A vr device video playing monitoring method and system

Abstract

The application provides a VR device video playing monitoring method and system, obtains to-be-processed VR video data, processes the to-be-processed VR video data through a video intelligent monitoring thread, generates image evaluation description of a video playing data set, obtains example evaluation description of the video playing data set, combines the image evaluation description and the example evaluation description, and generates a video playing monitoring strategy. The application can intelligently process the to-be-processed VR video data through the video intelligent monitoring thread, accurately determine the image evaluation description, effectively avoid various interferences and noises, and make the generated video playing monitoring strategy more accurate and reliable in monitoring video playing.

Description

Technical Field

[0001] The present application relates to the field of data monitoring and processing technology, and more specifically, to a method and system for monitoring video playback of a VR device. Background Art

[0002] VR technology is a computer simulation system that allows visitors to experience and construct virtual worlds. It uses computers to generate a virtual environment, immersing visitors in it. VR technology uses real-life data and information, using electronic signals generated by computer technology, and combines them with various output devices to transform them into perceptible phenomena. These phenomena can be real objects in the real world, as well as materials invisible to the naked eye, presented through three-dimensional modeling.

[0003] During video playback, data may freeze or interfere with the video. This makes it difficult to ensure the quality of VR video playback, resulting in a poor user experience. Currently, when VR video playback is abnormal, manual control is often used to play the abnormal clip, resulting in poor video playback continuity. Summary of the Invention

[0004] In order to improve the technical problems existing in the related technologies, the present application provides a method and system for monitoring video playback of a VR device.

[0005] In a first aspect, a method for monitoring video playback of a VR device is provided, which is applied to a monitoring system. The method at least includes: obtaining VR video data to be processed, wherein the VR video data to be processed includes a video playback data set of the VR device; processing the VR video data to be processed through a video intelligent monitoring thread to generate an image evaluation description of the video playback data set; obtaining an example evaluation description of the video playback data set; and generating a video playback monitoring strategy by combining the image evaluation description and the example evaluation description.

[0006] In an independently implemented embodiment, the VR device is a visualization VR box, and obtaining the example evaluation description of the video playback data set includes: determining label data corresponding to the visualization VR box; determining example VR video data corresponding to the visualization VR box in combination with the label data; and determining the example evaluation description through the video playback data set in the example VR video data.

[0007] In an independently implemented embodiment, the combination of the image evaluation description and the example evaluation description to generate a video playback monitoring strategy includes: generating a first video playback data set and a second video playback data set in combination with the example evaluation description, the first video playback data set representing a video playback data set formed by a range that needs to be displayed in the to-be-processed VR video data, and the second video playback data set representing a video playback data set formed by a range that is allowed to be displayed in the to-be-processed VR video data except for the first video playback data set; determining first occlusion information of the video playback data set on the first video playback data set and second occlusion information of the video playback data set on the second video playback data set in combination with the image evaluation description; and generating the video playback monitoring strategy in combination with the first occlusion information and the second occlusion information.

[0008] In an independently implemented embodiment, the combination of the first occlusion information and the second occlusion information to generate the video playback monitoring strategy includes at least the following situation: if the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is completely occluded, it is determined that there is no display abnormality; if the first occlusion information indicates that the first video playback data set is partially occluded, it is determined that there is a first abnormality indication; if the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is partially occluded, it is determined that there is a second abnormality indication.

[0009] In an independently implemented embodiment, the combination of the image evaluation description and the example evaluation description to generate a video playback monitoring strategy includes: determining the target number of the video playback data set in combination with the example evaluation description; determining the evaluation number of the video playback data set in combination with the image evaluation description; if the evaluation number exceeds the target number, determining that a film and television anomaly exists.

