CN116992016A

CN116992016A - Content processing method, device, computer equipment and storage medium

Info

Publication number: CN116992016A
Application number: CN202311056725.8A
Authority: CN
Inventors: 蒲婷婷; 陈根岩
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2023-08-21
Filing date: 2023-08-21
Publication date: 2023-11-03

Abstract

The present disclosure provides a content processing method, apparatus, computer device, and storage medium, wherein the method includes: determining information of each knowledge point associated with target content in response to obtaining the target content to be summarized; generating first model auxiliary information based on the knowledge point information, and generating abstract information of the target content by using the first model auxiliary information; displaying the abstract information and target knowledge point information associated with the abstract information; the target knowledge point information is related to a learning scene associated with the summary information. According to the embodiment of the disclosure, the related abstract and knowledge point information can be displayed aiming at the target content, so that the relationship between the finally displayed abstract and knowledge point is more intimate, the user is facilitated to know the summary and knowledge point of the target content more clearly, and the efficiency of acquiring effective information is further improved.

Description

Content processing method, device, computer equipment and storage medium

Technical Field

The disclosure relates to the field of information technology, and in particular relates to a content processing method, a content processing device, computer equipment and a storage medium.

Background

With the development of internet technology, users can conveniently browse various knowledge contents, and the users can learn useful information from the browsed knowledge contents. However, when the number of words involved in the browsed knowledge content is large and the knowledge content is complex, the user usually needs to spend a long time to read and comb the whole content, which affects the efficiency of the user to obtain effective information from the knowledge content.

Therefore, how to improve the efficiency of the user to obtain the effective information from the related knowledge content is a problem worthy of research.

Disclosure of Invention

The embodiment of the disclosure at least provides a content processing method, a content processing device, computer equipment and a storage medium.

In a first aspect, an embodiment of the present disclosure provides a content processing method, including:

determining information of each knowledge point associated with target content in response to obtaining the target content to be summarized;

generating first model auxiliary information based on the knowledge point information, and generating abstract information of the target content by using the first model auxiliary information;

displaying the abstract information and target knowledge point information associated with the abstract information; the target knowledge point information is related to a learning scene associated with the summary information.

In an optional implementation manner, the determining, in response to obtaining the target content to be summarized, information of each knowledge point associated with the target content includes:

determining first text information corresponding to target content to be summarized in response to obtaining the target content;

and inputting the first text information and second model auxiliary information indicating knowledge point summary into an artificial intelligent model to obtain information of each knowledge point associated with the target content.

In an optional embodiment, the generating the first model auxiliary information based on the knowledge point information includes:

determining at least one knowledge point type associated with each knowledge point information and attribute information of each knowledge point type;

and generating first model auxiliary information based on the knowledge point type and the corresponding attribute information.

In an optional embodiment, the generating summary information of the target content using the first model auxiliary information includes:

and inputting the first model auxiliary information and the first text information corresponding to the target content into an artificial intelligent model to obtain abstract information of the target content.

In an alternative embodiment, the target knowledge point information associated with the summary information is determined according to the following steps:

determining at least one target knowledge point type matched with the learning scene from the knowledge point types corresponding to the knowledge point information according to the learning scene corresponding to the abstract information;

and taking the knowledge point information under the type of the target knowledge point as the target knowledge point information.

In an alternative embodiment, the presenting the summary information, and the target knowledge point information associated with the summary information, includes:

displaying the abstract information and displaying the type information of each target knowledge point under the abstract information;

and displaying the information of each target knowledge point under the information of each target knowledge point type.

In an alternative embodiment, the inputting the first text information and the second model auxiliary information indicating knowledge point summary into an artificial intelligence model to obtain information of each knowledge point associated with the target content includes:

responding to the fact that the number of characters corresponding to the first text information is larger than a first threshold value, and carrying out segmentation processing on the first text information to obtain a plurality of sub-text information;

And inputting the sub-text information and second model auxiliary information indicating knowledge point summary into an artificial intelligent model aiming at each piece of sub-text information to obtain information of each knowledge point corresponding to the sub-text information.

