Image transmission method and device

Abstract

The invention provides an image transmission method and device, relates to the field of data transmission, and can improve user image transmission efficiency, reduce transmission time, reduce network bandwidth occupation and provide better user experience. According to the specific technical scheme, the method comprises the steps of predicting fragments required by a user by extracting features of a user picture; caching the fragments required by the user to a cache server; receiving feedback information of the intelligent cache module and adjusting the target parameter according to the feedback information; feedback information of the user is received, the adjusted target parameters are optimized according to the feedback information, and the feedback information of the user is determined according to the feedback information of the intelligent cache module and the adjusted target parameters. Through the modes of analyzing the characteristics of the user picture, predicting the user demand, dynamically adjusting the caching strategy and the transmission parameters and the like, the transmission efficiency is improved, the problems of delay, lagging and the like are reduced, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data transmission, and in particular to an image transmission method and device. Background Art

[0002] Currently, with the development of network technology, the demand for network transmission of user images is increasing.

[0003] However, due to the limitation of network bandwidth and the complexity of data transmission, the traditional user picture transmission system has certain limitations in transmission efficiency. Therefore, how to improve the efficiency of user picture transmission has become a problem to be solved urgently. Summary of the invention

[0004] The embodiments of the present disclosure provide an image transmission method and device, which can improve the user's image transmission efficiency, reduce the transmission time, reduce the network bandwidth occupation, and provide a better user experience. The technical solution is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an image transmission method, the method comprising: predicting the slices required by the user by extracting features of the user's screen; caching the slices required by the user to a cache server; receiving and adjusting target parameters based on feedback information from the intelligent cache module; receiving and optimizing the adjusted target parameters based on the user's feedback information, the user's feedback information being determined based on the feedback information from the intelligent cache module and the adjusted target parameters.

[0006] Based on the above solution, the user screen transmission process can be optimized through intelligent caching technology. Specifically, it improves transmission efficiency and reduces delays and freezes by analyzing the characteristics of user screens, predicting user needs, and dynamically adjusting caching strategies and transmission parameters. At the same time, the system also has better feasibility and practicality in actual applications, improving the user experience.

[0007] In some embodiments, predicting the slices required by the user by extracting features of the user screen includes: constructing a target prediction model by extracting features of the user screen; and predicting the slices required by the user based on historical data, current status, and real-time feedback through the target prediction model.

[0008] As an example, the intelligent cache module can extract features of the user's screen, which may include content type, color, layout, etc. These features can help the module understand the content the user is viewing and predict the segments that the user may need.

[0009] Then, based on the features of the extracted user screen, the intelligent cache module builds a prediction model (i.e., a target prediction model) to predict the shards that the user may need. For example, the prediction model built by the intelligent cache module uses a machine learning algorithm to predict the shards that the user needs based on historical data, current status, and real-time feedback.

[0010] In some embodiments, the target prediction model is continuously trained and optimized through a machine learning algorithm.

[0011] Specifically, the model can be trained and optimized using a machine learning algorithm. Through continuous training, learning and optimization, the intelligent cache module can more accurately predict user needs and provide a better user experience.

[0012] In some embodiments, the method further includes: determining a strategy for adjusting the cache according to the user's behavior and changes in the network environment; and adaptively adjusting the content, size, and location of the cache according to the strategy for adjusting the cache.

[0013] In some embodiments, the cache adjustment strategy includes the following methods: adjusting the cache based on the user's behavior, adjusting the cache based on changes in the network environment, distributed management of the cache, intelligent cache replacement strategy, and continuous learning and optimization.

[0014] By combining and applying the above strategies, the intelligent cache module can adaptively adjust the cache content, size, and location according to changes in user behavior and network environment, providing more efficient and intelligent cache services.

[0015] In some embodiments, the method further includes: classifying the slices according to prediction rules; and transmitting the slices of different classifications in parallel through different network paths.

[0016] In some embodiments, the prediction rule includes one or more of the following factors: content type of the shards, size and number of the shards, importance of the shards, timeliness of the shards, geographic location of the shards, and real-time network conditions.

[0017] Specifically, multi-path transmission technology can be used to transmit different types of fragments in parallel through different network paths, and the above strategy can be used to improve transmission efficiency and reliability.

[0018] In some embodiments, receiving and optimizing the target parameters after dynamic adjustment based on the feedback information of the user includes: determining the feedback information of the user by the user viewing the feedback information of the intelligent cache module and the target parameters after adjustment using a user interface; receiving and optimizing the target parameters after dynamic adjustment based on the feedback information of the user.