[0010] In an independently implemented embodiment, the combination of the image evaluation description and the example evaluation description to generate a video playback monitoring strategy includes at least the following situation: if the image evaluation description indicates the existence of a first comparison situation, it is determined that there is an interaction anomaly, and the minimum migration value of the first comparison situation is lower than the first target value; if the image evaluation description indicates the existence of a second comparison situation, it is determined that there is a hole-gel anomaly, and the matching degree of the benchmark of the second comparison situation is greater than the second target value; wherein, the first target value and the second target value are determined by the example evaluation description.

[0011] In an independently implemented embodiment, obtaining the VR video data to be processed includes: obtaining at least one VR video data to be identified; determining the confidence of each VR video data to be identified; determining at least one target VR video data to be identified, wherein the target VR video data to be identified is the VR video data to be identified whose confidence meets a pre-set condition; and generating the VR video data to be processed through the target VR video data to be identified.

[0012] In an independently implemented embodiment, the video intelligent monitoring thread includes a convolution thread, a stitching thread and an analysis thread. The video intelligent monitoring thread processes the VR video data to be processed to generate an image evaluation description of the video playback data set, including: performing multiple types of convolution processing on the VR video data to be processed by the convolution thread to generate several categories of first video descriptions; stitching the first video descriptions by the stitching thread to generate a target stitching result; and analyzing and processing the target stitching result by the analysis thread to generate the image evaluation description.

[0013] In an independently implemented embodiment, the first video description is spliced ​​through the splicing thread to generate a target splicing result, including: splicing the first video description according to a first arrangement of categories to generate second video descriptions of several categories; splicing the second video description according to a second arrangement of categories to generate a first splicing result; and generating the target splicing result by combining the first splicing result.

[0014] In an independently implemented embodiment, combining the first splicing result to generate the target splicing result includes: splicing third video descriptions of several categories in the first splicing result through features to generate a third splicing result; and determining the third splicing result as the target splicing result.

[0015] In an independently implemented embodiment, combining the first splicing result to generate the target splicing result includes: splicing the third video descriptions of several categories in the first splicing result through features to generate a third splicing result; splicing the third video descriptions through nodes to generate a fourth splicing result; and splicing the third splicing result and the fourth splicing result to generate the target splicing result.

[0016] In an independently implemented embodiment, the method also includes: obtaining first example VR video data, the first example VR video data carries video recording data of a video playback data set that needs to be analyzed; performing multi-category convolution processing on the first example VR video data through the convolution thread to generate first example expressions of several categories; splicing the first example expressions through the splicing thread to generate a target example splicing result; analyzing and processing the target example splicing result through the analysis thread to generate an example image evaluation description; combining the example image evaluation description and the video recording data to perform analysis and quantitative evaluation; and debugging the coefficients of the convolution thread, splicing thread and analysis thread in combination with the analysis and quantitative evaluation.

[0017] In an independently implemented embodiment, the method further includes: determining, in combination with the image evaluation description, whether a target video playback data set exists, the target video playback data set being a video playback data set of the first analysis or the second analysis; if so, obtaining second example VR video data in combination with the target video playback data set; determining video recording data corresponding to the second example VR video data; and optimizing the video intelligent monitoring thread through the second example VR video data and the video recording data corresponding to the second example VR video data.

[0018] In a second aspect, a VR device video playback monitoring system is provided, comprising a processor and a memory communicating with each other, wherein the processor is configured to read and execute a computer program from the memory to implement the above method.

[0019] The embodiment of the present application provides a method and system for monitoring video playback of a VR device, which obtains VR video data to be processed, processes the VR video data to be processed through a video intelligent monitoring thread, generates an image evaluation description of the video playback data set, obtains a sample evaluation description of the video playback data set, and combines the image evaluation description and the sample evaluation description to generate a video playback monitoring strategy. The present application can perform intelligent processing of the VR video data to be processed through a video intelligent monitoring thread, and can accurately determine the image evaluation description. In this way, it can effectively avoid various interferences and noise influences, and can enable the generated video playback monitoring strategy to monitor video playback more accurately and reliably. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flowchart of a method for monitoring video playback on a VR device provided in an embodiment of the present application.

