CN116521925A - Video recording, playing, retrieving and playback method and device, electronic equipment and medium - Google Patents

Abstract

The present invention relates to the field of video playback control technologies, and in particular, to a video recording and playing retrieval playback method, device, electronic equipment, and medium. The method comprises the following steps: processing the original video based on the acquired first playback instruction of the user and the called preset processing rule, and determining a video clip based on the processing result, wherein the first playback instruction of the user is an instruction which needs to be played back by the user; generating prompt information based on the video clips, wherein the prompt information is information for informing a user whether the video clips need to be screened again; and if a second playback instruction fed back by the user based on the prompt information is acquired, screening the video clips based on the second playback instruction, determining a target video clip and feeding back and displaying the target video clip. The method and the device can ensure that the target video clip wanted by the user is positioned quickly and accurately, and improve the watching experience of the user.

Description

A method, device, electronic equipment and medium for video recording and playback retrieval and playback

technical field

The present application relates to the field of data query technology, in particular to a method, device, electronic device and medium for video recording and broadcasting retrieval and playback.

Background technique

With the development of network technology, video has become an important way for people to learn or entertain. People can watch the content they are interested in through video without leaving home, and for some live recorded videos, people can also play them back through video. Come to know what's going on.

There are two methods of traditional video playback technology. When the user wants to watch part of the video repeatedly, the first method is to watch at double speed from the beginning, and then adjust to the normal double speed when the target video clip is played. Video Memory Drag the progress bar until the target video segment is found.

With traditional video playback technology, the operation of continuously dragging the progress bar to confirm the target video segment is too cumbersome, and the target video segment cannot be accurately located in a short period of time, resulting in a decline in the user's viewing experience.

Contents of the invention

In order to improve the user's viewing experience, the present application provides a method, device, electronic device and medium for retrieving and playing back video recording and broadcasting.

In the first aspect, the present application provides a method for retrieving and playing back video recording and broadcasting, which adopts the following technical solution:

A method for retrieving and playing back video recording and playback, comprising:

Processing the original video based on the acquired user's first playback instruction and the recalled preset processing rules, and determining the video segment based on the processing result;

The user's first playback instruction is an instruction that the user needs to play back;

generating prompt information based on the video segment;

The prompt information is information to inform the user whether to further screen the video segment;

If the second playback instruction fed back by the user based on the prompt information is acquired, the video segment is screened based on the second playback instruction, and a target video segment is determined and displayed as feedback.

By adopting the above technical solution, first obtain the first playback command that the user needs to play back, and perform video processing on the original video according to the preset processing rules, determine the video segment, and then generate prompt information informing the user whether to further retrieve the video segment , if the user chooses to, obtain the user's second playback instruction, and perform corresponding screening processing on the video segment based on the second playback instruction, and finally determine the target video segment required by the user; thus, it is possible to quickly and accurately locate the user's desired video clip. target video clips to improve the user's viewing experience.

In a possible implementation manner, the processing of the original video based on the acquired user's first playback instruction and the recalled preset processing rules includes:

Based on the user's first playback instruction and the preset processing rules, determine the characteristics of the characters in the original video;

Determining the appearance time point and disappearance time point corresponding to the character features;

Based on the appearance time point and the disappearance time point, determine a character video segment corresponding to the character feature, and set the character video segment as a first video segment.

By adopting the above technical solution, with the user's first playback instruction and the preset processing rules as the preconditions, all character features in the original video are determined, and then the appearing time point and disappearance of all character features are determined based on the character features that appear Time point, that is, each appearance time point and the corresponding disappearance time point form a video clip, and finally determine the video clips corresponding to all character features, and set them as the first video clip; provide users with characters as the main retrieval target search method.

In a possible implementation manner, the processing of the original video based on the acquired user's first playback instruction and the recalled preset processing rules includes:

Based on the user's first playback instruction and the preset processing rules, determine the voice features in the original video;

Determining the appearance time point and disappearance time point corresponding to the voice feature;

Based on the appearance time point and the disappearance time point, determine a voice video segment corresponding to the voice feature, and set the voice video segment as a second video segment.

