CN115098726A - Video data processing method and system - Google Patents
Video data processing method and system Download PDFInfo
- Publication number
- CN115098726A CN115098726A CN202210694926.XA CN202210694926A CN115098726A CN 115098726 A CN115098726 A CN 115098726A CN 202210694926 A CN202210694926 A CN 202210694926A CN 115098726 A CN115098726 A CN 115098726A
- Authority
- CN
- China
- Prior art keywords
- video data
- processed
- processing
- identifier
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a video data processing method and a video data processing system. Wherein, the method comprises the following steps: receiving video data to be processed and attribute information of the video data to be processed; analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed; constructing a processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier and the processing characteristics; receiving a processing label of video data to be processed, wherein the processing label comprises a processing label of a processing mode required by the video to be processed; clustering the video data to be processed and the processed video data in the processing set according to the processing label, and determining target processed video data corresponding to the video data to be processed; and processing the video data to be processed according to the processing mode of the target processed video data. The invention solves the technical problem of low processing efficiency of the video data processing method in the prior art.
Description
Technical Field
The invention relates to the field of video processing, in particular to a video data processing method and system.
Background
Audio and video data processing technology is mature, and audio and video data in various formats are processed according to a preset processing mode, and the preset processing mode is usually determined by a programmer. However, in the using process, considering the difference of the transmission parameters and the communication protocols of the acquisition terminal and the processing terminal, the transmitted audio and video data is processed in one or a few ways, and various problems exist, including unsmooth output or inconvenient data processing, so that the audio and video data processing and transmission efficiency is low.
Unreasonable problems. In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a video data processing method and a video data processing system, which at least solve the technical problem of low processing efficiency of a video data processing method in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a video data processing method, including: receiving video data to be processed and attribute information of the video data to be processed, wherein the attribute information comprises a first identifier of a collection device for collecting the video data to be processed and a second identifier of a processing device for processing and analyzing the video data to be processed; analyzing the video data to be processed, and determining processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating a processing mode of the video data to be processed; constructing a processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier and the processing characteristics, wherein the processing set comprises the numbers of the video data to be processed and the processed video data, and the corresponding first identifier, second identifier and processing characteristics; receiving a processing tag of the video data to be processed, wherein the processing tag comprises a processing tag of a processing mode required by the video to be processed; clustering video data to be processed and processed video data in the processing set according to the processing tag, and determining target processed video data corresponding to the video data to be processed; and processing the video data to be processed according to the processing mode of the target processed video data.
Optionally, the receiving the video data to be processed and the attribute information of the video data to be processed includes: creating a video acquisition task, wherein the video acquisition task comprises the attribute information; acquiring the video data to be processed through the acquisition equipment according to the acquisition task; receiving a plurality of data segments of the video data to be processed and the attribute information, which are sent by the acquisition equipment according to a preset sequence, wherein the data segments are obtained by the acquisition equipment by fragmenting the video data to be processed according to a real-time communication rate; and combining the plurality of data segments according to the preset sequence to generate the video data to be processed.
Optionally, before receiving the plurality of data segments of the video data to be processed sent by the acquisition device according to the preset sequence and the attribute information, the method further includes: determining available resources of a current cache, wherein after receiving the video data to be processed, the cache is used for performing cache post-processing; controlling the communication speed of a communication channel between the acquisition equipment and the acquisition equipment to be reduced to a first speed range under the condition that the available resources are smaller than a preset threshold value; under the condition that the available resources are not smaller than the preset threshold value, controlling the communication speed of a communication channel between the acquisition equipment and the acquisition equipment to be increased to a second speed range, wherein the second speed range is larger than the first speed range; controlling the size of the fragmented data fragments of the acquisition device by the first rate range or the second rate range.
Optionally, analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed includes: acquiring text information in the video data to be processed through a text recognition algorithm; processing the text information by using a preset word segmentation processing algorithm to obtain an entity name in the text information; inputting a key image in the video data to be processed into a trained image recognition model, and outputting object content in the key image by the image recognition model, wherein the key image is an image of a plurality of frames of images of the video data to be processed, including a complete object; and inputting the entity name and the object content into the trained recognition model, and outputting the processing characteristics corresponding to the video data to be processed by the recognition model.
Optionally, constructing the processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier, and the processing feature includes: determining processed video data meeting the first identification and/or the second identification according to the first identification and the second identification, wherein the identification of a collecting device of the processed video data is the same as the first identification, and/or the identification of a processing device of the processed video data is the same as the second identification; determining the processing score of the screened processed video data according to the weight of the processing characteristics; screening out processed data which do not reach a preset score under the condition that the quantity of the screened processed video data exceeds a preset quantity range until the quantity reaches the preset quantity range; under the condition that the number of the screened processed video data does not reach a preset number range, increasing the processed video data reaching the preset score until the number reaches the preset number range; and counting the processed video data in the preset quantity range and the video data to be processed to generate the processing set.
