Data compression method and system based on digital twinning and terminal equipment

Abstract

The invention provides a data compression method and system based on digital twinning and terminal equipment, and is suitable for the technical field of data processing, and the method comprises the steps: inputting to-be-compressed multimedia data into a digital twinning model, and generating decision information; determining a multimedia compression algorithm and recommendation parameters based on the decision information; and based on the recommendation parameters, performing compression processing on the to-be-compressed multimedia data through a multimedia compression algorithm to obtain compressed multimedia data. According to the digital twinning-based data compression method, based on different multimedia service requirements and the influence factors of the end-to-end link, multimedia data compression adapting to different service scene requirements of users is realized, and the method has practicability and usability.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data processing, and particularly relates to a data compression method and system based on digital twinning and a terminal device. BACKGROUND

[0002] With people's increasingly rich multimedia service needs, multimedia applications and systems are emerging in an endless stream. The large amount of data in multimedia applications and the high transmission bandwidth requirement bring great challenges to the storage, transmission and processing of systems. Multimedia compression technology can reduce data storage space, reduce transmission bandwidth and improve processing efficiency, and thus becomes an important technical link in multimedia systems.

[0003] However, in existing multimedia compression technology, video compression and audio compression form independent technical standards respectively, and lack of cross-type collaborative adaptation mechanisms. These technical standards are mostly fixed designs, and it is difficult to balance between ensuring service quality and reducing resource consumption when facing different network environments, terminal performance and content types, and the adaptability to complex dynamic application scenarios is obviously insufficient. SUMMARY

[0004] Therefore, the embodiments of the application provide a data compression method and system based on digital twinning and a terminal device, which can solve the problem of insufficient adaptability in different dynamic application scenarios.

[0005] The first aspect of the embodiments of the application provides a data compression method based on digital twinning, comprising: inputting to-be-compressed multimedia data into a digital twinning model to generate decision information; determining a multimedia compression algorithm and recommended parameters based on the decision information; performing compression processing on the to-be-compressed multimedia data by using the multimedia compression algorithm based on the recommended parameters to obtain compressed multimedia data.

[0006] The second aspect of the embodiments of the application provides a data compression system based on digital twinning, comprising: a user scenario simulator configured to input to-be-compressed multimedia data into a digital twinning model to generate decision information; a decision maker configured to determine a multimedia compression algorithm and recommended parameters based on the decision information; a data center configured to perform compression processing on the to-be-compressed multimedia data by using the multimedia compression algorithm based on the recommended parameters to obtain compressed multimedia data.

[0007] The third aspect of the embodiments of the present application provides a terminal device, the terminal device comprising a memory and a processor, the memory storing a computer program executable on the processor, and the processor implements the steps of the data compression method based on digital twinning according to any one of the first aspect.

[0008] The fourth aspect of the embodiments of the present application provides a computer readable storage medium comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the data compression method based on digital twinning according to any one of the first aspect.

[0009] The fifth aspect of the embodiments of the present application provides a computer program product, when the computer program product is executed on a terminal device, the terminal device executes the data compression method based on digital twinning according to any one of the first aspect.