[0019] In some embodiments, adjusting the target parameter includes one or more of the following methods:

[0020] Adjust transmission priorities, adjust transmission parameters, dynamic buffer management, traffic shaping and congestion control, dynamically adapt encoding, and error recovery and retry strategies.

[0021] In some embodiments, the feedback information of the intelligent cache module includes one or more of the following information: cache hit rate, behavior data of the user, network health, error rate and retry rate, and server load.

[0022] According to a second aspect of the embodiments of the present disclosure, an image transmission device is provided, comprising a memory and a processor. The memory stores a program. When the program is executed in the processor, the processor is used to execute the method of the first aspect and any embodiment of the first aspect.

[0023] Based on the above equipment, the user screen transmission process can be optimized through intelligent caching technology. Specifically, it improves transmission efficiency and reduces delays and freezes by analyzing the characteristics of user screens, predicting user needs, and dynamically adjusting caching strategies and transmission parameters. At the same time, the system also has better feasibility and practicality in actual applications, improving the user experience.

[0024] According to a third aspect of an embodiment of the present disclosure, there is provided an image transmission device, comprising: a prediction module, for predicting the slices required by the user by extracting features of the user's screen; a cache module, for caching the slices required by the user to a cache server; a first adjustment module, for receiving and adjusting target parameters according to feedback information from the intelligent cache module; an optimization module, for receiving and optimizing the adjusted target parameters according to the feedback information from the user, wherein the feedback information from the user is determined based on the feedback information from the intelligent cache module and the adjusted target parameters.

[0025] In some embodiments, the prediction module specifically includes: a construction submodule, used to construct a target prediction model by extracting features of the user screen; a prediction submodule, used to predict the segmentation required by the user based on historical data, current status, and real-time feedback through the target prediction model.

[0026] In some embodiments, the target prediction model is continuously trained and optimized through a machine learning algorithm.

[0027] In some embodiments, the image transmission device also includes: a determination module for determining a strategy for adjusting the cache based on the user's behavior and network environment changes; and a second adjustment module for adaptively adjusting the content, size, and location of the cache based on the cache adjustment strategy.

[0028] In some embodiments, the cache adjustment strategy includes the following methods: adjusting the cache based on the user's behavior, adjusting the cache based on changes in the network environment, distributed management of the cache, intelligent cache replacement strategy, and continuous learning and optimization.

[0029] In some embodiments, the image transmission device further includes: a classification module for classifying the slices according to prediction rules; and a transmission module for transmitting the slices of different classifications in parallel through different network paths.

[0030] In some embodiments, the prediction rules include one or more of the following factors: content type of the shards, size and number of the shards, importance of the shards, timeliness of the shards, geographic location of the shards, and real-time network conditions.

[0031] In some embodiments, the optimization module specifically includes: a determination submodule, used to determine the user's feedback information by viewing the feedback information of the intelligent cache module and the adjusted target parameters through the user using the user interface; an optimization submodule, used to receive and optimize the dynamically adjusted target parameters based on the user's feedback information.

[0032] In some embodiments, the adjusting target parameters includes one or more of the following methods: adjusting transmission priority, adjusting transmission parameters, dynamic buffer management, traffic shaping and congestion control, dynamic adaptive coding, and error recovery and retry strategy.

[0033] In some embodiments, the feedback information of the intelligent cache module includes one or more of the following information: cache hit rate, behavior data of the user, network health, error rate and retry rate, and server load.

[0034] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, characterized in that the computer program storage medium has program instructions, and when the program instructions are executed by a processor, the processor executes the method of the first aspect and any embodiment of the first aspect.

[0035] According to the fifth aspect of the embodiments of the present disclosure, a chip system is provided, characterized in that the chip system includes at least one processor, and when program instructions are executed in the at least one processor, the at least one processor executes the method of the first aspect and any embodiment of the first aspect.