In an optional implementation manner, the responding to the fact that the number of characters corresponding to the first text information is greater than a first threshold value, performing segmentation processing on the first text information to obtain a plurality of sub-text information, includes:

determining a first text position from the initial information of the first text information to the character number reaching a first threshold value in response to the character number corresponding to the first text information being larger than the first threshold value;

taking the ending position of the previous paragraph closest to the first text position as the cut-off position of the first sub-text information;

and taking the rest text information except the first sub-text information in the first text information as updated first text information, and repeatedly executing the step of determining the first text position until segmentation is completed, so as to obtain each sub-text information.

Determining initial segmentation character numbers according to the character numbers of the first text information and the preset maximum segmentation number in response to the character numbers corresponding to the first text information being larger than a first threshold and smaller than a second threshold; the second threshold is determined based on the first threshold and the maximum number of segments;

determining a second text position from the initial information of the first text information to the point that the number of characters reaches the initial segmentation character number;

judging whether the number of characters from the start information of the first text information to the end position of the paragraph closest to the second text position is smaller than or equal to the first threshold value;

if yes, the end position of the paragraph closest to the second text position is used as the cut-off position of the first sub-text information, otherwise, the end position of the previous paragraph closest to the second text position is used as the cut-off position of the first sub-text information;

and taking the rest text information except the first sub-text information in the first text information as updated first text information, and repeatedly executing the step of determining the second text position until segmentation is completed, so as to obtain each sub-text information.

generating segment abstract information corresponding to each piece of sub-text information;

integrating the segment summary information corresponding to each piece of sub-text information to obtain integrated second text information;

and inputting the second text information and the first model auxiliary information into an artificial intelligent model to obtain the abstract information in response to the character number of the second text information being smaller than or equal to the first threshold.

In an alternative embodiment, after obtaining the integrated second text information, the method further includes:

and in response to the number of characters of the second text information being greater than the first threshold, taking the second text information as new first text information, and returning to execute the step of segmenting the first text information to obtain a plurality of sub-text information until the number of characters of the second text information is less than or equal to the first threshold.

In an alternative embodiment, the response to the learning scenario includes a language learning scenario, the method further comprising:

When a plurality of pieces of target knowledge point information are displayed, responding to any piece of target knowledge point information to be triggered, and displaying detail information corresponding to the target knowledge point information; the detail information comprises text information in the target content associated with the target knowledge point information and paraphrasing and/or example sentence information corresponding to the target knowledge point information.

In a second aspect, an embodiment of the present disclosure further provides a content processing apparatus, including:

the first determining module is used for determining information of each knowledge point associated with target content in response to obtaining the target content to be summarized;

the generation module is used for generating first model auxiliary information based on the knowledge point information, and generating abstract information of the target content by utilizing the first model auxiliary information;

the first display module is used for displaying the abstract information and target knowledge point information associated with the abstract information; the target knowledge point information is related to a learning scene associated with the summary information.

In a third aspect, embodiments of the present disclosure further provide a computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the alternative embodiments of the first aspect.

In a fourth aspect, the presently disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the first aspect, or any of the alternative embodiments of the first aspect, described above.

According to the content processing method provided by the embodiment of the disclosure, after the target content is acquired, each piece of knowledge point information related to the target content can be determined, first model auxiliary information for assisting in generating the abstract is generated based on each piece of knowledge point information, the obtained first model auxiliary information is related to the knowledge point, the attribute characteristics of the knowledge point can be reflected, and the attribute characteristics of the related knowledge point can be reflected based on the generated abstract information; and finally, selecting a target knowledge point in the learning scene associated with the abstract information from the knowledge points based on the generated abstract information for display. Therefore, the related abstract and knowledge point information can be displayed aiming at the target content, learning linkage can be formed between the abstract and the knowledge point, the relationship between the finally displayed abstract and knowledge point is more intimate, the user is facilitated to more clearly understand the summary and knowledge point of the target content, and further the efficiency of acquiring effective information is improved.

The foregoing objects, features and advantages of the disclosure will be more readily apparent from the following detailed description of the preferred embodiments taken in conjunction with the accompanying drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the embodiments are briefly described below, which are incorporated in and constitute a part of the specification, these drawings showing embodiments consistent with the present disclosure and together with the description serve to illustrate the technical solutions of the present disclosure. It is to be understood that the following drawings illustrate only certain embodiments of the present disclosure and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may admit to other equally relevant drawings without inventive effort.

