Method, device, medium and electronic device for identifying key segments in content

Abstract

This application provides a method, apparatus, computer-readable medium, and electronic device for identifying key segments in content. The method includes: dividing content into multiple segments; acquiring behavioral data generated by multiple objects when accessing various segments of the content; determining the criticality of each segment in the content based on the behavioral data generated by the multiple objects when accessing each segment, wherein the criticality is used to measure the importance of the segment in the content; and identifying at least one key segment among the multiple segments of the content based on the criticality of each segment. This application can automatically extract more valuable and worthwhile key segments from content, thereby improving the user's information acquisition efficiency and saving the user's time by providing these key segments. This application can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and more specifically, to a method, apparatus, computer-readable medium, and electronic device for identifying key segments in content. Background Technology

[0002] With the development of the internet, especially the mobile internet, the information age has arrived, and all kinds of content, such as articles, videos, and pictures, are flooding into people's lives.

[0003] While the internet provides users with a convenient way to access content, much of that content contains a large amount of information that is hardly worth browsing. This information consumes a significant amount of users' reading time and does not provide any valuable information, thus reducing the efficiency of information acquisition and resulting in a poor user experience. Summary of the Invention

[0004] Embodiments of this application provide a method, apparatus, computer-readable medium, and electronic device for identifying key segments in content, which can at least to some extent automatically extract key segments from content, thereby improving the user's information acquisition efficiency and saving the user's time by providing key segments to the user.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to one aspect of the embodiments of this application, a method for identifying key segments in content is provided. The method includes: dividing the content into multiple segments; acquiring behavioral data generated by multiple objects when accessing each segment in the content; determining the keyness of each segment in the content based on the behavioral data generated by the multiple objects when accessing each segment in the content, wherein the keyness is used to measure the degree of importance of the segment in the content; and identifying at least one key segment among the multiple segments of the content based on the keyness of each segment in the content.

[0007] According to one aspect of the embodiments of this application, an apparatus for identifying key segments in content is provided. The apparatus includes: a segmentation unit for dividing the content into multiple segments; a behavior data acquisition unit for acquiring behavior data generated by multiple objects when accessing each segment in the content; a determination unit for determining the keyness of each segment in the content based on the behavior data generated by the multiple objects when accessing each segment in the content, the keyness being used to measure the degree of importance of the segment in the content; and an identification unit for identifying at least one key segment among the multiple segments of the content based on the keyness of each segment in the content.

[0008] In some embodiments of this application, based on the foregoing scheme, the content is an article, and the behavior data acquisition unit is configured to: acquire the exposure duration of each exposure of each segment in the article by multiple objects when reading the article, so as to obtain the exposure duration corresponding to the multiple exposures of each segment, wherein the exposure duration is the duration from when the segment appears on the screen until the segment disappears from the screen.

[0009] In some embodiments of this application, based on the foregoing scheme, the determining unit is configured to: normalize the exposure duration corresponding to each exposure of a segment in the article based on the exposure duration of each exposure of multiple objects when reading the article, to obtain the normalized exposure duration of each segment; and determine the criticality of each segment in the article based on the normalized exposure duration of each segment in the article.

[0010] In some embodiments of this application, based on the foregoing scheme, the behavior data acquisition unit is further configured to: acquire the number of times each segment in the article is exposed by multiple objects while reading the article; the determination unit is further configured to: normalize the number of times each segment in the article is exposed based on the number of times each segment is exposed, to obtain the normalized exposure count of each segment; and determine the criticality of each segment in the content based on the normalized exposure duration and normalized exposure count of each segment in the article.

[0011] In some embodiments of this application, based on the foregoing scheme, the behavioral data further includes active operation record data, and the determining unit is configured to: for each segment in the article, according to the active operation record data generated when the segment is exposed, perform weighted processing on the exposure duration of at least one exposure of the segment, and replace the exposure duration with the corresponding weighted exposure duration; perform normalization processing on multiple exposure durations corresponding to each segment to obtain the normalized exposure duration of each segment, wherein the multiple exposure durations include the weighted exposure duration.

[0012] In some embodiments of this application, based on the foregoing scheme, the behavior data acquisition unit is further configured to: acquire each exposure record of each segment in the article by multiple objects while reading the article, and calculate an original exposure count based on each exposure record; for each segment in the article, weight the original exposure count of at least one exposure record of the segment based on the active operation record data generated when the segment is exposed, to obtain a weighted original exposure count; for each segment in the article, obtain the exposure count of the segment based on the weighted original exposure count of at least one exposure record of the segment and the original exposure count of other exposure records.

[0013] In some embodiments of this application, based on the foregoing scheme, the identification unit is configured to: determine a first candidate key segment from multiple segments of the content according to the keyness of each segment in the content; extract behavioral features of each segment from behavioral data generated by the multiple objects when accessing each segment of the content; input the behavioral features of each segment into a pre-established artificial intelligence model to obtain the predicted probability value corresponding to each segment output by the artificial intelligence model; determine a second candidate key segment from multiple segments of the content according to the predicted probability value corresponding to each segment in the content; and determine a key segment based on the first candidate key segment and the second candidate key segment.

[0014] In some embodiments of this application, based on the foregoing scheme, after identifying at least one key segment among multiple segments of the content according to the keyness of each segment in the content, the identification unit is further configured to: provide the content to the target object when the target object accesses the content, and highlight the key segment in the content.

[0015] In some embodiments of this application, based on the foregoing scheme, after identifying at least one key segment among multiple segments of the content according to the keyness of each segment in the content, the identification unit is further configured to: provide operation controls to the target object in the display interface of the content when the target object accesses the content; and in response to the target object's triggering operation on the operation controls, display only the key segment in the content in the display interface.

