Video processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a video processing method and device, and relates to the technical field of computers, in particular to the technical fields of large models, deep learning, image processing and the like. The specific implementation scheme is as follows: determining and playing a to-be-recommended video in at least two first video clips; obtaining first resource attribute information of the to-be-recommended video in response to determining that the to-be-recommended video meets the same-attribute video continuous playing condition; based on the resource attribute information, determining a first continuous playing video having the same resource attribute as the to-be-recommended video; and after the to-be-recommended video is played, the first continuous playing video is played, so that the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, specifically to technical fields such as large models, deep learning, and image processing, and in particular to a video processing method and device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Currently, watching short videos has become a way for people to relax in their daily lives, and various entertainment and funny content are emerging in an endless stream.

[0003] For film and television video recommendations, film and television video resources are generally recalled and sorted according to user interests, and finally displayed according to the order results given by the recommendation model. However, this display only shows one fragment of the content. After users are satisfied with consuming film and television content, they cannot watch consecutive short videos with the same plot, resulting in a poor user experience. Summary of the invention

[0004] The present disclosure provides a video processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to a first aspect, a video processing method is provided, the method comprising: determining and playing a video to be recommended from at least two first video clips; in response to determining that the video to be recommended meets a condition for playing videos with the same attributes, obtaining first resource attribute information of the video to be recommended; based on the first resource attribute information, determining a first video to be played in a continuous broadcast having the same resource attributes as the video to be recommended; and playing the first video to be played in a continuous broadcast after the video to be recommended is played.

[0006] According to a second aspect, a video processing device is provided, which includes: a determination unit, configured to determine and play a video to be recommended from at least two first video clips; an acquisition unit, configured to acquire first resource attribute information of the video to be recommended in response to determining that the video to be recommended meets a condition for playing videos with the same attributes; a query unit, configured to determine a first video to be played in a continuous broadcast having the same resource attributes as the video to be recommended based on the first resource attribute information; and a playback unit, configured to play the continuous broadcast video after the video to be recommended is played.

[0007] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0008] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0009] According to a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in any implementation manner of the first aspect when executed by a processor.

[0010] The video processing method and device provided by the embodiments of the present disclosure first determine and play the video to be recommended in at least two first video clips; secondly, in response to determining that the video to be recommended meets the condition of continuous broadcast of videos with the same attribute, obtain the first resource attribute information of the video to be recommended; thirdly, based on the resource attribute information, determine the first continuous broadcast video with the same resource attribute as the video to be recommended; finally, play the first continuous broadcast video after the video to be recommended is played. Therefore, when playing the video to be recommended, by judging whether the video to be recommended meets the condition of continuous broadcast of videos with the same attribute, the first continuous broadcast video is recommended and played for the user, which can effectively grasp the user's explicit video interest expression, and the user no longer needs to search for videos separately, which reduces the complexity of user operations, simplifies the user content distribution path, improves the accuracy of video recommendations, and improves user experience.

[0011] 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

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is a flow chart of an embodiment of a video processing method according to the present disclosure;

[0014] Figure 2 is a flowchart of another embodiment of the video processing method according to the present disclosure;

[0015] Figure 3 is a structural schematic diagram of an embodiment of a video processing device according to the present disclosure;

[0016] Figure 4 The block diagram is a block diagram of an electronic device for implementing the video processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] In traditional technologies, existing recommendation models do not take into account the same resource attributes of film and television resources. Since film and television resources are generally excerpted from long-form TV series and movies, only a fragment of the content can be displayed. After users are satisfied with consuming film and television content, they will naturally have immediate interest in other fragments of film and television content with the same resource attributes.

[0019] Compared with users' long-term interests, this type of interest expression has a certain timeliness. However, the original recommendation model adjusted based on posterior data has a certain lag in capturing such user interests and does not fully utilize the explicit interests expressed by users.

[0020] In traditional technology, when a user becomes interested in a certain film or television content, due to the uncertainty of algorithm-based recommendations, the user needs to search manually or go to the author's homepage to complete the relevant search. The process is long and the experience is poor.

[0021] In view of the defects in the traditional technology, the present disclosure proposes a video processing method, which can automatically play the first consecutive video without the need for user search, thereby improving the user experience. Figure 1 A process 100 according to an embodiment of a video processing method of the present disclosure is shown. The video processing method comprises the following steps:

[0022] Step 101: Determine and play videos to be recommended in at least two first video clips.

[0023] In this embodiment, the video clip is a part of a film or TV series, and the video clip has a short video duration, for example, only 1 to 5 seconds. The at least two first video clips can be clips obtained by intercepting multiple different types of film or TV series using a video clip interception tool. Each of the at least two first video clips can belong to the same film or TV series, or different film or TV series. Optionally, each first video clip can also belong to the same variety show, or different variety shows. Optionally, each first video clip can also belong to the same sports video, or different sports videos.

[0024] In this embodiment, the video to be recommended belongs to at least one of the at least two first video segments. The video to be recommended may be a first video segment selected from the at least two first video segments based on the user's long-term interests and hobbies; the video to be recommended may also be a first video segment selected from the at least two first video segments based on the user's age and gender information. Specifically, the above step 101 includes: based on the interests and hobbies of the user currently operating the video segment, selecting the video to be recommended from the at least two first video segments, and playing the video to be recommended.