Optionally, clustering the to-be-processed video data and the processed video data in the processing set according to the processing tag, and determining the target processed video data corresponding to the to-be-processed video data includes: determining an initial clustering center according to the processing labels, wherein the clustering center is determined by the middle point of the value range of the plurality of processing labels; shifting the initial clustering centers according to the processing labels with weights exceeding the preset weights, and determining a plurality of clustering centers; clustering the processing set according to a plurality of clustering centers, and determining a plurality of to-be-selected processed video data corresponding to the to-be-processed video data; calculating weighted Euclidean distances between a plurality of to-be-selected processed video data and the to-be-processed video data according to the weight of the processing label; and taking the processed video data to be selected with the minimum weighted Euclidean distance as the target processed video data.
Optionally, processing the video data to be processed according to the processing mode of the target processed video data includes: acquiring a processing log of the target processed video data; determining a processing mode of the target processed video data according to the processing log; and processing the video data to be processed according to the processing mode.
According to another aspect of an embodiment of the present invention, there is provided a video data processing system including: the device comprises a first receiving module, a second receiving module and a processing module, wherein the first receiving module is used for receiving video data to be processed and attribute information of the video data to be processed, and the attribute information comprises a first identifier of acquisition equipment for acquiring the video data to be processed and a second identifier of processing equipment for processing and analyzing the video data to be processed; the analysis module is used for analyzing the video data to be processed and determining the processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating the processing mode of the video data to be processed; a constructing module, configured to construct a processing set of the to-be-processed video data and the processed video data according to the first identifier, the second identifier, and the processing feature, where the processing set includes numbers of the to-be-processed video data and multiple processed video data, and a first identifier, a second identifier, and the processing feature that correspond to the numbers respectively; a second receiving module, configured to receive a processing tag of the to-be-processed video data, where the processing tag includes a processing tag of a processing manner that needs to be adopted for the to-be-processed video; the clustering module is used for clustering the video data to be processed and the processed video data in the processing set according to the processing label and determining target processed video data corresponding to the video data to be processed; and the processing module is used for processing the video data to be processed according to the processing mode of the target processed video data.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium storing program instructions, wherein when the program instructions are executed, the apparatus on which the computer storage medium is located is controlled to execute any one of the methods described above.
According to another aspect of the embodiments of the present invention, there is provided a processor, configured to run a program, wherein the program performs the method described in any one of the above when running.
In the embodiment of the invention, the video data to be processed and the attribute information of the video data to be processed are received, wherein the attribute information comprises a first identifier of acquisition equipment for acquiring the video data to be processed and a second identifier of processing equipment for processing and analyzing the video data to be processed; analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating the processing mode of the video data to be processed; constructing a processing set of the video data to be processed and the processed video data according to the first identification, the second identification and the processing characteristics, wherein the processing set comprises the numbers of the video data to be processed and the processed video data, and the corresponding first identification, the second identification and the processing characteristics; receiving a processing label of video data to be processed, wherein the processing label comprises a processing label of a processing mode required by the video to be processed; clustering the video data to be processed and the processed video data in the processing set according to the processing label, and determining target processed video data corresponding to the video data to be processed; the method for processing the video data to be processed according to the processing mode of the target processed video data achieves the aim of automatically matching the video processing mode according to the identification of the acquisition equipment and the processing equipment of the video data and the processing characteristic of the video data, thereby realizing the technical effects of improving the adaptability of video data processing and further improving the processing efficiency, and further solving the technical problem of low processing efficiency of the video data processing method in the prior art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a video data processing method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a video data processing system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with an embodiment of the present invention, there is provided an embodiment of a video data processing method, it should be noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that herein.
Fig. 1 is a flowchart of a video data processing method according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, receiving video data to be processed and attribute information of the video data to be processed, wherein the attribute information comprises a first identifier of a collection device for collecting the video data to be processed and a second identifier of a processing device for processing and analyzing the video data to be processed;
step S104, analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating the processing mode of the video data to be processed;
step S106, constructing a processing set of the video data to be processed and the processed video data according to the first identification, the second identification and the processing characteristics, wherein the processing set comprises the numbers of the video data to be processed and the processed video data, and the corresponding first identification, the second identification and the processing characteristics;
step S108, receiving processing labels of video data to be processed, wherein the processing labels comprise processing labels of processing modes required by the video to be processed;
step S110, clustering the video data to be processed and the processed video data in the processing set according to the processing label, and determining target processed video data corresponding to the video data to be processed;
and step S112, processing the video data to be processed according to the processing mode of the target processed video data.