[0016] According to one aspect of the embodiments of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for identifying key segments in content as described in the above embodiments.

[0017] According to one aspect of the embodiments of this application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method for identifying key segments in content as described in the above embodiments.

[0018] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium, a processor of a computer device reading the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to cause the computer device to perform the method for identifying key segments in content as described in the above embodiments.

[0019] In some embodiments of this application, after dividing content into multiple segments, behavioral data generated by multiple objects when accessing each segment of the content is obtained. The criticality of each segment is determined based on this behavioral data to measure its importance within the content. Finally, key segments are identified based on the criticality of each segment. Therefore, this method, leveraging big data, can automatically extract more valuable and worthwhile key segments from the content. Providing these key segments to users improves their information retrieval efficiency and saves them time.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0022] Figure 1 This diagram illustrates the application scenarios of text summarization technology in search engines.

[0023] Figure 2 This diagram illustrates an application scenario of text summarization technology in news event extraction.

[0024] Figure 3 This illustration shows a page diagram of an article with a low correlation between the body text and the title, according to one embodiment of this application;

[0025] Figure 4 A schematic diagram of a lengthy article according to an embodiment of this application is shown;

[0026] Figure 5 A schematic diagram of a clickbait article according to an embodiment of this application is shown;

[0027] Figure 6 A schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied is shown;

[0028] Figure 7 A flowchart illustrating a method for identifying key segments in content according to an embodiment of this application is shown;

[0029] Figure 8 An embodiment according to this application is shown. Figure 7 A flowchart detailing step 720 is provided.

[0030] Figure 9 An embodiment according to this application is shown. Figure 8 A flowchart detailing step 730 is provided.

[0031] Figure 10 A flowchart illustrating the process of obtaining the number of times each segment of an article is exposed by multiple objects while reading the article, according to an embodiment of this application;

[0032] Figure 11 An embodiment according to this application is shown. Figure 7 Flowchart of the steps following step 740;

[0033] Figure 12 Another embodiment according to this application is shown. Figure 7 Flowchart of the steps following step 740;

[0034] Figure 13 A schematic diagram of the overall process of a solution according to an embodiment of this application is shown;

[0035] Figure 14 A block diagram of an apparatus for identifying key segments in content according to an embodiment of this application is shown;

[0036] Figure 15 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0037] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0038] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0039] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0040] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0041] With the advent of the information age, users are like sailing in a sea of ​​information when accessing content on the internet, overwhelmed by a large amount of worthless information. Much of the content contains very little valuable information, requiring users to expend considerable effort to discern it, which wastes a significant amount of their time.

[0042] Among related technologies, those capable of automatically processing information mainly include text summarization technology and automatic news writing technology.

[0043] Text summarization technology can automatically generate or extract the central idea of ​​an article and use that central idea as a summary, thus transforming a long text into a shorter summary. Text summarization technology can be applied in scenarios such as search engines and news event extraction.

[0044] Search engines can retrieve URLs that match input keywords by using text summarization technology. Specifically, search engines can extract summaries from articles on each URL, and then determine which URL matches the keywords by checking if the keywords are present in the summary. Figure 1 This diagram illustrates the application scenario of text summarization technology in search engines. Please refer to [link / reference]. Figure 1 As shown, when a user enters the keyword "text summarization technology" into a search engine, the search engine returns corresponding search results. The summary of each URL in these search results matches "text summarization technology." For example, the summary of the first search result is the content in the rectangle, which contains "text summary" and "technology," clearly matching "text summarization technology."

[0045] In news event extraction applications, text summarization technology can be used to extract brief news events. Figure 2 This diagram illustrates an application scenario of text summarization technology in news event extraction. Please refer to [link / reference]. Figure 2As shown, many websites use text summarization technology to extract news events from their trending search lists.

[0046] In addition, there is also automatic news writing technology, which can generate news events quickly and easily, and is often used in breaking news or sports news reporting.

[0047] However, the main purpose of text summarization technology is to extract the content fragments most relevant to the search intent, rather than the most essential key fragments of the article; although automatic news writing technology has less redundant information, its application scenarios are relatively limited, and the news articles it produces are relatively short.

[0048] Therefore, the relevant technologies are unable to identify key segments in the articles; in addition, with the increasing number of self-media articles nowadays, the relevant technologies are clearly helpless against the large number of self-media articles and cannot achieve effective information processing of self-media articles.

[0049] Therefore, this application first provides a method for identifying key segments in content. The method for identifying key segments in content provided by the embodiments of this application can overcome the above-mentioned defects, and can identify essential key segments from a large amount of complex content. This allows users to more efficiently obtain key segments from articles and other content, enabling them to obtain key information more concisely and directly, improving information acquisition efficiency, saving time, and enhancing user experience. The method for identifying key segments in content provided by the embodiments of this application is particularly suitable for articles with the following problems: low relevance between the main text and the title, overly lengthy articles, and clickbait articles.

[0050] Articles with low relevance between the body text and the title refer to articles whose body text contains image and text information that is not closely related to the title. Users are easily lost in this uninformative information. Figure 3 This illustration shows a page layout of an article with a low correlation between the body text and the title, according to one embodiment of this application. See also... Figure 3 As shown, the article is titled "Research Shows: The Best Fitness Method XX", but the main text contains a lot of content that is not very relevant to "the best fitness method". This content is marked in a rounded rectangle.