[0025] In this embodiment, the video to be recommended can be played through a video player, and the execution entity on which the video processing method runs can record the number of times the video to be recommended is played and the number of times it is played in succession with multiple other video clips each time the video to be recommended is played, wherein the number of times the video to be recommended is played autonomously by the user, and the number of times the video to be recommended is played continuously while playing other video clips.

[0026] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of the first video clip are performed after authorization and comply with relevant laws and regulations. The information related to the user in the first video clip is information obtained after the user's permission, and the video processing related to the user is processed under confidentiality conditions.

[0027] Step 102: In response to determining that the video to be recommended meets the condition for continuous broadcast of videos with the same attribute, first resource attribute information of the video to be recommended is obtained.

[0028] In this embodiment, the same attribute video streaming condition is to determine whether the same resource attribute video streaming condition is met. When the same attribute video streaming condition is met, the first streaming video with the same resource attribute as the video to be recommended can be inserted after the current video to be recommended; when the same attribute video streaming condition is not met, the first streaming video with the same resource attribute as the video to be recommended cannot be inserted after the current video to be recommended. The first streaming video can be a video clip obtained from at least two first video clips, or a video clip obtained from other places.

[0029] In this embodiment, the conditions for continuous broadcast of videos with the same attributes may include at least one or more of the following: the video to be recommended is the first video segment recommended for the first time; the video to be recommended is the first video segment that the user has completed playing; the number of times the first continuous broadcast video with the same resource attributes as the video to be recommended is played back does not exceed the upper limit of the number of times.

[0030] In this embodiment, after determining that the video to be recommended meets the condition for continuous playback of videos with the same attribute, it is determined that after the current playback of the video to be recommended is completed, the first video segment with the same resource attribute as the video to be recommended in at least two first video segments can be played continuously.

[0031] In this embodiment, the first resource attribute information is the resource attribute information of the first broadcast video, and the resource attribute information is information that characterizes the attributes of the video resource itself. For example, the resource attribute information includes: the title and plot of the video clip. The resource attribute information is information extracted from the video clip. At least two video clips with the same resource attributes can be linked together through the resource attribute information.

[0032] In this embodiment, in order to more effectively characterize the video clips, the resource attribute information may be attribute information obtained by integrating the resource attributes of different video clips in the same drama. Specifically, the steps for obtaining the resource attribute information are as follows: for the at least two first video clips mentioned above, extract the first video clips belonging to the same drama; obtain the text information of the first video clips in the same drama; extract the information related to the resource attributes of each resource clip in the text information to obtain the resource attribute information.

[0033] Step 103: Based on the resource attribute information, determine the first streaming video having the same resource attribute as the video to be recommended.

[0034] In this embodiment, the first streaming video is a video clip. Compared with the long-term interests and hobbies of the user, the interest expression of the first streaming video has a certain timeliness compared with the long-term interests of the user, and the first streaming video can be a first video clip selected from the at least two first video clips, or a video clip obtained from other than the at least two first video clips. Resource attribute information tags can be added to all first video clips and video clips other than the first video clips. When determining the first streaming video with the same resource attribute as the video to be recommended, it is only necessary to compare the first resource attribute information of the video resource to be recommended with the resource attribute information of the first video clip and the video clips other than the first video clip.

[0035] Step 104: After the recommended video is played, the first continuous video is played.

[0036] In this embodiment, the resource attribute information links together multiple video clips with the same resource attribute, and the first resource attribute information of the video to be recommended links the video to be recommended with the video clip with the same resource attribute as the video to be recommended. For the first resource attribute information of the video to be recommended, there may be one or more video clips with the same first resource attribute information; based on the video content of the video to be recommended, the video clip with the same resource attribute information and the video clip most related to the video to be recommended is selected as the first continuous broadcast video, and the first continuous broadcast video is played after the video to be recommended is played.

[0037] The video processing method provided in this embodiment determines the first video to be broadcasted with the same resource attributes as the video to be recommended, provides a strategy for broadcasting video clips with the same resource attributes, simplifies the user's access to the video clip content of the point of interest, and simplifies the operation complexity.

[0038] The video processing method provided by the embodiment of the present disclosure first determines and plays the video to be recommended in at least two first video clips; secondly, in response to determining that the video to be recommended meets the condition of continuous broadcast of videos with the same attribute, obtains the first resource attribute information of the video to be recommended; thirdly, based on the first resource attribute information, determines the first continuous broadcast video with the same resource attribute as the video to be recommended; finally, plays the first continuous broadcast video after the video to be recommended is played. Therefore, when playing the video to be recommended, by judging whether the video to be recommended meets the condition of continuous broadcast of videos with the same attribute, the continuous broadcast video is recommended and played for the user, which can effectively grasp the user's explicit video interest expression, and the user no longer needs to search for videos separately, which reduces the complexity of user operations, simplifies the user content distribution path, improves the accuracy of video recommendations, and improves the user experience.