By adopting the above technical solution, taking the user's first playback instruction and preset processing rules as prerequisites, determine all voice features in the original video, and then use the preset voice pause time as a benchmark to determine the corresponding occurrence time points of all voice features and disappearing time points, that is, each appearing time point and corresponding disappearing time point form a video clip, finally determine the video clip corresponding to all voice features, and set it as the second video clip; provide users with voice-based retrieval How to retrieve the target.

In a possible implementation manner, the processing of the original video based on the acquired user's first playback instruction and the recalled preset processing rules includes:

Determining character features and voice features in the original video based on the user's first playback instruction and the preset processing rules;

Determining the time node at which the character features and the voice features exist at the same time;

Based on the time node, determine the voice video segment of the character, and set the voice video segment of the character as the third video segment.

By adopting the above-mentioned technical solution, taking the user's first playback instruction and preset processing rules as prerequisites, determine all character features and voice features in the original video, and then determine all character features and voice features based on the character features that appear at the same time Existing time nodes, that is, each time node corresponds to a video segment, and finally determine the video segments corresponding to all character features and voice features at the same time, and set it as the third video segment; provide users with characters and voice as the main retrieval target search method.

In a possible implementation manner, the target video segment includes at least one sub-target video segment, and if a second playback instruction fed back by the user based on the prompt information is obtained, the user's second playback instruction is based on the user's second playback instruction. The video clips are screened, and the target video clips are determined and displayed as feedback, including:

Based on the second playback instruction, generate a search box and display it in feedback;

Obtaining the keyword features input by the user in the search box;

Based on the keyword feature, the video segment is screened to determine a target video segment.

By adopting the above technical solution, the second playback instruction that the user needs to further screen the video clips is obtained, and a search box is automatically generated and displayed as a feedback. After receiving the keyword feature corresponding to the video clip input by the user in the search box, the key The word features are screened in the video clips to finally determine the target video clip; thereby more accurately locating the target video clip required by the user.

In a possible implementation manner, the keyword features are character text features and/or speech text features, and the acquisition of the keyword features input by the user in the search box further includes:

If the user inputs character text features, extract the character features in the video clip, and express in the form of text, and determine all the character text features;

If the user inputs the voice-text feature, the voice feature in the video segment is converted into text to determine all the voice-text features;

If the user inputs character text features and speech text features, extract all the character text features expressed in text form in the video clip, and extract all the speech text features in the video clip.

By adopting the above-mentioned technical scheme, if the user inputs character text features, then extract all the character features in the video clip, and represent the character features in the form of text; if the user inputs voice text features, then extract all the voice features in the video clip and convert them into Speech text, if the user inputs character text features and voice text features, the character text features and voice text features in the video clip are extracted at the same time; thus different combinations are provided to allow users to retrieve the target video clips they need.

In a possible implementation manner, the target video segment includes at least one sub-target video segment; and if the second playback instruction fed back by the user based on the prompt information is obtained, the video is played based on the second playback instruction. The fragments are screened, the target video fragments are determined and displayed as feedback, including:

Generate the time starting point corresponding to the sub-target video segment;

If the quantity of the sub-target video segment is a preset number, then directly jump to the corresponding time starting point of the sub-target video segment to play;

If the quantity of the sub-target video clips is greater than the preset number, then preferentially jump to the corresponding time start point of the earliest sub-target video clip of the time start point to play, and the remaining sub-target video clips included in the target video clip The corresponding time starting point is highlighted.

By adopting the above-mentioned technical solution, after the screening process of the electronic device is completed, the time starting point is generated based on the determined occurrence time points of all sub-target video segments, and then the number of sub-target video segments is judged. If the number of sub-target video segments is a preset number, It means that the filtered target video clip is unique, and the electronic device directly locates the time starting point of the target video clip to start playing; if the number of sub-target video clips exceeds the preset number, it means that there are multiple eligible video clips in the target video clip The sub-target video clips are sorted according to the sequence of time start points, the electronic device locates the first time start point to start playing, and the rest of the time start points are highlighted, so that users can clearly see the target video clips The position on the progress bar of the original video.