[0010] Compared with the prior art, the embodiments of the present application have the beneficial effects that: by inputting the to-be-compressed multimedia data into the digital twinning model, decision information is generated, and intelligent analysis of multimedia data compression requirements is realized. Based on the decision information, the multimedia compression algorithm and the recommended parameters are determined, and the matching of the compression scheme and the specific application scenario is realized. Based on the recommended parameters, the to-be-compressed multimedia data is compressed by the multimedia compression algorithm, and the compressed multimedia data is obtained, and the multimedia data compression is realized. The data compression method based on digital twinning is based on different multimedia service requirements and the influence factors of end-to-end links, and realizes the multimedia data compression adapting to different service scene requirements of users, and the present application has practicality and ease of use. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0012] Figure 1 is the implementation flowchart of the data compression method based on digital twinning provided by the embodiments of the present application; Figure 2 is the illustration diagram of the influence factors of the user scene digital twinning model provided by the embodiments of the present application; Figure 3 is the illustration diagram of the decision information provided by the embodiments of the present application; Figure 4 is the two-level tree storage structure diagram of the preset multimedia compression algorithm library provided by the embodiments of the present application; Figure 5 is a code diagram of a data segment corresponding to a multimedia compression algorithm category provided by an embodiment of the present application; Figure 6 is an implementation flow diagram of a data compression system based on digital twinning provided by an embodiment of the present application; Figure 7 is a structural diagram of a user scenario simulator provided by an embodiment of the present application; Figure 8 is a schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the present application. However, persons skilled in the art will understand that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0014] Multimedia service features include: (1) large data volume: for example, high-definition video on-demand services use a huge amount of data, and a one-hour length of high-definition video can have an original data volume of several hundred GB. (2) Low latency: for example, video live streaming services require small data processing latency to ensure real-time transmission and playback of video. There are also strict requirements for the synchronization of audio and video transmission. (3) Visual satisfaction: there is some redundant information in video data to meet people's visual comfort. Redundant information includes spatial redundancy, temporal redundancy, information entropy redundancy, and perceptual redundancy.

[0015] Based on the features of multimedia services, in order to reduce the demand for data storage, processing, and transmission under the condition of ensuring service quality, various multimedia compression technologies have emerged. The main principle of multimedia compression technology is to reduce the redundancy of data, or to extract and reconstruct data using statistical characteristics of data, so as to achieve the purpose of reducing the amount of data. According to the type of multimedia processed, there are image-oriented, video-oriented, or audio-oriented compression technologies, and according to the influence of processing quality, there are lossless compression and lossy compression schemes. Different compression technologies contain different algorithms and technical characteristics.

[0016] Video compression technology standards, video compression technology is developing rapidly, there are many different standards and evolution. There is no loss compression and loss compression, lossless compression due to limited compression efficiency and high data processing cost, generally used in specific professional field. Loss compression has higher compression efficiency and significantly reduces data processing cost, while various new compression technologies also take into account the video quality, processing speed and noise immunity, so as to be widely used. H.2 / AVC, H.2 / HEVC, H.266 / VVC formulated by International Telecommunication Union, VP8, VP9 led by Goolge, AV1 promoted by Open Media Alliance, AVS1 / 2 technology led by domestic.

[0017] Audio compression technology is less than video compression, but considering the different effects of audio and video on perception, and the characteristics of speech signals and music in audio are different, audio compression technology also has different characteristics compared with video compression technology. Respectively for speech compression method and music compression method, and lossless compression and loss compression for fidelity level.

[0018] Digital twin is the digital mapping of real entity, through virtual and real combination, real-time interaction, data-driven control and optimization of real entity. The main components of digital twin technology include: data acquisition and transmission, model modeling and simulation prediction, big data analysis and decision making. At present, it is gradually used in product scheme design and development, equipment and system monitoring and maintenance, etc. It is one of the foundations of intelligent transformation of traditional industries.

[0019] Application scenarios refer to the specific conditions of multimedia content use, such as indoor fixed scene (video conference, monitoring camera), outdoor dense fixed scene (street monitoring, concert live broadcast), outdoor open fixed scene (scenic spot live broadcast, unmanned aerial vehicle shooting), dense medium-speed moving scene (high-speed rail, bus), dense high-speed moving scene (airplane, racing car), open medium-speed moving scene (bicycle, motorcycle), open high-speed moving scene (car, truck) and other application scenarios.

[0020] In order to illustrate the technical solutions described in the present application, the following will be illustrated by specific embodiments.

[0021] Figure 1 The implementation flowchart of the data compression method based on digital twin provided by the embodiment one of the present application is shown, which is described in detail as follows: Step S100: input the to-be-compressed multimedia data into the digital twin model to generate decision information. Wherein, the to-be-compressed multimedia data includes audio data or video data.

[0022] Step S200: based on the decision information, determine the multimedia compression algorithm and recommended parameters.

[0023] Step S300: based on the recommended parameters, the multimedia compression algorithm is used to compress the to-be-compressed multimedia data to obtain compressed multimedia data.