FIG. 1 illustrates a flow chart of a content processing method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram showing summary information and various target knowledge point type information under the summary information when text content is shown, which is provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram showing summary information and showing various target knowledge point type information under the summary information when showing video content according to an embodiment of the present disclosure;

FIG. 4 illustrates a schematic diagram showing multiple target knowledge point information provided by an embodiment of the present disclosure;

fig. 5 shows a schematic diagram of detail information corresponding to information of a display target knowledge point provided by an embodiment of the present disclosure;

fig. 6 is a schematic diagram showing a structure of a content processing apparatus provided by an embodiment of the present disclosure;

fig. 7 shows a schematic diagram of a computer device provided by an embodiment of the disclosure.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. The components of the embodiments of the present disclosure, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure, as claimed, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be made by those skilled in the art based on the embodiments of this disclosure without making any inventive effort, are intended to be within the scope of this disclosure.

In the process of summarizing the browsed knowledge content, if the browsed knowledge content involves a large number of characters and the knowledge content is complex, the user usually needs to spend a long time to read and comb the whole content. Therefore, how to improve the efficiency of the user to obtain the effective information from the related knowledge content is a problem worthy of research.

Based on this, the present disclosure provides a content processing method including: determining information of each knowledge point associated with target content in response to obtaining the target content to be summarized; generating first model auxiliary information based on the knowledge point information, and generating abstract information of the target content by using the first model auxiliary information; displaying the abstract information and target knowledge point information associated with the abstract information; the target knowledge point information is related to a learning scene associated with the summary information.

According to the content processing method provided by the embodiment of the disclosure, after the target content is acquired, each piece of knowledge point information associated with the target content can be determined, first model auxiliary information for assisting in generating the abstract is generated based on each piece of knowledge point information, the obtained first model auxiliary information is associated with the knowledge point, the attribute characteristics of the knowledge point can be reflected, and the attribute characteristics of the related knowledge point can be reflected based on the generated abstract information; and finally, selecting a target knowledge point in the learning scene associated with the abstract information from the knowledge points based on the generated abstract information for display. Therefore, the related abstract and knowledge point information can be displayed aiming at the target content, so that the relationship between the finally displayed abstract and knowledge point is more intimate, the user is facilitated to know the summary and knowledge point of the target content more clearly, and the efficiency of acquiring the effective information is further improved.

The present invention is directed to a method for manufacturing a semiconductor device, and a semiconductor device manufactured by the method.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.

For the sake of understanding the present embodiment, first, a detailed description will be given of a content processing method disclosed in an embodiment of the present disclosure, where an execution body of the content processing method provided in the embodiment of the present disclosure is generally a computer device with a certain computing capability.

The content processing method provided in the embodiment of the present disclosure is described below by taking an execution subject as a terminal device as an example.

Referring to fig. 1, a flowchart of a content processing method according to an embodiment of the disclosure is shown, where the method includes S101 to S103, where:

s101: and determining information of each knowledge point associated with the target content in response to the acquisition of the target content to be summarized.

S102: generating first model auxiliary information based on the knowledge point information, and generating abstract information of the target content by using the first model auxiliary information.

S103: displaying the abstract information and target knowledge point information associated with the abstract information; the target knowledge point information is related to a learning scene associated with the summary information.

In the embodiments of the present disclosure, the target content to be summarized may include video content or text content. In one approach, the content to be summarized may be content presented in a web page. When a user opens a webpage to browse content, the content in the webpage can be identified, and the target content to be summarized is obtained.

In the embodiment of the disclosure, after the target content is acquired, summary extraction of knowledge points can be performed on the target content, and the knowledge points to be extracted can be knowledge points related to various aspects. The knowledge points herein are related knowledge content that is summarized for the target content for the user to learn or understand. For example, for an english content, the knowledge point information may include knowledge points related to an english learning scenario, for example, in the case that the target content is an english related content, knowledge point information in terms of english words, grammar, and the like may be related to the target content; in addition, the extracted knowledge points may also include knowledge points of other non-english learning scenes such as encyclopedia learning scenes and news information learning scenes, for example, knowledge point information on aspects such as character introduction in the encyclopedia of characters; embodiments of the present disclosure may not be particularly limited.