[0022] Figure 2 This is a block diagram of a VR device video playback monitoring device provided in an embodiment of the present application.

[0023] Figure 3 This is an architectural diagram of a VR device video playback monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0025] See also Figure 1 , shows a method for monitoring video playback of a VR device, which may include the technical solution described in the following steps S10-S40.

[0026] S10: Obtain VR video data to be processed, where the VR video data to be processed includes a video playback data set of a VR device.

[0027] Since the effect of the VR video data obtained by identifying the video playback data set of the visualization VR box can interfere with the confidence of the video playback monitoring strategy obtained through the VR video data, it is possible to generate VR video data with higher effects through VR video data selection, thereby improving the confidence of display anomaly identification.

[0028] The method for obtaining the VR video data to be processed according to an embodiment of the present application is shown. The method for obtaining the VR video data to be processed may specifically include the following contents.

[0029] S11: Obtain at least one piece of VR video data to be identified.

[0030] In the embodiment of the present application, the VR video data to be identified is the VR video data obtained by identifying the video playback data set of the above-mentioned visualization VR box. The embodiment of the present application does not limit the number of the above-mentioned VR video data to be identified.

[0031] S12: Determine the confidence level of each of the VR video data to be identified.

[0032] The embodiments of this application do not limit the method for determining the confidence level. For example, each of the aforementioned VR video data can be input into a predetermined artificial intelligence thread to generate a confidence level determination result for the VR video data. The predetermined artificial intelligence thread can perform a global analysis of the VR video data based on its sound characteristics and its impact characteristics, and output a confidence level result for the VR video data.

[0033] S13: Determine at least one target VR video data to be identified, where the target VR video data to be identified is the VR video data to be identified whose confidence meets a pre-set condition.

[0034] The embodiments of the present application do not limit the specific method for determining the target VR video data to be identified. In this embodiment, the VR video data to be identified with the best confidence level can be determined as the target VR video data to be identified. In a possible embodiment, the VR video data to be identified with a confidence level greater than a set confidence target value can also be determined as the target VR video data to be identified.

[0035] S14: Generate the above-mentioned VR video data to be processed through the above-mentioned target VR video data to be identified.

[0036] In the embodiment of the present application, the above-mentioned VR video data to be processed can be processed by the video intelligent monitoring thread, and a video playback monitoring strategy is obtained based on the processing results. In this step, the above-mentioned target VR video data to be identified can be processed according to the requirements of the above-mentioned video intelligent monitoring thread for the input VR video data to generate the corresponding above-mentioned VR video data to be processed.

[0037] Through the above configuration, the unprocessed VR video data that meets the requirements of the video intelligent monitoring thread for the input VR video data can be obtained, so that the above unprocessed VR video data can be processed by the video intelligent monitoring thread, and finally a video playback monitoring strategy can be obtained.

[0038] S20: Processing the VR video data to be processed through the video intelligent monitoring thread to generate an image evaluation description of the video playback data set.

[0039] In the embodiment of the present application, the above-mentioned video intelligent monitoring thread can be used to analyze and process the pending VR video data, thereby analyzing the video playback data set in the above-mentioned pending VR video data, and expressing the analysis results as the above-mentioned image evaluation description. In an alternative embodiment, the video playback data set processing can also be performed on the pending VR video data, identifying the video playback data set in the pending VR video data, and generating the image evaluation description.

[0040] S30: Obtain a sample evaluation description of the video playback dataset.

[0041] In the embodiment of the present application, the example evaluation description represents the evaluation description of the video playback dataset of the visualization VR box. Different visualization VR boxes may have different display methods and accordingly generate different video playback datasets.

[0042] In this embodiment, the example evaluation description of obtaining the video playback dataset may specifically include the following steps.

[0043] S31: Determine the label data corresponding to the above-mentioned visualization VR box.

[0044] S32: Determine the example VR video data corresponding to the visualization VR box according to the label data.

[0045] S33: Determine the example evaluation description using the video playback data set in the example VR video data.