In the second aspect, the present application provides a video recording and broadcasting retrieval and playback device, which adopts the following technical solution:

A device for retrieving and replaying video recording and broadcasting, comprising: a video segment determination module, a prompt module and a target video segment determination module, wherein,

A video segment determination module, configured to process the original video based on the acquired user's first playback instruction and the recalled preset processing rules, and determine the video segment based on the processing result;

The user's first playback instruction is an instruction that the user needs to play back;

A prompt module, configured to generate prompt information based on the video clip;

The prompt information is information to inform the user whether to further screen the video segment;

The target video segment determination module is configured to, if the second playback instruction fed back by the user based on the prompt information is obtained, perform screening processing on the video segment based on the second playback instruction, determine the target video segment and display it in feedback.

By adopting the above-mentioned technical solution, firstly, the video clip determination module acquires the first playback instruction that the user needs to play back, and performs video processing on the original video according to the preset processing rules to determine the video clip, and then the prompt module generates and informs the user whether the video clip needs to be edited. The prompt information retrieved in another step, if the user selects the need, then the target video segment determination module obtains the user's second playback instruction, and based on the second playback instruction, the video segment is subjected to corresponding screening processing, and finally determines the target video segment required by the user ; so that the target video segment desired by the user can be quickly and accurately located, and the viewing experience of the user can be improved.

In a possible implementation manner, the video segment determination module includes: a character determination unit, a character time determination unit, and a first video segment unit, wherein,

A character determination unit, configured to determine the character characteristics in the original video based on the user's first playback instruction and the preset processing rules;

A character time determination unit, configured to determine the appearance time point and disappearance time point corresponding to the character features;

The first video segment unit is configured to determine a character video segment corresponding to the character feature based on the appearance time point and the disappearance time point, and set the character video segment as the first video segment.

In a possible implementation manner, the video segment determination module includes: a voice determination unit, a voice time determination unit, and a second video segment unit, wherein,

A voice determination unit, configured to determine voice features in the original video based on the user's first playback instruction and the preset processing rules;

A voice time determination unit, configured to determine the appearance time point and disappearance time point corresponding to the voice feature;

The second video segment unit is configured to determine a voice video segment corresponding to the voice feature based on the appearance time point and the disappearance time point, and set the voice video segment as a second video segment.

In a possible implementation manner, the video segment determination module includes: a character voice determination unit, a time node determination unit, and a third video segment unit, wherein,

A character voice determining unit, configured to determine character features and voice features in the original video based on the user's first playback instruction and the preset processing rules;

A time node determination unit, configured to determine a time node at which the character features and the voice features coexist;

The third video segment unit is configured to determine a character voice video segment based on the time node, and set the character voice video segment as a third video segment.

In a possible implementation manner, the target video segment determination module includes: a search box unit, an input unit, and a screening unit, wherein,

A search box unit, configured to generate a search box based on the second playback instruction and display it in feedback;

an input unit, configured to acquire keyword features input by the user in the search box;

The screening unit is configured to perform screening processing on the video clips based on the keyword feature to determine a target video clip.

In a possible implementation manner, the device for retrieving and playing back video recording and broadcasting further includes: a character text module, a voice text module, and a character and voice text module, wherein,

The character text module is used to extract the character features in the video clip if the user inputs the character text features, and express in the form of text, and determine all the character text features;

The voice-to-text module is used to convert the voice features in the video clip to text if the user inputs the voice-to-text features to determine all the voice-to-text features;

Character and voice text module, for if the user inputs character text features and voice text features, extract all the character text features expressed in text form in the video clip, extract all the voice text in the video clip feature.

In a possible implementation manner, the target video clip determination module includes: a time starting point unit, a first jump unit, and a second jump unit, wherein,

A time starting point unit, configured to generate a time starting point corresponding to the sub-target video segment;

The first jump unit is used to directly jump to the corresponding time starting point of the sub-target video segment to play if the number of the sub-target video segments is a preset number;

The second jump unit is used for if the quantity of the sub-target video clip is greater than the preset number, then preferentially jump to the time start point corresponding to the earliest sub-target video segment of the time start point to play, and the target video The time start points corresponding to the remaining sub-target video clips included in the clip are highlighted.

In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

An electronic device comprising:

at least one processor;

memory;

At least one application program, wherein at least one application program is stored in a memory and is configured to be executed by at least one processor, and the at least one application program is configured to: execute the above video recording and playback retrieval and playback method.