Knowledge point information associated with the target content can be obtained by summarizing and analyzing the target content. Before the summary analysis of the target content, text information of the target content can be determined, and knowledge point information is obtained according to the text information. In one embodiment, in response to obtaining the target content to be summarized, determining information of each knowledge point associated with the target content includes: determining first text information corresponding to target content in response to obtaining the target content to be summarized; and inputting the first text information and the second model auxiliary information indicating knowledge point summary into the artificial intelligent model to obtain information of each knowledge point associated with the target content.

In the above embodiment, for the target content in text form, the entire target content may be used as the first text information, and the key content of the target content may be extracted as the first text information, for example, the title information, the main content, and the like of the target content except for the annotation. For target content in a video form, caption information of the video content can be obtained as first text information, in addition, semantic recognition processing can be carried out on video pictures in the video content, the video pictures can be converted into text information, and the caption information of the video and the text information converted into the video pictures can be used as the first text information.

The second model assistance information may be used to instruct the artificial intelligence model to knowledge point summarize the first text information, and the second model assistance information may be configured based on the target content. For example, the second model auxiliary information may indicate "summarizing knowledge points based on the target content", and in addition, the second model auxiliary information may indicate some requirements for summarizing knowledge points, for example, in the case of identifying english content, may indicate requirements for summarized words, phrases and sentence patterns, for example, may indicate the number of words, the number of phrases and the number of sentence patterns, and may further include "the summarized words, phrases and sentence patterns should be highly related to the subject of the target content, and are commonly used in english learning" and other instructions that are beneficial for improving the quality of the summarized knowledge points.

After the first text information and the second model auxiliary information are input into the artificial intelligent model, the artificial intelligent model can summarize the first text information under the instruction of the second model auxiliary information to obtain information of each knowledge point related to the target content.

In consideration of the maximum number of characters of the first text information which can be processed by the server, in the process of determining the information of each knowledge point associated with the target content, if the number of characters of the first text information is larger, the first text information needs to be segmented. Here, the threshold value of the number of characters of the first text information that can be processed by the server, that is, the maximum number of characters of the first text information that can be processed, may be set and recorded as the first threshold value. In one embodiment, inputting the first text information and the second model auxiliary information indicating knowledge point summary into the artificial intelligence model to obtain information of each knowledge point associated with the target content, wherein the method comprises the following steps: responding to the fact that the number of characters corresponding to the first text information is larger than a first threshold value, segmenting the first text information to obtain a plurality of sub-text information; and inputting the sub-text information and second model auxiliary information indicating knowledge point summary into an artificial intelligent model aiming at each sub-text information to obtain information of each knowledge point corresponding to the sub-text information.

In the above embodiment, the first text information may be subjected to the segmentation processing in different segmentation manners. Among them, a procedure of performing the segmentation process will be described later.

The second model assistance information for knowledge point summarization of different sub-text information may be the same or different. The second model auxiliary information corresponding to each sub-text information may be generated in advance before the respective sub-text information and the second model auxiliary information are input to the artificial intelligence model. After each piece of sub-text information and the second model auxiliary information are respectively input into the artificial intelligent model, each piece of knowledge point information aiming at each piece of sub-text information can be obtained.

Before describing the process of performing the segmentation process, the type of the first text information is first introduced. The types of the first text information may be divided according to the number of characters of the first text information, and specifically may include the following types: the number of characters is less than a first threshold; (II) the number of characters is greater than a first threshold and less than a second threshold; and (III) the number of characters is greater than a second threshold.

Wherein the second threshold may be related to the first threshold, the maximum number of segments, and in one manner, the second threshold may be a product of the first threshold and the maximum number of segments. In addition, in the english scene, the threshold value of the number of characters may be replaced with the threshold value of the number of words. For example, the first threshold may be 9k if scaled to the number of words and the maximum number of segments is 8, and the second threshold may be 72k if scaled to the number of words.

The process of performing the segmentation process may be different for different types of first text information.

For the first text information of the first (first) type, that is, when the number of characters of the first text information is smaller than the first threshold, that is, smaller than the maximum number of characters that can be processed by the server, segmentation of the first text information may not be required.