[0039] Figure 2 A process 200 according to an embodiment of a video processing method of the present disclosure is shown. The video processing method comprises the following steps:

[0040] Step 201: Determine videos to be recommended in at least two first video clips.

[0041] Step 202: Add the video to be recommended to the video recommendation list.

[0042] In this embodiment, the video recommendation list may be a list of video clips displayed on the player. Through the video recommendation list, the user can intuitively determine the video currently being played by the player.

[0043] Step 203: Play the video to be recommended according to the video recommendation list.

[0044] In this embodiment, the video to be recommended may be one video clip or multiple video clips. Therefore, after the video to be recommended is added to the video recommendation list, the video clips in the video recommendation list may be one video clip or multiple video clips.

[0045] Step 204: in response to the video to be recommended satisfying the condition for continuous broadcast of videos with the same attribute, obtaining first resource attribute information of the video to be recommended.

[0046] Step 205: Based on the first resource attribute information, determine a first streaming video having the same resource attribute as the video to be recommended.

[0047] In this embodiment, it should be understood that the operations and features in the above-mentioned step 201 and step 204-step 205 correspond to the operations and features in steps 101-103, respectively. Therefore, the above-mentioned descriptions of the operations and features in steps 101-103 are also applicable to step 201 and step 204-step 205, and will not be repeated here.

[0048] Step 206, adding the sequential video to the video recommendation list, and playing the first sequential video after the recommended video is finished playing.

[0049] In this embodiment, based on the long-term interests of the user who plays the video to be recommended, the video to be recommended determined from the multiple video clips can be one or more. For this purpose, the one or more videos to be recommended are put into the video recommendation list of the player to obtain a video recommendation list with one video clip or multiple video clips; after the continuous broadcast video of the video to be recommended is determined, the video clip corresponding to the first continuous broadcast video with the same resource attribute as the video to be recommended can be one or more. For this purpose, the continuous broadcast video can be added to the video clip of the video to be recommended in the video recommendation list. After the continuous broadcast video of each video to be recommended among the multiple videos to be recommended is determined, the first continuous broadcast video corresponding to each video to be recommended can be added to the respective video to be recommended. At this time, the first continuous broadcast video of each video to be recommended is inserted in different areas of the video recommendation list.

[0050] The video processing method provided in this embodiment adds the video to be recommended to the video recommendation list before playing the video to be recommended; adds the first consecutive video to the video recommendation list before playing the first consecutive video. The video to be recommended and the first consecutive video are both in the video recommendation list, which allows the user to intuitively view the video clip that is about to be played or is being played, so as to have a deeper understanding of the video playback trend and improve the user experience.

[0051] In some optional implementations of the present disclosure, the above method also includes: obtaining text information for the second video segment that includes text information in the first video segment; obtaining second resource attribute information in the text information using resource attribute extraction rules; the extraction rules are rules for extracting predetermined content in the text information.

[0052] In this embodiment, the above-mentioned obtaining the first resource attribute information of the video to be recommended includes: obtaining the first resource attribute information from the second resource attribute information.

[0053] In this optional implementation, the second video clip is a video clip in the first video clip that includes text information, the second resource attribute information is the resource attribute information of the second video clip, and the text information may be information directly extracted from the second video clip through a text extraction model. For example, the text information may be a title, subtitles, and other content, and the text information may include text, symbols, and other content.

[0054] In this optional implementation, the extraction rule of resource attributes is a rule set for the extraction of resource attributes. The extraction rule indicates that the extracted text information includes predetermined content, wherein the predetermined content can be determined based on the extraction requirements, for example, the predetermined content is the title of a video series. For another example, the extraction rule is a rule that indicates the title of a video clip in the text information and the most frequently occurring plot.

[0055] In this optional implementation, the acquiring of the first resource attribute information from the second resource attribute information includes: using the second resource attribute information of a video segment in the second video segment that is similar to the video to be recommended as the first resource attribute information.

[0056] The video processing method provided by this optional implementation adopts resource attribute extraction rules to extract the second resource attribute information in the text information when the second video clip has text information. Since the extraction rules are predefined rules, the predetermined content in the text information of the second video clip can be extracted and the predetermined content is used as the second resource attribute, thereby improving the accuracy of the second resource attribute information.

[0057] Optionally, the above method also includes: for a third video segment that does not include text information in the first video segment, inputting the third video segment into an image-text generation model to obtain text information of the third video segment, and using resource attribute extraction rules to extract third resource attribute information from the text information of the third video segment.

[0058] In some optional implementations of the present disclosure, the method further includes: for a third video segment that does not include text information in the first video segment, obtaining third resource attribute information of a fourth video segment whose video fingerprint is similar to the third video segment.

[0059] The above-mentioned obtaining the first resource attribute information of the video to be recommended includes: obtaining the first resource attribute information from the third resource attribute information.

