Data transmission optimization method and system, network device, medium and program product

Abstract

The invention provides a data transmission optimization method and device, network equipment, a medium and a program product, and relates to the technical field of wireless communication. The data transmission optimization method comprises the following steps: in response to an obtained data transmission request of a user, determining a corresponding transmission scene and a network slice configured for the transmission scene; determining a transmission target corresponding to the transmission scene; configuring a transmission strategy based on the transmission target, the monitored network working condition information and the cache information of the edge node; and based on the transmission strategy, indicating the network slice to transmit target semantic data obtained based on the compression ratio to the user and / or indicating the edge node to transmit target cache data to the user, so as to generate target request data of the data transmission request based on the target semantic data and / or the target cache data. Through the technical scheme of the invention, semantic communication and / or cache are dynamically selected, and data transmission optimization is realized by utilizing the advantage of high data compression ratio of semantic communication and the advantage of low delay of cache.

Description

Background Art

[0002] With the rapid development of network technology, the demand for data transmission has increased exponentially. To improve data transmission efficiency, semantic communication can be used to perform data transmission. By extracting semantic information from the data to be transmitted for transmission, due to the advantage of high data compression ratio, it can significantly reduce the amount of transmitted data. However, simply using semantic communication will reduce the accuracy of data transmission, especially in scenarios with high requirements for data accuracy, resulting in a poor user experience.

[0003] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a data transmission optimization method, a configuration device, a network device, a storage medium, and a computer program product, which at least overcome to some extent the problem of poor user experience caused by simply using semantic communication for data transmission in related technologies.

[0005] Other features and advantages of the present disclosure will become apparent through the following detailed description, or will be partially learned through the practice of the present disclosure.

[0006] According to one aspect of the present disclosure, a data transmission optimization method is provided, including: in response to a user's data transmission request being obtained, determining the corresponding transmission scenario and the network slice configured for the transmission scenario; determining the transmission target corresponding to the transmission scenario; based on the transmission target, the monitored network working condition information, and the cache information of the edge node, configuring at least one of the compression ratio for semantically compressing the transmission data, the service policy of the network slice, and the usage parameters of the cache information corresponding to the data transmission request, so as to generate a transmission policy based on the configuration result; based on the transmission policy, instructing the network slice to transmit target semantic data obtained based on the compression ratio to the user and / or instructing the edge node to transmit target cached data to the user, so as to generate target request data for the data transmission request based on the target semantic data and / or the target cached data.

[0007] In an embodiment of the present disclosure, determining the transmission target corresponding to the transmission scenario includes: based on the transmission scenario, determining the service type and data requirements of the data transmission request, where the data requirements include at least one of accuracy requirements, transmission delay requirements, and security requirements;

[0008] Determine the transmission target based on the service type and the data requirements. In an embodiment of the present disclosure, determining the transmission target based on the service type and the data requirements includes: monitoring the processing energy consumption generated by the data transmission optimization; determining the transmission target based on the balance configuration of the processing energy consumption, the service type, and the data requirements.

[0009] In an embodiment of the present disclosure, based on the transmission target, the monitored network condition information, and the cache information of the edge node, configuring at least one of the compression ratio for semantically compressing the transmission data, the service policy of the network slice, and the usage parameters of the cache information corresponding to the data transmission request includes: the cache information includes the cache hit rate, determining the usage parameters based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption, where the usage parameters are used to determine the target cached data; determining the compression ratio based on the processing energy consumption, the accuracy requirement, and the transmission delay requirement; determining the service policy based on the transmission delay requirement, the network condition information, the service type, and the data security requirement, where the network condition information includes at least one of the bandwidth utilization rate, network delay, and packet loss rate of the network slice.

[0010] In an embodiment of the present disclosure, determining the usage parameters based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption includes: determining the data ratio provided by the edge node based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption; determining the usage parameters based on the data ratio.

[0011] In an embodiment of the present disclosure, determining the compression ratio based on the processing energy consumption, the accuracy requirement, and the transmission delay requirement includes: evaluating the tolerance of the semantic compression based on the processing energy consumption to obtain an evaluation result; setting a compression ratio range based on the accuracy requirement; selecting the compression ratio from the compression ratio range based on the evaluation result and the transmission delay requirement.

[0012] In an embodiment of the present disclosure, determining the service policy based on the transmission delay requirement, the network condition information, the service type, and the data security requirement includes: adjusting the bandwidth utilization rate and the priority of the network slice based on the transmission delay requirement and the network delay; selecting a matching security policy based on the service type and the data security requirement; determining the service policy based on the adjustment result and the security policy.

[0013] In an embodiment of the present disclosure, the service policy of the network slice further includes an access control policy and a routing policy configured for the network slice.

[0014] In one embodiment of the present disclosure, the cache information includes a cache hit rate, and further includes: if the cache hit rate is lower than a hit rate threshold, detecting the access frequencies of different service types in historical transmission data; based on the LRU algorithm and / or the LUF algorithm, replacing the data of a first service type with a lower access frequency than a first frequency threshold with the data of a second service type with a higher access frequency than a second frequency threshold, where the second frequency threshold is greater than or equal to the first frequency threshold.

[0015] In one embodiment of the present disclosure, before configuring a compression ratio for semantic compression of transmission data, it further includes: performing semantic extraction and compression operations on the transmission data based on a deep learning model.

[0016] In one embodiment of the present disclosure, before configuring a compression ratio for semantic compression of transmission data, it further includes: instructing a core network device to create and manage the network slice based on software-defined network (SDN) and network function virtualization (NFV).

[0017] In one embodiment of the present disclosure, it further includes: inputting the transmission policy, the received transmission feedback information, and the network working condition information during the transmission process into a policy optimization model to dynamically optimize the transmission policy, where the policy optimization model is generated based on model training of reinforcement learning.

[0018] In one embodiment of the present disclosure, determining a corresponding transmission scenario and a network slice configured for the transmission scenario includes: detecting whether the edge node stores all the target request data required for the data transmission request; if the detection result is yes, instructing the edge node to transmit all the target request data to the user; if the detection result is no, determining the transmission scenario and the network slice.

