Document generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a document generation method and device, electronic equipment and a storage medium. The method comprises the steps that at least two target video clips corresponding to a target video are determined, the at least two target video clips are generated by performing video splitting on the target video, and the similarity of video picture contents of different target video clips does not meet a preset similarity condition; identifying target text content corresponding to the target video clip; and generating a target document corresponding to the target video based on the at least two target video clips and the target text content corresponding to the target video clips. According to the scheme, the situation that key points to be expressed by the video clip cannot be concerned when video clip analysis and text conversion are carried out due to inconsistency of video pictures in the video clip can be avoided, the accuracy of generating the document based on the video clip and the corresponding target text content can be improved, and the generation efficiency is improved; and the labor cost caused by manual checking of the generated document is reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a document generation method, device, electronic device, and storage medium. Background Art

[0002] With the continuous development of video applications, more and more information is presented in the form of videos. The increase in videos means that a large number of videos need to be processed. In some scenarios, it is necessary to watch the entire video to obtain important information from the video to form the required document content. However, this method not only takes a lot of time and is very inconvenient, but also has low document generation efficiency and is not suitable for processing a large number of videos. Summary of the invention

[0003] The present disclosure provides a document generation method, device, electronic device and storage medium to achieve rapid and accurate analysis of videos to generate effective documents containing graphics and text, thereby improving the efficiency and accuracy of document generation.

[0004] In a first aspect, an embodiment of the present disclosure provides a document generation method, the method comprising:

[0005] Determine at least two target video segments corresponding to the target video, wherein the at least two target video segments are generated by splitting the target video, and similarity of video picture contents of different target video segments does not satisfy a preset similarity condition;

[0006] Identifying target text content corresponding to the target video clip;

[0007] A target document corresponding to the target video is generated based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segment.

[0008] In a second aspect, an embodiment of the present disclosure further provides a document generation device, the device comprising:

[0009] A determination module, configured to determine at least two target video segments corresponding to a target video, wherein the at least two target video segments are generated by splitting the target video, and similarities of video screen contents of different target video segments do not satisfy a preset similarity condition;

[0010] An identification module, used to identify target text content corresponding to the target video clip;

[0011] A generating module is used to generate a target document corresponding to the target video based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segment.

[0012] In a third aspect, an electronic device is also provided in an embodiment of the present disclosure, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the document generation method described in any one of the above embodiments.

[0016] In a fourth aspect, a computer-readable medium is also provided in an embodiment of the present disclosure, wherein the computer-readable medium stores computer instructions, and the computer instructions are used to enable a processor to implement the document generation method described in any one of the above embodiments when executed.

[0017] The disclosed embodiment splits the target video into at least two separate target video segments by analyzing the target video, and ensures that the similarity of the video screen contents in different target video segments does not satisfy a preset similarity condition, so as to effectively analyze the video screen contents in the same target video segment, obtain the target text content that matches the target video segment, and avoid placing the content that does not satisfy the preset similarity condition into the same video segment. Because the inconsistent video screen makes it impossible to focus on the key points to be expressed in the video segment when converting the video segment analysis into text, the text content converted from the video segment recognition is inconsistent with the content to be expressed in the video segment, thereby improving the accuracy of generating a target document including graphics and text based on the video segment and the corresponding target text content and improving the generation efficiency, and reducing the labor cost caused by manual verification of document generation.

[0018] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 It is a flowchart of a document generation method provided by an embodiment of the present disclosure;

[0021] Figure 2a It is a schematic diagram of video segmentation in a document generation process provided by an embodiment of the present disclosure;

[0022] Figure 2b This is a video segmentation effect diagram in a document generation process provided by an embodiment of the present disclosure;

[0023] Figure 2c It is a schematic diagram of an architecture in a document generation process provided by an embodiment of the present disclosure;

[0024] Figure 3 is a flowchart of another document generation method provided by an embodiment of the present disclosure;

[0025] Figure 4 It is a flowchart of another document generation method provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of a document generation device provided by an embodiment of the present disclosure;

[0027] Figure 6 It is a structural schematic diagram of an electronic device for implementing a document generation method provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0035] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0036] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0037] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0038] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0039] Figure 1 A flowchart of a document generation method provided in an embodiment of the present disclosure is provided. The embodiment of the present disclosure is applicable to the case of converting video content into a document containing graphic information. The method can be executed by a document generation device, which can be implemented in the form of software and / or hardware and is generally integrated on any electronic device with network communication function, which can be a mobile terminal, PC or server, etc.

[0040] like Figure 1 As shown, the document generation method of the embodiment of the present disclosure may include the following process:

[0041] S110: Determine at least two target video segments corresponding to the target video, where the at least two target video segments are generated by splitting the target video, and similarities between video picture contents of different target video segments do not satisfy a preset similarity condition.