[0024] The data compression method based on digital twinning, by inputting the to-be-compressed multimedia data into the digital twinning model to generate decision information, and based on the decision information to determine the applicable multimedia compression algorithm and its recommended parameters, finally realizes intelligent and efficient compression processing of the to-be-compressed multimedia data, thereby improving the adaptability of the multimedia compression technology.

[0025] In an embodiment, before step S100, the method further comprises: Step S101: using a set of influence factors to train the to-be-trained digital twinning model to obtain a digital twinning model. The set of influence factors includes training source feature information, training channel feature information, training terminal feature information, and training content feature information.

[0026] Figure 2 An explanatory diagram of the influence factors of the user scenario digital twinning model provided by the embodiments of the present application is shown. By way of example, the training source feature information includes frame rate information, resolution information, and code rate information. By way of example, the training channel feature information includes application scenario information, network information, and transmission bandwidth resource information. Specifically, the application scenario information is one of indoor fixed scenario information, outdoor dense fixed scenario information, outdoor open fixed scenario information, dense medium-speed mobile scenario information, dense high-speed mobile scenario information, open medium-speed mobile scenario information, and open high-speed mobile scenario information. Specifically, the network information is one of 3G network information, 4G network information, 5G network information, WIFI network information, and wired network information. By way of example, the training terminal feature information includes device processor information, device memory information, and screen size information. By way of example, the training content feature information is live mode or on-demand mode.

[0027] The method trains the to-be-trained digital twinning model using a set of influence factors including training source feature information, training channel feature information, training terminal feature information, and training content feature information, thereby obtaining a digital twinning model that can adapt to various scenarios, accurately profiling the actual application scenario, realizing digital modeling of the actual application scenario, making the established digital twinning model have good adaptability, and effectively reducing the data volume and computational complexity in subsequent applications.

[0028] In an embodiment, before step S101, the method further comprises: obtaining the training source feature information from a source; obtaining the training channel feature information from a channel; obtaining the training terminal feature information from a terminal; and obtaining the training content feature information from training content.

[0029] The method collects training source feature information such as data generation rate, data type from the source end, training channel feature information including bandwidth capacity, signal quality, delay from the channel end, training terminal feature information such as processing capability, screen resolution, battery state from the terminal device end, and training content feature information such as video frame rate, resolution, encoding format, content complexity from the content acquisition module, integrates the feature information from different dimensions, and constructs a multi-dimensional, system-level influence factor set. The method realizes end-to-end definition of the whole chain of multimedia systems from data generation, transmission, processing to content itself, ensures that the set can completely cover and accurately map the system features in various complex and variable actual application scenarios, and lays a solid foundation for subsequent accurate compression strategy decision.

[0030] In an embodiment, after obtaining the training source feature information from the source, the method further includes: performing compression processing on the training source feature information. The method realizes that the compression algorithm can more finely analyze and process the local characteristics of the training source feature information, thereby improving the compression efficiency and / or ensuring the training source feature information after compression.

[0031] Figure 3 A description diagram of the decision information provided by the embodiments of the present application is shown. Exemplarily, the compression feature information includes compression ratio information, processing delay information, encoding format information, quantization parameter information, color sampling information, and encoding complexity information. Exemplarily, the perception feature information includes audio and video stall information and audio and video delay information. Exemplarily, the multimedia service tag information includes data type, specifically, the data type is audio or video. Exemplarily, the multimedia service tag information includes data loss type, specifically, the data loss type is lossy or lossless.

[0032] In an embodiment, the decision information includes a multimedia service tag. Before step S200, the method further includes: determining a multimedia compression algorithm category in a preset multimedia compression algorithm library based on the multimedia service tag.

[0033] Exemplarily, the multimedia service tag information includes data type and data loss type, specifically, the data type is audio or video, and the data loss type is lossy or lossless. Exemplarily, the multimedia compression algorithm category includes video lossless, video lossy, audio lossless, and audio lossy.

[0034] Specifically, determining the multimedia compression algorithm category in the preset multimedia compression algorithm library based on the multimedia service tag includes: if the data type is video, determining whether the data loss type is lossy; if yes, determining the multimedia compression algorithm category as video lossy; otherwise, determining the multimedia compression algorithm category as video lossless.