[0019] In one embodiment of the present disclosure, before instructing the network slice to transmit target semantic data based on the compression ratio to the user and / or instructing the edge node to transmit target cache data to the user based on the transmission policy, it further includes: performing encryption processing on the semantic data and / or the target cache data.

[0020] According to another aspect of the present disclosure, there is provided a data transmission optimization system, including: a control and optimization module, configured to determine a corresponding transmission scenario in response to a user's data transmission request; a network slicing module, configured to configure a network slice for the transmission scenario; the control and optimization module is further configured to: determine a transmission target corresponding to the transmission scenario; the data transmission optimization system further includes: a semantic communication module, configured to perform semantic compression on transmission data; a caching module, configured to cache information at an edge node; the control and optimization module is further configured to: configure at least one of a compression ratio for performing semantic compression on the transmission data, a service policy of the network slice, and usage parameters of the cached information corresponding to the data transmission request based on the transmission target, monitored network condition information, and the cached information of the edge node, so as to generate a transmission policy based on the configuration result; the control and optimization module is further configured to: instruct the network slice to transmit target semantic data based on the compression ratio and / or instruct the edge node to transmit target cached data to the user based on the transmission policy, so as to generate target request data of the data transmission request based on the target semantic data and / or the target cached data.

[0021] According to still another aspect of the present disclosure, there is provided a network device, including: a processor; and a memory, configured to store executable instructions of the processor; the processor is configured to execute the data transmission optimization method of the first aspect above by executing the executable instructions.

[0022] According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the data transmission optimization method described above is implemented.

[0023] According to yet another aspect of the present disclosure, there is provided a computer program product, on which a computer program is stored, and when the computer program is executed by a processor, the data transmission optimization method described above is implemented.

[0024] The data transmission optimization solution provided by the embodiments of the present disclosure determines the transmission scenario by analyzing and identifying the user data transmission request, and configures a suitable network slice for it using network slicing, achieving the on-demand allocation of network resources. By combining the transmission scenario to determine the transmission target, the specific direction and requirements of data transmission are clarified. Based on the transmission target, network working condition information, and edge node cache information, semantic compression, network slice service strategy configuration, and cache information usage parameter configuration are used to generate an optimized data transmission strategy. By instructing the network slice and edge node to transmit data according to the transmission strategy, the target request data is generated. By dynamically selecting semantic communication and / or caching, the high data compression ratio advantage of semantic communication and the low latency advantage of caching are fully utilized, while reducing the accuracy loss of semantic communication and the storage resource consumption of caching, achieving efficient, low-power, and secure data transmission.

[0025] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and cannot limit the present disclosure. Brief Description of the Drawings

[0026] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0027] Figure 1 Show a flowchart of a data transmission optimization method in an embodiment of the present disclosure;

[0028] Figure 2 Show a flowchart of another data transmission optimization method in an embodiment of the present disclosure;

[0029] Figure 3 Show a flowchart of yet another data transmission optimization method in an embodiment of the present disclosure;

[0030] Figure 4 Show a flowchart of still another data transmission optimization method in an embodiment of the present disclosure;

[0031] Figure 5 Show a schematic diagram of a data transmission optimization system in an embodiment of the present disclosure;

[0032] Figure 6 Show a structural block diagram of a computer device in an embodiment of the present disclosure. Detailed Embodiments

[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments.

[0034] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0035] With the rapid development of 5G, the Internet of Things (IoT), and edge computing, the demand for data transmission has increased exponentially. The data transmission method faces problems such as insufficient bandwidth, high energy consumption, and large latency. As an emerging technology, semantic communication aims to achieve efficient data transmission. By extracting, encoding, and transmitting the semantics of data, the receiving end can recover content close to the meaning of the original data based on the received semantic information. Its core idea is to perform semantic understanding and processing on the data at the sending end, extract the key semantic information, and then compress and encode this semantic information and transmit it to the receiving end; the receiving end then reconstructs the semantic content of the original data based on the received semantic encoding and its own semantic knowledge. By extracting the semantic information of the data for transmission, it has the advantage of a high data compression ratio and can significantly reduce the amount of transmitted data. However, the disadvantage of semantic communication is that it will reduce the accuracy of data transmission and may affect the user experience, especially in scenarios where high data accuracy is required (such as medical image transmission, industrial control).

[0036] The caching technology can achieve fast data transmission and reduce latency by storing data in edge nodes close to users. However, the caching technology requires a large amount of storage resources, and the total amount of transmitted data is large, which may lead to increased energy consumption. In addition, the cached data may become invalid due to changes in user needs, resulting in waste of storage resources.

[0037] The network slicing technology can provide customized network services for different applications and ensure the security of data transmission by dividing network resources into multiple virtual networks. Currently, the collaborative advantages of network slicing, caching, and semantic communication have not been fully utilized, and the optimal transmission method cannot be dynamically selected according to user needs.

[0038] Therefore, how to combine the advantages of semantic communication, caching, and network slicing technologies, avoid their respective disadvantages, and design an intelligent data transmission system that can dynamically select the transmission method according to user needs has become an urgent problem to be solved.

[0039] Next, each step of the data transmission optimization method in this exemplary embodiment will be described in more detail with reference to the accompanying drawings and embodiments.

[0040] Figure 1 The flowchart of a data transmission optimization method in an embodiment of the present disclosure is shown.

[0041] As Figure 1 shown, according to an embodiment of the present disclosure, the data transmission optimization method includes:

[0042] Step S102, in response to the obtained user data transmission request, determine the corresponding transmission scenario and the network slice configured for the transmission scenario.

[0043] In some embodiments, the user data transmission request may include the data type requested (such as text, image, video, etc.), the application used (such as instant messaging, video conferencing, file transfer, etc.), and the network environment where the user is located. By analyzing and identifying this information, different transmission scenarios can be determined, such as a video call scenario with high real-time requirements, a medical data transmission scenario with high data accuracy requirements, etc.