For the first text information of the second type, that is, when the number of characters of the first text information is greater than the first threshold and smaller than the second threshold, in order to ensure that the number of characters of each sub-text information does not exceed the first threshold as much as possible and the number of characters of each sub-text information is uniformly distributed, in one embodiment, in response to the number of characters corresponding to the first text information being greater than the first threshold, the first text information is segmented to obtain a plurality of sub-text information, including: responding to the fact that the number of characters corresponding to the first text information is larger than a first threshold value and smaller than a second threshold value, and determining the initial segmentation number of characters according to the number of characters of the first text information and the preset maximum segmentation number; the second threshold is determined based on the first threshold and the maximum number of segments (e.g., the first threshold 12k times the maximum number of segments 8 equals the second threshold 96 k); determining a second text position from the initial information of the first text information to the point that the number of characters reaches the initial segmentation number of characters; judging whether the number of characters from the start information of the first text information to the end position of the paragraph closest to the second text position is smaller than or equal to a first threshold value; if yes, the end position of the paragraph closest to the second text position is used as the cut-off position of the first sub-text information, otherwise, the end position of the previous paragraph closest to the second text position is used as the cut-off position of the first sub-text information; and taking the rest text information except the first sub-text information in the first text information as the updated first text information, and repeatedly executing the step of the second text position until the segmentation is completed, so as to obtain each sub-text information.

In the above embodiment, the initial segmentation character number determined according to the character number of the first text information and the preset maximum segmentation number may be a ratio of the character number of the first text information to the preset maximum segmentation number, in which case the initial segmentation character number is necessarily smaller than the first threshold value since the character number corresponding to the first text information is smaller than the second threshold value, which is determined based on the first threshold value and the maximum segmentation number. A second text position determined in terms of the initial segmentation character number may occur as a position in the paragraph.

Therefore, in order to ensure the semantic integrity of each segment after segmentation, the situation that the second text position is the position in the paragraph is avoided, and the end position of the paragraph closest to the second text position can be determined. The end position of the paragraph may be the previous paragraph or the subsequent paragraph. If the end position of the paragraph is the previous paragraph, the number of characters of the obtained first sub-text information is necessarily smaller than or equal to the first threshold value after the end position of the paragraph is taken as the cut-off position of the first sub-text information. If the end position of the paragraph is the following paragraph, the number of characters of the obtained first sub-text information may be larger than the first threshold after the end position of the paragraph is taken as the cut-off position of the first sub-text information.

To avoid this, it may be determined whether the number of characters from the start information of the first text information to the end position of the paragraph closest to the second text position is less than or equal to the first threshold.

If yes, the end position of the paragraph closest to the second text position is taken as the cut-off position of the first sub-text information, otherwise, the end position of the previous paragraph closest to the second text position is taken as the cut-off position of the first sub-text information. The first sub-text information thus obtained may be text information having a number of characters smaller than the first threshold, and thus the server may successfully process the first sub-text information.

After the rest text information except the first sub-text information in the first text information is used as the updated first text information, the step of determining the second text position is carried out, and each obtained sub-text information can be text information with the character number smaller than a first threshold value, so that knowledge point information corresponding to each sub-text information can be successfully obtained.

The above embodiment may be applied to a scenario in which the first text information having the number of characters greater than the first threshold value and less than the second threshold value is summarized in terms of segmentation.

For the first text information of the third type, that is, when the number of characters of the first text information is greater than the first threshold, in one embodiment, in response to the number of characters corresponding to the first text information being greater than the first threshold, the first text information is subjected to segmentation processing to obtain a plurality of sub-text information, including: determining a first text position from the initial information of the first text information to the character number reaching a first threshold value in response to the character number corresponding to the first text information being greater than the first threshold value; taking the ending position of the previous paragraph closest to the first text position as the cut-off position of the first sub-text information; and taking the rest text information except the first sub-text information in the first text information as updated first text information, and repeatedly executing the step of determining the first text position until the segmentation is completed, so as to obtain each sub-text information.

In the above embodiment, the number of characters corresponding to the text information from the start information of the first text information to the first text position where the number of characters reaches the first threshold value is the first threshold value. The first text position may be a position in a paragraph, and accurate knowledge point information may not be obtained according to text information of an incomplete paragraph, so that an ending position of a previous paragraph closest to the first text position may be used as a cut-off position of the first sub-text information, and the obtained first sub-text information may be text information with a character number smaller than a first threshold value, so that the server side may successfully process the first sub-text information.