[0036] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0038] Figure 1 is a schematic diagram of an image transmission method 100 provided in an embodiment of the present disclosure;

[0039] Figure 2 is a flowchart of a specific implementation method 200 applicable to the embodiment of the present disclosure;

[0040] Figure 3 is a structural diagram of an image transmission device 300 provided in an embodiment of the present disclosure;

[0041] Figure 4 is a structural diagram of an image transmission device 400 provided in an embodiment of the present disclosure;

[0042] Figure 5 is another structural diagram of an image transmission device 400 provided in an embodiment of the present disclosure;

[0043] Figure 6 is another structural diagram of an image transmission device 400 provided in an embodiment of the present disclosure;

[0044] Figure 7 is another structural diagram of an image transmission device 400 provided in an embodiment of the present disclosure;

[0045] Figure 8 4 is another structural diagram of an image transmission device 400 provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0047] Currently, with the development of network technology, the demand for network transmission of user images is increasing.

[0048] However, due to the limitation of network bandwidth and the complexity of data transmission, the traditional user picture transmission system has certain limitations in transmission efficiency. Therefore, how to improve the efficiency of user picture transmission has become a problem to be solved urgently.

[0049] In view of this, the present disclosure provides an image transmission method, which can improve the above problems and enhance the user experience.

[0050] It should be understood that in the following embodiments, an intelligent cache module, a transmission control module and a user interface module are involved. Here, the above modules are briefly introduced first:

[0051] Smart Cache Module: It is mainly responsible for extracting the features of the user screen, predicting the segments that the user may need, and caching them in the cache server. The features analyzed specifically include content type, color, layout, etc. These features can help the smart cache module understand the content that the user is viewing and predict the segments that he may need.

[0052] Transmission control module: mainly responsible for controlling the transmission process of user images. It can dynamically adjust the transmission priority and parameters according to the feedback information of the cache module.

[0053] User interface module: mainly provides a user interface, allowing users to view the current transmission status, cache status and feedback. Users can use the interface to understand the transmission progress, cache hit rate and other information in real time, and provide feedback on the picture quality and cache effect. This feedback information is further used to optimize the cache strategy and transmission parameters.

[0054] The present disclosure provides an image transmission method 100, such as Figure 1 As shown, the image transmission method 100 includes the following steps:

[0055] S110, predicting the slices required by the user by extracting features of the user's screen.

[0056] Specifically, this step can be achieved by:

[0057] By extracting the features of the user's screen, a target prediction model is constructed; then, the target prediction model is used to predict the shards required by the user based on historical data, current status, and real-time feedback.

[0058] As an example, the intelligent cache module can extract features of the user's screen, which may include content type, color, layout, etc. These features can help the module understand the content the user is viewing and predict the segments that the user may need.

[0059] Then, based on the features of the extracted user screen, the intelligent cache module builds a prediction model (i.e., a target prediction model) to predict the shards that the user may need. For example, the prediction model built by the intelligent cache module uses a machine learning algorithm to predict the shards that the user needs based on historical data, current status, and real-time feedback.

[0060] Furthermore, the target prediction model can be continuously trained and optimized through machine learning algorithms.

[0061] Specifically, the model can be trained and optimized using a machine learning algorithm. Through continuous training, learning and optimization, the intelligent cache module can more accurately predict user needs and provide a better user experience.

[0062] In other words, in order to ensure the accuracy of the prediction, the intelligent cache module also needs to continuously learn and optimize the prediction model, which can be done by collecting user feedback and behavior data. Through continuous learning and optimization, the intelligent cache module can more accurately predict user needs and provide a better user experience.

[0063] It should be understood that in actual applications, the intelligent cache module needs to work closely with the backend server and the cache server. When the content in the cache server needs to be updated, the intelligent cache module needs to communicate with the backend server to obtain the latest data and update the cache. At the same time, it also needs to work with the cache server to ensure the correctness and validity of the cached content.

[0064] In addition, the intelligent cache module also has the ability to dynamically adjust the cache strategy, and adaptively adjust the cache content, size and location according to changes in user behavior and network environment. Furthermore, the method 100 may also include:

[0065] Determine the strategy for adjusting cache based on user behavior and network environment changes;

[0066] According to the cache adjustment strategy, the cache content, size, and location are adaptively adjusted.

[0067] Furthermore, the cache adjustment strategy may include the following methods:

[0068] Adjust the cache based on user behavior, adjust the cache based on network environment changes, manage the cache in a distributed manner, implement intelligent cache replacement strategies, and continuously learn and optimize.

[0069] The following will introduce the above cache adjustment strategies one by one:

[0070] 1. Adjust the cache based on user behavior:

[0071] Access frequency analysis: Monitor the frequency of users accessing specific content. If a certain content is frequently accessed, consider caching it.