[0035] Specifically, based on the multimedia service tag, the multimedia compression algorithm category is determined in the preset multimedia compression algorithm library, including: if the data type is audio, then it is determined whether the data loss type is lossy; if so, the multimedia compression algorithm category is determined to be audio lossy; otherwise, the multimedia compression algorithm category is determined to be audio lossless.

[0036] This method first extracts specific multimedia service tags from decision information, and then filters and matches them within a pre-defined multimedia compression algorithm library based on the business characteristics or application scenario requirements represented by these tags. This accurately determines the category of multimedia compression algorithms suitable for the current task. This method utilizes high-level business semantics to guide the selection of underlying technologies, ensuring that subsequent compression processing can quickly and accurately focus on the most relevant subset of algorithms. It avoids inefficient and blind searches within a vast algorithm library, improving the efficiency and relevance of compression strategy formulation.

[0037] In one embodiment, step S200 includes: Step S201: Based on the multimedia compression algorithm category, locate the preset multimedia compression algorithm sub-library corresponding to the multimedia compression algorithm category in the preset multimedia compression algorithm library.

[0038] In one embodiment, the multimedia service tag information includes data type and data loss type. Figure 4 This diagram illustrates a two-level tree-like storage structure of a preset multimedia compression algorithm library provided in an embodiment of this application. Specifically, the data type is audio or video, and the data loss type is lossy or lossless.

[0039] For example, the preset multimedia compression algorithm library adopts a two-level tree-like storage structure, the specific structure of which is shown in the figure. This preset multimedia compression algorithm library's two-level tree-like storage structure has a root node, which is the root directory of the compression library. Under this root directory, there are two first-level child nodes: a video library subdirectory and an audio library subdirectory. Each of these first-level child nodes further divides into two second-level child nodes: a lossless library subdirectory and a lossy library subdirectory. Specifically, the video library subdirectory has two second-level directories: a lossless video library and a lossy video library; the audio library subdirectory has two second-level directories: a lossless audio library and a lossy audio library.

[0040] The pre-designed multimedia compression algorithm library employs a two-level tree-structured storage architecture, resulting in a clearer and more organized library that facilitates quick location of the appropriate compression algorithm sub-library based on different multimedia service tags (such as data type and data loss type). This two-level tree-structured storage architecture enables more efficient management and invocation of various compression algorithms to meet the multimedia data processing needs of different scenarios.

[0041] In one embodiment, the data segment corresponding to the multimedia compression algorithm category is provided with two data segments. The first data segment is used to store the data type to identify the type of multimedia data; the second data segment is used to store the data loss type field to distinguish the loss characteristics of the compression algorithm. Figure 5 As shown, specifically, the data type of the first data segment is an enumerated value type, and the data type of the second data segment is an enumerated value type. The corresponding preset multimedia compression algorithm sub-library is determined by combining the first data segment and the second data segment. Among them, the enumerated value of the first data segment is "video" or "audio", and the enumerated value of the second data segment is "lossy" or "lossless".

[0042] This method explicitly defines the data segments of multimedia compression algorithm categories into two independent storage areas. The first data segment uses an enumerated value type to store information identifying the multimedia data type as "video" or "audio." The second data segment also uses an enumerated value type to store information characterizing the loss characteristics of the compression algorithm as "lossy" or "lossless." Based on the effective combination of these two data segments, the corresponding preset multimedia compression algorithm sub-library is uniquely determined, thus realizing a clear, easily expandable, accurate, and efficient multimedia compression algorithm selection mechanism. This design enables the rapid and accurate location of the most suitable compression algorithm sub-library based on the data type and its data integrity requirements when processing multimedia data, effectively improving the decision-making efficiency of the multimedia data processing system and the matching accuracy of the compression scheme.

[0043] Step S202: Based on compression feature information and perception feature information, determine the algorithm weight of each compression algorithm in the preset multimedia compression algorithm sub-library.