In the fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

A computer-readable storage medium, comprising: storing a computer program capable of being loaded by a processor and executing the above-mentioned method for retrieving and playing back video recording and broadcasting.

In summary, the application includes the following beneficial technical effects:

First obtain the first playback command that the user needs to play back, and process the original video according to the preset processing rules to determine the video segment, and then generate a prompt message informing the user whether to further retrieve the video segment. If the user chooses to, Then obtain the user's second playback instruction, and based on the second playback instruction, perform corresponding screening processing on the video segment, and finally determine the target video segment required by the user; thereby being able to quickly and accurately locate the target video segment desired by the user, and improve User viewing experience.

Description of drawings

Fig. 1 is a schematic flow chart of the method for retrieving and replaying video recording and broadcasting according to the embodiment of the present application;

Fig. 2 is a schematic block diagram of an embodiment of the present application based on video recording and playback retrieval and playback device;

Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed ways

The present application will be described in further detail below in conjunction with accompanying drawings 1-3.

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

The embodiment of the present application provides a method for retrieving and playing back video recording and broadcasting, which is executed by an electronic device. The electronic device can be a server or a terminal device, where the server can be an independent physical server or multiple physical servers. A server cluster or a distributed device composed of servers may also be a cloud server that provides cloud computing services. The terminal device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server may be connected directly or indirectly through wired or wireless communication. Do limit.

Referring to Fig. 1, the method includes: step S101, step S102 and step S103, wherein:

S101. Process the original video based on the acquired user's first playback instruction and the recalled preset processing rule, and determine a video segment based on the processing result.

For this embodiment of the application, the user's first playback instruction indicates that the user needs to play back the instruction, and the preset processing rules are the rules for splitting and processing the original video, including character rules, voice rules, and character and voice rules.

Specifically, after the electronic device obtains the user's instruction to play back, it invokes the preset processing rules, splits and processes the original video into three types of video clips based on character rules, voice rules, and character and voice rules, and then The electronic device obtains the user's selection method, and according to the user's selection, determines one of the video clips to display to the user. For example, the user selects a voice rule, and the electronic device determines that the video clip that has been split and processed by the voice rule is displayed to the user.

Further, the storage method of the preset processing rule may include at least one of the following methods. In the first method, the preset processing rule may be stored in the storage space of the electronic device itself; in the second method, the preset processing rule may be stored in a computer connected to the electronic device. In the hardware storage device; method 3, the preset processing rules can be stored in the cloud storage space for easy recall at any time.

S102. Generate prompt information based on the video segment.

For the embodiment of the present application, the prompt information is information notifying the user whether to further screen the video segment.

Specifically, based on the video clips displayed to the user, the electronic device generates prompt information at a position that does not affect the user's viewing, asking whether it is necessary to further screen the video clips. Fragment satisfaction, so that the preset processing rules can be continuously improved according to the user's feedback based on the prompt information.

It should be noted that the embodiment of the present application does not specifically limit the prompting manner and prompting position of the prompting information.

S103. If the second playback instruction fed back by the user based on the prompt information is acquired, perform screening processing on the video clips based on the second playback instruction, determine a target video clip, and display it in feedback.

For the embodiment of the present application, the screening process includes character feature and/or voice feature screening.

Specifically, after the user gives feedback on the generated prompt information, if the user chooses not to perform further screening processing, the prompt information is closed to facilitate the user to watch the video clip; if the user needs to perform further screening processing, the electronic device generates The second playback instruction, and based on the second playback instruction, the video clips are further screened, the video clips are compared and screened by character features and/or voice features, and finally the target video clip is determined, and the target video clip is displayed, wherein, The target video clip may contain multiple target video clips, and through further screening, a more precise search method is provided to allow the user to obtain the target video clip he needs.

The embodiment of the present application provides a method for retrieving and playing back video recording and broadcasting. When the electronic device receives the first playback instruction that the user wants to play back, the electronic device first simultaneously disassembles the original video through character rules, voice rules, and character and voice rules. Then, based on the user's selection of the splitting method, the corresponding video segment is displayed as the processing result, and a prompt message is generated to ask the user whether the current video segment needs to be further screened. If not, the prompt message is closed to It is convenient for the user to watch the video segment of the first processing result. If necessary, the electronic device receives the user's second playback instruction, and compares the features input by the user with the character features and/or voice features obtained after feature extraction of the current video segment. For screening, determine the target video segment as the final processing result, and display it to the user; so as to quickly and accurately locate the target video segment that the user wants to playback, and improve the user's viewing experience.