[0060] In this optional implementation, the third resource attribute information is the resource attribute information of the fourth video segment. Assigning the third resource attribute information to the third video segment can effectively set the resource attribute information for the third video segment. It should be noted that the fourth video segment can be a video segment in the first video segment or a video segment outside the first video segment. When obtaining a fourth video segment with a video fingerprint similar to the third video segment, the first video segment can be first searched for video segments with video fingerprints similar to the third video segment. When there is no video segment with a video fingerprint similar to the third video segment in the first video segment, the video segment with a video fingerprint similar to the third video segment can be searched for from video segments outside the first video segment to determine it as the fourth video segment. It should be noted that before searching for video segments with video fingerprints similar to the third video segment from video segments outside the first video segment, it is necessary to annotate the video segments outside the first video segment with resource attribute information so that each video segment outside the first video segment has corresponding resource attribute information.

[0061] The acquiring of the first resource attribute information from the third resource attribute information includes: taking the third resource attribute information of the video segment similar to the to-be-recommended video in the third video segment and the fourth video segment as the first resource attribute information.

[0062] In this optional implementation, the video fingerprint refers to a video key frame, and similar video fingerprints can be determined by matching video key frames of different video clips.

[0063] The video processing method provided by this optional implementation method, in which the third video segment in the first video segment does not include text information, obtains the third resource attribute information of the fourth video segment that is similar to the video fingerprint of the third video segment, and obtains the first resource attribute information from the third resource attribute information, can generate the third resource attribute information for the third video segment that does not include text information, thereby improving the accuracy of the generation of the third resource attribute information.

[0064] Optionally, the method further includes: inputting resource attribute information of a video clip similar to the fingerprint information of the video clip into a large text image generation model to obtain a generated image output by the large text image generation model, detecting the similarity between the generated image and the image frame in the video clip; in response to the similarity being greater than a similarity threshold, using the resource attribute information of the video clip similar to the fingerprint information of the video clip as the resource attribute information of the video clip. The resource attribute information acquisition method provided in this embodiment can effectively verify the resource attribute information, thereby improving the accuracy of obtaining the resource attribute information.

[0065] In some optional implementations of the present disclosure, the above method further includes: acquiring text information; and determining extraction rules based on the text information.

[0066] In this optional implementation, the text information may contain symbols, and the symbols in the text information may include: book title marks, colons, and vertical lines; the above-mentioned determination of extraction rules based on the text information includes: in response to the presence of book title marks in the text information, extracting the information within the book title marks in the text information as the extraction rule; in response to the presence of a colon in the text information, detecting and extracting the information before the colon in the text information as the extraction rule; in response to the presence of a vertical line in the text information, extracting the information after the vertical line in the text information as the extraction rule.

[0067] The video processing method provided by this optional implementation determines the extraction rules of resource attributes based on text information. Different extraction rules can be set when the content of the text information is different, thereby improving the accuracy of resource attribute information extraction.

[0068] In some embodiments of the present disclosure, the above-mentioned determination of the first continuous broadcast video with the same resource attributes as the video to be recommended includes: selecting a second continuous broadcast video with the same key value as the first resource attribute information from a resource attribute dictionary; obtaining a video clip related to the video to be recommended from the second continuous broadcast video; in response to the number of obtained video clips being 1, determining the obtained video clip as the first continuous broadcast video.

[0069] In this optional implementation, the resource attribute dictionary is a pre-constructed video segment storage dictionary, in which resource attribute information and video segments are represented in the form of key-value pairs, and the second streaming video is a video segment stored in the resource attribute dictionary.

[0070] The method for determining the first video in a series of broadcasts provided by this optional implementation method selects a second video in a series of broadcasts having the same key value as the first resource attribute information from a resource attribute dictionary, obtains a video clip related to the video to be recommended from the second video in a series of broadcasts, and when the number of obtained video clips is 1, determines the obtained video clip as the first video in a series of broadcasts. The method is simple to operate and easy to implement, and improves the accuracy of determining the first video in a series of broadcasts.

[0071] In some optional implementations of the present disclosure, the above-mentioned determining the first continuous broadcast video with the same resource attributes as the video to be recommended based on the first resource attribute information also includes: in response to the number of acquired video clips being at least two, based on at least two target information, sorting the acquired video clips to obtain a video sorting sequence; and determining the video clip with the highest target information score in the video sorting sequence as the first continuous broadcast video.

[0072] In this optional implementation, the target information is the information obtained by the video clip's own performance or other subjects' evaluation of the video clip during the presentation process. Specifically, at least two target information can be at least two indicators of goals such as click-through rate, satisfaction, completion rate, and duration; the video sorting sequence is a sequence obtained after sorting the acquired video clips, and the video clip with the highest target information score in the video sorting sequence refers to: the video clip with the highest score for each goal in the multiple target information. For example, the target information includes: click-through rate and satisfaction, then the video clip with the highest target information score in the video sorting sequence is the video clip with the highest click-through rate score and the highest satisfaction score in the video sorting sequence.

[0073] The method for determining the first video to be broadcasted provided by this optional implementation method obtains the second video to be broadcasted having the same first resource attribute information key value as the video to be recommended from the resource attribute dictionary, obtains video clips related to the video to be recommended from the second video to be broadcasted, and when the number of the obtained video clips is at least two, sorts the obtained video clips based on at least two target information to obtain a video sorting sequence; and determines the video clip with the highest target information score in the video sorting sequence as the first video to be broadcasted, thereby further improving the accuracy of determining the first video to be broadcasted.