After the rest text information except the first sub-text information in the first text information is used as updated first text information, the step of determining the first text position is carried out, and each obtained sub-text information can be text information with the character number smaller than a first threshold value, so that knowledge point information corresponding to each sub-text information can be successfully obtained.

The above embodiment may be applied to a scenario in which a sentence title summary, a difficulty summary, a summary, a knowledge point summary, and the like are performed on first text information having a number of characters greater than a first threshold, and a scenario in which a core viewpoint summary is performed on first text information having a number of characters greater than a second threshold.

And calculating the duty ratio of each piece of difficulty, and taking the difficulty value with the largest duty ratio as the difficulty corresponding to the first piece of text information.

After obtaining the knowledge point information associated with the target content, first model auxiliary information may be generated according to the knowledge point information, and summary information of the target content may be generated by using the first model auxiliary information, that is, S102.

The first model assistance information may relate to knowledge point types and attribute information associated with the knowledge point information. In one embodiment, generating first model assistance information based on the respective knowledge point information includes: determining at least one knowledge point type associated with each knowledge point information and attribute information of each knowledge point type; and generating first model auxiliary information based on the knowledge point type and the corresponding attribute information.

In the above embodiment, the types of knowledge points that need to be covered when the knowledge point summary is performed, and the attribute characteristics that each type of knowledge point should satisfy, such as the number of words, may be indicated in the first model auxiliary information. Illustratively, in an english learning scenario, knowledge point types may include types of words, phrases, sentences, etc.; in a non-learning scenario, knowledge point types may include personals encyclopedia, and the like. The attribute information of the knowledge point type may include, for example, the number of knowledge points, such as how many common words, how many phrases, what sentence patterns, and the like, and also the knowledge point difficulty. The generated first model auxiliary information can indicate the artificial intelligent model to summarize learning scenes and core semantics of the video, and illustrate each knowledge point type and the corresponding number of knowledge points in the corresponding learning scenes.

Summary information for the target content may be generated using an artificial intelligence model. In one embodiment, the first model auxiliary information and the first text information corresponding to the target content may be input into an artificial intelligence model to obtain summary information of the target content.

Here, the artificial intelligence model may perform summary analysis on the first text information based on the first model auxiliary information to obtain summary information of the target content. The first model auxiliary information is already described above and will not be described here again.

In an embodiment, in the process of generating the summary information of the target content by using the first model auxiliary information, the segmented summary information corresponding to the sub-text information may be generated for each sub-text information; integrating the segment summary information corresponding to each piece of sub-text information to obtain integrated second text information; and inputting the second text information and the first model auxiliary information into the artificial intelligent model to obtain abstract information in response to the number of characters of the second text information being smaller than or equal to a first threshold.

In the above embodiment, for each piece of sub-text information, the first model auxiliary information and the sub-text information may be input into the artificial intelligence model, so as to obtain the segment summary information corresponding to the sub-text information.

After the segment abstracts are integrated, the obtained second text information may be initial abstract information corresponding to the target content, and in order to obtain final abstract information corresponding to the target content, which is matched with the auxiliary information of the first model, the initial abstract information may be further analyzed and summarized.

Here, the second text information is still guaranteed to be less than or equal to the first threshold value when the second text information is summarized in an analysis. If the number of characters of the second text information is smaller than or equal to the first threshold value, the second text information and the first model auxiliary information can be input into the artificial intelligent model to obtain abstract information. If the number of characters of the second text message is greater than the first threshold, in one embodiment, the second text message may be used as a new first text message, and the step of segmenting the first text message to obtain a plurality of sub-text messages may be performed back until the number of characters of the second text message is less than or equal to the first threshold. This procedure is similar to the previous procedure and will not be described here again.

In the embodiment of the present disclosure, the first model auxiliary information used for obtaining the summary information of the target content and the second model auxiliary information used for obtaining the knowledge point information associated with the target content may be the same or different, and specifically, the number of summary characters corresponding to the first model auxiliary information and the second model auxiliary information may be different.

After obtaining the summary information of the target content, the summary information and the target knowledge point information associated with the summary information may be presented, i.e. step S103.