[0044] In one embodiment, in a preset multimedia compression algorithm sub-library, each compression algorithm is configured with a first preset weight coefficient corresponding to the compression feature information and a second preset weight coefficient corresponding to the perceived feature information. Step S202 includes: Step S2021: The compressed feature information is filtered based on a first preset weight coefficient to obtain a first filtering weight corresponding to the compressed feature information. For example,

[0045] in, , , It is the first preset weighting coefficient. It is the first filter weight. It is compressed feature information. It represents the index corresponding to the compressed feature information being processed. Is it related to the present Adjacent feature interval boundary indices used for interpolation calculations, and, , They are all integers.

[0046] Step S2022: The perceived feature information is filtered based on a second preset weight coefficient to obtain a second filtering weight corresponding to the perceived feature information. For example,

[0047] in, , , It is the second preset weighting coefficient. It is the second filter weight. It is the perception of feature information. It represents an index corresponding to the perceptual feature information being processed. Is it related to the present Adjacent feature interval boundary indices used for interpolation calculations, and, , They are all integers.

[0048] Step S2023: Based on the first filter weight and the second filter weight, the compression feature information and the perception feature information are weighted to determine the algorithm weight of each compression algorithm in the preset multimedia compression algorithm sub-library. For example,

[0049] in, It is the algorithm weight corresponding to the k-th compression algorithm in the preset multimedia compression algorithm sub-library. It corresponds to the k-th compression algorithm. The first filtering weights for grouping compressed feature information, It corresponds to the k-th compression algorithm. The second filtering weights for the group sensing feature information, wherein... and The values ​​are equal. N is the preset number of data blocks. For example, "collecting by content blocks" (such as video by frame blocks, audio by segments), specifically, 1 hour of video is divided into 100 frames / blocks, N = 360 (3600 seconds ÷ 100 frames / block), which means that the algorithm weight is calculated using the features of 360 frame blocks.

[0050] This method pre-configures specific weight coefficients corresponding to compression feature information and perception feature information for each compression algorithm in a pre-defined multimedia compression algorithm sub-library. When determining the algorithm weight, these coefficients are first used to perform filtering on the corresponding feature information to generate a first filtering weight and a second filtering weight. Then, the compression feature information and perception feature information are weighted and fused based on the generated filtering weights, thereby accurately calculating the final algorithm weight for each compression algorithm in the sub-library. This enables a refined quantitative evaluation of the correlation between the performance of the compression algorithm and specific feature information.

[0051] Step S203: Based on the algorithm weight of each compression algorithm, filter all compression algorithms in the preset multimedia compression algorithm sub-library to determine the multimedia compression algorithm.

[0052] In one embodiment, step S203 includes: Step S2031: Based on the algorithm weight of each compression algorithm, sort all compression algorithms in the preset multimedia compression algorithm sub-library in descending order to obtain a descending algorithm set; Step S2032: If the algorithm weight is greater than the preset threshold, then the first compression algorithm in the descending algorithm set is selected as the multimedia compression algorithm.

[0053] This method first sorts all compression algorithms in a preset multimedia compression algorithm sub-library in descending order according to their respective algorithm weights, generating a descending set of algorithms arranged from highest to lowest weight (step S2031). Then, it determines whether the algorithm weight of the algorithm with the highest weight in this set (i.e., the first compression algorithm) is greater than a preset threshold (step S2032). When this condition is met, the algorithm with the highest weight is selected as the final multimedia compression algorithm. This two-step decision-making mechanism based on weight sorting and threshold selection enables the rapid and accurate identification and selection of the optimal compression algorithm with sufficient adaptability from the candidate algorithm subset, effectively improving the efficiency of algorithm selection and the reliability of decision-making, while ensuring that the selected algorithm has good performance in practical applications.

[0054] In one embodiment, the multimedia compression algorithm is configured with preset parameters, which are used as recommended parameters. The preset parameters include preset compression ratio information, preset processing delay information, preset encoding format information, preset quantization parameter information, preset color sampling information, and preset encoding complexity information.

[0055] Based on the recommended parameters, the multimedia data to be compressed is processed by the multimedia compression algorithm to obtain compressed multimedia data.