[0042] The target video may be a video that needs to convert the video screen content in the video into a target document containing graphic information through intelligent graphic operation. In response to the operation for triggering the target document generation task, the target video specified by the target document generation task is determined. The target video specified by the target document generation task is determined, including: determining the target video specified by the target document generation task from a video library, or starting the video shooting function to obtain a video through a video acquisition operation and determining the acquired video as the target video.

[0043] See also Figure 2a , by parsing the video screen content in the target video, the target video is split into multiple continuous target video segments, and at the same time, for each split target video segment, the similarity of the video screen content of different target video segments is maintained not to meet the preset similarity condition, or the dissimilarity of the video screen content of different target video segments is maintained to meet the preset dissimilarity condition, so that the similarity of the video screen content in the same target video segment meets the preset similarity condition, and the similarity of the video screen content in the target video segment meets the preset similarity condition. Optionally, the similarity of the video screen content of each frame in the same target video segment meets the preset similarity condition, and the similarity of the video screen content of different target video segments does not meet the preset similarity condition, such as maintaining the similarity of the video screen content of each frame in each target video segment greater than a preset similarity threshold, so that the similarity of the video screen content of each frame in the split single target video segment can be high, such as Figure 2bThe figure shows the effect of splitting the target video into multiple target video segments.

[0044] For the above scheme, when the similarity of the content of each video screen in a video clip is high, the key points to be expressed by the content of each frame of the video screen in the video clip will be emphasized when analyzing the video clip and converting it into text. This can minimize the problem of not being able to find the key points to be expressed in a single video clip due to large differences in video screen content. At the same time, since the similarity of the content of each frame of the video screen in a single video clip is high, the subsequent video-to-text conversion only needs to consider the key points to be highlighted in one video screen content, without having to pay attention to multiple different video screen contents at the same time. This can simplify the recognition complexity of the subsequent video-to-text conversion and improve the accuracy and efficiency of the subsequent video-to-text conversion.

[0045] S120: Identify target text content corresponding to the target video clip.

[0046] After obtaining at least two target video segments corresponding to the target video, identification and analysis can be performed on the content of each frame of video in each target video segment, and target text content that can describe the key information to be expressed by the target video segment in text form can be identified from the content of each frame of video.

[0047] Optionally, identifying target text content corresponding to the target video clip includes: by performing video recognition analysis on the split target video clip, target text content matching the target video clip can be identified from the target video clip, and the target text content can describe the video picture content of each frame in the target video clip and the audio and subtitles corresponding to the video picture content in text form.

[0048] As an optional but non-limiting implementation, identifying the target text content corresponding to the target video clip includes the following steps A1-A3:

[0049] Step A1: extract corresponding first text content from the video screen content corresponding to the target video segment by performing video recognition analysis on the target video segment, where the first text content is used to describe the video screen content in words.

[0050] Step A2: extracting corresponding second text content from the audio and audio subtitles of the target video clip.

[0051] Step A3: Determine target text content corresponding to the target video clip based on the first text content and the second text content.

[0052] See also Figure 2cIn each video screen content of the target video clip, in addition to the key information of the video screen content describing the video, subtitle information is also displayed in the video screen content, and there is also matching audio for the video screen content. To this end, video recognition analysis can be performed on each frame of video screen content corresponding to the target video clip, and a first text content that can describe the video screen content in text form can be extracted. At the same time, character recognition can be performed on the subtitles corresponding to each frame of video screen content corresponding to the target video clip, and speech-to-text processing can be performed on the audio corresponding to each frame of video screen content corresponding to the target video clip, and the corresponding second text content can be extracted. Furthermore, the first text content and the second text content are combined to form the target text content initially generated corresponding to the target video clip, and each target video clip corresponds to one target text content.

[0053] S130: Generate a target document corresponding to the target video based on at least two target video segments and target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segments.

[0054] See also Figure 2b and Figure 2c For each of the at least two target video segments, corresponding video screen content is included. For this purpose, appropriate video screen content can be selected from the video screen content corresponding to the target video segment as an illustration and combined with the target text content corresponding to the target video segment to form a target document corresponding to the target video that includes text content and image content determined based on the target video segment, and presented on the display interface.

[0055] Optionally, after identifying the target text content corresponding to the target video clip, the target text content can be used to form a candidate document, and then suitable video screen content is selected as an illustration from the video screen content contained in the target video clip, and then the video screen content selected as the illustration is inserted into the candidate document at the position of the target text content corresponding to the target video clip that matches the illustration, so as to form a target document corresponding to the target video containing text content and image content determined based on the target video clip.