[0072] Access path optimization: Record the user's access path. If you find that the content under a certain path is frequently accessed, you can add this content to the cache.

[0073] Time series analysis: Analyze the time series patterns of user access. For example, during a specific time period on weekdays, the demand for certain content may increase, and the cache volume of this content can be increased at this time.

[0074] 2. Adjust the cache based on changes in the network environment:

[0075] Traffic awareness: Dynamically adjust the size and content of the cache based on changes in network bandwidth. For example, when the bandwidth is high, the cache amount can be increased; when the bandwidth is low or unstable, the cache amount can be reduced or smaller and lighter content can be cached.

[0076] Latency optimization: If you find that the response time of user requests is long, it may be because the content in the cache is inconsistent with the content of the backend server. At this time, the smart cache module can update the cache content or adjust the cache location.

[0077] Packet loss handling: If a high packet loss rate is detected, the smart cache module can take measures such as re-requesting lost packets or adjusting the cache strategy to reduce the impact of packet loss.

[0078] 3. Distributed cache management:

[0079] Load balancing: Dynamically allocate cache content based on the load of each cache node to ensure load balancing of each node.

[0080] Content distribution: Intelligently select the best cache node to store and provide content based on user distribution and network traffic.

[0081] 4. Intelligent cache replacement strategy:

[0082] Least Recently Used (LRU): Replaces cache items that have not been used in the longest time.

[0083] Based on access frequency: replace the cache items that are accessed least frequently.

[0084] Based on expiration time: replace the cache item that expires the earliest.

[0085] 5. Continuous learning and optimization:

[0086] The intelligent cache module should continuously collect and analyze user behavior data and network environment data, and constantly learn and adjust its cache strategy to achieve the best performance and user experience.

[0087] By combining and applying the above strategies, the intelligent cache module can adaptively adjust the cache content, size, and location according to changes in user behavior and network environment, providing more efficient and intelligent cache services.

[0088] S120, cache the slices required by the user to the cache server.

[0089] Specifically, when it is predicted that a user may need a certain shard, the intelligent cache module will cache the shard in the cache server. At the same time, it also needs to maintain cache management, such as cache elimination strategy, cache update mechanism, etc.

[0090] S130, receiving and adjusting target parameters according to feedback information from the intelligent cache module.

[0091] Specifically, the transmission control module is responsible for controlling the transmission process of the user picture, and it can dynamically adjust the transmission priority and parameters (ie, target parameters) according to the feedback information of the intelligent cache module.

[0092] The feedback information of the intelligent cache module may include one or more of the following information:

[0093] Cache hit rate, user behavior data, network health, error rate and retry rate, and server load.

[0094] The following will introduce the above information one by one:

[0095] Cache hit rate: The smart cache module records which content is successfully cached and which requests are satisfied in the cache. This data can help the transmission control module understand the effectiveness of the cache and decide whether to adjust the transmission priority or parameters.

[0096] User behavior data: Data from the user behavior analysis system, such as user click-through rate, viewing time, replay behavior, etc., can reflect the user's preference or demand for different content or specific transmission parameters.

[0097] Network health status: The network health status monitoring module can provide real-time network bandwidth, delay, packet loss rate and other data to help the transmission control module determine the current network environment and adjust the transmission parameters accordingly.

[0098] Error rate and retry rate: If the user encounters an error or needs to retry when receiving the image, this information will also be fed back to the transmission control module, indicating that the stability or priority of the transmission may need to be adjusted.

[0099] Server load: Server load data can help the transmission control module understand the current workload of the server and decide whether to adjust the priority or parameters of certain transmission tasks.

[0100] Furthermore, adjusting the target parameters may include one or more of the following methods:

[0101] Adjust transmission priorities, adjust transmission parameters, dynamic buffer management, traffic shaping and congestion control, dynamically adapt encoding, and error recovery and retry strategies.

[0102] The following will introduce the above methods one by one:

[0103] Adjusting transmission priority: Based on user behavior feedback or server load data, the transmission control module can dynamically adjust the transmission priority of different tasks or content. For example, a higher transmission priority can be given to content with a high click-through rate or a long viewing time.

[0104] Adjust transmission parameters: If it is found that the error rate is high during the transmission of certain content or the network environment changes, the transmission control module can adjust the relevant transmission parameters, such as changing the bit rate, adjusting the frame rate, or selecting a different codec.