Through the steps, the video data to be processed and the attribute information of the video data to be processed are received, wherein the attribute information comprises a first identifier of acquisition equipment for acquiring the video data to be processed and a second identifier of processing equipment for processing and analyzing the video data to be processed; analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating the processing mode of the video data to be processed; constructing a processing set of the video data to be processed and the processed video data according to the first identification, the second identification and the processing characteristics, wherein the processing set comprises the numbers of the video data to be processed and the processed video data, and the corresponding first identification, the second identification and the processing characteristics; receiving a processing label of video data to be processed, wherein the processing label comprises a processing label of a processing mode required by the video to be processed; clustering the video data to be processed and the processed video data in the processing set according to the processing label, and determining target processed video data corresponding to the video data to be processed; the method for processing the video data to be processed according to the processing mode of the target processed video data achieves the aim of automatically matching the video processing mode according to the identification of the acquisition equipment and the processing equipment of the video data and the processing characteristic of the video data, thereby realizing the technical effects of improving the adaptability of video data processing and further improving the processing efficiency, and further solving the technical problem of low processing efficiency of the video data processing method in the prior art.
The execution subject of the steps can be a processor, a computer, a server or other devices with arithmetic capability. The execution main body is used for processing a large amount of video data, for example, a video processing server is used for processing the video data according to requirements, and the processing of the video data comprises encoding according to different modes, decoding according to corresponding modes, editing according to different modes, compressing according to different modes and enhancing according to different modes. It should be noted that the video data may also include audio data, and the processing of the video data may also include the processing of the audio data.
The adopted formats are different for terminal equipment with different video data. The format of video data is very many, for example, avi format, mov format, mpg format, asf format, wmv format, rm format, rmvb format, etc., and different formats may or may not be compatible, depending on the capability of the processing software, but most of the formats are not directly versatile. For example, the video data acquired by the acquisition device is in an avi format, but most of processing software processes the video in an mov format, so that there is a situation that the video acquired by the acquisition device cannot be directly used for processing by the processing software, format conversion is required if the formats are different, but data loss is caused in the format conversion process, and even in many cases, the existing video format cannot be converted into the desired data format. The direct problem is that the user can not use the device when using the device, and the user can not know how to deal with the device.
In this embodiment, the attribute information of the video data to be processed is obtained while the video data to be processed is obtained, where the attribute information includes a first identifier of the acquisition device and a second identifier of the processing device. The first identifier may indicate the acquisition device, correspond to the acquisition device one to one, and after the acquisition device confirms the format of the to-be-processed video data acquired by the acquisition device, the format may also specify attribute information, such as resolution, size, whether audio exists, and the like, of the to-be-processed video data acquired by the acquisition device. Correspondingly, the second identifier may indicate the processing device, correspond to the processing device one to one, and after the processing device confirms the format of the video data to be processed acquired by the processing device, the format may also specify the attribute information of the video data to be processed acquired by the acquisition device. The format and the attribute information can be used as the determining factors of the processing mode of the video processing between the acquisition equipment and the processing equipment, namely, the processing mode of the video to be processed is determined by the format and the attribute information on the acquisition equipment and the format and the attribute information on the processing equipment.
Optionally, the receiving the video data to be processed and the attribute information of the video data to be processed includes: creating a video acquisition task, wherein the video acquisition task comprises attribute information; acquiring video data to be processed through acquisition equipment according to an acquisition task; receiving a plurality of data segments of video data to be processed and attribute information, which are sent by acquisition equipment according to a preset sequence, wherein the plurality of data segments are obtained by the acquisition equipment by fragmenting the video data to be processed according to a real-time communication rate; and combining the plurality of data segments according to a preset sequence to generate the video data to be processed.
When the processing equipment processes the video data, an active processing mode can be adopted, so that a user can manage and control the whole system through the processing equipment, and the processing equipment can perform passive processing without a request at a video acquisition end. Specifically, a video capture task may be created on a processing device, and the processing device may correspond to a plurality of capture devices. For example, in an intelligent home scene, many household appliances such as an intelligent television, an intelligent refrigerator, an intelligent sound box, and the like can acquire video data, but processing logic in different household appliances is not through, and may be equivalent to a plurality of acquisition devices corresponding to the processing device, when some tasks which need video data to be processed are executed, for example, when the user's use state is judged, an acquisition device with a good shooting view angle needs to be selected as an acquisition device for video data, and the processing device also instructs to process videos to be processed acquired by the acquisition device.
Therefore, a video acquisition task can be correspondingly created on the processing device, the video acquisition task includes attribute information, the attribute information here can include an IP address or an identifier of the acquisition device to be used, and can also include acquisition duration, a focal length and a range of video acquisition, a target object of video acquisition, and the like, which can be issued to the acquisition device in the manner of the attribute information, and the acquisition device acquires the video according to the attribute information.