[0056] Optionally, the type of the target document can be a technical document, an explanation note document, a video clip document, and a social sharing document. Among them, technical videos usually need to be accompanied by graphic descriptions for better understanding and application. Through video to text conversion, technical videos can be converted into graphic documents, which is convenient for quick generation of technical documents; explanation videos usually need to be accompanied by graphic notes for better understanding and memory. Through video to text conversion, explanation videos can be converted into graphic notes for quick understanding and memory; video editing refers to dividing a video into multiple segments and editing and processing each segment. Through video to text conversion, a video can be converted into a graphic document, which is convenient for video editing and editing; social sharing refers to sharing content on social media platforms for sharing with others. Through video to text conversion, graphic documents can be shared on social media, which is convenient for sharing your own documents with others.

[0057] The disclosed embodiment splits the target video into at least two separate target video segments by analyzing the target video, and ensures that the similarity of the video screen contents in different target video segments does not satisfy a preset similarity condition, so as to effectively analyze the video screen contents in the same target video segment, obtain the target text content that matches the target video segment, and avoid placing the content that does not satisfy the preset similarity condition into the same video segment. Because the inconsistent video screen makes it impossible to focus on the key points to be expressed in the video segment when converting the video segment analysis into text, the text content converted from the video segment recognition is inconsistent with the content to be expressed in the video segment, thereby improving the accuracy of generating a target document including graphics and text based on the video segment and the corresponding target text content and improving the generation efficiency, and reducing the labor cost caused by manual verification of document generation.

[0058] Figure 3 A flow chart of another document generation method provided for an embodiment of the present disclosure. The technical solution of this embodiment further optimizes the process of determining at least two target video segments corresponding to the target video in the aforementioned embodiment on the basis of the technical solution of the aforementioned embodiment. This embodiment can be combined with various optional solutions in one or more of the aforementioned embodiments.

[0059] like Figure 3 As shown, the document generation method of the embodiment of the present disclosure may include the following process:

[0060] S310: Determine video picture content change status information between multiple adjacent frames of video picture content in a target video, where the video picture content change status information includes whether the video picture content has changed and the degree of change of the video picture content.

[0061] The target video is composed of a series of video screen contents. The series of video screen contents included in the target video are not static. Some video screen contents have a certain degree of similarity, the differences between the video screen contents are relatively small, and the key information to be described is relatively similar or nearly consistent; however, some video screen contents have a low degree of similarity, the differences between the video screen contents are relatively large, and the key information to be described is basically inconsistent.

[0062] In order to facilitate the subsequent video-to-text conversion and simplify the computational complexity of the video-to-text conversion, the video screen contents with similar video screen contents can be grouped together as a single video segment, so that the video screen contents with inconsistent video screen contents or with little similarity can be grouped into different video segments. To this end, multiple frames of adjacent video screen contents can be continuously acquired, and the degree of change of the video screen contents between the video screen contents can be analyzed to determine whether there is a change between the adjacent video screen contents and the degree of change of the video screen contents before and after.

[0063] Among them, the greater the degree of change of the video screen content, the greater the difference between the video screen contents, and it is necessary to divide them into different video segments respectively; the smaller the degree of change of the video screen content or no change, the smaller the difference between the video screen contents, and it is necessary to divide them into the same video segment for subsequent video recognition analysis of video-to-text conversion.

[0064] As an optional but non-limiting implementation method, determining the video picture content change state information between adjacent multiple frames of video picture content in the target video includes the following steps:

[0065] For adjacent multiple frames of video content, the picture pixel information of the video content (such as the pixel value of the pixel point) can be obtained for each frame of video content. Based on the picture pixel information corresponding to each frame of video content, the pixel value sizes of the pixel points included in the two video content can be compared to determine the change information between the two frames of video content, and then determine the video content change status information between adjacent multiple frames of video content.

[0066] As another optional but non-limiting implementation, determining the video picture content change state information between adjacent multiple frames of video picture content in the target video includes the following steps B1-B3:

[0067] Step B1: determine the picture pixel information corresponding to each of the adjacent multiple frames of video picture content in the target video.

[0068] Step B2: determining the video picture content similarity between the adjacent multiple frames of video picture content based on the picture pixel information corresponding to each of the adjacent multiple frames of video picture content.

[0069] Step B3: determining the video picture content change status information between adjacent multiple frames of video picture content based on the video picture content similarity.

[0070] As another optional but non-limiting implementation, determining video picture content change state information between adjacent multiple frames of video picture content in the target video includes the following steps:

[0071] Determine the target key objects contained in each of the adjacent multiple frames of video screen content in the target video, and compare the target key objects included in the two video screen contents to determine the change information between the two frames of video screen content, and then analyze and determine the video screen content change state information between the adjacent multiple frames of video screen content. The target key object can be the corresponding key point area in the foreground content of the video screen content except the background.

[0072] As another optional but non-limiting implementation, determining video picture content change state information between adjacent multiple frames of video picture content in the target video includes the following steps:

[0073] Determine the picture pixel information of the target key object contained in each of the adjacent multiple frames of video picture content in the target video; determine the video picture content similarity between the adjacent multiple frames of video picture content based on the picture pixel information of the target key object contained in each of the adjacent multiple frames of video picture content; determine the video picture content change state information between the adjacent multiple frames of video picture content based on the video picture content similarity.