[0044] In some embodiments, network slicing technology divides physical network resources into multiple virtual and isolated network slices, and each slice can be customized according to different transmission scenario requirements.

[0045] Step S104, determine the transmission target corresponding to the transmission scenario.

[0046] In some embodiments, the transmission scenario determines the characteristics and requirements of data transmission. Based on the service type (such as entertainment, finance, industrial control, etc.) and data requirements (accuracy requirements, transmission delay requirements, security requirements, etc.) determined by the transmission scenario, the goals that data transmission needs to achieve can be clarified. Different service types have different focuses on data transmission. For example, entertainment services may pay more attention to the smoothness and low latency of transmission, while financial services have extremely high requirements for data security and accuracy. Data requirements further refine the specific indicators of transmission. By combining these factors, the transmission target that meets the transmission scenario can be determined, providing a clear direction for formulating subsequent data transmission strategies.

[0047] Step S106, based on the transmission target, the monitored network working condition information, and the cache information of the edge node, configure at least one of the compression ratio for semantic compression of the transmission data, the service policy of the network slice, and the usage parameters of the cache information corresponding to the data transmission request, so as to generate a transmission policy based on the configuration result.

[0048] In some embodiments, the transmission target defines the expected result of data transmission, the network working condition information reflects the actual operating state of the current network (such as bandwidth utilization, network latency, packet loss rate, etc.), and the cache information of the edge node reflects the storage and usage conditions of the data in the cache (such as cache hit rate, timeliness of the cached data, etc.).

[0049] In some embodiments, semantic compression is performed by extracting the semantic information of the data for compression to reduce the amount of data transmission. According to the requirements of the transmission target, combined with the network working conditions and cache information, the compression ratio of semantic compression can be reasonably configured to optimize the amount of data transmission while ensuring data accuracy and transmission efficiency.

[0050] In some embodiments, for the service policy of the network slice, according to the network working conditions and the transmission target, the bandwidth allocation, priority setting, etc. of the network slice can be adjusted to meet the requirements of different services. In some embodiments, the configuration of the usage parameters of the cache information determines how to utilize the cached data according to the cache situation and the transmission target, such as determining the proportion of data obtained from the cache. Combining these configuration results, a comprehensive transmission policy is generated to achieve efficient and high-quality data transmission.

[0051] Step S108, based on the transmission policy, instruct the network slice to transmit the target semantic data obtained based on the compression ratio to the user and / or instruct the edge node to transmit the target cached data to the user, so as to generate the target request data of the data transmission request based on the target semantic data and / or the target cached data.

[0052] In some embodiments, the network slice transmits the target semantic data obtained by semantic compression to the user according to the instruction of the transmission policy, realizing the effective transmission of data.

[0053] In some embodiments, if there is target cached data that meets the requirements in the edge node cache, it will also be transmitted to the user according to the instruction of the transmission policy. Through these two methods, finally, the target request data that meets the user's data transmission request is generated based on the target semantic data and / or the target cached data, completing the data transmission process and realizing the user's requirements.

[0054] In some embodiments, in some simplified implementation scenarios, when the user has a low requirement for data transmission accuracy, semantic communication is preferentially used; when the user has a high requirement for data transmission latency, caching is preferentially used; and when the user has high requirements for both data transmission accuracy and latency, semantic communication and caching are combined.

[0055] In this embodiment, by analyzing and identifying the transmission scenario of the user data transmission request and using network slicing to configure a suitable network slice for it, the on-demand allocation of network resources is achieved. By combining the transmission scenario to determine the transmission target, the specific direction and requirements of data transmission are clarified. Based on the transmission target, network working condition information, and edge node cache information, semantic compression, network slice service strategy configuration, and cache information usage parameter configuration are used to generate an optimized data transmission strategy. By instructing the network slice and edge node to transmit data according to the transmission strategy, the target request data is generated. By dynamically selecting semantic communication and / or caching, the advantages of the high data compression ratio of semantic communication and the low latency advantage of caching are fully utilized, while reducing the accuracy loss of semantic communication and the storage resource consumption of caching, thus achieving efficient, low-power, and secure data transmission.

[0056] As Figure 2 shown, in an embodiment of the present disclosure, determining the transmission target corresponding to the transmission scenario includes:

[0057] Step S202, determining the service type and data requirements of the data transmission request based on the transmission scenario, where the data requirements include at least one of accuracy requirements, transmission delay requirements, and security requirements.

[0058] Among them, the data transmission accuracy requirement is used to clarify the specific requirements for data accuracy in the transmission target, such as whether a certain degree of compression loss is allowed, whether the original accuracy of the data needs to be maintained, etc.

[0059] The data transmission delay requirement is used to determine the maximum data transmission delay time allowed by the transmission target, which will directly affect the subsequent configuration of the network slice and semantic compression ratio.

[0060] The data security requirement is used to determine the requirements for data security in the transmission target, such as whether encrypted transmission is required, whether there are specific security protocols, etc.

[0061] The data volume requirement refers to the expectation for the data volume in the transmission target, such as whether it is desired to minimize the transmitted data volume to save bandwidth, etc.

[0062] The service type is determined according to the transmission scenario. Different service types have specific characteristics for transmission requirements. For example, real-time services (such as video calls and online games) have extremely high requirements for low latency, while file transfer services may pay more attention to data integrity and accuracy.

[0063] In some embodiments, different transmission scenarios correspond to different service types, such as video streaming, file downloading, real-time data monitoring, etc. Each service type has specific requirements for data. The accuracy requirement determines the acceptable error range during data transmission and processing. The transmission delay requirement is related to the real-time experience of the service. For example, real-time video calls have very high delay requirements, while ordinary file downloads have relatively low delay requirements. Security requirements involve aspects such as data confidentiality, integrity, and availability. For example, the transmission of financial transaction data requires extremely high security.

[0064] Determine the transmission target based on the business type and data requirements.

[0065] In one embodiment of the present disclosure, an implementation method for determining a transmission target based on a service type and data requirements includes:

[0066] Step S204: monitoring the processing energy consumption generated based on the data transmission optimization.