[0046] The embodiments of the present application do not limit the specific method for determining the above-mentioned example evaluation description. In this embodiment, the video playback data set in the above-mentioned example VR video data can be manually recorded, and the recording result represents the above-mentioned example evaluation description. In a possible embodiment, the above-mentioned example VR video data can also be input into the above-mentioned video intelligent monitoring thread, and the above-mentioned video intelligent monitoring thread can analyze the above-mentioned video playback data set in the above-mentioned example VR video data, and the generated analysis result represents the above-mentioned example evaluation description.

[0047] S40: Generate a video playback monitoring strategy based on the above-mentioned image evaluation description and example evaluation description.

[0048] In this embodiment, a flow chart of step S40 of the method for monitoring video playback of a VR device according to an embodiment of the present application is shown. The video playback monitoring strategy is generated based on the above-mentioned image evaluation description and example evaluation description, and specifically may include the following content.

[0049] S41: According to the above-mentioned example evaluation description, a first video playback data set and a second video playback data set are generated, wherein the above-mentioned first video playback data set represents a video playback data set formed by a range that needs to be displayed in the above-mentioned VR video data to be processed, and the above-mentioned second video playback data set represents a video playback data set formed by a range that is allowed to be displayed in the above-mentioned VR video data to be processed except the above-mentioned first video playback data set.

[0050] S43: Determine first occlusion information of the video playback dataset with respect to the first video playback dataset, and second occlusion information of the video playback dataset with respect to the second video playback dataset according to the image evaluation description.

[0051] In an embodiment of the present application, if the video playback data set represented by the above-mentioned image evaluation description occludes the entire range of the above-mentioned first video playback data set, then the first occlusion information indicates that the above-mentioned first video playback data set is completely occluded; otherwise, the above-mentioned first occlusion information indicates that the above-mentioned first video playback data set is partially occluded.

[0052] If the video playback dataset represented by the image evaluation description blocks the entire range of the second video playback dataset, the second occlusion information indicates that the second video playback dataset is completely blocked; otherwise, the second occlusion information indicates that the second video playback dataset is partially blocked.

[0053] S45: Generate the video playback monitoring strategy according to the first occlusion information and the second occlusion information.

[0054] In this embodiment, if the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is completely occluded, then it is determined that no display anomaly exists. If both the first video playback data set and the second video playback data set are completely occluded, then it can be considered that the display result meets the display requirements, and in this case, it can be considered that no display anomaly exists.

[0055] If the first occlusion information indicates that the first video playback data set is partially occluded, a first abnormality indication is determined to exist. Since the first video playback data set is not completely occluded, which may affect the visual effect of the VR box, the first abnormality indication is a more serious abnormality. If it is determined to be the first abnormality indication, the abnormality type can be further determined. The abnormality type can be a hole glue abnormality, a video abnormality, or an interaction abnormality.

[0056] If the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is partially occluded, then a second abnormality indication is determined to be present. As long as the second video playback data set is not completely occluded, the visual VR box effect is not significantly affected, and therefore the second abnormality indication is a minor abnormality.

[0057] Through the above configuration, it is possible to quickly and accurately determine whether there is a display abnormality and obtain an identification result of the display abnormality based on the above first occlusion information and the second occlusion information.

[0058] In this embodiment, anomaly detection can be performed based on the first and second occlusion information. This diagram illustrates another flow chart of step S40 of the VR device video playback monitoring method according to an embodiment of the present application. Based on the image evaluation description and example evaluation description, a video playback monitoring strategy is generated, which may specifically include the following content.

[0059] S42. Determine the target number of the video playback dataset based on the example evaluation description.

[0060] S44. Determine the evaluation number of the video playback data set according to the image evaluation description.

[0061] S46. If the above evaluation number exceeds the above target number, it is determined that there is a film and television anomaly.