[0074] S320: Determine at least one video splitting position used when splitting the target video according to the video picture content change state information.

[0075] See also Figure 2a and Figure 2b , continuously read multiple frames of video content according to the intelligent segmentation algorithm, analyze the degree of change of the video content in the target video, decide whether the target video contains a location with drastic video content changes according to the degree of change of the video content, and segment the single target video into multiple target video segments with independent video content according to the location where the drastic video content changes occur in the target video. Each video segment is relatively stable, and the video content contained in each video segment is also relatively stable. This not only ensures that video recognition analysis can be performed in segments when generating text content, but also because the similarity of the video content of the same target video segment meets the preset similarity condition, it can ensure that the same key points are concentrated on when performing video recognition analysis on the target video segment, thereby improving the accuracy of video recognition analysis.

[0076] As an optional but non-limiting implementation, determining at least one video splitting position used when splitting the target video according to the video picture content change state information includes the following steps C1-C2:

[0077] Step C1: If the video picture content change status information indicates that the change degree of the video picture content is greater than a preset change degree threshold, the position between adjacent frames of video picture content is determined as a video splitting position.

[0078] Step C2: If the video picture content change status information indicates that the change degree of the video picture content is not greater than a preset change degree threshold, the position between adjacent multiple frames of video picture content is not determined as the video splitting position.

[0079] The video split position is a timestamp corresponding to the video split position in the target video, or can be described by a time difference between the video split position and the start point of the target video.

[0080] S330: Split the target video into at least two target video segments based on at least one video splitting position, and similarity between video picture contents of different target video segments does not satisfy a preset similarity condition.

[0081] See also Figure 2a and Figure 2b , using each video splitting position in at least one video splitting position as a cutting point for video splitting in the target video, cutting the target video into multiple target video segments, such as Figure 2b As shown, the similarity of the video screen contents of different target video clips does not meet the preset similarity condition, but the similarity of the video screen contents in the same target video clip is ensured to meet the preset similarity condition as much as possible, and the video screen contents of two adjacent target video clips can be similar, but the similarity of the video screen contents of two adjacent target video clips is lower than the similarity of the video screen contents in the same target video clip, so that the video can be split as evenly as possible, so that the key information to be expressed by the video screen content in each video clip can be more concentrated.

[0082] S340: Identify target text content corresponding to the target video segment.

[0083] S350: Generate a target document corresponding to the target video based on at least two target video segments and target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segments.

[0084] The disclosed embodiment splits the target video into at least two separate target video segments by analyzing the target video, and ensures that the similarity of the video screen contents in different target video segments does not satisfy a preset similarity condition, so as to effectively analyze the video screen contents in the same target video segment, obtain the target text content that matches the target video segment, and avoid placing the content that does not satisfy the preset similarity condition into the same video segment. Because the inconsistent video screen makes it impossible to focus on the key points to be expressed in the video segment when converting the video segment analysis into text, the text content converted from the video segment recognition is inconsistent with the content to be expressed in the video segment, thereby improving the accuracy of generating a target document including graphics and text based on the video segment and the corresponding target text content and improving the generation efficiency, and reducing the labor cost caused by manual verification of document generation.

[0085] Figure 4 A flow chart of another document generation method provided for an embodiment of the present disclosure. The technical solution of this embodiment further optimizes the process of generating a target document corresponding to a target video based on at least two target video clips and the target text content corresponding to the target video clips in the aforementioned embodiment on the basis of the technical solution of the aforementioned embodiment. This embodiment can be combined with various optional solutions in one or more of the aforementioned embodiments.

[0086] like Figure 4 As shown, the document generation method of the embodiment of the present disclosure may include the following process:

[0087] S410: Determine at least two target video segments corresponding to the target video, where the at least two target video segments are generated by splitting the target video, and similarities between video screen contents of different target video segments do not satisfy a preset similarity condition.

[0088] S420: Identify target text content corresponding to the target video segment.

[0089] S430: Determine a target key frame image from video screen contents corresponding to at least two target video clips, where the target key frame image is an illustration that can make the textual idea expressed by the target text content clearer and more distinct.

[0090] See also Figure 2b ,For some videos, such as popular science videos, there are a lot of video clips generated after ,video segmentation, and there are a lot of changes in the video ,screen content. Some video screen content may only have a few frames, for example Figure 2bThe 10-minute video shown generates 30 video clips, some of which are almost invalid video screen content. These invalid video screens cannot provide a clearer explanation of the textual ideas expressed in the text content. Therefore, it is necessary to select the video screen content that meets the requirements from the video screen content corresponding to each target video clip as the target key frame image.