Then, video data to be processed are collected through collection equipment according to collection tasks, a plurality of data fragments of the video data to be processed and attribute information sent by the collection equipment according to a preset sequence are received, the attribute information and the attribute information of the video collection tasks can be the same information, and the processing equipment needs to correspond to a plurality of collection equipment, so after the collected video data to be processed are received, the video data to be processed can be checked by combining the attribute information carried by the processing equipment, and whether the popularity meets the attribute information, namely whether the popularity meets the requirements of the video collection tasks is determined.
The method comprises the steps that a plurality of data segments are obtained by fragmenting video data to be processed by acquisition equipment according to a real-time communication rate; specifically, the communication rate plays a decisive role in transmitting the video data to be processed, one video data to be processed is usually large and can reach hundreds of megabits, even thousands of megabits, and it is unrealistic to directly package and transmit one video data to be processed, and even under the condition that the current 5G has a certain popularization degree, tens of megabits can be transmitted at a higher speed for one second. Therefore, when video data is transmitted, the video data to be processed needs to be fragmented according to the real-time communication rate. It can be simply understood that the faster the communication rate, the larger the amount of data transmitted at one time. The purpose of the fragmentation is to transmit the video data to be processed for multiple times, and the number of the fragmentation can be as small as possible under the condition that the communication rate is faster, so as to improve the transmission efficiency of the video data to be processed. On the contrary, the slower the communication rate is, the smaller the data volume transmitted at one time is, and in this case, the number of the fragments can be as much as possible, so as to ensure that the data volume transmitted at each time can meet the data volume transmission requirement of at least one fragment, so as to ensure the transmission accuracy of the video data to be processed, and avoid the problem that the accuracy of data transmission is low due to data loss caused by the fact that one fragment is spread for several times.
And then, after receiving the data segments obtained by the fragmentation, the processing equipment combines the multiple data segments according to a preset sequence to generate the video data to be processed. It should be noted that the preset sequence may be a sequence of timestamps of the received data segments, the timestamps are generated by the acquisition device for the corresponding data segments, and transmission time or generation time of the data segments may be identified. It should be noted that the sequence of the timestamps may indicate the sequence of transmission and the sequence of generation time, which requires that the acquisition device performs fragmentation or transmission of data segments according to the positions of the data segments in the video data to be processed when performing data fragmentation and data segment transmission, so as to ensure that the processing device can successfully combine a plurality of data segments into complete video data to be processed according to the sequence.
For example, when data is sliced, the data is sliced gradually backward from the start position of the video to be processed, and the generation time of the data slice can identify the position of the data slice in the video data to be processed, specifically, the earlier the generation time is, the earlier the position is in the video data to be processed. For another example, in data transmission, for a plurality of data segments, the earlier a data segment closer to the start position of the video to be processed is transmitted, the transmission time of the data segment can identify the position of the data segment in the video data to be processed, specifically, the earlier the transmission time is, the earlier the position in the video data to be processed is. It should be noted that, the data fragment process and the data fragment transmission process are two processes, and in implementation, the two processes may interfere with each other or may not interfere with each other according to circumstances, and it is clear that, when the data fragment is transmitted, the data fragment needs to have a position identifier in a video to be processed, and a specific form may be a timestamp, a real position, or a reference position of a previous data fragment.
Optionally, before receiving the plurality of data segments of the video data to be processed sent by the acquisition device according to the preset sequence and the attribute information, the method further includes: determining available resources of a current cache, wherein after receiving video data to be processed, cache post-processing is carried out through the cache; controlling the communication rate of a communication channel between the acquisition equipment and the acquisition equipment to be reduced to a first rate range under the condition that the available resources are smaller than a preset threshold value; under the condition that the available resources are not smaller than a preset threshold value, the communication speed of a communication channel between the control device and the acquisition device is increased to a second speed range, wherein the second speed range is larger than the first speed range; the size of the fragmented data segments of the acquisition device is controlled by the first rate range or the second rate range.
Considering that a processing device may need to process a plurality of video data, but the processing time for one video data may be continuous, and it is inevitable to receive other video data that needs to be processed in this process, this embodiment configures a buffer for the processing device, determines the available resources of the current buffer before receiving the data segment of the video data to be processed, and performs buffer post-processing through the buffer after receiving the video data to be processed; controlling the communication rate of a communication channel between the acquisition equipment and the acquisition equipment to be reduced to a first rate range under the condition that the available resources are smaller than a preset threshold value; under the condition that the available resources are not less than a preset threshold value, controlling the communication speed of a communication channel between the acquisition equipment and the acquisition equipment to be increased to a second speed range, wherein the second speed range is greater than the first speed range; therefore, the communication speed between the processing equipment and the acquisition equipment is controlled through the cache, and the size of the fragmented data fragment of the acquisition equipment is further controlled through the first speed range or the second speed range to form dynamic adjustment, so that the uploading interruption of the video data of the acquisition equipment can be avoided, the processing equipment can be ensured not to have larger processing load, the space in the cache of the processing equipment is limited, the data cannot be stacked infinitely, when the amount of the data to the ground is larger, on one hand, the reading speed from the cache can be influenced, on the other hand, the problems of data interference and data loss are easily caused, and the situation can be completely avoided through the dynamic adjustment.