[0074] In some optional implementations of the present disclosure, the method further includes: constructing an initial dictionary with resource attribute information of the first video clip as the primary key and the first video clip as the value; generating a resource attribute dictionary based on the initial dictionary and a video posterior sorting algorithm.

[0075] In this optional implementation, the resource attribute dictionary is a database that records the first video clip and the first resource attribute information. The units stored in the resource attribute dictionary appear in the form of key-value pairs, where the primary key of the key-value pair is the resource attribute information and the value of the key-value pair is the second continuous video.

[0076] The initial dictionary is a relatively rough word for generating a resource attribute dictionary. The units stored in the resource attribute dictionary appear in the form of key-value pairs, wherein the primary key of the key-value pair is the resource attribute information, and the value of the key-value pair is the first video clip. The first video clip stored in the initial dictionary has corresponding resource attribute information, and the resource attribute information is the key information of the first video clip. By storing the key information of the first video clip and the first video clip in the dictionary, the first continuous video can be quickly and conveniently extracted.

[0077] In this optional implementation, the video posterior sorting algorithm is an algorithm for sorting and screening the first video clip in the dictionary video, that is, the video posterior sorting algorithm first sorts the first video clip in the initial dictionary, and obtains the second continuous broadcast video that can be stored in the resource attribute dictionary based on the sorting result. The second continuous broadcast video also includes at least one video clip. Compared with the dictionary video, the video clip in the second continuous broadcast video is more consistent with the resource attribute information.

[0078] The method for generating a resource attribute dictionary provided by this optional implementation first constructs an initial dictionary, and then generates a resource attribute dictionary based on the initial dictionary and a video posterior sorting algorithm, providing a reliable implementation means for optimizing the resource attribute dictionary; at the video clip recall level, a dedicated recall channel for resource attribute information is established through the resource attribute dictionary to ensure the resource supply of resources with the same resource attribute information at the recall level; at the video clip sorting level, when the video to be recommended has been completed, the resources with the same resource attribute information are located in the recalled resources, and the resources with the same resource attribute information are displayed through forced insertion and selection, thereby ensuring the continuity of resource recommendation for the same resource attribute information.

[0079] Optionally, the above method also includes: processing the first video clip to obtain a second continuous broadcast video; constructing a resource attribute dictionary with resource attribute information as the primary key and the second continuous broadcast video as the value, in which each resource attribute information corresponds to at least one second continuous broadcast video, and one second continuous broadcast video corresponds to one resource attribute information.

[0080] Optionally, the method further includes: constructing an initial dictionary with resource attribute information as the primary key and the first video clip as the value, using a sorting model to sort each video clip in the first video clip, selecting a preset positioned video clip as the second continuous broadcast video, and generating a resource attribute dictionary.

[0081] In some optional implementations of the present disclosure, the above-mentioned generation of a resource attribute dictionary based on the initial dictionary and the video posterior sorting algorithm includes: using the video posterior sorting algorithm to score the first video clips with the same resource attribute information in the initial dictionary to obtain the scores of the first video clips under each resource attribute information; sorting the scores of the first video clips under each resource attribute information, and intercepting the first video clip positioned in advance as the second continuous broadcast video to generate a resource attribute dictionary.

[0082] In this optional implementation, the video posterior sorting algorithm is: pow(average playback time, w1)*pow(click rate, w2), w1 and w2 are hyperparameters of average playback time and click rate, and the pow() function is a common mathematical function in programming languages, which is used to calculate the power of a number.

[0083] In this optional implementation, the pre-set positioning refers to the pre-set positioning video clips with higher scores, and the value of the pre-set positioning can be set based on development requirements, for example, the value of the pre-set positioning is the top 200.

[0084] The method for generating a resource attribute dictionary provided by this optional implementation adopts a video posterior sorting algorithm to score the first video clip to obtain the score of the first video clip under each resource attribute information, and obtains the resource attribute dictionary by sorting the scores, thereby improving the accuracy of obtaining the resource attribute dictionary.

[0085] In some optional implementations of the present disclosure, the above-mentioned conditions for continuous broadcasting of videos with the same attribute include at least one of the following: the number of continuous broadcasts of the video to be recommended is less than or equal to a first preset number threshold; the number of unsatisfactory consumption of the video to be recommended is less than or equal to a second preset number threshold.

[0086] In this optional implementation, the first preset number threshold and the second preset number threshold can be set based on development requirements. Specifically, the first preset number threshold is 10 times, and the second preset number threshold is 5 times. By setting the number of recommended video playbacks and the number of unsatisfactory consumptions, when the number of consecutive playbacks is too many or the number of unsatisfactory consumptions is too many, the video playback system will no longer explore the same resource attributes, thereby avoiding screen dominance, consumer fatigue and other factors that affect the user experience.