[0062] The embodiment of the present application obtains unprocessed VR video data, processes the unprocessed VR video data through a video intelligent monitoring thread, generates an image evaluation description of the video playback data set, obtains a sample evaluation description of the video playback data set, and combines the image evaluation description and the sample evaluation description to generate a video playback monitoring strategy. The present application can perform intelligent processing of unprocessed VR video data through a video intelligent monitoring thread, accurately determining the image evaluation description. In this way, it can effectively avoid various interference and noise influences, and enable the generated video playback monitoring strategy to monitor video playback more accurately and reliably.

[0063] In this embodiment, a video intelligent monitoring thread according to an embodiment of the present application is illustrated. The video intelligent monitoring thread includes a convolution thread, a splicing thread, and an analysis thread. According to step S20 of the VR device video playback monitoring method according to an embodiment of the present application, the video intelligent monitoring thread processes the aforementioned unprocessed VR video data to generate an image evaluation description of the aforementioned video playback dataset, which may specifically include the following steps.

[0064] S21. Perform multi-category convolution processing on the VR video data to be processed through the convolution thread to generate first video descriptions of several categories.

[0065] S22. Splice the first video description using the splicing thread to generate a target splicing result.

[0066] In this embodiment, the first video description is spliced ​​through the splicing thread to generate a target splicing result, which may specifically include the following contents.

[0067] S221. According to the first arrangement of categories, the first video descriptions are spliced ​​together to generate second video descriptions of several categories.

[0068] S222. Splice the second video descriptions according to the second arrangement of categories to generate a first splicing result.

[0069] In the embodiment of the present application, the second video descriptions obtained by splicing different features correspond to different categories. According to the second category arrangement method, the second video descriptions can be spliced ​​to generate third video descriptions of several categories, and each of the third video descriptions constitutes the first splicing result.

[0070] S223. Generate the target splicing result based on the first splicing result.

[0071] S23. Analyze and process the target stitching result through the analysis thread to generate the image evaluation description.

[0072] Through the above configuration, the video intelligent monitoring thread can accurately analyze the VR video data to be processed and generate a high-confidence image assessment description.

[0073] The following further explains the process of configuring the above-mentioned video intelligent monitoring thread and illustrates the method of training the artificial intelligence thread, which may include the following content.

[0074] S101. Obtain first example VR video data, where the first example VR video data carries video recording data of a video playback data set that needs to be analyzed.

[0075] The embodiment of the present application does not limit the number and acquisition method of the first example VR video data. The analysis capability of the video intelligent monitoring thread can be improved by enriching the first example VR video data.

[0076] S102. Perform multi-category convolution processing on the first example VR video data through the convolution thread to generate first example expressions of several categories.

[0077] S103. Splice the first example expression through the splicing thread to generate a target example splicing result.

[0078] S104. Analyze and process the target example stitching result through the analysis thread to generate an example image evaluation description.

[0079] S105. Analyze the quantitative assessment based on the above example image assessment description and the above video recording data.

[0080] S106. Based on the above analysis and quantitative evaluation, the coefficients of the above convolution thread, splicing thread and analysis thread are debugged.

[0081] Through the above configuration, the video intelligent monitoring thread can be configured so that the video intelligent monitoring thread can accurately analyze the video playback data set.

[0082] According to the embodiment of the present application, the method for optimizing the video intelligent monitoring thread may specifically include the following content.

[0083] S201. According to the above image evaluation description, determine whether a target video playback dataset exists, where the target video playback dataset is the first analysis or second analysis video playback dataset.

[0084] S202. If it exists, obtain the second example VR video data according to the target video playback data set.

[0085] For the target video playback data set, the embodiment of the present application may determine the to-be-processed VR video data where the target video playback data set is located as the second example VR video data.

[0086] S203: Determine the video recording data corresponding to the second example VR video data.

[0087] S204. Optimize the video intelligent monitoring thread using the second example VR video data and the video recording data corresponding to the second example VR video data.