Optionally, analyzing the video data to be processed, and determining the processing characteristics of the video data to be processed includes: acquiring text information in video data to be processed through a text recognition algorithm; processing the text information by using a preset word segmentation processing algorithm to obtain an entity name in the text information; inputting a key image in video data to be processed into a trained image recognition model, and outputting object content in the key image by the image recognition model, wherein the key image is an image of a plurality of frames of images of the video data to be processed, including a complete object; and inputting the entity name and the object content into the trained recognition model, and outputting the processing characteristics corresponding to the video data to be processed by the recognition model.
The processing characteristics may be video characteristics that can affect the processing manner, and include characteristics newly corresponding to the attributes, such as the ratio of resolution and picture frame rate, whether audio exists, a segment of a video having a target object, text in a video, and the like. The processing features in this embodiment include text features and image features, where the text features obtain text information in video data to be processed through a text recognition algorithm, and the text information is processed through a preset word segmentation algorithm to obtain entity names in the text information, for example, in some video data with subtitles or barrages, the content included in the text information is also very important, and the entity names in the text information need to be obtained through text recognition and then word segmentation processing, and the entity names may be understood as nouns, verbs or proprietary vocabularies, that is, information entities included in the text information, for example, behaviors of a first are illegal, where the behaviors of a first, behaviors and illegal activities may all be used as information entities.
The image characteristics are well understood, the key image in the video data to be processed is input into the trained image recognition model, and the image recognition model outputs the object content in the key image, wherein the key image is an image of a plurality of frames of the video data to be processed, including a complete object. The complete object may be understood as a complete target area in the target object, for example, a human face. And is not limited to all regions of the target object.
And inputting the entity name and the object content into the trained recognition model, and outputting the processing characteristics corresponding to the video data to be processed by the recognition model. The image recognition model and the recognition model are machine learning models and can be used only after being trained. The image recognition model is trained by first training data, the first training data comprises a plurality of groups, and each group comprises an input image and a corresponding output object content. The recognition image is trained from second training data, the second training data comprising a plurality of groups, each group comprising an input entity name and object content, and a corresponding output processing feature.
Optionally, constructing a processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier, and the processing characteristics includes: and determining processed video data meeting the first identification and/or the second identification according to the first identification and the second identification, wherein the identification of the acquisition equipment of the processed video data is the same as the first identification, and/or the identification of the processing equipment of the processed video data is the same as the second identification. And selecting the processed video data with similar processing characteristics as a reference for determining the processing mode of the video data to be processed. In an extreme case, there is very little chance that processed video data exactly identical to the case of the video data to be processed can be found, i.e. processed video data that hit both the first identifier and the second identifier, and the same processing characteristics. In this case, the processing method of the processed video data may be directly used as the processing method of the video data to be processed, but this case is very small, and therefore, it is necessary to determine the processed video data closest to the video data to be processed by means of clustering.
Then, determining the processing score of the screened processed video data according to the weight of the processing characteristics; screening out processed data which do not reach a preset score under the condition that the quantity of the screened processed video data exceeds a preset quantity range until the quantity reaches the preset quantity range; under the condition that the number of the screened processed video data does not reach the preset number range, increasing the processed video data reaching the preset score until the number reaches the preset number range; and counting the processed video data and the video data to be processed within a preset quantity range to generate a processing set.
Optionally, clustering the to-be-processed video data and the processed video data in the processing set according to the processing tag, and determining the target processed video data corresponding to the to-be-processed video data includes: determining an initial clustering center according to the processing labels, wherein the clustering center is determined by the middle point of the value range of the processing labels; shifting the initial clustering centers according to the processing labels with the weights exceeding the preset weights, and determining a plurality of clustering centers; clustering the processing set according to the plurality of clustering centers, and determining a plurality of to-be-selected processed video data corresponding to the to-be-processed video data; calculating weighted Euclidean distances between a plurality of to-be-selected processed video data and to-be-processed video data according to the weight of the processing label; and taking the processed video data to be selected with the minimum weighted Euclidean distance as the target processed video data. Therefore, the target processed video data closest to the video data to be processed is accurately determined. And processing the video data to be processed by the processing mode of the target processed video data.
Specifically, processing the video data to be processed according to the processing mode of the target processed video data includes: acquiring a processing log of target processed video data; determining a processing mode of the target processed video data according to the processing log; and processing the video data to be processed according to the processing mode. Therefore, according to the identification of the video data acquisition equipment and the processing equipment and the video processing mode automatically matched with the processing characteristics of the video data, the adaptability of video data processing is improved, the processing efficiency is further improved, and the technical problem of low processing efficiency of the video data processing method in the prior art is solved.