[0105] Dynamic cache management: Combined with the feedback from the intelligent cache module, the transmission control module can manage cache content more intelligently. For example, when it is found that the hit rate of a certain content in the cache is particularly high, it can consider increasing the cache amount of the content or extending its cache validity period.

[0106] Traffic shaping and congestion control: Based on the feedback from network health, the transmission control module can implement traffic shaping strategies to avoid network congestion and adopt congestion control algorithms to ensure the stability and efficiency of data transmission.

[0107] Dynamic adaptive encoding: According to the changes in network bandwidth, the transmission control module can adjust the encoding parameters of the video stream to adapt to different bandwidth requirements. For example, when the bandwidth is low, a lower resolution or bit rate can be selected to ensure smooth playback.

[0108] Error recovery and retry strategy: Based on the feedback of error rate and retry rate, the transmission control module can adjust the error recovery mechanism and retry strategy to improve the reliability and stability of data transmission, and give priority to the transmission of uncached fragments or high-priority fragments.

[0109] At the same time, the transmission control module also uses multi-path transmission technology to transmit different types of slices in parallel through different network paths. Furthermore, the method 100 may also include:

[0110] Classify the shards according to the prediction rules;

[0111] The fragments of different categories are transmitted in parallel through different network paths.

[0112] The prediction rules include one or more of the following factors:

[0113] The content type of the shards, the size and number of shards, the importance of the shards, the timeliness of the shards, the geographical location of the shards, and the real-time network status.

[0114] The following will introduce the above factors one by one:

[0115] Content type of the fragment: The fragments are classified according to their content type, such as text, picture, audio, video, etc. Different types of fragments have different transmission requirements and priorities, so different network paths are required for transmission.

[0116] The size and number of shards: The size and number of shards are also one of the criteria for classification. For smaller shards, a faster transmission path can be used; for larger shards, a more stable transmission path or shard merging and other technologies may be required to improve transmission efficiency.

[0117] Importance of shards: shards are classified according to their importance or priority. For example, for critical metadata shards or important business data shards, a more reliable transmission path or a higher transmission priority can be used.

[0118] Timeliness of fragments: Fragments are classified according to their timeliness. For fragments that need to be transmitted in a timely manner, such as real-time audio and video streams or time-sensitive data, a faster transmission path can be used.

[0119] Geographic location of shards: shards are classified according to their source or destination geographic location. For shard transmission within a specific region, a transmission path closer to the region can be used to reduce latency.

[0120] Real-time network status: Dynamic classification based on changes in network status. For example, based on real-time network bandwidth, latency, and packet loss rate data, the transmission control module can dynamically adjust the transmission path or priority of different fragments.

[0121] The above strategies can improve transmission efficiency and reliability.

[0122] S140, receiving and optimizing the adjusted target parameters according to the user's feedback information.

[0123] The user's feedback information is determined based on the feedback information of the intelligent cache module and the adjusted target parameters.

[0124] Specifically, this step can be achieved by:

[0125] The user uses a user interface to view the feedback information of the intelligent cache module and the adjusted target parameters to determine the user's feedback information; then, the dynamically adjusted target parameters are received and optimized based on the user's feedback information.

[0126] For example, the user can understand the transmission status, caching status and feedback (i.e., the feedback information of the intelligent caching module and the target parameters after adjustment) in real time through the user interface provided by the user interface module, and provide feedback on the picture quality and caching effect (i.e., the user's feedback information). These feedback information are further used to optimize the caching strategy and transmission parameters; thereafter, the caching strategy and transmission parameters can be further optimized based on the user's feedback information (i.e., optimizing the target parameters after dynamic adjustment).

[0127] Also, as an example, Figure 2 It is a flowchart of a specific implementation method 200 applicable to the embodiment of the present disclosure.

[0128] Based on the above solution, the user screen transmission process can be optimized through intelligent caching technology. Specifically, it improves transmission efficiency and reduces delays and freezes by analyzing the characteristics of user screens, predicting user needs, and dynamically adjusting caching strategies and transmission parameters. At the same time, the system also has better feasibility and practicality in actual applications, improving the user experience.

[0129] It should be understood that the present disclosure also provides a user screen transmission optimization system based on intelligent caching technology, which is intended to improve the efficiency of user screen transmission. The system includes: an intelligent caching module, a transmission control module and a user interface module. The specific implementation scheme of each module can refer to the corresponding description in the above method 100.