[0067] In some embodiments, processing energy consumption refers to the energy consumption generated by various devices performing data processing, storage, forwarding and other operations during the data transmission optimization process.

[0068] Step S206, determining a transmission target based on a balanced configuration of processing energy consumption, service type, and data requirements.

[0069] In some embodiments, the energy consumption of the system is optimized through an energy consumption model. For example, the power consumption of cache nodes is reduced during low-load periods. For example, during low-load periods at night, some cache nodes are set to sleep mode to reduce energy consumption.

[0070] In some embodiments, a deep learning-based energy consumption prediction model can also be used, which can predict system energy consumption and optimize resource allocation according to network status and user needs. For example, during peak hours, the cache strategy and semantic compression ratio can be dynamically adjusted according to the prediction results to reduce system energy consumption.

[0071] In some embodiments, the service type and data requirements determine the basic goals and quality bottom line of data transmission. For example, high-precision services must ensure data accuracy, and real-time services must meet strict delay thresholds. Processing energy consumption is the resource cost required to achieve these goals. The transmission target is determined based on the balanced configuration of the three to determine the balance point. While meeting the service type and data requirements, the processing energy consumption is reduced as much as possible, or the business needs are guaranteed within the energy consumption limit.

[0072] In this embodiment, by determining the service type and data requirements based on the transmission scenario, and combining the processing energy consumption information during the data transmission optimization process obtained by using real-time monitoring technology, a multi-dimensional collaborative decision-making mechanism is constructed based on the processing energy consumption, service type, and data requirements for balanced configuration, so as to consider resource consumption starting from business requirements, achieve dynamic balance of multiple objectives, enable data transmission to meet the requirements of different services for accuracy, latency, and security as much as possible, and at the same time achieve control of the processing energy consumption, thereby facilitating the improvement of the comprehensive efficiency of data transmission.

[0073] In an embodiment of the present disclosure, based on the transmission target, the monitored network condition information, and the cache information of the edge node, at least one of the compression ratio for semantically compressing the transmitted data, the service policy of the network slice, and the usage parameters of the cache information corresponding to the data transmission request is configured, including:

[0074] The cache information includes the cache hit rate. The usage parameters are determined based on the cache hit rate, service type, accuracy requirement, and processing energy consumption, and the usage parameters are used to determine the target cached data.

[0075] In some embodiments, the cache hit rate reflects the usage efficiency of the cache. A higher hit rate means that the data in the cache can frequently meet user requests. Different service types have different degrees of dependence on and usage methods of the cache. The accuracy requirement determines whether the data obtained from the cache can meet the service's requirements for data quality. The processing energy consumption is also an important consideration factor because frequently reading or updating data from the cache will also consume a certain amount of energy. Therefore, it is necessary to optimize the use of the cache as much as possible to reduce energy consumption on the premise of ensuring business requirements. By comprehensively considering these factors to determine the usage parameters, the cache resources can be reasonably utilized according to different business scenarios and requirements, improving the efficiency and quality of data transmission while reducing energy consumption.

[0076] The compression ratio is determined based on the processing energy consumption, accuracy requirement, and transmission latency requirement.

[0077] In some embodiments, the higher the semantic compression ratio, the worse the semantic data accuracy. Reasonably adjusting the compression ratio can reduce the energy consumption of data processing and transmission on the premise of meeting a certain accuracy requirement. For services with not extremely high requirements for data accuracy, such as ordinary text messages, social media short videos, etc., appropriately increasing the semantic compression ratio can reduce the data volume. The smaller data volume occupies less network bandwidth during transmission, reducing the transmission energy consumption of network devices.

[0078] In some embodiments, the processes of semantic compression and decompression take a certain amount of time, which is related to the compression ratio. The higher the compression ratio, the longer the compression and decompression times. It is necessary to determine the data transmission delay requirements according to the network environment and device performance. For some services with extremely high real-time requirements, such as real-time video calls and online games, it is necessary to ensure the real-time transmission of data, even if the compression ratio is low. For some services with low real-time requirements, such as file transfer and email, the compression ratio can be appropriately increased to reduce the data transmission volume and processing energy consumption.

[0079] Determine the service policy based on the transmission delay requirements, network operating conditions information, service type, and data security requirements. The network operating conditions information includes at least one of the bandwidth utilization rate, network delay, and packet loss rate of the network slice.

[0080] In some embodiments, different service types have different tolerances for transmission delay. The network operating conditions information (including the bandwidth utilization rate, network delay, packet loss rate, etc. of the network slice) reflects the actual operating state of the current network. In addition, the service type also affects the formulation of the service policy. For example, real-time services require a more stable and low-latency network service, while services with high data security requirements require enhanced security protection measures for the network slice, such as encryption and access control. Considering these factors comprehensively, it is possible to formulate a personalized service policy according to the actual situation of the network and the needs of the service.

[0081] In this embodiment, by determining the cache usage parameters based on the cache hit rate, service type, accuracy requirements, and processing energy consumption, it is possible to rationally utilize the cache resources according to different service scenarios and requirements. By determining the compression ratio based on the processing energy consumption, accuracy requirements, and transmission delay requirements, it is possible to flexibly adjust the data compression policy under different service requirements and energy consumption limitations, and balance the relationship between data transmission in terms of energy consumption, accuracy, and delay. By determining the service policy based on the transmission delay requirements, network operating conditions information, service type, and data security requirements, it is possible to dynamically optimize the service parameters of the network slice according to the real-time state of the network and the characteristics of the service, provide customized network services for different services, ensure the security and efficiency of data transmission, and improve the quality and efficiency of data transmission, reduce energy consumption, ensure data security, thereby enhancing the performance and reliability of the entire data transmission system.

[0082] In an embodiment of the present disclosure, determining the usage parameters based on the cache hit rate, service type, accuracy requirements, and processing energy consumption includes:

[0083] Determine the data ratio provided by the edge node based on the cache hit rate, service type, accuracy requirements, and processing energy consumption; determine the usage parameters based on the data ratio.

