodule is used to input the first URL and the target page content into the resource recommendation model; The fourth acquisition submodule is used to acquire the third URL output by the resource recommendation model; wherein the resource recommendation model is a model pre-trained based on the second training samples.

23. The apparatus of claim 22, further comprising: The second acquisition module is used to acquire the access information sent by the first terminal to the third URL; The fourth determining module is used to determine, based on the access situation, the first difference content and / or the first related content of the target page content corresponding to the first URL and the unaccessed third URL respectively; The first update module is used to update the resource recommendation model based on the first difference content and / or the first related content.

24. The apparatus of claim 22, further comprising: The third acquisition module is used to acquire the access information sent by the first terminal to the third URL; The fifth determining module is used to determine, based on the access situation, the second difference content and / or the second related content of the target page content corresponding to the first URL and the accessed third URL respectively; The second update module is used to update the resource recommendation model based on the differences in the second difference content and / or the second related content.

25. The apparatus of claim 21, further comprising: The third receiving module is used to receive the second correspondence relationship sent by the first terminal; wherein the second correspondence relationship is the relationship between the target page content of the first URL established by the first terminal and the user characteristics of the first terminal; The second storage module is used to store the second correspondence.

26. The apparatus of claim 25, further comprising: The sixth determining module is used to determine the common user characteristics of the first terminal and the second terminal in response to detecting that the first correspondence from the second terminal is stored locally; The third module is used to establish a third correspondence between the common user characteristics and the target page content.

27. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-13.

28. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-13.

29. A computer program product comprising a computer program stored on a storage medium, the computer program implementing the method according to any one of claims 1-13 when executed by a processor.

Images