[0056] This application describes a data compression method based on digital twins. This method is applied to a data compression system based on digital twins, and its specific implementation is as follows: A digital twin system for commonly used services is built in this scheme. User scenarios are simulated based on different multimedia service requirements and influencing factors in the end-to-end link. Monitoring features are received, and simulation predictions are performed in the digital twin model. The predicted information is transmitted to the decision-maker, and a recommendation result for multimedia compression technology and related parameters is given based on the decision algorithm.

[0057] Different multimedia audio and video compression technologies have their own characteristics and varying degrees of adaptability to different services, such as compression performance, processing complexity, multimedia terminal performance, and visual satisfaction. To flexibly configure the optimal compression technology and solution to meet diverse needs, this application combines digital twin and artificial intelligence technologies to provide a data compression system based on digital twins. User scenario influencing factors can eliminate the siloed effect of application scenarios, ensuring the generalization of the digital twin system. Secondly, a compression algorithm library is established, and decision information and a core weighted decision algorithm are proposed. Based on the information from the digital twin system, compression algorithm recommendations are provided for the respective multimedia applications.

[0058] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0059] Corresponding to the method in the above embodiments, Figure 6 A structural block diagram of a data compression system based on digital twins provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown. Figure 6 The example of a digital twin-based data compression system can be the execution entity of the digital twin-based data compression method provided in the aforementioned embodiment 1.

[0060] Reference Figure 6 The data compression system based on digital twins includes: User scenario simulators are used to input multimedia data to be compressed into digital twin models to generate decision information; A decision-maker is used to determine a multimedia compression algorithm and recommended parameters based on the decision information. The data center is used to compress the multimedia data to be compressed using the multimedia compression algorithm based on the recommended parameters, thereby obtaining compressed multimedia data.

[0061] In one embodiment, the digital twin-based data compression system further includes: A base station is used to receive uncompressed multimedia data from a terminal, or to send compressed multimedia data to a terminal.

[0062] And, a base station, used to forward uncompressed multimedia data from a terminal to a data center, or used to receive compressed multimedia data from a data center.

[0063] A terminal is used to send compressed multimedia data to a base station, or to receive compressed multimedia data from a base station.

[0064] In one embodiment, such as Figure 7 As shown, the user scenario simulator includes a training content receiving module, a source receiving module, a channel receiving module, and a terminal receiving module.

[0065] The source receiving module is used to obtain the training source feature information from the source. A channel receiving module is used to acquire the training channel feature information from the channel; A terminal receiving module is used to obtain the training terminal feature information from the terminal; The training content receiving module is used to obtain the feature information of the training content from the training content.

[0066] For example, the user scenario simulator includes a console for sending decision information generated by the user scenario simulator to a decision maker.

[0067] For example, the user scenario simulator includes a compression module for compressing the training source feature information after obtaining the training source feature information from the source.

[0068] This application aims to provide a data compression system based on digital twins. Firstly, it proposes a set of end-to-end multimedia transmission influencing factors, and uses this set to establish a digital twin system and algorithm library for multimedia applications. Secondly, based on deep learning and big data analysis, it establishes a decision information set and a weighted decision algorithm. This method can significantly improve the adaptability of multimedia compression technology.

[0069] The process by which each module in the digital twin-based data compression system provided in this application implements its respective function can be found in the foregoing. Figure 1 The description of Embodiment 1 shown will not be repeated here.

[0070] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0071] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0072] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0073] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first," "second," etc., are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. For example, a first table may be named a second table, and similarly, a second table may be named a first table, without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0074] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0075] Figure 8 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 8 As shown, the terminal device 8 of this embodiment includes: at least one processor 80 ( Figure 8 (Only one is shown in the image) A memory 81 stores a computer program 82 that can run on the processor 80. When the processor 80 executes the computer program 82, it implements the steps in the various embodiments of the digital twin-based data compression method described above, for example... Figure 1Steps 100 to 300 are shown. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the above-described device embodiments.

[0076] The terminal device 8 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of terminal device 8 and does not constitute a limitation on terminal device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmission devices, network access devices, buses, etc.