[0088] In the embodiment of the present application, the above-mentioned second example VR video data and the video recording data corresponding to the above-mentioned second example VR video data form a training example for the video intelligent monitoring thread. According to the training example, the coefficient of the video intelligent monitoring thread can be debugged, so that the debugged video intelligent monitoring thread can have the ability to correctly analyze the target video playback data set. By continuously optimizing the video intelligent monitoring thread, the analysis reliability can be improved.

[0089] Based on the above, please refer to Figure 2 , provides a VR device video playback monitoring device 200, which is applied to a VR device video playback monitoring system, and the device includes:

[0090] A data acquisition module 210 is configured to obtain VR video data to be processed, wherein the VR video data to be processed includes a video playback data set of a VR device;

[0091] A description evaluation module 220 is configured to process the to-be-processed VR video data through a video intelligent monitoring thread to generate an image evaluation description of the video playback data set;

[0092] The strategy generation module 230 obtains the example evaluation description of the video playback data set and generates a video playback monitoring strategy by combining the image evaluation description and the example evaluation description.

[0093] Based on the above, please refer to Figure 3, shows a VR device video playback monitoring system 300, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0094] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0095] In summary, based on the above scheme, the VR video data to be processed is obtained, the VR video data to be processed is processed by the video intelligent monitoring thread, an image evaluation description of the video playback data set is generated, and a sample evaluation description of the video playback data set is obtained. The image evaluation description and the sample evaluation description are combined to generate a video playback monitoring strategy. The present application can perform intelligent processing on the VR video data to be processed through the video intelligent monitoring thread, and can accurately determine the image evaluation description. In this way, various interferences and noise influences can be effectively avoided, and the generated video playback monitoring strategy can be more accurate and reliable in monitoring video playback.

[0096] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of the present application. Not only can hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, they can also be implemented using software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0097] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0098] The basic concepts have been described above. It will be apparent to those skilled in the art that the detailed disclosure above is merely illustrative and does not limit the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to the present application. Such modifications, improvements, and amendments are suggested in the present application and remain within the spirit and scope of the exemplary embodiments of the present application.

[0099] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or multiple times in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

[0100] In addition, it will be understood by those skilled in the art that various aspects of the present application can be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application can be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0101] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.

[0102] The computer program code required for the operation of the various parts of this application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be executed entirely on the user's computer, or as a stand-alone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0103] In addition, unless expressly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0104] Similarly, it should be noted that, in order to simplify the presentation of this application and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this application sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not mean that the subject matter of this application requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single embodiment disclosed above.

[0105] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0106] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this application, as well as documents (currently or subsequently attached to this application) that limit the broadest scope of the claims of this application. It should be noted that if the descriptions, definitions, and / or use of terms in the accompanying materials of this application are inconsistent or conflicting with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0107] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this application may be considered consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.

[0108] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for monitoring video playback of a VR device, characterized in that: Applied to a monitoring system, the method at least includes: Obtaining VR video data to be processed, where the VR video data to be processed includes a video playback data set of a VR device; Processing the to-be-processed VR video data through a video intelligent monitoring thread to generate an image evaluation description of the video playback data set; Obtaining a sample evaluation description of the video playback data set; generating a video playback monitoring strategy by combining the image evaluation description and the sample evaluation description; The VR device is a visualization VR box, and obtaining a sample evaluation description of the video playback dataset includes: Determine label data corresponding to the visualization VR box; Determining the example VR video data corresponding to the visualization VR box in combination with the label data; determining the example evaluation description through the video playback data set in the example VR video data; The step of combining the image evaluation description and the example evaluation description to generate a video playback monitoring strategy includes: In combination with the example evaluation description, a first video playback dataset and a second video playback dataset are generated, wherein the first video playback dataset represents a video playback dataset formed by a range of the VR video data to be processed that needs to be displayed, and the second video playback dataset represents a video playback dataset formed by a range of the VR video data to be processed that is allowed to be displayed, excluding the first video playback dataset; Determining first occlusion information of the first video playback data set and second occlusion information of the second video playback data set in combination with the image evaluation description; generating the video playback monitoring strategy by combining the first occlusion information and the second occlusion information; The step of combining the first occlusion information and the second occlusion information to generate the video playback monitoring strategy includes at least the following situation: If the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is completely occluded, determining that there is no presentation anomaly; If the first occlusion information indicates that the first video playback data set is partially occluded, determining that a first abnormality indication exists; If the first occlusion information indicates that the first video playback data set is completely occluded, and the second occlusion information indicates that the second video playback data set is partially occluded, determining that a second abnormality indication exists; If it is determined to be the first abnormal indication, the abnormality type is further determined, and the abnormality types include hole glue abnormality, film and television abnormality and interaction abnormality; Determine the target number of the video playback data set in combination with the example evaluation description; determine the evaluation number of the video playback data set in combination with the image evaluation description; If the evaluation number exceeds the target number, determining that a film and television anomaly exists; determining that an interaction anomaly exists if the image assessment description indicates that a first comparison condition exists, wherein the minimum migration value of the first comparison condition is lower than a first target value; If the image evaluation description indicates the presence of a second comparison situation, it is determined that a pore gel abnormality exists, and the matching degree of the benchmark of the second comparison situation is greater than a second target value; wherein the first target value and the second target value are determined by the example evaluation description.