Fig. 2 is a schematic structural diagram of a video data processing system according to an embodiment of the present invention, and as shown in fig. 2, according to another aspect of the embodiment of the present invention, there is provided a video data processing system including: a first receiving module 200, an analyzing module 202, a constructing module 204, a second receiving module 206, a clustering module 208, and a processing module 210. The system is described in detail below.
A first receiving module 200, configured to receive video data to be processed and attribute information of the video data to be processed, where the attribute information includes a first identifier of a collection device that collects the video data to be processed and a second identifier of a processing device that processes and analyzes the video data to be processed; an analyzing module 202, connected to the first receiving module 200, configured to analyze the video data to be processed and determine a processing characteristic of the video data to be processed, where the processing characteristic is used to indicate a processing mode of the video data to be processed; a constructing module 204, connected to the analyzing module 202, configured to construct a processing set of the to-be-processed video data and the processed video data according to the first identifier, the second identifier, and the processing characteristics, where the processing set includes numbers of the to-be-processed video data and the processed video data, and corresponding first identifier, second identifier, and processing characteristics; a second receiving module 206, connected to the constructing module 204, configured to receive a processing tag of the to-be-processed video data, where the processing tag includes a processing tag of a processing manner that needs to be adopted for the to-be-processed video; a clustering module 208, connected to the second receiving module 206, configured to cluster the to-be-processed video data and the processed video data in the processing set according to the processing tag, and determine target processed video data corresponding to the to-be-processed video data; and the processing module 210 is connected to the clustering module 208, and is configured to process the video data to be processed according to a processing manner of the target processed video data.
Through the system, the first receiving module 200 is adopted to receive the video data to be processed and the attribute information of the video data to be processed, wherein the attribute information comprises a first identifier of a collecting device for collecting the video data to be processed and a second identifier of a processing device for processing and analyzing the video data to be processed; the analysis module 202 analyzes the video data to be processed, and determines processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating a processing mode of the video data to be processed; the constructing module 204 constructs a processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier, and the processing characteristics, wherein the processing set includes numbers of the video data to be processed and the processed video data, and the corresponding first identifier, second identifier, and processing characteristics; the second receiving module 206 receives processing tags of the video data to be processed, where the processing tags include processing tags of processing modes required by the video to be processed; the clustering module 208 clusters the video data to be processed and the processed video data in the processing set according to the processing tag, and determines target processed video data corresponding to the video data to be processed; the processing module 210 processes the video data to be processed according to the processing mode of the target processed video data, so as to achieve the purpose of automatically matching the video processing mode according to the identification of the acquisition device and the processing device of the video data and the processing characteristic of the video data, thereby realizing the technical effects of improving the adaptability of video data processing and further improving the processing efficiency, and further solving the technical problem of low processing efficiency of the video data processing method in the prior art.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium storing program instructions, wherein when the program instructions are executed, the apparatus in which the computer storage medium is located is controlled to perform the method of any one of the above.
According to another aspect of the embodiments of the present invention, there is provided a processor for executing a program, wherein the program executes to perform the method of any one of the above.
The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments.
In the above embodiments of the present invention, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described in detail in a certain embodiment.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method of processing video data, comprising:
receiving video data to be processed and attribute information of the video data to be processed, wherein the attribute information comprises a first identifier of a collection device for collecting the video data to be processed and a second identifier of a processing device for processing and analyzing the video data to be processed;
analyzing the video data to be processed, and determining processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating a processing mode of the video data to be processed;
constructing a processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier and the processing characteristics, wherein the processing set comprises the numbers of the video data to be processed and the processed video data, and the corresponding first identifier, second identifier and processing characteristics;
receiving a processing tag of the video data to be processed, wherein the processing tag comprises a processing tag of a processing mode required to be adopted by the video to be processed;
clustering the video data to be processed and the processed video data in the processing set according to the processing label, and determining target processed video data corresponding to the video data to be processed;
and processing the video data to be processed according to the processing mode of the target processed video data.
2. The method of claim 1, wherein receiving video data to be processed and attribute information of the video data to be processed comprises:
creating a video acquisition task, wherein the video acquisition task comprises the attribute information;
acquiring the video data to be processed through the acquisition equipment according to the acquisition task;
receiving a plurality of data segments of the video data to be processed and the attribute information, which are sent by the acquisition equipment according to a preset sequence, wherein the data segments are obtained by the acquisition equipment slicing the video data to be processed according to a real-time communication rate;
and combining the plurality of data fragments according to the preset sequence to generate the video data to be processed.