[0084] In some embodiments, the cache hit rate characterizes the availability of cached data at the edge node. Different service types have different requirements for data transmission characteristics. Services with high-precision requirements, such as financial transaction data and medical image transmission, have extremely high requirements for data accuracy and integrity. Processing data at the edge node consumes energy. If the processing energy consumption is too high, even if the cache hit rate is high, it is necessary to control the data supply ratio.

[0085] In some embodiments, the data ratio clarifies the status of the edge node in data supply. Based on this, usage parameters can be set specifically. If the data ratio of the edge node is high, the cache update strategy can be optimized to improve the freshness of the cached data, such as shortening the update period of the cached data and adopting a more efficient cache replacement algorithm, etc.

[0086] In this embodiment, by constructing a decision structure with the cache hit rate, service type, precision requirement, and processing energy consumption as input variables, the edge node data ratio as the intermediate calculation result, and the usage parameters as the final output, the data acquisition path is dynamically allocated according to the cache hit rate, the best transmission strategy is matched using the characteristics of the service type, the data quality bottom line is guaranteed based on the precision requirement, and the resource utilization efficiency is optimized in combination with the processing energy consumption, so as to meet the timeliness and accuracy requirements of data transmission in different service scenarios, reasonably control the energy consumption and load of the edge node, reduce network resource waste, and improve the overall performance and stability of the data transmission system.

[0087] In an embodiment of the present disclosure, determining the compression ratio based on the processing energy consumption, precision requirement, and transmission delay requirement includes:

[0088] Evaluating the tolerance of semantic compression based on the processing energy consumption to obtain an evaluation result; setting a compression ratio range based on the precision requirement; and selecting a compression ratio from the compression ratio range based on the evaluation result and the transmission delay requirement.

[0089] In some embodiments, the semantic compression process requires the device to perform a series of data processing operations, such as feature extraction, encoding, etc. Different devices or systems have different processing capabilities and energy consumption limitations. If the processing capacity of the device is limited or there are strict requirements for energy consumption, then the semantic compression complexity it can withstand is relatively low.

[0090] In some embodiments, the precision requirement refers to the accuracy that the data needs to retain after semantic compression. For some services with extremely high precision requirements, such as medical image diagnosis and financial transaction data, the compression ratio cannot be too high, otherwise it will cause important information loss in the data and affect the normal operation of the service. For some services with relatively low precision requirements, such as text messages on social media and ordinary video previews, the compression ratio can be appropriately increased. Therefore, a reasonable compression ratio range can be determined according to the specific precision requirement.

[0091] In this embodiment, the evaluation result reflects the tolerance of the device or system to semantic compression in terms of energy consumption, while the transmission delay requirement reflects the demand of the service for data transmission speed. By comprehensively considering these two factors to select a specific compression ratio from the compression ratio range set based on the accuracy requirement, it is beneficial to ensure the reliability of the obtained semantic compression ratio.

[0092] As Figure 3 shown, in an embodiment of the present disclosure, a service policy is determined based on the transmission delay requirement, network working condition information, service type, and data security requirement, including:

[0093] Step S302, adjust the bandwidth utilization rate and the priority of network slices based on the transmission delay requirement and network delay.

[0094] In some embodiments, when the network delay is high, the bandwidth for services with high transmission delay requirements can be appropriately increased to improve their bandwidth utilization rate and shorten the transmission time.

[0095] In some embodiments, by adjusting the priority of network slices, it is possible to ensure that services with high transmission delay requirements preferentially use network resources, reduce their queuing waiting time in the network, and thus reduce the transmission delay.

[0096] Step S304, select a matching security policy based on the service type and data security requirement.

[0097] In some embodiments, different service types have different requirements for data security. Data security requirements include data confidentiality, integrity, and availability, etc. According to the service type and data security requirement, a matching security policy can be selected, including encryption algorithms, access control mechanisms, identity authentication, etc.

[0098] Step S306, determine the service policy based on the adjustment result and the security policy.

[0099] In some embodiments, an independent security policy is configured for each network slice, including access control, data encryption, and privacy protection. For example, in the financial data transmission slice, the AES-256 encryption algorithm is used to ensure data security.

[0100] In this embodiment, by adjusting the bandwidth utilization rate and the priority of network slices based on the transmission delay requirement and network delay, selecting a matching security policy based on the service type and data security requirement, and combining the two to determine the service policy, it is realized that in a complex network environment, the network resource allocation and security protection measures can be dynamically adjusted according to the characteristics and requirements of different services, so as to provide customized network services for the services.

[0101] In one embodiment of the present disclosure, the service policy of the network slice further includes an access control policy and a routing policy configured for the network slice.

[0102] In this embodiment, by configuring an access control policy and a routing policy for the network slice, the access control policy can strictly limit the users, devices, or application programs that can access the network slice, effectively prevent unauthorized access, enhance the security of the network slice, and protect the data transmitted therein from being illegally obtained or tampered with. The routing policy, on the other hand, can plan the optimal path for data transmission according to factors such as network conditions and service requirements, reduce transmission latency and packet loss rate, and improve the efficiency and reliability of data transmission.

[0103] In one embodiment of the present disclosure, the cache information includes the cache hit rate, and further includes: if the cache hit rate is lower than the hit rate threshold, detecting the access frequencies of different service types in the historical transmission data; based on the LRU algorithm and / or the LUF algorithm, replacing the data of the first service type with a lower access frequency than the first frequency threshold with the data of the second service type with a higher access frequency than the second frequency threshold, where the second frequency threshold is greater than or equal to the first frequency threshold.

[0104] In this embodiment, when the cache hit rate is low, it means that the utilization rate of the cache is not high. By detecting the access frequencies, it can accurately identify which service type of data is frequently accessed and which is rarely accessed. Using the LRU (Least Recently Used) algorithm and / or the LUF (Least Frequently Used) algorithm for data replacement can ensure that the most valuable and most likely to be accessed again data is stored in the cache, which is beneficial to improving the cache hit rate, reducing the time to obtain data from remote locations, enhancing the data access speed, and optimizing the technical effect of the cache resource utilization efficiency.