[0091] As an optional but non-limiting implementation, determining a target key frame image from video screen contents corresponding to at least two target video clips includes the following steps D1-D3:

[0092] Step D1: Determine the length of each target video segment in at least two target video segments and the number of characters in the corresponding target text content.

[0093] Step D2: Screening at least two target video segments based on the segment length of each target video segment and the number of characters in the corresponding target text content.

[0094] Step D3: determining a target key frame image from video picture contents corresponding to at least two target video clips.

[0095] See also Figure 2b When selecting the video screen content that meets the requirements from the video screen content corresponding to each target video segment, the segment length of each target video segment and the number of characters in the corresponding target text content can be determined first, and then which video segments in each target video segment contain a large amount of invalid video screen content according to the segment length of the target video segment and the number of characters in the corresponding target text content can be judged, and then the target video segments that may contain invalid video screen content can be screened out, and then the target key frame images can be screened out from the video screen content corresponding to the remaining target video segments.

[0096] Optionally, the shorter the length of the video segment, the greater the possibility that the video segment contains invalid video screen content, and the longer the length of the video segment, the smaller the possibility that the video segment contains invalid video screen content; the more characters in the text content, the smaller the possibility that the text content corresponds to the video segment containing invalid video screen content, and the fewer characters in the text content, the greater the possibility that the text content corresponds to the video segment containing invalid video screen content.

[0097] As an optional but non-limiting implementation, determining a target key frame image from video screen contents corresponding to at least two target video clips includes the following steps E1-E3:

[0098] Step E1: Determine the repetition degree of video picture content between the video picture content of each frame in the target video segment.

[0099] Step E2: based on the repetition of video picture contents between the video picture contents of each frame, deduplication processing is performed on the video picture contents whose repetition is greater than a preset repetition threshold.

[0100] Step E3: extracting a target key frame image from the target video segment that has undergone deduplication processing.

[0101] See also Figure 2b , the similarity of the video screen content of different target video clips does not meet the preset similarity condition, so that the similarity of the video screen content in the same target video clip meets the preset similarity condition as much as possible, so the video screen content repetition between the video screen content of each frame in the same target video clip will also be relatively high. If all are obtained, a large number of repetitions will be visually generated in the document. For this reason, the video screen content repetition between the video screen content of each frame can be calculated, and the video screen content with a video screen content repetition greater than the preset repetition threshold can be deduplicated. Then, the target key frame image is extracted from the target video clip that has been deduplicated, for example, the video screen content with a smaller repetition of the video screen content in different target video clips can be extracted as the target key frame image.

[0102] As an optional but non-limiting implementation, determining the video picture content repetition between the video picture content of each frame in the target video segment includes the following steps F1-F2:

[0103] Step F1: Determine the video picture content features corresponding to the video picture content of each frame in the target video segment.

[0104] Step F2: Based on the video picture content features corresponding to the video picture content of each frame, the video picture content duplication between the video picture contents of each frame is determined by comparing the video picture contents of each frame with each other.

[0105] S440: Generate a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video segment, where the target document includes text content and image content determined based on the target video segment.

[0106] Optionally, text adjustment is performed on the target text content corresponding to the target video clip so that the richness of the text content after the adjustment on the basis of the target text content is greater than the richness of the target text content before the adjustment, and then based on the target key frame image and the target text content corresponding to the target video clip, a target document corresponding to the target video is generated, which includes text content and image content determined based on the target video clip.

[0107] As an optional but non-limiting implementation, based on the target key frame image and the target text content corresponding to the target video clip, generating a target document containing images and text corresponding to the target video includes the following steps H1-H2:

[0108] Step H1, executing a preset text processing task through a preset text processing model to update and adjust the target text content corresponding to the target video clip, the preset text processing task includes at least one of text expansion, text continuation, text rewriting and text rewriting, and the preset text processing model is pre-configured and generated based on a natural language model.

[0109] Step H2: Generate a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video clip.

[0110] Optionally, after identifying the target text content corresponding to the target video clip, the target text content can be used to form a candidate document, and then the target text content that matches the target key frame image is selected from the target text content corresponding to the target video clip. The target key frame image and the matching target text content are derived from the same or similar video screen content, and then the selection is inserted into the candidate document as the target key frame image at the position of the target text content that matches the target key frame image, so as to form a target document corresponding to the target video.

[0111] As an optional but non-limiting implementation, generating a target document corresponding to a target video based on a target key frame image and a target text content corresponding to a target video segment includes the following steps K1-K3:

[0112] Step K1: Determine the target text content that matches the target key frame image from the target text content corresponding to the target video clip.

[0113] Step K2: insert the target key frame image into the location where the matching target text content is located.

[0114] Step K3: Generate a target document corresponding to the target video based on the inserted target key frame image and the target text content corresponding to the target video clip.