[0087] In this optional implementation, in order to prevent excessive recommendation of content with the same resource attribute from causing a decrease in recommendation diversity and excessive aggravation of information cocoons, an upper limit of the number of consecutive broadcasts of the first preset number threshold is set. In addition, when the user manually swipes away to break the consecutive broadcast, the saturation of the recommendation of the information content with this resource attribute is explicitly expressed through the second preset number threshold. From the user experience, the consumption of the completed video resources will be recommended one after another, unless it is manually swiped away or the upper limit of the consecutive broadcast is triggered, and the user will continue to immerse himself in the consumption of video content related to the same resource attribute.

[0088] The optional implementation method provides a condition for setting the broadcast condition of videos with the same attribute, which can effectively ensure the exit of the exploration of the same resource attribute by effectively setting the number of recommended video broadcasts and the number of unsatisfactory consumptions, thereby improving the user experience.

[0089] In some optional implementations of the present disclosure, the above method includes: in response to determining that the video to be recommended includes resource attribute information, based on the resource attribute information, obtaining the number of consecutive broadcasts of the video to be recommended; in response to determining that the number of consecutive broadcasts is less than a predetermined number, determining that the video to be recommended meets the condition for consecutive broadcasts of videos with the same attributes.

[0090] In this optional implementation, the predetermined number of times can be set based on development requirements, for example, the predetermined number of times is 5 times.

[0091] In this optional implementation, by detecting whether the video to be recommended includes resource attribute information, it can be detected whether the executing subject has extracted the resource attribute information for the video to be recommended. If the executing subject has extracted the resource attribute information for the video to be recommended, the number of consecutive broadcasts of the video to be recommended can be obtained in the resource attribute dictionary through the resource attribute information, where the number of consecutive broadcasts is the number of times the video to be recommended is played continuously. The number of consecutive broadcasts can be used to detect whether the conditions for consecutive broadcasts of videos with the same attributes are met.

[0092] The video processing method provided by this optional implementation obtains the number of consecutive broadcasts of the video to be recommended based on resource attribute information; based on the number of consecutive broadcasts, detects whether the video to be recommended meets the consecutive broadcast condition of videos with the same attributes, thereby improving the reliability of the consecutive broadcast condition detection of videos with the same attributes.

[0093] Optionally, the above method also includes: in response to determining that the video to be recommended includes resource attribute information, based on the resource attribute information, obtaining the number of unsatisfactory consumption times of the video to be recommended; in response to the number of unsatisfactory consumption times being less than a number threshold, determining that the video to be recommended meets the condition for continuous broadcasting of videos with the same attributes.

[0094] Optionally, the method further includes: in response to determining that the video to be recommended is a video clip played for the first time, determining that the video to be recommended meets a condition for continuous broadcast of videos with the same attributes.

[0095] Further references Figure 3 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a video processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically implemented in various electronic devices.

[0096] like Figure 3 As shown, the video processing device 300 provided in this embodiment includes: a determination unit 301, an acquisition unit 302, a query unit 303, and a playback unit 304. Among them, the above-mentioned determination unit 301 can be configured to determine and play the video to be recommended in at least two first video clips. The above-mentioned acquisition unit 302 can be configured to obtain the first resource attribute information of the video to be recommended in response to determining that the video to be recommended meets the same attribute video continuous broadcast condition. The above-mentioned query unit 303 can be configured to determine the first continuous broadcast video with the same resource attribute as the video to be recommended based on the first resource attribute information; the above-mentioned playback unit 304 can be configured to play the continuous broadcast video after the video to be recommended is played.

[0097] In this embodiment, the specific processing of the determination unit 301, the acquisition unit 302, the query unit 303, and the playback unit 304 and the technical effects thereof can be referred to in detail. Figure 1The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0098] In some optional implementations of this embodiment, the above-mentioned device 300 also includes: an adding unit (not shown in the figure), the above-mentioned adding unit is configured to add the video to be recommended and the first continuous broadcast video to the video recommendation list, and play the video to be recommended according to the video recommendation list; the above-mentioned playing unit 304 can be configured to play the first continuous broadcast video according to the video recommendation list.

[0099] In some optional implementations of the present embodiment, the apparatus further includes: a first generation unit (not shown in the figure), the first generation unit being configured to: obtain text information for a second video segment including text information in the first video segment; obtain second resource attribute information in the text information using resource attribute extraction rules; the extraction rules indicating that the extracted text information includes predetermined content; the acquisition unit 302 being configured to obtain the first resource attribute information from the second resource attribute information.

[0100] In some optional implementations of the present embodiment, the above-mentioned device 300 also includes: a second generation unit (not shown in the figure), and the above-mentioned second generation unit is configured to: for the third video segment that does not include text information in the first video segment, obtain the third resource attribute information of the fourth video segment whose video fingerprint is similar to the third video segment; the above-mentioned acquisition unit 302 is configured to obtain the first resource attribute information from the third resource attribute information.

[0101] In some optional implementations of this embodiment, the apparatus 300 further includes: (not shown in the figure), the extraction unit is configured to: obtain text information; and determine extraction rules based on the text information.

[0102] In some optional implementations of this embodiment, the query unit 303 is configured to: select a second video stream having the same key value as the first resource attribute information from the resource attribute dictionary; obtain a video clip related to the video to be recommended from the second video stream; and in response to the number of obtained video clips being 1, determine the obtained video clip as the first video stream.