Wherein the target knowledge point information associated with the summary information may be related to a learning scenario. In one embodiment, the target knowledge point information associated with summary information may be determined according to the following steps: determining at least one target knowledge point type matched with the learning scene from the knowledge point types corresponding to the knowledge point information according to the learning scene corresponding to the abstract information; and taking the knowledge point information under the type of the target knowledge point as target knowledge point information.

In the above embodiment, for example, in the case where the learning scene corresponding to the summary information is an english learning scene, the at least one target knowledge point type matched with the english learning scene may be a common word, a common sentence pattern, or the like. Here, each knowledge point information under each target knowledge point type may be regarded as target knowledge point information.

With the foregoing embodiments in mind, in one embodiment, when presenting summary information, and target knowledge point information associated with the summary information, the method includes: displaying abstract information and displaying the type information of each target knowledge point under the abstract information; and displaying the information of each target knowledge point under the information of each target knowledge point type.

In a specific implementation, the display mode of the target knowledge point type information and the target knowledge point information under each target knowledge point type information may be different. For example, the target knowledge point type information can be highlighted, so that a user can conveniently view the target knowledge point information under each target knowledge point type information.

Fig. 2 and 3 show diagrams showing summary information and various target knowledge point type information under the summary information when text content and video content are shown, respectively. In fig. 2, not only summary information and knowledge points but also various viewpoint information obtained by analyzing and summarizing text contents are shown. The plurality of point of view information may be ordered by number. In fig. 3, not only summary information and knowledge points but also various viewpoint information obtained by analyzing and summarizing video content (here, subtitle information which may be corresponding to the video content) are shown. The plurality of opinion information may be ordered by time of occurrence of opinion.

In the embodiment of the present disclosure, the learning scene associated with the summary information may include, for example, a language learning scene, a natural science learning scene, a concept idea learning scene, and the like. Under the condition of different learning scenes, the display modes of knowledge point information can be different. In one embodiment, when the learning scene comprises a language learning scene and a plurality of pieces of target knowledge point information are displayed, detailed information corresponding to the target knowledge point information can be displayed in response to any piece of target knowledge point information being triggered; the detail information comprises text information in target content associated with the target knowledge point information and paraphrasing and/or example sentence information corresponding to the target knowledge point information.

In a specific embodiment, in response to any one of the target knowledge point information being triggered, a knowledge point information detail page can be displayed, and detail information corresponding to the target knowledge point information can be displayed in the knowledge point information detail page; the detailed information may also be displayed at a corresponding position of the target knowledge point information in the page displaying the target knowledge point information, which may not be particularly limited here.

As shown in fig. 4, the information of multiple target knowledge points in the english learning scene is shown, which may specifically include common words and common sentence patterns. Any target knowledge point information is triggered, and can jump to a knowledge point information detail page, wherein corresponding detail information can be displayed in the knowledge point information detail page, as shown in fig. 5, and the knowledge point information can specifically comprise a knowledge point structure, a original sentence pattern, an example sentence and the like.

Here, by displaying the text information in the target content associated with the target knowledge point information, the positioning of the text information in the target content can be realized, so that the user can understand and learn the target knowledge point information by combining the text information in the target content.

Paraphrasing and/or example sentence information corresponding to the target knowledge point information can be generated by an artificial intelligence model, and is not particularly limited herein.

According to the content processing method disclosed by the embodiment of the disclosure, related abstract and knowledge point information can be displayed aiming at target content, so that the relationship between the finally displayed abstract and knowledge point is more intimate, the user is facilitated to more clearly understand the summary and knowledge point of the target content, and the efficiency of acquiring effective information is further improved.

It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.

Based on the same inventive concept, the embodiments of the present disclosure further provide a content processing device corresponding to the content processing method, and since the principle of solving the problem by the device in the embodiments of the present disclosure is similar to that of the content processing method in the embodiments of the present disclosure, the implementation of the device may refer to the implementation of the method, and the repetition is omitted.