[0051] An overly long article refers to an article with too many words. Figure 4 The illustration shows a page diagram of a lengthy article according to one embodiment of this application. It can be seen that the article's title is related to banking, the body text occupies a considerable amount of space, and banking-related content is distributed throughout the body text.

[0052] Clickbait articles are those with exaggerated titles, but the main text may be completely unrelated or only marginally connected to the title. Figure 5 A schematic diagram of a clickbait article page according to one embodiment of this application is shown. Figure 5 As can be seen, clickbait articles may attract users to click, but the articles themselves are of low value. Only a small portion of the main text contains information worth reading, wasting users' reading time.

[0053] By using the method for identifying key segments in the content provided in the embodiments of this application to process the articles with the aforementioned problems, the key segments in these articles can be automatically identified. By providing these key segments directly to users, users can efficiently, directly, and quickly obtain the most valuable information in the articles.

[0054] Figure 6 A schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied is shown. Please refer to... Figure 6 As shown, the system architecture 600 may include: a content uploading terminal 610, a server 620, and multiple user terminals. Specifically, the multiple user terminals include a first user terminal 630, a second user terminal 640, and a third user terminal 650. Communication connections are established between each user terminal and the server 620, as well as between the content uploading terminal 610 and the server 620. The content uploading terminal 610 has a content uploading client, and each user terminal runs an access client. The server 620 is equipped with a server that provides services to the access clients on the user terminals and the content uploading clients on the content uploading terminal 610. Taking the server 620 as the execution terminal in this embodiment as an example, when the method for identifying key segments in content provided in this application is applied... Figure 6 In the system architecture shown, a process can be as follows: First, after creating content, the user of content uploading terminal 610 uploads the content to server 620 through the content uploading client. Then, the server 620 identifies key segments in the content by executing the following process: dividing the content into multiple segments; sending the content to at least two user terminals based on content access requests from at least two user terminals; acquiring behavioral data generated by each user terminal when accessing each segment of the content; determining the criticality of each segment based on the behavioral data, and identifying at least one key segment among the multiple segments of the content based on the criticality of each segment; finally, when a target user terminal requests access to the content, server 620, while returning the content to the target user terminal, highlights the key segments in the content or provides a button on the content display interface so that when the user of the target user terminal triggers the button, the key segments in the content are highlighted or only displayed. This allows the user of the target user terminal to directly access the more valuable and worthwhile key segments, thereby improving information acquisition efficiency.

[0055] In some embodiments of this application, the content includes any one of the following: articles, videos, audio, and images, including pictures and / or text.

[0056] In some embodiments of this application, the content uploaded by the content uploading terminal 610 to the server 620 is a self-media article.

[0057] It should be understood that Figure 6 The number of content upload terminals, servers, and user terminals shown is merely illustrative. Depending on implementation needs, there can be any number of content upload terminals, servers, and user terminals. For example, there can be multiple content upload terminals, a server cluster consisting of multiple servers, and three or more user terminals.

[0058] It should be noted that, Figure 6 The illustration shown is merely one embodiment of this application. Although in Figure 6 In the embodiment, the content uploading terminal is a laptop, the execution terminal is a server, and the user terminal is a smartphone. The content uploading terminal and the user terminal are of different types. However, in other embodiments of this application, the content uploading terminal, the execution terminal, and the user terminal can be various terminal devices such as desktop computers, laptops, iPads, smartphones, and in-vehicle terminals, and the content uploading terminal and the user terminal can also be of the same type. Although in Figure 6 In this embodiment, the content is a self-media article, but this is easy to understand. In other embodiments of this application, the content can also be articles from authoritative media or other types of articles, and the content can even be books; although Figure 6 The proposed solution identifies key segments in the content by acquiring behavioral data generated by each user terminal when accessing various segments of the content. However, in other embodiments of this application, the content can also be sent to the terminal of a content approver, and key segments can be identified by acquiring behavioral data generated by the content approver when accessing various segments of the content. This application does not limit the scope of protection in any way, nor should it restrict the scope of protection of this application.

[0059] It is readily understood that the method for identifying key segments in content provided in the embodiments of this application is generally executed by a server, and correspondingly, the apparatus for identifying key segments in content is generally located in the server. However, in other embodiments of this application, the terminal device may also have similar functions to the server, thereby executing the scheme for identifying key segments in content provided in the embodiments of this application.

[0060] Therefore, the solutions in this application can be applied to terminals or servers. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0061] The implementation details of the technical solutions in the embodiments of this application are described in detail below:

[0062] Figure 7 A flowchart illustrating a method for identifying key segments in content according to an embodiment of this application is shown. This method can be executed by various computing and processing devices, such as user terminals or cloud servers. User terminals include, but are not limited to, mobile phones, computers, smart voice interaction devices, smart home appliances, in-vehicle terminals, and wearable devices. Embodiments of this application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, and assisted driving.

[0063] Please refer to Figure 7 As shown, the method for identifying key segments in content includes at least the following steps:

[0064] In step 710, the content is divided into multiple segments.

[0065] The content can be any of the following: books, articles, videos, audio, or pictures. When the content is an article, it can include not only text and symbols, but also at least one type of information such as videos, audio, pictures, and tables.

[0066] Content can be divided according to various rules, and the division method can be selected according to the different content types. For example, when the content is audio or video, it can be divided according to duration, with each minute divided into a segment to make the segments similar in length; when the content is a book, each page of the book can be divided into a segment.

[0067] The following will use an article as an example to further illustrate the solution of this application.

[0068] In one embodiment of this application, the content is an article, which includes multiple sentences. Dividing the content into multiple segments includes: dividing the article into multiple segments based on the sentences, so that the number of characters in each segment does not exceed a predetermined number of characters.