In step S101, the original video is processed based on the acquired user's first playback instruction and the recalled preset processing rules, specifically including: determining the characteristics of characters in the original video based on the user's first playback instruction and preset processing rules; Determine the appearance time point and disappearance time point corresponding to the character feature; based on the appearance time point and disappearance time point, determine the character video segment corresponding to the character feature, and set the character video segment as the first video segment.

For the embodiment of this application, there can be multiple appearance time points and disappearance time points. Similarly, the first video clip can also contain multiple first sub-video clips. It should be noted that the description here is to illustrate the A clip can contain multiple sub-video clips, which will be used below and will not be repeated here.

Specifically, when the electronic device receives the user's playback instruction, it collects the character image information in the original video, and at the same time, the electronic device records the appearance time point and the corresponding disappearance time point of the character head information, and marks them in the progress bar of the original video, that is , determine a first sub-video segment, repeat the above operations until the original video is completely collected, and ensure that each first sub-video segment contains character image information, save and summarize all the first sub-video segments into For the first video segment, the electronic device displays the first video segment including multiple time nodes.

In step S101, the original video is processed based on the obtained user's first playback instruction and the recalled preset processing rules, which specifically includes: determining the voice features in the original video based on the user's first playback instruction and preset processing rules ; Determine the appearance time point and disappearance time point corresponding to the voice feature; based on the appearance time point and the disappearance time point, determine the voice video segment corresponding to the voice feature, and set the voice video segment as the second video segment.

For the embodiment of the present application, when the electronic device receives the user's playback instruction, it determines the voice and audio information in the original video, and at the same time, the electronic device sequentially records the appearance time point and the corresponding disappearance time point of the voice and audio information, and displays them in the original video progress bar. Mark, that is, determine a second sub-video segment, repeat the above operations until the original video is completely collected, and ensure that each second sub-video segment contains voice and audio information, and separate all the second sub-video segments The second video clip is saved and summarized, and the electronic device displays the second video clip including multiple time nodes.

In step S101, the original video is processed based on the acquired user's first playback instruction and the recalled preset processing rules, which specifically includes: determining the characteristics of the characters in the original video based on the user's first playback instruction and the preset processing rules and voice features; determine the time node at which the character features and voice features coexist; based on the time node, determine the voice video segment of the character, and set the voice video segment of the character as the third video segment.

For this embodiment of the application, when the electronic device receives the playback instruction from the user, it collects the character image information and voice and audio information in the original video, and at the same time, the electronic device sequentially records the time nodes when the character image information and the voice and audio information appear and disappear at the same time, and Mark in the original video progress bar, that is, determine a third sub-video segment, repeat the above operations until the original video is completely collected, and ensure that each third sub-video segment contains character image information and voice and audio information , saving and summarizing all the third sub-video segments into a third video segment, and the electronic device displays the third video segment including multiple time nodes.

In step S103, if the second playback instruction fed back by the user based on the prompt information is obtained, the video segment is screened based on the user's second playback instruction, and the target video segment is determined and displayed as feedback. Specifically, it also includes: based on the second playback instruction, Generate a search box and display it in feedback; obtain the keyword features entered by the user in the search box; based on the keyword features, screen the video clips to determine the target video clip.

In the embodiment of the present application, the keyword features represent character text features and/or speech text features in the target video segment that the user wants to query.

Specifically, based on the second playback instruction received by the electronic device that the user needs to further filter as a condition, a search box is generated and displayed in feedback. When the user enters a keyword feature in the search box, the electronic device based on the keyword feature, previously selected Screen the corresponding character text features and/or voice-text features from the corresponding video clips, and extract the video clips that meet the features as target video clips. All video segments corresponding to the second video segment containing the voice of "study well" are extracted as the final target video segment.