[0105] In one embodiment of the present disclosure, before configuring the compression ratio for semantic compression of the transmission data, it further includes: performing semantic extraction and compression operations on the transmission data based on a deep learning model.

[0106] In this embodiment, by applying the deep learning model to the semantic extraction and compression operations of the transmission data, in the semantic compression link, the deep learning model can perform differential processing according to the importance degree of data semantics, effectively reducing the accuracy loss while achieving a high compression ratio.

[0107] In one embodiment of the present disclosure, before configuring the compression ratio for semantic compression of the transmission data, it further includes: instructing the core network device to create and manage network slices based on software-defined network (SDN) and network function virtualization (NFV).

[0108] In this embodiment, by instructing the core network device to create and manage network slices based on software-defined network (SDN) and network function virtualization (NFV), SDN separates the control plane and data plane of the network, enabling network administrators to flexibly configure and manage the network through a centralized controller. NFV decouples network functions from dedicated hardware devices and runs them in software form on general-purpose servers, reducing the cost and complexity of network devices.

[0109] In an embodiment of the present disclosure, it further includes: inputting a transmission policy, received transmission feedback information, and network condition information during the transmission process into a policy optimization model to dynamically optimize the transmission policy, and the policy optimization model is generated based on model training of reinforcement learning.

[0110] In this embodiment, by inputting a transmission policy, received transmission feedback information, and network condition information during the transmission process into a policy optimization model generated based on reinforcement learning training to dynamically optimize the transmission policy, the reinforcement learning model can learn the effects of different transmission policies in different environments according to the continuously input feedback information and network condition information, realizing that the transmission policy can be dynamically adjusted according to the real-time network conditions and service requirements to improve the optimization effect of data transmission.

[0111] In an embodiment of the present disclosure, determining a corresponding transmission scenario and the network slice configured for the transmission scenario includes: detecting whether the edge node stores all the target request data required for the data transmission request; if the detection result is yes, instructing the edge node to transmit all the target request data to the user; if the detection result is no, determining the transmission scenario and the network slice.

[0112] In this embodiment, by detecting whether the edge node stores all the target request data required for the data transmission request, when the edge node stores all the target request data, it is directly instructed to transmit it to the user, preventing unnecessary network overhead and delay and improving the speed of data transmission. If the edge node does not store all the data, the transmission scenario and the network slice are further determined, and the most suitable network resources and policies can be selected for data transmission according to the specific situation to optimize the data transmission path and throughput.

[0113] In an embodiment of the present disclosure, before instructing the network slice to transmit target semantic data obtained based on the compression ratio and / or instructing the edge node to transmit target cache data to the user based on the transmission policy, it further includes: encrypting the slogan semantic data and / or the target cache data.

[0114] In some embodiments, encrypting the semantic information before transmission ensures the security of data transmission. For example, in medical data transmission, encrypting the extracted semantic information to prevent data leakage.

[0115] In some embodiments, encryption technology is adopted when storing data to ensure the security of cached data. For example, in video streaming services, the cached video content is encrypted to prevent illegal access.

[0116] In this embodiment, the target semantic data and / or target cached data are encrypted. The encryption process can convert the data into ciphertext form to effectively protect the confidentiality and integrity of the data.

[0117] In some embodiments, in the scenario of selecting semantic communication, when the user has a low requirement for data transmission accuracy (such as text transmission, voice communication), semantic communication is preferentially used; when the network bandwidth resource is tight, semantic communication is preferentially used to reduce bandwidth occupancy; in instant messaging applications, the semantic information of the text is extracted and compressed, significantly reducing the amount of transmitted data to achieve dynamic adjustment of the transmission strategy.

[0118] In some embodiments, in the scenario of selecting caching, when the user has a high requirement for data transmission latency (such as real-time video stream, online game), caching is preferentially used; when the data access frequency is high and the data volume is large, caching is preferentially used to reduce the overhead of repeated transmission; in online games, common game resources are cached at edge nodes to achieve fast loading.

[0119] In some embodiments, in the scenario of selecting the combination of semantic communication and caching, when the user has high requirements for both data transmission accuracy and latency, semantic communication and caching are combined. For example, semantic information is cached at edge nodes, which not only reduces the amount of transmitted data but also reduces latency; when both network bandwidth and storage resources are limited, semantic communication and caching are combined to optimize resource utilization; in an intelligent transportation system, the semantic information of traffic data is cached at edge nodes, which not only reduces the amount of transmitted data but also enables fast response.

[0120] As Figure 4 shown, a data transmission optimization method according to another embodiment of the present disclosure includes:

[0121] Step S402, calculating the costs and gains of different semantic communications and the extraction of cached data transmission respectively.

[0122] Among them, for semantic communication, during the execution of semantic communication, certain computing resources are required to perform operations such as semantic extraction, encoding, and compression of data. The main gain of semantic communication lies in its high data compression ratio, which can significantly reduce the amount of transmitted data.

[0123] For the extraction cache data transmission, the cost of the extraction cache data transmission is mainly related to cache management. If the cache hit rate is low and data is frequently searched in the cache but not found, it will increase the latency of data access. The gain of the extraction cache data transmission lies in its low-latency feature.

[0124] Step S404, in response to the obtained user data transmission request, determine the corresponding transmission scenario, the network slice configured for the transmission scenario, and the transmission target corresponding to the transmission scenario.

[0125] Step S406, configure the allocation ratio of semantic communication and extraction cache data transmission based on the transmission target, cost, and gain.

[0126] In some embodiments, after determining the transmission target and the costs and gains of different transmission methods (semantic communication and extraction cache data transmission), the allocation ratio of the two transmission methods is reasonably configured according to this information. For example, if the transmission target is to achieve low-latency transmission while ensuring a certain data accuracy, and the current network bandwidth is limited, and the cache hit rate is high, the proportion of extraction cache data transmission can be increased to make full use of the low-latency advantage of the cache, and at the same time, the proportion of semantic communication can be appropriately reduced to prevent excessive computational cost and accuracy loss. On the contrary, if the transmission target has a high requirement for the data compression ratio and the cache hit rate is low, the proportion of semantic communication may be increased to achieve a high data compression ratio and reduce the amount of data transmission.