[0069] The number of characters can be set as needed. For example, the number of characters can be 150. Therefore, by dividing the article into segments, the segment can be as short as a sentence and as long as several sentences of no more than 150 characters.

[0070] In one embodiment of this application, the article further includes at least one of video, audio, image, and table, dividing the content into multiple segments, and further includes dividing a video, an audio, an image, or a table in the article into a separate segment.

[0071] In one embodiment of this application, dividing an article into multiple segments based on sentences, such that the number of characters in each segment does not exceed a predetermined number of characters, includes: starting from the first sentence of the article, extracting one sentence from the sentences that have never been extracted and adding it to the sentence set extracted in this round; if continuing to extract the next sentence and adding it to the sentence set extracted in this round would cause the number of characters in the sentence set extracted in this round to exceed the predetermined number of characters, then the sentence set extracted in this round forms the current segment; if the number of characters in the first sentence added to the sentence set extracted in this round exceeds the predetermined number of characters, then the sentence is divided into two segments; continuing to extract sentences starting from the first sentence that has never been extracted from the article, and forming the next segment based on the sentence set extracted in the next round, until all sentences of the article are divided into corresponding segments.

[0072] If the first sentence added to the sentence set extracted in this round has more than 150 characters, then the sentence can be divided into two segments on average.

[0073] In one embodiment of this application, dividing the content into multiple segments includes: determining whether the content is an article of a preset type; if the content is an article of a preset type, then dividing the content into multiple segments.

[0074] The preset article type could be a self-media article. The quality of self-media articles varies greatly. By identifying key segments only in self-media articles, even when the content value of the self-media article is low, only key segments can be identified and provided to users, which can save users' time to a greater extent.

[0075] In one embodiment of this application, dividing the content into multiple segments includes: determining whether the number of words in the article exceeds a predetermined number of words; if the number of words in the article exceeds the predetermined number of words, then dividing the article into multiple segments.

[0076] Articles with excessive word count are rather lengthy. By identifying only key segments and providing them to users when an article is too long, we can save users' time to a greater extent.

[0077] In one embodiment of this application, dividing the content into multiple segments includes: determining the relevance between the article title and the article content; if the relevance is lower than a predetermined relevance threshold, then dividing the article content into multiple segments.

[0078] When the article title has a low relevance to the article content, it means that the article content contains a lot of information that is not related to the article title. In this case, identifying only the key segments and providing them to the user can save the user's time to a greater extent.

[0079] In step 720, behavioral data generated by multiple objects when accessing various fragments of the content is obtained.

[0080] An object can be an entity that can access content, such as a user account used by a user or the IP address used by a user's terminal.

[0081] By setting appropriate scripts or code for the content, you can obtain behavioral data of an object when accessing various fragments of the content.

[0082] When the content is an article, users can read it through a web page, thus gaining access to the content.

[0083] When the content is an article, the object can be either a user's account or an approver's account. Users can log in to the content platform with their user accounts to read articles, and approvers can also log in to the content platform with their accounts to approve articles uploaded to the content platform, which is equivalent to accessing the content.

[0084] Each object can access every segment in the content. Different objects accessing the same segment may generate different behavioral data. Of course, an object can also choose not to access one or more segments in the content, in which case no corresponding behavioral data will be generated.

[0085] Figure 8 An embodiment according to this application is shown. Figure 7 A flowchart detailing step 720. (See attached flowchart.) Figure 8 As shown, obtaining behavioral data generated by multiple objects when accessing various fragments of content can specifically include the following steps:

[0086] In step 720', the exposure duration of each exposure of each segment in the article by multiple objects when reading the article is obtained, so as to obtain the exposure duration corresponding to the multiple exposures of each segment. The exposure duration is the time from when the segment appears on the screen until the segment disappears from the screen.

[0087] Specifically, in this embodiment, the behavioral data includes the exposure duration of the segment in each exposure. Exposure refers to the segment appearing or fully appearing on the screen when the user is reading the article. The timer starts from the moment the segment appears on the screen. The timer ends when the user moves the article on the screen and the article is completely swiped off the screen, thus obtaining the exposure duration. Each user can expose the segment once each time they read an article, and different users will expose the same segment when reading the same article. Therefore, each segment will correspond to multiple exposures.

[0088] For an article, users will spend more time reading the key and more worthwhile parts. Therefore, exposure time directly reflects the importance of a part. Based on this behavioral data of the exposure time of a part in each exposure, key parts can be accurately identified.

[0089] In step 730, the criticality of each segment in the content is determined based on the behavioral data generated by multiple objects when accessing each segment in the content. The criticality is used to measure the importance of the segment in the content.

[0090] Keyness, also known as essence, refers to the higher the keyness of a segment in the content, the more worthwhile that segment is to access.

[0091] Figure 9 An embodiment according to this application is shown. Figure 8 A flowchart detailing step 730 is provided. Please refer to [link / reference]. Figure 9 As shown, the criticality of each segment in the content can be determined through the following steps:

[0092] In step 731, based on the exposure duration of each exposure of each segment in the article by multiple objects while reading the article, the exposure duration corresponding to the multiple exposures of each segment is normalized to obtain the normalized exposure duration of each segment.

[0093] Specifically, the normalized exposure duration for each segment can be obtained using the following formula:

[0094]

[0095] Among them, T i Let be the normalized exposure duration of the i-th segment. Let represent the exposure duration of the i-th segment during the j-th exposure, and n be the number of exposures for the segment. This is the sum of the exposure durations of all exposures across all segments.