[0115] As an optional but non-limiting implementation, determining the target text content matching the target key frame image from the target text content corresponding to the target video clip includes the following steps M1-M2:

[0116] Step M1, determine the first reference information of the target key frame image and the second reference information of the target text content corresponding to the target video clip, the first reference information is used to describe the timestamp corresponding to the target key frame image in the target video, and the second reference information is used to describe the timestamp corresponding to the target video clip corresponding to the target text content in the target video.

[0117] Step M2: determining target text content matching the target key frame image from the target text content corresponding to the target video segment based on the first reference information of the target key frame image and the second reference information of the target text content corresponding to the target video segment.

[0118] The disclosed embodiment splits the target video into at least two separate target video segments by analyzing the target video, and ensures that the similarity of the video screen contents in different target video segments does not satisfy a preset similarity condition, so as to effectively analyze the video screen contents in the same target video segment, obtain the target text content that matches the target video segment, and avoid placing the content that does not satisfy the preset similarity condition into the same video segment. Because the inconsistent video screen makes it impossible to focus on the key points to be expressed in the video segment when converting the video segment analysis into text, the text content converted from the video segment recognition is inconsistent with the content to be expressed in the video segment, thereby improving the accuracy of generating a target document including graphics and text based on the video segment and the corresponding target text content and improving the generation efficiency, and reducing the labor cost caused by manual verification of document generation.

[0119] Figure 5 This is a structural schematic diagram of a document generation device provided in an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the case of converting video content into a document containing graphic information. The document generation device can be implemented in the form of software and / or hardware, and is generally integrated on any electronic device with network communication function, which can be a mobile terminal, PC or server, etc.

[0120] like Figure 5 As shown, the document generation device of the embodiment of the present disclosure may include: a determination module 510, an identification module 520 and a generation module 530. Among them:

[0121] A determination module 510 is used to determine at least two target video segments corresponding to a target video, wherein the at least two target video segments are generated by splitting the target video, and similarity of video screen contents of different target video segments does not satisfy a preset similarity condition;

[0122] An identification module 520, configured to identify target text content corresponding to the target video segment;

[0123] The generating module 530 is configured to generate a target document corresponding to the target video based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segments.

[0124] Based on the technical solution of the above embodiment, optionally, determining at least two target video segments corresponding to the target video includes:

[0125] Determine video picture content change state information between adjacent multiple frames of video picture content in the target video, wherein the video picture content change state information includes whether the video picture content has changed and the degree of change of the video picture content;

[0126] Determining at least one video splitting position used when splitting the target video according to the video picture content change state information;

[0127] Based on the at least one video splitting position, the target video is split into at least two target video segments.

[0128] Based on the technical solution of the above embodiment, optionally, determining the video picture content change state information between adjacent multiple frames of video picture content in the target video includes:

[0129] Determine the picture pixel information corresponding to each of the adjacent multiple frames of video picture content in the target video;

[0130] Determine the video picture content similarity between the adjacent multiple frames of video picture content based on the picture pixel information corresponding to each of the adjacent multiple frames of video picture content;

[0131] The video picture content change state information between adjacent multiple frames of video picture content is determined based on the video picture content similarity.

[0132] On the basis of the technical solution of the above embodiment, optionally, determining at least one video splitting position used when splitting the target video according to the video picture content change state information includes:

[0133] If the video picture content change state information indicates that the change degree of the video picture content is greater than a preset change degree threshold, a position between adjacent multiple frames of video picture content is determined as a video splitting position;

[0134] If the video picture content change status information indicates that the change degree of the video picture content is not greater than the preset change degree threshold, the position between adjacent multiple frames of video picture content is not determined as the video splitting position.

[0135] Based on the technical solution of the above embodiment, optionally, identifying the target text content corresponding to the target video segment includes:

[0136] By performing video recognition analysis on the target video segment, a first text content corresponding to the target video segment is extracted from the video screen content corresponding to the target video segment, where the first text content is used to describe the video screen content in words;

[0137] Extracting corresponding second text content from the audio and audio subtitles of the target video clip;

[0138] Based on the first text content and the second text content, target text content corresponding to the target video clip is determined.

[0139] On the basis of the technical solution of the above embodiment, optionally, generating a target document corresponding to the target video based on the at least two target video segments and the target text content corresponding to the target video segments includes:

[0140] Determining a target key frame image from the video screen contents corresponding to the at least two target video clips, wherein the target key frame image is an illustration that can make the textual idea expressed by the target text content more clear and distinct;

[0141] A target document corresponding to the target video is generated based on the target key frame image and the target text content corresponding to the target video segment.

[0142] Based on the technical solution of the above embodiment, optionally, determining the target key frame image from the video picture contents corresponding to the at least two target video clips includes:

[0143] Determining the segment length of each target video segment in the at least two target video segments and the number of characters in the corresponding target text content;

[0144] Based on the length of each target video segment and the number of characters in the corresponding target text content, the at least two target video segments are screened;

[0145] A target key frame image is determined from video picture contents corresponding to the at least two target video clips.