[0077] The processor 80 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0078] In some embodiments, the memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device 8. Furthermore, the memory 81 may include both internal and external storage units of the terminal device 8. The memory 81 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 81 can also be used to temporarily store data that has been sent or will be sent.

[0079] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0080] This application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, it causes the terminal device to implement the steps in any of the above method embodiments.

[0081] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0082] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0083] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0084] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0085] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0086] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A data compression method based on digital twins, characterized in that, include: The multimedia data to be compressed is input into the digital twin model to generate decision-making information; Based on the decision information, a multimedia compression algorithm and recommended parameters are determined; Based on the recommended parameters, the multimedia data to be compressed is processed by the multimedia compression algorithm to obtain compressed multimedia data.

2. The data compression method based on digital twins as described in claim 1, characterized in that, Before inputting the multimedia data to be compressed into the digital twin model to generate decision information, the method includes: The digital twin model to be trained is obtained by using a set of influence factors, wherein the set of influence factors includes training source feature information, training channel feature information, training terminal feature information, and training content feature information.

3. The data compression method based on digital twins as described in claim 1, characterized in that, The decision information includes multimedia service tags; Before determining the multimedia compression algorithm and recommended parameters based on the decision information, the method includes: Based on the multimedia service tag, the multimedia compression algorithm category is determined from the preset multimedia compression algorithm library.

4. The data compression method based on digital twins as described in claim 3, characterized in that, The decision information includes compressed feature information and perceived feature information; The process of determining the multimedia compression algorithm and recommended parameters based on the decision information includes: Based on the multimedia compression algorithm category, locate the preset multimedia compression algorithm sub-library corresponding to the multimedia compression algorithm category in the preset multimedia compression algorithm library; Based on the compression feature information and perception feature information, the algorithm weight of each compression algorithm in the preset multimedia compression algorithm sub-library is determined; Based on the algorithm weight of each compression algorithm, all compression algorithms in the preset multimedia compression algorithm sub-library are screened to determine the multimedia compression algorithm.

5. The data compression method based on digital twins as described in claim 4, characterized in that, In the preset multimedia compression algorithm sub-library, each compression algorithm is configured with a first preset weight coefficient corresponding to the compression feature information and a second preset weight coefficient corresponding to the perception feature information; determining the algorithm weight of each compression algorithm in the preset multimedia compression algorithm sub-library based on the compression feature information and the perception feature information includes: Based on the first preset weight coefficient, the compressed feature information is filtered to obtain the first filtering weight corresponding to the compressed feature information; Based on the second preset weight coefficient, the perceived feature information is filtered to obtain the second filtering weight corresponding to the perceived feature information; Based on the first filter weight and the second filter weight, the compression feature information and the perception feature information are weighted to determine the algorithm weight of each compression algorithm in the preset multimedia compression algorithm sub-library.

6. The data compression method based on digital twins as described in claim 4, characterized in that, The preset multimedia compression algorithm sub-library includes two or more compression algorithms; the step of filtering all compression algorithms in the preset multimedia compression algorithm sub-library based on the algorithm weight of each compression algorithm to determine the multimedia compression algorithm includes: Based on the algorithm weight of each compression algorithm, all compression algorithms in the preset multimedia compression algorithm sub-library are sorted in descending order to obtain a descending algorithm set; If the algorithm weight is greater than a preset threshold, then the first compression algorithm in the descending algorithm set is selected as the multimedia compression algorithm.

7. The data compression method based on digital twins as described in claim 2, characterized in that, Before training the digital twin model using a set of influence factors to obtain the digital twin model, the method includes: Obtain the training source feature information from the source; Obtain the training channel feature information from the channel; Obtain the training terminal feature information from the terminal; The feature information of the training content is obtained from the training content.

8. A data compression system based on digital twins, characterized in that, include: User scenario simulators are used to input multimedia data to be compressed into digital twin models to generate decision information; A decision-maker is used to determine a multimedia compression algorithm and recommended parameters based on the decision information. The data center is used to compress the multimedia data to be compressed using the multimedia compression algorithm based on the recommended parameters, thereby obtaining compressed multimedia data.

9. A terminal device, characterized in that, The terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images