[0096] In one embodiment of this application, before normalizing the exposure duration corresponding to multiple exposures of each segment based on the exposure duration of each exposure of each segment in the article by multiple objects while reading the article, the method for identifying essential segments in the content further includes:

[0097] Remove segments whose exposure duration does not exceed the preset exposure duration threshold.

[0098] The preset exposure duration threshold can be set according to the actual application scenario, for example, it can be set to 1 second.

[0099] Short exposure times are unlikely to be critical segments. By removing short exposure times in advance, computational workload is saved.

[0100] In step 732, the criticality of each segment in the article is determined based on the normalized exposure duration of each segment.

[0101] The normalized exposure duration of a clip can be used directly as its keyness, or the keyness can be obtained by further calculating the normalized exposure duration, as long as the normalized exposure duration is positively correlated with the keyness.

[0102] When determining the criticality of a segment, normalization can be used to more accurately measure its criticality.

[0103] In one embodiment of this application, acquiring behavioral data generated by multiple objects when accessing various segments of content further includes: acquiring the number of times each segment of the article is exposed by multiple objects while reading the article; determining the criticality of each segment of the article based on the normalized exposure duration of each segment, including: normalizing the exposure count of each segment of the article based on the exposure count of each segment of the article to obtain the normalized exposure count of each segment; and determining the criticality of each segment of the content based on the normalized exposure duration and the normalized exposure count of each segment of the article.

[0104] Each time a fragment of an article appears completely on the screen, it is considered one exposure of that fragment. The behavioral data in this embodiment also includes the number of exposures of the fragment.

[0105] Similar to the method of normalizing exposure duration, the normalized exposure count for each segment can be obtained using the following formula:

[0106]

[0107] Among them, E i Let i be the normalized exposure count of the i-th segment. This represents the number of exposures of the i-th segment during the j-th exposure, where n is the total number of original exposures for the segment. This is the sum of the exposure times for all exposures across all segments.

[0108] As can be seen from the above formula, both the normalized exposure duration and the normalized exposure count are real numbers between 0 and 1. By determining the criticality of a segment based on the normalized exposure duration and the normalized exposure count, the criticality of the segment can be measured more accurately.

[0109] The criticality of a clip can be calculated in various ways based on the normalized exposure duration and the normalized exposure count. The key is simply to ensure that the calculated criticality is positively correlated with the normalized exposure duration and the normalized exposure count.

[0110] In one embodiment of this application, the criticality of each segment in the content is determined based on the normalized exposure duration and normalized exposure count of each segment in the article, including: determining the weighted sum of the normalized exposure duration and normalized exposure count of each segment as the criticality of each segment.

[0111] When calculating the weighted sum, the weights of normalized exposure duration and normalized exposure count can be set as needed. For example, the weight of normalized exposure duration can be greater than the weight of normalized exposure count.

[0112] In one embodiment of this application, the criticality of a segment is determined by the following formula:

[0113]

[0114] Among them, E i T represents the normalized exposure count of the i-th segment. i Let ν be the normalized exposure duration of the i-th segment. i Let be the keyness of the i-th segment.

[0115] In one embodiment of this application, the behavioral data further includes active operation record data. Based on the exposure duration of each exposure of various segments in the article by multiple objects while reading the article, the exposure duration corresponding to multiple exposures of each segment is normalized to obtain a normalized exposure duration for each segment. This includes: for each segment in the article, based on the active operation record data generated when the segment is exposed, weighting the exposure duration of at least one exposure of the segment, and replacing the exposure duration with the corresponding weighted exposure duration; normalizing the multiple exposure durations corresponding to each segment to obtain a normalized exposure duration for each segment, wherein the multiple exposure durations include the weighted exposure duration.

[0116] In one embodiment of this application, the active operation recording data includes at least one of the following: exposing a segment by swiping up, selecting at least a portion of the segment, and displaying the segment in a target area of ​​the screen.

[0117] When a clip generates active operation recording data during a certain exposure, the exposure duration of that exposure needs to be weighted. The weighting method can be set as needed, as long as the weighted exposure duration generated by the weighting process is greater than the exposure duration on which the weighted exposure duration was based. Therefore, for a clip, normalization processing will be performed based on the weighted exposure duration of at least one exposure of the clip and the exposure durations of other exposures.

[0118] Specifically, the screen can be divided into upper, middle, and lower areas. These areas can be divided evenly or according to other specified proportions. The target area of ​​the screen can be the middle area. Since users' attention spans vary across different screen areas, content displayed in the middle area is more likely to be what the user is reading. By displaying segments in the target area as active operation data, and by specially processing behavioral data such as the exposure duration of these segments, the normalized exposure duration can be determined more accurately, thereby enabling more accurate identification of key segments.

[0119] When a clip is displayed in the middle of the screen, the exposure duration of the clip in the middle area can be weighted only. For example, the exposure duration of the clip in the middle area can be multiplied by 2, while the exposure duration in other areas remains unchanged, so as to calculate the weighted exposure duration.

[0120] Users typically read articles by swiping down. When a user swipes up to expose a certain segment, it signals that the user is reading it repeatedly, and the exposure time of that segment can be weighted double.

[0121] When a user selects at least a portion of a segment, it indicates that the user is paying extra attention to the selected content. The exposure duration of that segment can be doubled. Alternatively, the weighting of the exposure duration of the segment can be determined based on the ratio of the length of the selected content to the length of the segment.

[0122] Figure 10 A flowchart illustrating the process of obtaining the number of times each segment of an article is viewed by multiple objects while reading the article, according to one embodiment of this application, is provided. Figure 10 As shown, obtaining the number of times each segment of an article is exposed by multiple objects while reading the article can specifically include the following steps:

[0123] In step 1010, the exposure records of each segment in the article by multiple objects while reading the article are obtained, and the original exposure count is calculated based on each exposure record.