Referring to fig. 6, a schematic structural diagram of a content processing apparatus according to an embodiment of the disclosure is provided, where the apparatus includes:

a first determining module 601, configured to determine, in response to obtaining target content to be summarized, information of each knowledge point associated with the target content;

A generating module 602, configured to generate first model auxiliary information based on the knowledge point information, and generate summary information of the target content using the first model auxiliary information;

a first display module 603, configured to display the summary information and target knowledge point information associated with the summary information; the target knowledge point information is related to a learning scene associated with the summary information.

In an alternative embodiment, the first determining module 601 is specifically configured to:

In an alternative embodiment, the generating module 602 is specifically configured to:

In an alternative embodiment, the apparatus further includes a second determining module configured to determine target knowledge point information associated with the summary information;

the second determining module is specifically configured to:

In an alternative embodiment, the second determining module is specifically configured to:

In an alternative embodiment, the apparatus further comprises:

and the return module is used for responding to the fact that the number of characters of the second text information is larger than the first threshold value, taking the second text information as new first text information, and returning to execute the step of carrying out segmentation processing on the first text information to obtain a plurality of sub-text information until the number of characters of the second text information is smaller than or equal to the first threshold value.

In an alternative embodiment, the apparatus further comprises:

the second display module is used for responding to any one of the target knowledge point information to be triggered when displaying a plurality of target knowledge point information, and displaying detail information corresponding to the target knowledge point information; the detail information comprises text information in the target content associated with the target knowledge point information and paraphrasing and/or example sentence information corresponding to the target knowledge point information.

The process flow of each module in the apparatus and the interaction flow between the modules may be described with reference to the related descriptions in the above method embodiments, which are not described in detail herein.

Based on the same technical concept, the embodiment of the disclosure also provides computer equipment. Referring to fig. 7, a schematic diagram of a computer device 700 according to an embodiment of the disclosure includes a processor 701, a memory 702, and a bus 703. The memory 702 is configured to store execution instructions, including a memory 7021 and an external memory 7022; the memory 7021 is also referred to as an internal memory, and is used for temporarily storing operation data in the processor 701 and data exchanged with the external memory 7022 such as a hard disk, and the processor 701 exchanges data with the external memory 7022 through the memory 7021, and when the computer device 700 operates, the processor 701 and the memory 702 communicate through the bus 703, so that the processor 701 executes the following instructions:

The disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the content processing method described in the method embodiments above. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.

Embodiments of the present disclosure further provide a computer program product, where the computer program product carries program code, where instructions included in the program code may be used to perform steps of a content processing method described in the foregoing method embodiments, and specifically reference may be made to the foregoing method embodiments, which are not described herein.

Wherein the above-mentioned computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.

It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the apparatus described above, which is not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or a part of the technical solution, or in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present disclosure, and are not intended to limit the scope of the disclosure, but the present disclosure is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, it is not limited to the disclosure: any person skilled in the art, within the technical scope of the disclosure of the present disclosure, may modify or easily conceive changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features thereof; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A content processing method, comprising:

2. The method of claim 1, wherein the determining, in response to obtaining the target content to be summarized, the respective knowledge point information associated with the target content comprises:

3. The method of claim 1, wherein generating first model assistance information based on the respective knowledge point information comprises:

4. The method of claim 1, wherein generating summary information of the target content using the first model assistance information comprises:

5. The method of claim 1, wherein the target knowledge point information associated with the summary information is determined in accordance with the steps of:

6. The method of claim 5, wherein said presenting said summary information, and target knowledge point information associated with said summary information, comprises:

7. The method of claim 2, wherein inputting the first text information and second model assistance information indicating knowledge point summary into an artificial intelligence model to obtain knowledge point information associated with the target content, comprises:

8. The method of claim 7, wherein responsive to the number of characters corresponding to the first text message being greater than a first threshold, performing segmentation processing on the first text message to obtain a plurality of sub-text messages, comprises:

9. The method of claim 7, wherein responsive to the number of characters corresponding to the first text message being greater than a first threshold, performing segmentation processing on the first text message to obtain a plurality of sub-text messages, comprises:

10. The method of claim 7, wherein generating summary information of the target content using the first model assistance information comprises:

11. The method of claim 10, further comprising, after obtaining the integrated second text information:

12. The method of claim 1, wherein the responsive to the learning scenario comprises a language learning scenario, the method further comprising:

13. A content processing apparatus, comprising:

14. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the content processing method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the content processing method according to any of claims 1 to 12.