[0130] Based on the above Figure 1 The image transmission method described in the corresponding embodiment is as follows: an embodiment of the device disclosed herein, which can be used to execute the embodiment of the method disclosed herein.

[0131] The present disclosure provides an image transmission device 300, such as Figure 3 The image transmission device 300 includes: a memory 301 and a processor 302 .

[0132] The memory 301 is used to store programs.

[0133] When the program is executed in the processor 302 , the processor 302 is used to execute the above-mentioned image transmission method.

[0134] Processor 302 is used to: predict the slices required by the user by extracting features of the user's screen; cache the slices required by the user to a cache server; receive and adjust target parameters based on feedback information from the intelligent cache module; receive and optimize the adjusted target parameters based on the user's feedback information, wherein the user's feedback information is determined based on the feedback information from the intelligent cache module and the adjusted target parameters.

[0135] Optionally, the processor 302 is specifically used to: construct a target prediction model by extracting features of the user screen; and predict the slice required by the user according to historical data, current status, and real-time feedback through the target prediction model.

[0136] Optionally, the target prediction model is continuously trained and optimized through a machine learning algorithm.

[0137] Optionally, the processor 302 is further configured to: determine a cache adjustment strategy according to the user's behavior and network environment changes; and adaptively adjust the cache content, size, and location according to the cache adjustment strategy.

[0138] Optionally, strategies for adjusting the cache include the following: adjusting the cache based on the user's behavior, adjusting the cache based on changes in the network environment, distributed management of the cache, intelligent cache replacement strategy, and continuous learning and optimization.

[0139] Optionally, the processor 302 is further configured to classify the slices according to the prediction rule; and transmit the slices of different classifications in parallel through different network paths.

[0140] Optionally, the prediction rule includes one or more of the following factors: content type of the segment, size and number of the segment, importance of the segment, timeliness of the segment, geographic location of the segment, and real-time network status.

[0141] Optionally, the processor 302 is specifically used to: determine the user's feedback information by having the user use a user interface to view the feedback information of the intelligent cache module and the adjusted target parameters; receive and optimize the dynamically adjusted target parameters based on the user's feedback information.

[0142] Optionally, the adjusting target parameters includes one or more of the following methods: adjusting transmission priority, adjusting transmission parameters, dynamic cache management, traffic shaping and congestion control, dynamic adaptive coding, and error recovery and retry strategy.

[0143] Optionally, the feedback information of the intelligent cache module includes one or more of the following information: cache hit rate, behavior data of the user, network health, error rate and retry rate, and server load.

[0144] The image transmission device provided by the embodiment of the present disclosure outputs the related processing services of the barrage on the terminal, which can reduce the dependence on the remote screen and provide a smooth barrage display effect, especially in scenarios with poor network quality and low game video frame rate, which can greatly improve the user experience.

[0145] Based on the above Figure 1 The image transmission method described in the corresponding embodiment is as follows: an embodiment of the device disclosed herein, which can be used to execute the embodiment of the method disclosed herein.

[0146] Based on the above Figure 1 Corresponding to the image transmission method described in the embodiment, the embodiment of the present disclosure also provides an image transmission device 400, such as Figure 4 shown.

[0147] The image transmission device 400 includes: a prediction module 410, which is used to predict the slices required by the user by extracting the features of the user's picture; a cache module 420, which is used to cache the slices required by the user to a cache server; a first adjustment module 430, which is used to receive and adjust the target parameters according to the feedback information of the intelligent cache module; an optimization module 440, which is used to receive and optimize the adjusted target parameters according to the feedback information of the user, wherein the feedback information of the user is determined based on the feedback information of the intelligent cache module and the adjusted target parameters.

[0148] Alternatively, if Figure 5 As shown, the prediction module 410 specifically includes: a construction submodule 4101, which is used to construct a target prediction model by extracting the features of the user screen; a prediction submodule 4102, which is used to predict the segmentation required by the user based on historical data, current status, and real-time feedback through the target prediction model.

[0149] Optionally, the target prediction model is continuously trained and optimized through a machine learning algorithm.

[0150] Alternatively, if Figure 6 As shown, the image transmission device 400 also includes: a determination module 450, which is used to determine a strategy for adjusting the cache according to the user's behavior and network environment changes; a second adjustment module 460, which is used to adaptively adjust the content, size, and position of the cache according to the cache adjustment strategy.