[0127] Step S408, perform data transmission based on the configuration result.

[0128] In some embodiments, perform data transmission operations based on the configuration result. During the actual transmission process, the data will be transmitted through semantic communication and extraction cache data transmission respectively according to the allocation ratio, and finally the data will be transmitted to the user side to meet the user's data transmission request and achieve the transmission target.

[0129] It should be noted that the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the time sequence of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0130] Next, refer to Figure 5 to describe the data transmission optimization system 500 according to the embodiments of the present invention. Figure 5 The data transmission optimization system 500 shown is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present invention.

[0131] The data transmission optimization system 500 is presented in the form of a hardware module. The components of the data transmission optimization system 500 may include but are not limited to: a control and optimization module 502 for determining a corresponding transmission scenario in response to the acquired user data transmission request; a network slicing module 504 for configuring a network slice for the transmission scenario; the control and optimization module 502 is further configured to: determine a transmission target corresponding to the transmission scenario; the data transmission optimization system further includes: a semantic communication module 506 for semantically compressing the transmission data; a caching module 508 for caching information at the edge node; the control and optimization module 502 is further configured to: configure at least one of a compression ratio for semantically compressing the transmission data, a service policy for the network slice, and usage parameters for the cached information corresponding to the data transmission request based on the transmission target, monitored network operating conditions information, and cached information of the edge node, so as to generate a transmission policy based on the configuration result; the control and optimization module 502 is further configured to: instruct the network slice to transmit target semantic data based on the compression ratio and / or instruct the edge node to transmit target cached data to the user based on the transmission policy, so as to generate target request data for the data transmission request based on the target semantic data and / or the target cached data.

[0132] In some embodiments, the control and optimization module 502 may be integrated into the control server of the core network, the network slicing module 504 is deployed on the core network device and the control plane device related to the network slice, the semantic communication module 506 may be deployed on the node device close to the data source or the data transmission path, and the caching module 508 is mainly concentrated on the edge node device.

[0133] In some embodiments, the network slicing module 504 is used to divide network resources into multiple virtual network slices, and each slice provides customized network services for specific users or applications.

[0134] In some embodiments, software-defined network (SDN) and network function virtualization (NFV) technologies are used to implement the dynamic creation and management of network slices.

[0135] In some embodiments, an independent security policy is configured for each network slice, including access control, data encryption, and privacy protection. For example, a high-strength encryption algorithm and strict access control policy are configured for the medical data transmission slice.

[0136] In some embodiments, in a 5G network, an independent network slice is created for industrial Internet of Things (IoT) devices to ensure low latency and high reliability.

[0137] In some embodiments, the semantic communication module 506 is used to extract semantic information of the data and compress it to reduce the amount of transmission data.

[0138] In some embodiments, a Transformer-based deep learning model is used for semantic extraction and compression.

[0139] In some embodiments, the compression ratio is dynamically adjusted according to user requirements. For example, in a text transmission scenario, the compression ratio can be as high as 90%, while in a medical image transmission scenario, the compression ratio is reduced to 50% to ensure accuracy.

[0140] In some embodiments, in voice communication, semantic information (such as text content) of the voice is extracted and compressed, significantly reducing the amount of transmitted data.

[0141] In some embodiments, the cache module 508 is used to store frequently used data or semantic information at the edge node, reducing the data transmission distance and latency.

[0142] In some embodiments, a distributed cache system is deployed at the edge node, and the LRU (Least Recently Used) algorithm is used to optimize the cache replacement policy.

[0143] In some embodiments, the cache content is dynamically adjusted according to the data access frequency. For example, popular video content is cached at the edge node to reduce the overhead of repeated transmission.

[0144] In some embodiments, in video streaming services, frequently watched video segments of users are cached at the edge node to achieve fast loading.

[0145] In some embodiments, the control and optimization module 502 is used to coordinate the work of network slicing, semantic communication, and the cache module, optimizing the data transmission path, resource allocation, and energy consumption management.

[0146] In some embodiments, an optimization algorithm based on reinforcement learning is used to analyze the network state and user behavior in real time, dynamically adjusting system parameters.

[0147] In some embodiments, the system energy consumption is optimized through an energy consumption model. For example, the power consumption of the cache node is reduced during low load periods.

[0148] In some embodiments, when the network is congested, semantic communication is preferentially used to reduce bandwidth occupancy; when the network is idle, the cache is preferentially used to reduce latency.

[0149] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, method, or program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0150] The following refers toFigure 6 Describe the electronic device 600 according to this embodiment of the present invention. It can be a network device or a terminal. Figure 6 The shown electronic device 600 is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0151] As Figure 6 shown, the electronic device 600 is presented in the form of a general computing device. The components of the electronic device 600 may include but are not limited to: the above-mentioned at least one processing unit 610, the above-mentioned at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).

[0152] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification. For example, the processing unit 610 can execute as Figure 1 described in the solution.

[0153] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0154] The storage unit 620 may further include a program / utility 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0155] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0156] The electronic device 600 can also communicate with one or more external devices 670 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. As shown in the figure, the network adapter 660 communicates with other modules of the electronic device 600 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0157] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0158] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which a program product capable of implementing the above method of this specification is stored. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on an electronic device, the program code is used to enable the electronic device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0159] The program product for implementing the above method according to the embodiments of the present invention can adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can run on an electronic device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

[0160] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0162] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0163] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0164] It should be noted that although several modules or units of devices for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by a plurality of modules or units.

[0165] In addition, although the various steps of the methods in the present disclosure are described in a specific order in the accompanying drawings, this is not a requirement or implication that these steps must be performed in that specific order, or that all of the steps shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0166] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of the present disclosure.