[0124] Each exposure of a clip corresponds to one exposure record, meaning that each exposure of a clip counts as one original exposure.

[0125] In step 1020, for each segment in the article, the original exposure count of at least one exposure record of the segment is weighted based on the active operation record data generated when the segment is exposed, so as to obtain the weighted original exposure count.

[0126] When a segment generates active operation record data during a certain exposure, it is necessary to perform weighted processing on the original exposure count of that exposure. The weighting method can be set as needed, as long as the weighted original exposure count is greater than the original exposure count corresponding to the weighted original exposure count.

[0127] When a segment is exposed by a user's swipe up, or at least part of the segment is selected by the user, or the segment is displayed in the middle area of ​​the screen, the weighted original exposure count can be obtained by multiplying the original exposure count of the segment's single exposure by 2.

[0128] In step 1030, for each segment in the article, the exposure count of the segment is obtained based on the weighted original exposure count of at least one exposure record of the segment and the original exposure count of other exposure records.

[0129] If no active operation record data is generated, the original exposure count of the exposure record is 1; however, if active operation record data is generated during the exposure of the segment, the original exposure count after weighted processing of that exposure is a real number greater than 1.

[0130] When a segment generates multiple active operation records during a certain exposure, a larger weight can be set for weighted processing to further improve the accuracy of the calculated keyness.

[0131] In this embodiment of the application, by weighting the exposure duration and / or number of exposures based on the active operation recording data generated when the segment is exposed, the criticality used to measure the criticality of the segment in the content can be calculated more accurately, thereby more accurately identifying key segments.

[0132] In step 740, at least one key segment is identified among multiple segments of the content based on the keyness of each segment in the content.

[0133] Key segments are typically considered more critical than other segments in the content.

[0134] In one embodiment of this application, identifying at least one key segment among multiple segments of the content based on the keyness of each segment in the content includes: identifying the segment with the highest keyness in the content as the key segment.

[0135] In one embodiment of this application, identifying at least one key segment among multiple segments of the content based on the keyness of each segment in the content includes: selecting segments from the content whose keyness is higher than a predetermined keyness threshold as key segments.

[0136] In one embodiment of this application, identifying at least one key segment from multiple segments of content based on the keyness of each segment in the content includes: determining a first candidate key segment from multiple segments of content based on the keyness of each segment in the content; extracting behavioral features of each segment from behavioral data generated by multiple objects when accessing each segment of the content; inputting the behavioral features of each segment into a pre-established artificial intelligence model to obtain a predicted probability value corresponding to each segment output by the artificial intelligence model; determining a second candidate key segment from multiple segments of content based on the predicted probability value corresponding to each segment in the content; and determining a key segment based on the first candidate key segment and the second candidate key segment.

[0137] The types of behavioral features can be predefined by experts. Behavioral features can be calculated in various ways, even using the same methods as normalized exposure duration and normalized exposure counts. Each segment can have multiple behavioral features. Artificial intelligence models can employ various algorithms such as logistic regression and deep learning models. The predicted probability value output by the artificial intelligence model is used to predict the probability that a segment belongs to a key segment.

[0138] You can choose the segment whose predicted probability value is greater than a predetermined probability threshold as the second candidate key segment, or you can choose the segment with the highest predicted probability value as the second candidate key segment.

[0139] In this embodiment, the corresponding candidate key segments are identified by using two methods respectively, and then the key segment is identified by combining the two candidate key segments, thereby improving the accuracy of key segment identification.

[0140] In one embodiment of this application, determining a key segment based on a first candidate key segment and a second candidate key segment includes: if the first candidate key segment and the second candidate key segment are the same, then the first candidate key segment or the second candidate key segment is used as the key segment.

[0141] In one embodiment of this application, there are multiple first candidate key segments and multiple second candidate key segments. Determining a key segment based on the first candidate key segments and the second candidate key segments includes: taking the intersection of the first candidate key segments and the second candidate key segments as the key segment.

[0142] In the embodiments of this application, only a segment that belongs to both the first candidate key segment and the second candidate key segment can become a key segment, thus ensuring the accuracy of key segment identification.

[0143] Figure 11 An embodiment according to this application is shown. Figure 7 A flowchart of the steps following step 740. Please refer to [link / reference]. Figure 11 As shown, the following steps may be included after step 740:

[0144] In step 750, when the target object accesses the content, the content is provided to the target object, and key segments in the content are highlighted.

[0145] When a user requests access to an article, the article is returned to the user, and key sections of the article are highlighted.

[0146] Key segments can be highlighted by one or more of the following methods: bolding, changing the font, enlarging, italicizing, adding an underline, or changing the color.

[0147] Figure 12 Another embodiment according to this application is shown. Figure 7 A flowchart of the steps following step 740. Please refer to [link / reference]. Figure 12 As shown, the following steps may be included after step 740:

[0148] In step 760, when the target object accesses the content, operation controls are provided to the target object in the content display interface.

[0149] Operation controls can be, for example, buttons. When a user is reading an article, the display interface will show the full content of the article; at the same time, the display interface of the article also has a button.

[0150] In step 770, in response to the target object's trigger operation on the operation control, only key segments of the content are displayed in the display interface.

[0151] When a user clicks the button with a mouse or by pressing the screen, the article's display will switch directly from showing the full content to showing key excerpts, thereby improving the efficiency of the user's information retrieval.

[0152] Of course, in other embodiments of this application, the key segments in the article can be toggled by setting operation controls.