[0146] Based on the technical solution of the above embodiment, optionally, determining the target key frame image from the video picture contents corresponding to the at least two target video clips includes:

[0147] Determining the repetition of video picture content between the video picture content of each frame in the target video segment;

[0148] Based on the repetition of video picture content between each frame of video picture content, deduplication processing is performed on video picture content whose repetition is greater than a preset repetition threshold;

[0149] A target key frame image is extracted from the target video segment that has undergone deduplication processing.

[0150] Based on the technical solution of the above embodiment, optionally, determining the video picture content repetition between the video picture content of each frame in the target video segment includes:

[0151] Determine the video picture content features corresponding to the video picture content of each frame in the target video segment;

[0152] Based on the video picture content features corresponding to the video picture contents of each frame, the video picture content repetition between the video picture contents of each frame is determined by comparing the video picture contents of each frame in pairs.

[0153] On the basis of the technical solution of the above embodiment, optionally, generating a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video segment includes:

[0154] Executing a preset text processing task through a preset text processing model to update and adjust the target text content corresponding to the target video clip, wherein the preset text processing task includes at least one of text expansion, text continuation, text rewriting and text rewriting, and the preset text processing model is pre-configured and generated based on a natural language model;

[0155] A target document corresponding to the target video is generated based on the target key frame image and the target text content corresponding to the target video segment.

[0156] On the basis of the technical solution of the above embodiment, optionally, generating a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video segment includes:

[0157] Determining target text content that matches the target key frame image from target text content corresponding to the target video clip;

[0158] Inserting the target key frame image into the location where the matching target text content is located;

[0159] A target document corresponding to the target video is generated based on the inserted target key frame image and the target text content corresponding to the target video segment.

[0160] On the basis of the technical solution of the above embodiment, optionally, determining the target text content matching the target key frame image from the target text content corresponding to the target video segment includes:

[0161] Determine first reference information of the target key frame image and second reference information of the target text content corresponding to the target video segment, wherein the first reference information is used to describe a timestamp corresponding to the target key frame image in the target video, and the second reference information is used to describe a timestamp corresponding to the target video segment corresponding to the target text content in the target video;

[0162] Based on the first reference information of the target key frame image and the second reference information of the target text content corresponding to the target video segment, the target text content matching the target key frame image is determined from the target text content corresponding to the target video segment.

[0163] The technical solution provided by the embodiment of the present disclosure analyzes the target video to split the target video into at least two separate target video segments, and ensures that the similarity of the video screen content in different target video segments does not meet the preset similarity condition, so as to effectively analyze the video screen content in the same target video segment, obtain the target text content that matches the target video segment, and avoid placing the content that does not meet the preset similarity condition into the same video segment. Because the inconsistent video screen makes it impossible to pay attention to the key points to be expressed in the video segment when converting the video segment analysis into text, which leads to the inconsistency between the text content converted from the video segment recognition and the content to be expressed by the video segment, thereby improving the accuracy of generating the target document including graphics and text based on the video segment and the corresponding target text content and improving the generation efficiency, and reducing the labor cost caused by manual verification of document generation.

[0164] The document generation device provided in the embodiments of the present disclosure can execute the document generation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the document generation method.

[0165] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0166] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 6 , which shows an electronic device (eg, Figure 6The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0167] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An edit / output (I / O) interface 605 is also connected to the bus 604.

[0168] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0169] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the document generation method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the document generation method of the embodiment of the present disclosure are executed.

[0170] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0171] The electronic device provided by the embodiment of the present disclosure and the document generation method provided by the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0172] The embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the document generation method provided by the above embodiment is implemented.

[0173] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0174] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0175] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0176] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0177] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: determines at least two target video segments corresponding to the target video, wherein the at least two target video segments are generated by splitting the target video, and the similarity of video screen contents of different target video segments does not meet a preset similarity condition; identifies the target text content corresponding to the target video segments; and generates a target document corresponding to the target video based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segments.

[0178] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0179] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0180] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0181] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0182] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0183] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0184] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0185] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A document generation method, characterized in that: The method comprises: Determine at least two target video segments corresponding to the target video, wherein the at least two target video segments are generated by splitting the target video, and similarity of video picture contents of different target video segments does not satisfy a preset similarity condition; Identifying target text content corresponding to the target video clip; A target document corresponding to the target video is generated based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segment.

2. The method according to claim 1, characterized in that Determining at least two target video segments corresponding to the target video includes: Determine video picture content change state information between adjacent multiple frames of video picture content in the target video, wherein the video picture content change state information includes whether the video picture content has changed and the degree of change of the video picture content; Determining at least one video splitting position used when splitting the target video according to the video picture content change state information; Based on the at least one video splitting position, the target video is split into at least two target video segments.