[0167] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

Claims

1. A data transmission optimization method, characterized in that, An application network device includes: In response to a user's data transmission request obtained, determining a corresponding transmission scenario and a network slice configured for the transmission scenario; Determining a transmission target corresponding to the transmission scenario; Based on the transmission target, monitored network working condition information, and cache information of an edge node, configuring at least one of a compression ratio for semantically compressing transmission data, a service policy of the network slice, and usage parameters of cache information corresponding to the data transmission request, so as to generate a transmission policy based on the configuration result; Based on the transmission policy, instructing the network slice to transmit target semantic data obtained based on the compression ratio to the user and / or instructing the edge node to transmit target cache data to the user, so as to generate target request data of the data transmission request based on the target semantic data and / or the target cache data.

2. The data transmission optimization method according to claim 1, wherein Determining a transmission target corresponding to the transmission scenario includes: Based on the transmission scenario, determining a service type and data requirements of the data transmission request, where the data requirements include at least one of an accuracy requirement, a transmission delay requirement, and a security requirement; Based on the service type and the data requirements, determining the transmission target.

3. The data transmission optimization method according to claim 2, wherein Based on the service type and the data requirements, determining the transmission target includes: Monitoring processing energy consumption generated based on the data transmission optimization; Based on an equilibrium configuration of the processing energy consumption, the service type, and the data requirements, determining the transmission target.

4. The data transmission optimization method according to claim 3, wherein Based on the transmission target, monitored network working condition information, and cache information of an edge node, configuring at least one of a compression ratio for semantically compressing transmission data, a service policy of the network slice, and usage parameters of cache information corresponding to the data transmission request includes: The cache information includes a cache hit rate. Based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption, determining the usage parameters, where the usage parameters are used to determine the target cache data; Based on the processing energy consumption, the accuracy requirement, and the transmission delay requirement, determining the compression ratio; Based on the transmission delay requirement, the network working condition information, the service type, and a data security requirement, determining the service policy, where the network working condition information includes at least one of a bandwidth utilization rate, a network delay, and a packet loss rate of the network slice.

5. The data transmission optimization method according to claim 4, wherein Based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption, determining the usage parameters includes: Based on the cache hit rate, the service type, the accuracy requirement, and the processing energy consumption, determining a data ratio provided by the edge node; Based on the data ratio, determining the usage parameters.

6. The data transmission optimization method according to claim 4, wherein Based on the processing energy consumption, the accuracy requirement, and the transmission delay requirement, determining the compression ratio includes: Based on the processing energy consumption, evaluating the tolerance of the semantic compression to obtain an evaluation result; Based on the accuracy requirement, setting a compression ratio range; Based on the evaluation result and the transmission delay requirement, selecting the compression ratio from the compression ratio range.

7. The data transmission optimization method according to claim 4, wherein Determine the service policy based on the transmission delay requirement, the network working condition information, the service type, and the data security requirement, including: Adjust the bandwidth utilization rate and the priority of the network slice based on the transmission delay requirement and the network latency; Select a matching security policy based on the service type and the data security requirement; Determine the service policy based on the adjustment result and the security policy.

8. The data transmission optimization method according to claim 7, wherein The service policy of the network slice also includes an access control policy and a routing policy configured for the network slice.

9. The data transmission optimization method according to claim 1, wherein The cache information includes the cache hit rate, and also includes: If the cache hit rate is lower than the hit rate threshold, detect the access frequencies of different service types in the historical transmission data; Based on the LRU algorithm and / or the LUF algorithm, replace the data of the first service type with a lower access frequency than the first frequency threshold with the data of the second service type with a higher access frequency than the second frequency threshold, where the second frequency threshold is greater than or equal to the first frequency threshold.

10. The data transmission optimization method according to claim 1, wherein Before configuring the compression ratio for semantic compression of the transmission data, it also includes: Perform semantic extraction and compression operations on the transmission data based on a deep learning model.

11. The data transmission optimization method according to claim 1, wherein Before configuring the compression ratio for semantic compression of the transmission data, it also includes: Instruct the core network device to create and manage the network slice based on software-defined network (SDN) and network function virtualization (NFV).

12. The data transmission optimization method according to claim 1, wherein It also includes: Input the transmission policy, the received transmission feedback information, and the network working condition information during the transmission process into a policy optimization model to dynamically optimize the transmission policy, where the policy optimization model is generated based on model training of reinforcement learning.

13. The data transmission optimization method according to claim 1, wherein Determine the corresponding transmission scenario and the network slice configured for the transmission scenario, including: Detect whether the edge node stores all the target request data required for the data transmission request; If the detection result is yes, instruct the edge node to transmit all the target request data to the user; If the detection result is no, determine the transmission scenario and the network slice.

14. The data transmission optimization method according to claim 1, wherein Before instructing the network slice to transmit the target semantic data based on the compression ratio to the user and / or instructing the edge node to transmit the target cache data to the user based on the transmission policy, it also includes: Perform encryption processing on the semantic data and / or the target cache data.

15. A data transmission optimization system, characterized in that, It includes: A control and optimization module, configured to determine the corresponding transmission scenario in response to the acquired data transmission request of the user; A network slice module, configured to configure the network slice for the transmission scenario; The control and optimization module is further configured to: determine the transmission target corresponding to the transmission scenario; The data transmission optimization system further includes: a semantic communication module, configured to perform semantic compression on the transmission data; A cache module, configured to cache information at the edge node; The control and optimization module is further configured to: configure at least one of the compression ratio for semantic compression of the transmission data, the service policy of the network slice, and the usage parameters of the cache information corresponding to the data transmission request based on the transmission target, the monitored network working condition information, and the cache information of the edge node, so as to generate a transmission policy based on the configuration result; The control and optimization module is further configured to: based on the transmission policy, instruct the network slice to transmit target semantic data obtained based on the compression ratio to the user and / or instruct the edge node to transmit target cached data to the user, so as to generate target request data of the data transmission request based on the target semantic data and / or the target cached data.

16. A network device, characterized in that, Comprising: A processor; And A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the data transmission optimization method according to any one of claims 1 to 14 by executing the executable instructions.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the data transmission optimization method according to any one of claims 1 to 14.

18. A computer program product, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the data transmission optimization method according to any one of claims 1 to 14.

Images