[0153] Figure 13 A schematic diagram of the overall process according to an embodiment of this application is shown. Please refer to... Figure 13 As shown, the specific process may include the following steps: First, divide the article into segments; then, record behavioral data based on the segments to obtain behavioral data; next, process the behavioral data; finally, calculate the keyness of each segment based on the processing results, and identify key segments based on the keyness.

[0154] In summary, the method for identifying key segments in content provided in this application, leveraging big data, can automatically extract more valuable and worthwhile key segments from the content. Providing these key segments to users improves their information acquisition efficiency and saves them time. When the content is an article, this solution can use behavioral data analysis to identify the most worthwhile parts of the article, allowing users to quickly grasp the essence and focus on both key points and details. This provides users with a concise and fast reading experience while giving them greater control over the entire reading process.

[0155] The following describes an apparatus embodiment of this application, which can be used to execute the method for identifying key segments in content as described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method for identifying key segments in content described above.

[0156] Figure 14 A block diagram of an apparatus for identifying key segments in content according to an embodiment of this application is shown.

[0157] Reference Figure 14 As shown, an apparatus 1400 for identifying key segments in content according to an embodiment of this application includes: a segmentation unit 1410, a behavior data acquisition unit 1420, a determination unit 1430, and an identification unit 1440. The segmentation unit 1410 is used to divide the content into multiple segments; the behavior data acquisition unit 1420 is used to acquire behavior data generated by multiple objects when accessing each segment of the content; the determination unit 1430 is used to determine the criticality of each segment in the content based on the behavior data generated by the multiple objects when accessing each segment, the criticality being used to measure the importance of the segment in the content; and the identification unit 1440 is used to identify at least one key segment among the multiple segments of the content based on the criticality of each segment.

[0158] In some embodiments of this application, based on the foregoing scheme, the content is an article, and the behavior data acquisition unit 1420 is configured to: acquire the exposure duration of each exposure of each segment in the article by multiple objects when reading the article, so as to obtain the exposure duration corresponding to the multiple exposures of each segment, wherein the exposure duration is the duration from when the segment appears on the screen to when the segment disappears from the screen.

[0159] In some embodiments of this application, based on the foregoing scheme, the determining unit 1430 is configured to: normalize the exposure duration corresponding to each exposure of a segment in the article based on the exposure duration of each exposure of multiple objects when reading the article, to obtain the normalized exposure duration of each segment; and determine the criticality of each segment in the article based on the normalized exposure duration of each segment in the article.

[0160] In some embodiments of this application, based on the foregoing scheme, the behavior data acquisition unit 1420 is further configured to: acquire the number of times each segment in the article is exposed by multiple objects while reading the article; the determination unit 1430 is further configured to: normalize the number of times each segment in the article is exposed based on the number of times each segment is exposed, to obtain the normalized exposure number of each segment; and determine the criticality of each segment in the content based on the normalized exposure duration and normalized exposure number of each segment in the article.

[0161] In some embodiments of this application, based on the foregoing scheme, the behavioral data further includes active operation record data, and the determining unit 1430 is configured to: for each segment in the article, according to the active operation record data generated when the segment is exposed, perform weighted processing on the exposure duration of at least one exposure of the segment, and replace the exposure duration with the corresponding weighted exposure duration; perform normalization processing on multiple exposure durations corresponding to each segment to obtain the normalized exposure duration of each segment, wherein the multiple exposure durations include the weighted exposure duration.

[0162] In some embodiments of this application, based on the foregoing scheme, the behavior data acquisition unit 1420 is further configured to: acquire each exposure record of each segment in the article by multiple objects while reading the article, and calculate an original exposure count based on each exposure record; for each segment in the article, weight the original exposure count of at least one exposure record of the segment based on the active operation record data generated when the segment is exposed, to obtain a weighted original exposure count; for each segment in the article, obtain the exposure count of the segment based on the weighted original exposure count of at least one exposure record of the segment and the original exposure count of other exposure records.

[0163] In some embodiments of this application, based on the foregoing scheme, the identification unit 1440 is configured to: determine a first candidate key segment from multiple segments of the content based on the keyness of each segment in the content; extract behavioral features of each segment from behavioral data generated by the multiple objects when accessing each segment of the content; input the behavioral features of each segment into a pre-established artificial intelligence model to obtain the predicted probability value output by the artificial intelligence model corresponding to each segment; determine a second candidate key segment from multiple segments of the content based on the predicted probability value corresponding to each segment in the content; and determine a key segment based on the first candidate key segment and the second candidate key segment.

[0164] In some embodiments of this application, based on the foregoing scheme, after identifying at least one key segment among multiple segments of the content according to the keyness of each segment in the content, the identification unit 1440 is further configured to: provide the content to the target object when the target object accesses the content, and highlight the key segment in the content.

[0165] In some embodiments of this application, based on the foregoing scheme, after identifying at least one key segment among multiple segments of the content according to the keyness of each segment in the content, the identification unit 1440 is further configured to: provide operation controls to the target object in the display interface of the content when the target object accesses the content; and in response to the target object's triggering operation on the operation controls, display only the key segment in the content in the display interface.

[0166] Figure 15 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0167] It should be noted that, Figure 15 The computer system 1500 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0168] like Figure 15As shown, the computer system 1500 includes a Central Processing Unit (CPU) 1501, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1502 or programs loaded from storage portion 1508 into Random Access Memory (RAM) 1503, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1503. The CPU 1501, ROM 1502, and RAM 1503 are interconnected via bus 1504. An Input / Output (I / O) interface 1505 is also connected to bus 1504.