2. The method according to claim 1, characterized in that The obtaining of the VR video data to be processed includes: Obtaining at least one piece of VR video data to be identified; and determining a confidence level of each piece of VR video data to be identified; Determine at least one target VR video data to be identified, where the target VR video data to be identified is the VR video data to be identified whose confidence meets a pre-set condition; and generate the VR video data to be processed using the target VR video data to be identified.

3. The method according to claim 2, characterized in that The video intelligent monitoring thread includes a convolution thread, a splicing thread, and an analysis thread. The video intelligent monitoring thread processes the VR video data to be processed to generate an image evaluation description of the video playback data set, including: Performing multi-category convolution processing on the to-be-processed VR video data through the convolution thread to generate first video descriptions of multiple categories; Splicing the first video description through the splicing thread to generate a target splicing result; The target stitching result is analyzed and processed by the analysis thread to generate the image evaluation description.

4. The method according to claim 3, characterized in that The step of splicing the first video description by the splicing thread to generate a target splicing result includes: splicing the first video descriptions according to the first arrangement of categories to generate second video descriptions of multiple categories; splicing the second video descriptions according to the second arrangement of categories to generate a first splicing result; and combining the first splicing result to generate the target splicing result; The step of combining the first splicing result to generate the target splicing result includes: Splicing the third video descriptions of the plurality of categories in the first splicing result by features to generate a third splicing result; Determining the third splicing result as the target splicing result; The step of combining the first splicing result to generate the target splicing result includes: Splicing the third video descriptions of the plurality of categories in the first splicing result by features to generate a third splicing result; Splicing the third video description through nodes to generate a fourth splicing result; splicing the third splicing result and the fourth splicing result to generate the target splicing result; The method further comprises: Obtaining first example VR video data, where the first example VR video data carries video recording data of a video playback data set to be analyzed; Performing multi-class convolution processing on the first example VR video data by the convolution thread to generate first example expressions of multiple categories; Splicing the first example expression through the splicing thread to generate a target example splicing result; Analyzing and processing the target example splicing result through the analysis thread to generate an example image evaluation description; analyzing and quantifying the evaluation description and the video recording data; and debugging the coefficients of the convolution thread, the splicing thread, and the analysis thread based on the analysis and quantification evaluation; The method further comprises: In combination with the image evaluation description, determining whether a target video playback dataset exists, the target video playback dataset being the first analyzed or second analyzed video playback dataset; If so, combining the target video playback data set to obtain second example VR video data; determining the video recording data corresponding to the second example VR video data; The video intelligent monitoring thread is optimized through the second example VR video data and the video recording data corresponding to the second example VR video data.

5. A VR device video playback monitoring system, characterized in that: The method comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 4.

Images