Further, the acquisition of the keyword features input by the user in the search box specifically includes: if the user enters the character text features, extract the character features in the video clip and express them in the form of text, and determine all the character text features; if the user inputs Voice-to-text features, converting the voice features in the video clip to text to determine all the voice-to-text features; if the user inputs character text features and voice-to-text features, extract all character texts expressed in text form in the video clip feature, extracting all the speech-text features in the video clip.

In the embodiment of the present application, the character features may include clothing features and character names, and the voice features may include audio information.

Specifically, if the user inputs character text features, the clothing features and character names in the video clip are represented in text form. For example, there is a clip of a man in a suit giving a speech in the video, and the keyword feature input by the user can be "suit speech ", the corresponding video segment can be retrieved; if the user enters the voice text feature, all the voice segments in the video will be converted into voice text, which is convenient for the user to search through the text later. Upward every day", the keyword feature input by the user can be "learning" or "study hard", and the corresponding video clip can be retrieved. If the user enters character text features and voice text features, the character text features and Speech text features, for example, there is a clip in the video where a man in a suit is giving a speech about how to learn, and the keyword feature input by the user can be "learn in a suit speech", and the corresponding video clip can be retrieved.

It should be noted that the keyword feature may be the keyword feature of each language, which is not specifically limited in this application.

In step S103, the target video segment includes at least one sub-target video segment. If the second playback instruction fed back by the user based on the prompt information is obtained, the video segment is screened based on the user's second playback instruction, and the target video segment is determined and displayed in feedback. , specifically includes: generating the time start point corresponding to the sub-target video segment; if the number of sub-target video segments is the preset number, directly jump to the time start point corresponding to the sub-target video segment to play; if the number of sub-target video segments If the number is greater than the preset number, jump to the time start point corresponding to the earliest sub-target video clip at the time start point first, and then highlight the time start points corresponding to the remaining sub-target video clips included in the target video clip.

In the embodiment of the present application, the preset number is 1.

Specifically, after the electronic device screening process is completed, based on the determined occurrence time points of all sub-target video segments, a time starting point is generated, and then the number of sub-target video segments is judged. If the number of sub-target video segments is 1, it means that the target video segment If there is only one corresponding time starting point, the electronic device will directly locate the time starting point of the target video segment and start playing; if the number of sub-target video segments exceeds 1, it means that the target video segment has multiple sub-target video segments that meet the conditions. and contains multiple time starting points, according to the sequence of the time starting points, the electronic device will firstly locate the time starting point that appears first to start playing, and the rest of the time starting points will be highlighted, so as to help users see clearly The position of the target video clip on the progress bar of the original video.

The video recording and playback retrieval and playback device 20 may specifically include: a video segment determination module 201, a prompt module 202, and a target video segment determination module 203, wherein,

The video segment determination module 201 is used to process the original video based on the obtained user's first playback instruction and the preset processing rule called, and determine the video segment based on the processing result;

The user's first playback instruction is an instruction that the user needs to play back;

Prompt module 202, for generating prompt information based on the video segment;

The prompt information is information to inform the user whether to further screen the video clip;

The target video segment determining module 203 is configured to, if the second playback instruction fed back by the user based on the prompt information is obtained, perform screening processing on the video segment based on the second playback instruction, determine the target video segment and display it as feedback.

In a possible implementation of the embodiment of the present application, the video segment determination module 201 includes a character determination unit, a character time determination unit, and a first video segment unit, wherein,

A character determination unit, configured to determine the character features in the original video based on the user's first playback instruction and preset processing rules;

A character time determination unit, configured to determine the appearance time point and disappearance time point corresponding to the character features;

The first video segment unit is configured to determine a character video segment corresponding to the character feature based on the appearance time point and the disappearance time point, and set the character video segment as the first video segment.

In a possible implementation of the embodiment of the present application, the video segment determination module 201 further includes: a voice determination unit, a voice time determination unit, and a second video segment unit, wherein,

A voice determination unit, configured to determine voice features in the original video based on the user's first playback instruction and preset processing rules;

A voice time determination unit, configured to determine the appearance time point and disappearance time point corresponding to the voice feature;

The second video segment unit is configured to determine the audio video segment corresponding to the voice feature based on the appearance time point and the disappearance time point, and set the audio video segment as the second video segment.