[0169] The following components are connected to I / O interface 1505: an input section 1506 including a keyboard, mouse, etc.; an output section 1507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1508 including a hard disk, etc.; and a communication section 1509 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1509 performs communication processing via a network such as the Internet. A drive 1510 is also connected to I / O interface 1505 as needed. Removable media 1511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1510 as needed so that computer programs read from them can be installed into storage section 1508 as needed.

[0170] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1509, and / or installed from removable medium 1511. When the computer program is executed by central processing unit (CPU) 1501, it performs various functions defined in the system of this application.

[0171] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0172] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0173] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0174] In one aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0175] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0176] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0177] It is understood that in the specific implementation of this application, data related to user access to content is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0178] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0179] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method of identifying key segments in content, characterized by, The method includes: Determine whether the article is of a preset type; If the article is of a preset type, the article will be divided into multiple segments so that the number of characters in each segment does not exceed a predetermined number of characters; The exposure duration of each exposure of each segment in the article by multiple objects when reading the article is obtained, so as to obtain the exposure duration corresponding to the multiple exposures of each segment, wherein the exposure duration is the time from when the segment appears on the screen to when the segment disappears from the screen; Get the number of times each segment of the article is exposed by multiple objects while reading the article; For each segment in the article, based on the active operation recording data generated when the segment is exposed, the exposure duration of at least one exposure of the segment is weighted and replaced with the corresponding weighted exposure duration. The active operation recording data is at least one of the following: exposing the segment by swiping up, selecting at least a part of the segment, or displaying the segment in a target area of ​​the screen. The multiple exposure durations corresponding to each segment are normalized to obtain the normalized exposure duration of each segment, wherein the multiple exposure durations include the weighted exposure duration; Based on the exposure count of each segment in the article, the exposure count of each segment in the article is normalized to obtain the normalized exposure count of each segment; Based on the normalized exposure duration and normalized exposure count of each segment in the article, the criticality of each segment in the article is determined, and the criticality is used to measure the importance of the segment in the article; Based on the criticality of each segment in the article, at least one key segment is identified among multiple segments of the article; When the target object accesses the article, the article is provided to the target object, and the key sections in the article are highlighted.

2. The method of claim 1, wherein, The step of obtaining the number of times each segment of the article is exposed by multiple objects while reading the article includes: Obtain the exposure records of each segment in the article by multiple objects while reading the article, and calculate the original exposure count based on each exposure record; For each segment in the article, based on the active operation record data generated when the segment is exposed, the original exposure count of at least one exposure record of the segment is weighted to obtain the weighted original exposure count; For each segment in the article, the exposure count of the segment is obtained by weighting the original exposure count of at least one exposure record of the segment and the original exposure count of other exposure records.

3. The method of claim 1, wherein, The step of identifying at least one key segment among multiple segments of the article based on the keyness of each segment in the article includes: Based on the criticality of each segment in the article, a first candidate key segment is determined from multiple segments of the article; Extract the behavioral features of each segment from the behavioral data generated by the multiple objects when they access each segment in the article; The behavioral features of each segment are input into a pre-established artificial intelligence model to obtain the predicted probability value corresponding to each segment output by the artificial intelligence model. Based on the predicted probability value corresponding to each segment in the article, a second candidate key segment is determined from multiple segments of the article; Key segments are determined based on the first candidate key segments and the second candidate key segments.

4. The method of claim 1-3, wherein, After identifying at least one key segment among multiple segments of the article based on the keyness of each segment in the article, the method further includes: When the target object accesses the article, operation controls are provided to the target object in the article's display interface; In response to the target object's triggering operation on the operation control, only the key segments of the article are displayed in the display interface.

5. An apparatus for identifying key segments in content, the apparatus comprising: The device includes: The segmentation unit is used to determine whether the article is of a preset type; if the article is of a preset type, the article is divided into multiple segments so that the number of characters in each segment does not exceed a predetermined number of characters. The behavior data acquisition unit is used to acquire the exposure duration of each exposure of each segment in the article by multiple objects when reading the article, so as to obtain the exposure duration corresponding to the multiple exposures of each segment, wherein the exposure duration is the duration from when the segment appears on the screen to when the segment disappears from the screen; and to acquire the number of exposures of each segment in the article by multiple objects when reading the article. A determining unit is configured to, for each segment in the article, perform weighted processing on the exposure duration of at least one exposure of the segment based on active operation recording data generated when the segment is exposed, and replace the exposure duration with the corresponding weighted exposure duration. The active operation recording data includes at least one of the following: exposing the segment by swiping up, selecting at least a part of the segment, or displaying the segment in a target area of ​​the screen. The unit also normalizes multiple exposure durations corresponding to each segment to obtain a normalized exposure duration for each segment, wherein the multiple exposure durations include the weighted exposure duration. Furthermore, it normalizes the exposure count of each segment in the article based on the exposure count of each segment in the article to obtain a normalized exposure count for each segment. Finally, it determines the criticality of each segment in the article based on the normalized exposure duration and normalized exposure count, wherein the criticality is used to measure the importance of the segment in the article. The identification unit is used to identify at least one key segment among multiple segments of the article based on the keyness of each segment in the article; The device is also used to: provide the article to the target object when the target object accesses the article, and highlight the key segments in the article.

6. A computer readable medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for identifying key segments in the content as described in any one of claims 1 to 4.

7. An electronic device, comprising: include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method for identifying key segments in content as described in any one of claims 1 to 4.

8. A computer program product, characterised in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor of a computer device reading the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to cause the computer device to perform the method for identifying key segments in content as described in any one of claims 1 to 4.

Images