[0103] In some optional implementations of the present embodiment, the query unit 303 is further configured to: in response to at least two acquired video clips, sort the acquired video clips based on at least two target information to obtain a video sorting sequence; and determine the video clip with the highest target information score in the video sorting sequence as the first continuous broadcast video.

[0104] In some optional implementations of the present embodiment, the above-mentioned device 300 also includes a construction unit (not shown in the figure), and the above-mentioned construction unit is configured to: construct an initial dictionary with the resource attribute information of the first video clip as the primary key and the first video clip as the value; generate a resource attribute dictionary based on the initial dictionary and the video posterior sorting algorithm.

[0105] In some optional implementations of the present embodiment, the construction unit is further configured to: score the first video clips with the same resource attribute information in the initial dictionary using a video posterior sorting algorithm to obtain the scores of the first video clips under each resource attribute information; sort the scores of the first video clips under each resource attribute information, and capture the pre-set first video clip as the second continuous broadcast video to generate a resource attribute dictionary.

[0106] In some optional implementations of the present disclosure, the above-mentioned conditions for continuous broadcasting of videos with the same attribute include at least one of the following: the number of continuous broadcasts of the video to be recommended is less than or equal to a first preset number threshold; the number of unsatisfactory consumption of the video to be recommended is less than or equal to a second preset number threshold.

[0107] In some optional implementations of the present disclosure, the above-mentioned device 300 also includes: a detection unit (not shown in the figure), and the above-mentioned detection unit is configured to: in response to determining that the video to be recommended includes resource attribute information, based on the resource attribute information, obtain the number of consecutive broadcasts of the video to be recommended; in response to the number of consecutive broadcasts being less than a predetermined number, determine that the video to be recommended meets the condition for consecutive broadcasts of videos with the same attributes.

[0108] The video processing device provided by the embodiment of the present disclosure, first, the determination unit 301 determines and plays the video to be recommended in at least two first video clips; secondly, the acquisition unit 302 obtains the first resource attribute information of the video to be recommended in response to determining that the video to be recommended meets the condition of continuous broadcast of videos with the same attribute; thirdly, the query unit 303 determines the first continuous broadcast video with the same resource attribute as the video to be recommended based on the resource attribute information, and finally, the playback unit 304 plays the first continuous broadcast video after the video to be recommended is played. Therefore, when playing the video to be recommended, by judging whether the video to be recommended meets the condition of continuous broadcast of videos with the same attribute, the first continuous broadcast video is recommended and played for the user, which can effectively grasp the user's explicit video interest expression, and the user does not need to search for videos separately, which reduces the complexity of user operations, simplifies the user content distribution path, improves the accuracy of video recommendation, and improves the user's video clip consumption experience.

[0109] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0110] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0111] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0112] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0113] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0114] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as video processing methods. For example, in some embodiments, the video processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the video processing method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the video processing method in any other appropriate manner (e.g., by means of firmware).

[0115] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable video processing device, so that the program code, when executed by the processor or controller, causes the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0117] 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.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an information server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0120] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0122] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A video processing method, wherein: The method comprises: Determine and play videos to be recommended in at least two first video clips; In response to determining that the video to be recommended meets the same attribute video streaming condition, obtaining first resource attribute information of the video to be recommended; Based on the first resource attribute information, determining a first streaming video having the same resource attribute as the video to be recommended; After the to-be-recommended video is played, the first streaming video is played.

2. The method according to claim 1, wherein: Before playing the first streaming video after the to-be-recommended video is played, the method further includes: Adding the to-be-recommended video and the first consecutively-broadcasted video to a video recommendation list; Play the video to be recommended according to the video recommendation list; Playing the first continuous video after the to-be-recommended video is played includes: The first streaming videos are played according to the video recommendation list.

3. The method according to claim 1, wherein: The method further includes: acquiring the text information for a second video segment including text information in the first video segment; Acquire the second resource attribute information in the text information by using a resource attribute extraction rule; the extraction rule indicates that the extracted text information includes predetermined content; The obtaining the first resource attribute information of the video to be recommended includes: The first resource attribute information is acquired from the second resource attribute information.

4. The method according to claim 1 or 3, wherein: The method further comprises: For a third video segment that does not include text information in the first video segment, obtaining third resource attribute information of a fourth video segment whose video fingerprint is similar to the third video segment; the obtaining first resource attribute information of the video to be recommended includes: The first resource attribute information is acquired from the third resource attribute information.

5. The method according to claim 3, wherein: The method further comprises: Obtaining the text information; Based on the text information, the extraction rule is determined.

6. The method according to claim 1, wherein: The determining, based on the first resource attribute information, a first streaming video having the same resource attribute as the video to be recommended includes: Selecting a second streaming video having the same key value as the first resource attribute information from the resource attribute dictionary; Acquire a video clip related to the video to be recommended from the second streaming video; In response to the number of acquired video segments being 1, the acquired video segments are determined as the first streaming videos.