3. The method according to claim 2, characterized in that Determine the video picture content change state information between adjacent multiple frames of video picture content in the target video, including: Determine the picture pixel information corresponding to each of the adjacent multiple frames of video picture content in the target video; Determine the video picture content similarity between the adjacent multiple frames of video picture content based on the picture pixel information corresponding to each of the adjacent multiple frames of video picture content; The video picture content change state information between adjacent multiple frames of video picture content is determined based on the video picture content similarity.

4. The method according to claim 2, characterized in that Determining at least one video splitting position used when splitting the target video according to the video picture content change state information includes: If the video picture content change state information indicates that the change degree of the video picture content is greater than a preset change degree threshold, a position between adjacent multiple frames of video picture content is determined as a video splitting position; If the video picture content change status information indicates that the change degree of the video picture content is not greater than the preset change degree threshold, the position between adjacent multiple frames of video picture content is not determined as the video splitting position.

5. The method according to claim 1, characterized in that Identifying target text content corresponding to the target video segment includes: By performing video recognition analysis on the target video segment, a first text content corresponding to the target video segment is extracted from the video screen content corresponding to the target video segment, where the first text content is used to describe the video screen content in words; Extracting corresponding second text content from the audio and audio subtitles of the target video clip; Based on the first text content and the second text content, target text content corresponding to the target video clip is determined.

6. The method according to claim 1, characterized in that Generating a target document corresponding to the target video based on the at least two target video segments and target text contents corresponding to the target video segments includes: Determining a target key frame image from the video screen contents corresponding to the at least two target video clips, wherein the target key frame image is an illustration that can make the textual idea expressed by the target text content more clear and distinct; A target document corresponding to the target video is generated based on the target key frame image and the target text content corresponding to the target video segment.

7. The method according to claim 6, characterized in that Determining a target key frame image from video screen contents corresponding to the at least two target video clips includes: Determining the segment length of each target video segment in the at least two target video segments and the number of characters in the corresponding target text content; Based on the length of each target video segment and the number of characters in the corresponding target text content, the at least two target video segments are screened; A target key frame image is determined from video picture contents corresponding to the at least two target video clips.

8. The method according to claim 6 or 7, characterized in that: Determining a target key frame image from video screen contents corresponding to the at least two target video clips includes: Determining the repetition of video picture content between the video picture content of each frame in the target video segment; Based on the repetition of video picture content between each frame of video picture content, deduplication processing is performed on video picture content whose repetition is greater than a preset repetition threshold; A target key frame image is extracted from the target video segment that has undergone deduplication processing.

9. The method according to claim 8, characterized in that Determining the video picture content repetition between the video picture content of each frame in the target video segment includes: Determine the video picture content features corresponding to the video picture content of each frame in the target video segment; Based on the video picture content features corresponding to the video picture contents of each frame, the video picture content repetition between the video picture contents of each frame is determined by comparing the video picture contents of each frame in pairs.

10. The method according to claim 6, characterized in that Generating a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video segment includes: Executing a preset text processing task through a preset text processing model to update and adjust the target text content corresponding to the target video clip, wherein the preset text processing task includes at least one of text expansion, text continuation, text rewriting and text rewriting, and the preset text processing model is pre-configured and generated based on a natural language model; A target document corresponding to the target video is generated based on the target key frame image and the target text content corresponding to the target video segment.

11. The method according to claim 6 or 10, characterized in that: Generating a target document corresponding to the target video based on the target key frame image and the target text content corresponding to the target video segment includes: Determining target text content that matches the target key frame image from target text content corresponding to the target video clip; Inserting the target key frame image into the location where the matching target text content is located; A target document corresponding to the target video is generated based on the inserted target key frame image and the target text content corresponding to the target video segment.

12. The method according to claim 11, characterized in that Determining target text content that matches the target key frame image from target text content corresponding to the target video segment includes: Determine first reference information of the target key frame image and second reference information of the target text content corresponding to the target video segment, wherein the first reference information is used to describe a timestamp corresponding to the target key frame image in the target video, and the second reference information is used to describe a timestamp corresponding to the target video segment corresponding to the target text content in the target video; Based on the first reference information of the target key frame image and the second reference information of the target text content corresponding to the target video segment, the target text content matching the target key frame image is determined from the target text content corresponding to the target video segment.

13. A document generation device, characterized in that: The device comprises: A determination module, configured to determine at least two target video segments corresponding to a target video, wherein the at least two target video segments are generated by splitting the target video, and similarities of video screen contents of different target video segments do not satisfy a preset similarity condition; An identification module, used to identify target text content corresponding to the target video clip; A generation module is used to generate a target document corresponding to the target video based on the at least two target video segments and the target text content corresponding to the target video segments, wherein the target document includes text content and image content determined based on the target video segment.

14. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the document generation method according to any one of claims 1 to 12.

15. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the document generation method according to any one of claims 1 to 12.

Images