In a possible implementation of the embodiment of the present application, the video segment determination module 201 further includes: a character voice determination unit, a time node determination unit, and a third video segment unit, wherein,

A character voice determining unit, configured to determine character features and voice features in the original video based on the user's first playback instruction and preset processing rules;

A time node determining unit, configured to determine a time node at which character features and voice features coexist;

The third video segment unit is configured to determine the character voice video segment based on the time node, and set the character voice video segment as the third video segment.

In a possible implementation of the embodiment of the present application, the target video segment determination module 203 further includes: a search box unit, an input unit, and a screening unit, wherein,

A search box unit, configured to generate a search box based on the second playback instruction and display it in feedback;

The input unit is used to obtain the keyword features entered by the user in the search box;

The screening unit is configured to perform screening processing on video clips based on keyword features to determine target video clips.

In a possible implementation of the embodiment of the present application, the device 20 for retrieving and playing back video recording and broadcasting further includes: a character text module, a voice text module, and a character and voice text module, wherein,

The character text module is used to extract the character features in the video clip if the user inputs the character text features, and express them in the form of text to determine all the character text features;

The voice-to-text module is used to convert the voice features in the video clip to text if the user inputs the voice-to-text features to determine all the voice-to-text features;

The character and speech text module is used to extract all character text features expressed in text form in the video clip and extract all the speech text features in the video clip if the user inputs character text features and speech text features.

In a possible implementation of the embodiment of the present application, the target video segment determination module 203 further includes: a time starting point unit, a first jump unit, and a second jump unit, wherein,

The time start point unit is used to generate the time start point corresponding to the sub-target video segment;

The first jump unit is used to directly jump to the corresponding time starting point of the sub-target video segment to play if the quantity of the sub-target video segment is a preset number;

The second jump unit is used to jump to the corresponding time starting point of the earliest sub-target video segment of the time starting point if the number of sub-target video segments is greater than the preset number, and play the remaining sub-target video segments included in the target video segment. The time starting point corresponding to the target video segment is highlighted.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

The embodiment of the present application also introduces an electronic device from the perspective of a physical device. As shown in FIG. 3 , the electronic device 30 shown in FIG. 3 includes: a processor 301 and a memory 303 . Wherein, the processor 301 is connected to the memory 303 , such as through a bus 302 . Optionally, the electronic device 30 may further include a transceiver 304 . It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not limit the embodiment of the present application.

The processor 301 may be a CPU (Central Processing Unit, central processing unit), a general-purpose processor, a DSP (Digital Signal Processor, a data signal processor), an ASIC (Application Specific Integrated Circuit, an application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure. The processor 301 may also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

Bus 302 may include a path for communicating information between the components described above. The bus 302 may be a PCI (Peripheral Component Interconnect, Peripheral Component Interconnect Standard) bus or an EISA (Extended Industry Standard Architecture, Extended Industry Standard Architecture) bus or the like. The bus 302 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 3 , but it does not mean that there is only one bus or one type of bus.

The memory 303 can be ROM (Read Only Memory, read-only memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory, random access memory) or other types of static storage devices that can store information and instructions Dynamic storage devices can also be EEPROM (Electrically Erasable Programmable Read Only Memory, Electrically Erasable Programmable Read-Only Memory), CD-ROM (Compact DiscRead Only Memory, CD-ROM) or other CD storage, CD storage (including compact CD, laser discs, compact discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer media, but not limited to this.

The memory 303 is used to store application program codes for executing the solutions of the present application, and the execution is controlled by the processor 301 . The processor 301 is configured to execute the application program code stored in the memory 303, so as to realize the contents shown in the foregoing method embodiments.

Among them, electronic devices include but are not limited to: mobile phones, notebook computers, digital broadcast receivers, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc. Mobile terminals such as digital TVs, desktop computers, etc. and fixed terminals. Also for servers etc. The electronic device shown in FIG. 3 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

It should be understood that although the various steps in the flow chart of the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages may not necessarily be executed at the same time, but may be executed at different times, and the order of execution is also It is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

The above are only some implementations of the present application. It should be pointed out that for those of ordinary skill in the art, some improvements and modifications can be made without departing from the principle of the application, and these improvements and modifications should also be considered as For the scope of protection of this application.