7. The method according to claim 6, wherein: The first resource attribute information determines that the first streaming video has the same resource attribute as the video to be recommended further includes: In response to the number of acquired video clips being at least two, the acquired video clips are sorted based on at least two target information to obtain a video sorting sequence; The video segment with the highest target information score in the video sorting sequence is determined as the first continuous broadcast video.

8. The method according to claim 6, wherein: The method further comprises: Constructing an initial dictionary with the resource attribute information of the first video segment as the primary key and the first video segment as the value; A resource attribute dictionary is generated based on the initial dictionary and the video posterior sorting algorithm.

9. The method according to claim 8, wherein: The generating of a resource attribute dictionary based on the initial dictionary and the video posterior sorting algorithm comprises: For the first video clips with the same resource attribute information in the initial dictionary, scoring is performed using a video posterior sorting algorithm to obtain scores of the first video clips under various resource attribute information; The scores of the first video segments under each resource attribute information are sorted, and the first video segment with a preset position is intercepted as the second continuous broadcast video to generate a resource attribute dictionary.

10. The method according to claim 1, wherein: The same attribute video streaming condition includes at least one of the following: The number of consecutive broadcasts of the video to be recommended is less than or equal to a first preset number threshold; The number of times of unsatisfactory consumption of the video to be recommended is less than or equal to a second preset number threshold.

11. The method according to any one of claims 1 to 10, wherein: The method further comprises: In response to determining that the video to be recommended includes resource attribute information, obtaining the number of consecutive broadcasts of the video to be recommended based on the resource attribute information; In response to determining that the number of consecutive broadcasts is less than a predetermined number, it is determined that the video to be recommended meets the condition for consecutive broadcasts of videos with the same attribute.

12. A video processing device, comprising: A determination unit, configured to determine and play videos to be recommended in at least two first video clips; An acquisition unit is configured to acquire first resource attribute information of the video to be recommended in response to determining that the video to be recommended meets the same attribute video streaming condition; A query unit is configured to determine, based on the first resource attribute information, a first streaming video having the same resource attribute as the video to be recommended; The playing unit is configured to play the first continuous video after the to-be-recommended video is played.

13. The device according to claim 12, further comprising: an adding unit, configured to add the to-be-recommended video and the first serially-broadcasted video to a video recommendation list, and play the to-be-recommended video according to the video recommendation list; The playback unit is further configured to play the first continuous broadcast video according to the video recommendation list.

14. The device according to claim 12, wherein: The device also includes: a first generating unit, the first generating unit is configured to: obtain the text information of the second video segment including text information in the first video segment; obtain the second resource attribute information in the text information by using a resource attribute extraction rule; the extraction rule indicates that the extracted text information includes predetermined content; the acquisition unit is configured to obtain the first resource attribute information from the second resource attribute information.

15. The device according to claim 14, wherein: The device also includes: a second generating unit, which is configured to: for a third video segment that does not include text information in the first video segment, obtain third resource attribute information of a fourth video segment whose video fingerprint is similar to the third video segment; and the obtaining unit is configured to obtain the first resource attribute information from the third resource attribute information.

16. The device according to claim 14, wherein: The device further includes: an extraction unit, wherein the extraction unit is configured to: obtain the text information; and determine the extraction rule based on the text information.

17. The device according to claim 12, wherein: The query unit is configured to: select a second video in a streaming sequence having the same key value as the first resource attribute information from a resource attribute dictionary; obtain a video clip related to the video to be recommended from the second video in a streaming sequence; and in response to the number of obtained video clips being 1, determine the obtained video clip as the first video in a streaming sequence.

18. The device according to claim 17, wherein: The query unit is further configured to: in response to the number of acquired video clips being at least two, sort the acquired video clips based on at least two target information to obtain a video sorting sequence; and determine the video clip with the highest target information score in the video sorting sequence as the first continuous broadcast video.

19. The device according to claim 18, wherein: The device also includes a construction unit, which is configured to: construct an initial dictionary with the resource attribute information of the first video clip as a primary key and the first video clip as a value; and generate a resource attribute dictionary based on the initial dictionary and a video posterior sorting algorithm.

20. The device according to claim 19, wherein The construction unit is further configured to: score the first video clips with the same resource attribute information in the initial dictionary using a video posterior sorting algorithm to obtain the scores of the first video clips under each resource attribute information; sort the scores of the first video clips under each resource attribute information, and intercept the first video clip with a preset position as the second continuous broadcast video to generate a resource attribute dictionary.

21. The device according to claim 12, wherein: The same attribute video streaming condition includes at least one of the following: The number of consecutive broadcasts of the video to be recommended is less than or equal to a first preset number threshold; The number of times of unsatisfactory consumption of the video to be recommended is less than or equal to a second preset number threshold.

22. The device according to any one of claims 12 to 21, wherein: The device also includes: a detection unit, which is configured to: in response to determining that the video to be recommended includes resource attribute information, obtain the number of consecutive broadcasts of the video to be recommended based on the resource attribute information; in response to the number of consecutive broadcasts being less than a predetermined number, determine that the video to be recommended meets the condition for consecutive broadcasts of videos with the same attributes.

23. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 11.

25. A computer program product, comprising a computer program, which, when executed by a processor, implements the method of any one of claims 1 to 11.

Images