3. The method according to claim 2, wherein before receiving the plurality of data segments of the video data to be processed, which are sent by the capture device according to the preset sequence, and the attribute information, the method further comprises:
determining available resources of a current cache, wherein after receiving the video data to be processed, the cache is used for performing cache post-processing;
under the condition that the available resources are smaller than a preset threshold value, controlling the communication speed of a communication channel between the acquisition equipment and the acquisition equipment to be reduced to a first speed range;
under the condition that the available resources are not smaller than the preset threshold value, controlling the communication speed of a communication channel between the acquisition equipment and the acquisition equipment to be increased to a second speed range, wherein the second speed range is larger than the first speed range;
controlling the size of the fragmented data fragments of the acquisition device by the first rate range or the second rate range.
4. The method of claim 3, wherein analyzing the video data to be processed and determining the processing characteristics of the video data to be processed comprises:
acquiring text information in the video data to be processed through a text recognition algorithm;
processing the text information by using a preset word segmentation processing algorithm to obtain an entity name in the text information;
inputting a key image in the video data to be processed into a trained image recognition model, and outputting object content in the key image by the image recognition model, wherein the key image is an image of a plurality of frames of images of the video data to be processed, including a complete object;
and inputting the entity name and the object content into the trained recognition model, and outputting the processing characteristics corresponding to the video data to be processed by the recognition model.
5. The method of claim 4, wherein constructing the processing set of the video data to be processed and the processed video data according to the first identifier, the second identifier, and the processing feature comprises:
determining processed video data meeting the first identification and/or the second identification according to the first identification and the second identification, wherein the identification of the acquisition equipment of the processed video data is the same as the first identification, and/or the identification of the processing equipment of the processed video data is the same as the second identification;
determining the processing score of the screened processed video data according to the weight of the processing characteristics;
screening out processed data which do not reach a preset score under the condition that the quantity of the screened processed video data exceeds a preset quantity range until the quantity reaches the preset quantity range;
under the condition that the number of the screened processed video data does not reach a preset number range, increasing the processed video data reaching the preset score until the number reaches the preset number range;
and counting the processed video data in the preset quantity range and the video data to be processed to generate the processing set.
6. The method of claim 5, wherein clustering the to-be-processed video data and the processed video data in the processing set according to the processing tag, and determining the target processed video data corresponding to the to-be-processed video data comprises:
determining an initial clustering center according to the processing labels, wherein the clustering center is determined by the middle point of the value range of the plurality of processing labels;
shifting the initial clustering centers according to processing labels with weights exceeding preset weights, and determining a plurality of clustering centers;
clustering the processing set according to a plurality of clustering centers, and determining a plurality of to-be-selected processed video data corresponding to the to-be-processed video data;
calculating weighted Euclidean distances between a plurality of to-be-selected processed video data and the to-be-processed video data according to the weight of the processing label;
and taking the processed video data to be selected with the minimum weighted Euclidean distance as the target processed video data.
7. The method of claim 6, wherein processing the video data to be processed in accordance with the processing of the target processed video data comprises:
acquiring a processing log of the target processed video data;
determining a processing mode of the target processed video data according to the processing log;
and processing the video data to be processed according to the processing mode.
8. A video data processing system for implementing the video data processing method according to any one of claims 1 to 7, comprising:
the device comprises a first receiving module, a second receiving module and a processing module, wherein the first receiving module is used for receiving video data to be processed and attribute information of the video data to be processed, and the attribute information comprises a first identifier of acquisition equipment for acquiring the video data to be processed and a second identifier of processing equipment for processing and analyzing the video data to be processed;
the analysis module is used for analyzing the video data to be processed and determining the processing characteristics of the video data to be processed, wherein the processing characteristics are used for indicating the processing mode of the video data to be processed;
a constructing module, configured to construct a processing set of the to-be-processed video data and the processed video data according to the first identifier, the second identifier, and the processing feature, where the processing set includes numbers of the to-be-processed video data and multiple processed video data, and a first identifier, a second identifier, and the processing feature that correspond to the numbers respectively;
a second receiving module, configured to receive a processing tag of the to-be-processed video data, where the processing tag includes a processing tag of a processing manner that needs to be adopted for the to-be-processed video;
the clustering module is used for clustering the video data to be processed and the processed video data in the processing set according to the processing label and determining target processed video data corresponding to the video data to be processed;
and the processing module is used for processing the video data to be processed according to the processing mode of the target processed video data.
9. A computer storage medium having stored thereon program instructions, wherein the program instructions, when executed, control an apparatus in which the computer storage medium is located to perform the method of any one of claims 1 to 7.