[0151] Optionally, the cache adjustment strategy includes the following methods: adjusting the cache based on the user's behavior, adjusting the cache based on changes in the network environment, distributed management of the cache, intelligent cache replacement strategy, and continuous learning and optimization.

[0152] Alternatively, if Figure 7 As shown, the image transmission device 400 further includes: a classification module 470, for classifying the slices according to the prediction rule; and a transmission module 480, for transmitting the slices of different classifications in parallel through different network paths.

[0153] Optionally, the prediction rules include one or more of the following factors: the content type of the shards, the size and number of the shards, the importance of the shards, the timeliness of the shards, the geographic location of the shards, and real-time network conditions.

[0154] Alternatively, if Figure 8 As shown, the optimization module 440 specifically includes: a determination submodule 4401, used to determine the user's feedback information by allowing the user to view the feedback information of the intelligent cache module and the adjusted target parameters using the user interface; an optimization submodule 4402, used to receive and optimize the target parameters after dynamic adjustment based on the user's feedback information.

[0155] Optionally, the adjusting target parameters includes one or more of the following methods: adjusting transmission priority, adjusting transmission parameters, dynamic cache management, traffic shaping and congestion control, dynamic adaptive coding, and error recovery and retry strategy.

[0156] Optionally, the feedback information of the intelligent cache module includes one or more of the following information: cache hit rate, behavior data of the user, network health, error rate and retry rate, and server load.

[0157] Based on the above Figure 1 In accordance with the image transmission method described in the embodiment, the embodiment of the present disclosure further provides a computer-readable storage medium. For example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, or an optical data storage device. The storage medium stores computer instructions for executing the above Figure 1 The image transmission method described in the corresponding embodiment will not be repeated here.

[0158] Based on the above Figure 1Corresponding to the image transmission method described in the embodiment, the embodiment of the present disclosure also provides a chip system, the chip system includes at least one processor, when the program instruction is executed in the at least one processor, the at least one processor executes the above Figure 1 The image transmission method described in the corresponding embodiment will not be repeated here.

[0159] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0160] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image transmission method, characterized in that: The method comprises: By extracting features of the user's screen, predicting the slices required by the user; Cache the slices required by the user to the cache server; Receive and adjust target parameters according to feedback information from the intelligent cache module; The adjusted target parameters are received and optimized according to the feedback information of the user, wherein the feedback information of the user is determined according to the feedback information of the intelligent cache module and the adjusted target parameters.

2. The method according to claim 1, characterized in that The extracting the features of the user screen to predict the slices required by the user includes: By extracting the features of the user screen, a target prediction model is constructed; The target prediction model is used to predict the shards required by the user based on historical data, current status, and real-time feedback.

3. The method according to claim 2, characterized in that The target prediction model is continuously trained and optimized through machine learning algorithms.

4. The method according to claim 1, characterized in that: The method further comprises: Determining a cache adjustment strategy based on the user's behavior and network environment changes; According to the cache adjustment strategy, the content, size and location of the cache are adaptively adjusted.

5. The method according to claim 4, characterized in that The cache adjustment strategy includes the following methods: The cache is adjusted based on the user's behavior, the cache is adjusted based on the changes in the network environment, the cache is managed in a distributed manner, an intelligent cache replacement strategy is implemented, and continuous learning and optimization are performed.

6. The method according to claim 1, characterized in that The method further comprises: classifying the slices according to a prediction rule; The fragments of different categories are transmitted in parallel through different network paths.

7. The method according to claim 6, characterized in that The prediction rules include one or more of the following factors: The content type of the shards, the size and number of the shards, the importance of the shards, the timeliness of the shards, the geographical location of the shards, and the real-time network status.

8. The method according to claim 1, characterized in that The receiving and optimizing the dynamically adjusted target parameters according to the user's feedback information includes: Determining the feedback information of the user by the user viewing the feedback information of the intelligent cache module and the adjusted target parameter using a user interface; Receive and optimize the dynamically adjusted target parameters according to the user's feedback information.

9. The method according to claim 1, characterized in that: The adjustment of the target parameters includes one or more of the following methods: Adjust transmission priorities, adjust transmission parameters, dynamic buffer management, traffic shaping and congestion control, dynamically adapt encoding, and error recovery and retry strategies.

10. The method according to claim 1, characterized in that The feedback information of the intelligent cache module includes one or more of the following information: cache hit rates, behavioral data about said users, network health, error and retry rates, and server load.

Images