Claims (10)

1. A video recording, playback and retrieval method, comprising:

processing the original video based on the acquired first playback instruction of the user and the called preset processing rule, and determining a video clip based on a processing result;

the first playback instruction of the user is an instruction that the user needs to play back;

generating prompt information based on the video clips;

the prompt information is information for informing a user whether the video clips need to be screened again;

and if a second playback instruction fed back by the user based on the prompt information is acquired, screening the video clips based on the second playback instruction, determining a target video clip and feeding back and displaying the target video clip.

2. The method for video recording, playback and retrieval according to claim 1, wherein the processing the original video based on the acquired user first playback instruction and the invoked preset processing rule comprises:

Determining character features in the original video based on the first playback instruction of the user and the preset processing rule;

determining appearance time points and disappearance time points corresponding to the character features;

and determining a character video clip corresponding to the character feature based on the appearance time point and the disappearance time point, and setting the character video clip as a first video clip.

3. The method for video recording, playback and retrieval according to claim 1, wherein the processing the original video based on the acquired user first playback instruction and the invoked preset processing rule comprises:

determining voice characteristics in the original video based on the first playback instruction of the user and the preset processing rule;

determining an appearance time point and a disappearance time point corresponding to the voice feature;

and determining a voice video segment corresponding to the voice feature based on the occurrence time point and the disappearance time point, and setting the voice video segment as a second video segment.

4. The method for video recording, playback and retrieval according to claim 1, wherein the processing the original video based on the acquired user first playback instruction and the invoked preset processing rule comprises:

Determining character features and voice features in the original video based on the first playback instruction of the user and the preset processing rule;

determining a time node at which the character feature and the voice feature coexist;

and determining a character voice video segment based on the time node, and setting the character voice video segment as a third video segment.

5. The method of claim 1, wherein if a second playback instruction fed back by a user based on prompt information is obtained, screening the video segments based on the second playback instruction of the user, determining a target video segment, and feeding back and displaying the target video segment, comprising:

generating a search box and feeding back and displaying the search box based on the second playback instruction;

acquiring keyword characteristics input by a user in the search box;

and screening the video clips based on the keyword features to determine target video clips.

6. The method for video recording, searching and replaying according to claim 5, wherein the keyword features are human text features and/or voice text features, and the step of obtaining the keyword features input by the user in the search box further comprises the steps of:

If the user inputs character text features, extracting the character features in the video clips, representing the character features in a text form, and determining all the character text features;

if the user inputs the voice text features, performing text conversion on the voice features in the video clips, and determining all the voice text features;

if the user inputs character text features and voice text features, extracting all character text features expressed in a text form in the video segment, and extracting all voice text features in the video segment.

7. The video recording, retrieving and playback method as set forth in claim 1, wherein the target video clip comprises at least one sub-target video clip; if a second playback instruction fed back by the user based on the prompt information is acquired, screening the video clips based on the second playback instruction, determining a target video clip and feeding back and displaying the target video clip, including:

generating a time starting point corresponding to the sub-target video segment;

if the number of the sub-target video clips is the preset number, directly jumping to a time starting point corresponding to the sub-target video clips for playing;

If the number of the sub-target video clips is greater than the preset number, preferentially jumping to the time starting point corresponding to the sub-target video clip with the earliest time starting point for playing, and performing highlighting processing on the time starting points corresponding to the rest sub-target video clips contained in the target video clip.

8. A video recording, playback and retrieval device, comprising:

the video segment determining module is used for processing the original video based on the acquired first playback instruction of the user and the called preset processing rule and determining a video segment based on the processing result;

the first playback instruction of the user is an instruction that the user needs to play back;

the prompt module is used for generating prompt information based on the video clips;

the prompt information is information for informing a user whether the video clips need to be screened again;

and the target video segment determining module is used for screening the video segments based on the second playback instruction if the second playback instruction fed back by the user based on the prompt information is acquired, determining the target video segments and feeding back and displaying the target video segments.

9. An electronic device, comprising:

At least one processor;

a memory;

at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a video recording and playback retrieval method according to any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed in a computer, causes the computer to perform a video recording, retrieving and playback method according to any one of claims 1 to 7.