10. A processor, configured to run a program, wherein the program when running performs the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694926.XA CN115098726B (en) | 2022-06-20 | 2022-06-20 | Video data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694926.XA CN115098726B (en) | 2022-06-20 | 2022-06-20 | Video data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115098726A true CN115098726A (en) | 2022-09-23 |
| CN115098726B CN115098726B (en) | 2023-05-02 |
Family
ID=83290921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210694926.XA Active CN115098726B (en) | 2022-06-20 | 2022-06-20 | Video data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115098726B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130073389A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for providing sports and sporting events related social/geo/promo link promotional data sets for end user display of interactive ad links, promotions and sale of products, goods, gambling and/or services integrated with 3d spatial geomapping, company and local information for selected worldwide locations and social networking |
| US20130073473A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods & services, entertainment and auctions, with geospatial mapping technology |
| CN110049341A (en) * | 2019-03-08 | 2019-07-23 | 视联动力信息技术股份有限公司 | Method for processing video frequency and device |
| CN110348209A (en) * | 2018-04-08 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| CN111984803A (en) * | 2020-08-20 | 2020-11-24 | 北京达佳互联信息技术有限公司 | Multimedia resource processing method and device, computer equipment and storage medium |
| CN113656927A (en) * | 2021-10-20 | 2021-11-16 | 腾讯科技（深圳）有限公司 | Data processing method, related equipment and computer program product |
| CN113822127A (en) * | 2021-06-25 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Video processing method, video processing device, video processing equipment and storage medium |
| CN114510564A (en) * | 2020-11-16 | 2022-05-17 | 上海哔哩哔哩科技有限公司 | Video knowledge graph generation method and device |
-
2022
- 2022-06-20 CN CN202210694926.XA patent/CN115098726B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130073389A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for providing sports and sporting events related social/geo/promo link promotional data sets for end user display of interactive ad links, promotions and sale of products, goods, gambling and/or services integrated with 3d spatial geomapping, company and local information for selected worldwide locations and social networking |
| US20130073473A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods & services, entertainment and auctions, with geospatial mapping technology |
| CN110348209A (en) * | 2018-04-08 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| CN110049341A (en) * | 2019-03-08 | 2019-07-23 | 视联动力信息技术股份有限公司 | Method for processing video frequency and device |
| CN111984803A (en) * | 2020-08-20 | 2020-11-24 | 北京达佳互联信息技术有限公司 | Multimedia resource processing method and device, computer equipment and storage medium |
| CN114510564A (en) * | 2020-11-16 | 2022-05-17 | 上海哔哩哔哩科技有限公司 | Video knowledge graph generation method and device |
| CN113822127A (en) * | 2021-06-25 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Video processing method, video processing device, video processing equipment and storage medium |
| CN113656927A (en) * | 2021-10-20 | 2021-11-16 | 腾讯科技（深圳）有限公司 | Data processing method, related equipment and computer program product |
Non-Patent Citations (2)
| Title |
|---|
| TAO XIANG等: "Video behavior profiling for anomaly detection" * |
| 沈鑫: "大规模互联网服务系统中的个性化推荐技术研究" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115098726B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230012732A1 (en) | Video data processing method and apparatus, device, and medium | |
| CN110784759B (en) | Bullet screen information processing method and device, electronic equipment and storage medium | |
| CN109408639B (en) | Bullet screen classification method, bullet screen classification device, bullet screen classification equipment and storage medium | |
| CN105144141A (en) | Systems and methods for addressing a media database using distance associative hashing | |
| EP3513310A1 (en) | Summarizing video content | |
| CN202998337U (en) | Video program identification system | |
| US20160210367A1 (en) | Transition event detection | |
| KR101541495B1 (en) | Apparatus, method and computer readable recording medium for analyzing a video using the image captured from the video | |
| CN106407268A (en) | Method and system for content retrieval based on rate-coverage optimization | |
| CN111274449B (en) | Video playing method, device, electronic equipment and storage medium | |
| US20220417540A1 (en) | Encoding Device and Method for Utility-Driven Video Compression | |
| US9807453B2 (en) | Mobile search-ready smart display technology utilizing optimized content fingerprint coding and delivery | |
| CN115098726B (en) | Video data processing method and system | |
| CN111263183A (en) | Singing state identification method and singing state identification device | |
| WO2013018913A1 (en) | Video processing system, method of determining viewer preference, video processing apparatus, and control method and control program therefor | |
| CN115379233B (en) | Big data video information analysis method and system | |
| CN112350986B (en) | Shaping method and system for audio and video network transmission fragmentation | |
| CN116189706A (en) | Data transmission method, device, electronic equipment and computer readable storage medium | |
| CN110163043B (en) | Face detection method, device, storage medium and electronic device | |
| Nesvadba et al. | Real-time and distributed AV content analysis system for consumer electronics networks | |
| CN110933462B (en) | Video processing method, system, electronic device and storage medium | |
| CN110704680B (en) | Label generation method, electronic device and storage medium | |
| US20230007276A1 (en) | Encoding Device and Method for Video Analysis and Composition | |
| US20230177083A1 (en) | Method and apparatus for simultaneous video retrieval and alignment | |
| CN117177012A (en) | Video broadcasting monitoring method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |