Wireless interface protocol stack architecture for AI service enhancement and data transmission method

Abstract

The invention provides a wireless interface protocol stack architecture for AI service enhancement and a data transmission method. The architecture comprises a wireless bearer; the radio bearer comprises a signaling bearer and a data bearer; the signaling bearer comprises a first signaling bearer and a second signaling bearer; the data bearer comprises a first data bearer and a second data bearer; the first signaling bearing is used for transmitting signaling information corresponding to the communication service; the second signaling bearing is used for transmitting signaling information corresponding to the artificial intelligence service; the first data bearer is used for transmitting data corresponding to the communication service; the second data bearer is used for transmitting data corresponding to the artificial intelligence service. According to the embodiment of the invention, the signaling and data of different services are transmitted by using different bearers, so that corresponding connection control and data transmission support can be provided for the artificial intelligence service in a targeted manner, and the data corresponding to the artificial intelligence service can be transmitted efficiently.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a wireless interface protocol stack architecture and a data transmission method for AI service enhancement. Background Art

[0002] With the development of computer technology and communication technology, AI-related applications inevitably need to interact with the network side during use. When AI-related applications transmit data, the data scale involved is large, and people have high requirements for instant response of AI-related applications.

[0003] When it comes to data transmission for AI-related applications, the design of traditional access network protocol stacks does not differentiate between data transmission for AI-related applications and traditional communication services, resulting in large data delays for AI-related applications, making it difficult to meet the needs of AI-related applications, and causing a decline in user service quality. Summary of the invention

[0004] The present disclosure proposes a wireless interface protocol stack architecture and a data transmission method for AI service enhancement to solve the problem that data delay for AI-related applications in related technologies is large and the needs of AI-related applications are difficult to meet, resulting in a decrease in user service quality.

[0005] The first aspect of the present disclosure provides a wireless interface protocol stack architecture for AI service enhancement, the architecture comprising:

[0006] Radio bearer;

[0007] The radio bearer includes a signaling bearer and a data bearer;

[0008] The signaling bearer includes a first signaling bearer and a second signaling bearer;

[0009] The data bearer includes a first data bearer and a second data bearer;

[0010] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0011] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0012] The first data bearer is used to transmit data corresponding to the communication service;

[0013] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0014] An embodiment of a second aspect of the present disclosure provides a data transmission method, which is applied to the wireless interface protocol stack architecture for AI service enhancement described in the first aspect, including:

[0015] receiving signaling information or communication data;

[0016] Determine the service to which the signaling information belongs and the service to which the communication data belongs;

[0017] When it is determined that the service described in the signaling information is a communication service, the signaling information is transmitted to the first signaling bearer; when it is determined that the service described in the signaling information is an artificial intelligence service, the signaling information is transmitted to the second signaling bearer;

[0018] If it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to the first data bearer; if it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to the second data bearer;

[0019] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0020] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0021] The first data bearer is used to transmit data corresponding to the communication service;

[0022] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0023] An embodiment of a third aspect of the present disclosure provides a data transmission device, which is applied to the wireless interface protocol stack architecture for AI service enhancement described in the first aspect, and the device includes:

[0024] A receiving unit, receiving signaling information or communication data;

[0025] A determination unit, configured to determine the service to which the signaling information belongs and the service to which the communication data belongs;

[0026] a transmission unit, configured to transmit the signaling information to a first signaling bearer when it is determined that the service to which the signaling information belongs is a communication service; and to transmit the signaling information to a second signaling bearer when it is determined that the service to which the signaling information belongs is an artificial intelligence service;

[0027] If it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to the first data bearer; if it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to the second data bearer;

[0028] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0029] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0030] The first data bearer is used to transmit data corresponding to the communication service;

[0031] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0032] An embodiment of a fourth aspect of the present disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the second aspect above.

[0033] An embodiment of the fifth aspect of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement the method described in the second aspect.

[0034] The technical solution provided in the embodiments of the present disclosure has at least the following technical effects or advantages:

[0035] The present disclosure proposes a wireless interface protocol stack architecture and data transmission method for AI service enhancement, the architecture comprising: a wireless bearer; the wireless bearer comprises a signaling bearer and a data bearer; the signaling bearer comprises a first signaling bearer and a second signaling bearer; the data bearer comprises a first data bearer and a second data bearer; the first signaling bearer is used to transmit signaling information corresponding to the communication service; the second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; the first data bearer is used to transmit data corresponding to the communication service; the second data bearer is used to transmit data corresponding to the artificial intelligence service. The embodiments of the present application transmit the signaling and data of different services separately using different bearers, thereby providing corresponding connection control and data transmission support for the artificial intelligence service in a targeted manner, so as to efficiently transmit the data corresponding to the artificial intelligence service.

[0036] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will become apparent from the following description or be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present disclosure. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0038] In the attached picture:

[0039] Figure 1 A schematic diagram of an internal protocol stack of a receiving end or a sending end of a data transmission system provided by an embodiment of the present disclosure is shown;

[0040] Figure 2 A flow chart of a data transmission method provided by an embodiment of the present disclosure is shown;

[0041] Figure 3 A schematic diagram of a data transmission method provided by an embodiment of the present disclosure is shown;

[0042] Figure 4 A schematic structural diagram of a data transmission device provided by another embodiment of the present disclosure is shown;

[0043] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;

[0044] Figure 6 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.

[0047] Based on the above background technology, the traditional 5G access network protocol stack can be divided into two planes: control plane (CP) and user plane (UP). The control plane protocol refers to the protocol used for the control signaling transmission of the system, and the user plane protocol refers to the protocol cluster used for user data transmission. The traditional 5G access network protocol stack includes multiple layers, each of which plays a key role to support efficient wireless communication and data transmission, mainly including the physical layer (PHY), which is responsible for processing the physical signals and modulation and demodulation of wireless transmission; the medium access control layer (MAC), which manages and coordinates the allocation of wireless resources between multiple users; the radio link control layer (RLC), which provides reliable data transmission services, including data segmentation, reorganization and error control; the packet data consistency protocol (PDCP), which is responsible for handling the security, compression and transmission of IP data packets; the radio resource control layer (RRC), which is responsible for managing the connection establishment, maintenance and release of wireless resources to ensure that the network can effectively respond to the connection needs of mobile devices; the service data adaptation protocol (SDAP), which is responsible for data transmission and adaptation of different service types, such as the optimization processing of low-latency services and high-throughput services. The control plane protocol includes the above-mentioned RRC layer, PDCP layer, RLC layer, MAC layer and PHY layer from top to bottom; the user plane protocol includes the above-mentioned SDAP layer, PDCP layer, RLC layer, MAC layer and PHY layer from top to bottom. Through the collaborative work of these layers, the 5G access network can achieve the requirements of high-speed data transmission, low-latency services and multi-device connections, providing strong support and flexible network management capabilities for various application scenarios.

[0048] Traditional access networks show obvious deficiencies when facing the emerging AI services of 6G. AI services are usually characterized by large data transmission volume and sensitivity to delay. In AI services, a large amount of data transmission requires customized, high-speed, and high-capacity network support. In the design of traditional access networks, AI services are not distinguished from traditional communication services, making it difficult to meet the growing demand for AI services, resulting in a continuous decline in user service quality QoS.

[0049] In view of this, the present disclosure proposes a wireless interface protocol stack architecture and data transmission method for AI service enhancement, the architecture including: wireless bearer; the wireless bearer includes a signaling bearer and a data bearer; the signaling bearer includes a first signaling bearer and a second signaling bearer; the data bearer includes a first data bearer and a second data bearer; the first signaling bearer is used to transmit signaling information corresponding to the communication service; the second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; the first data bearer is used to transmit data corresponding to the communication service; the second data bearer is used to transmit data corresponding to the artificial intelligence service. The embodiments of the present application use different bearers to transmit the signaling and data of different services respectively, so as to provide corresponding connection control and data transmission support for the artificial intelligence service in a targeted manner, so as to efficiently transmit the data corresponding to the artificial intelligence service.

[0050] In order to explain the access network system in detail, Figure 1 A structural schematic diagram of a wireless interface protocol stack architecture for AI service enhancement according to an embodiment of the present application is shown.

[0051] like Figure 1 As shown in the figure, the wireless interface protocol stack architecture for AI service enhancement includes:

[0052] Radio bearer;

[0053] Radio bearers include signaling bearers and data bearers;

[0054] The signaling bearer includes a first signaling bearer and a second signaling bearer;

[0055] The data bearer includes a first data bearer and a second data bearer;

[0056] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0057] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0058] The first data bearer is used to transmit data corresponding to the communication service;

[0059] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0060] The first signaling bearer and the second signaling bearer may include multiple sub-signaling bearers, and the sub-signaling bearers of the first signaling bearer are Figure 1 In the example, SRB0-3 is used to represent the sub-signaling bearer of the second signaling bearer. Figure 1 It is represented by SRB-AI.

[0061] The first data bearer and the second data bearer may include multiple sub-data bearers. The sub-data bearers of the first data bearer are Figure 1In the example, DRB0-3 is used to represent the sub-data bearer of the second data bearer. Figure 1 It is represented by DRB-AI.

[0062] Among them, the wireless bearer supports two types of bearers: signaling bearer and data bearer. Signaling refers to the information used to control and manage the network during the communication process. It includes establishing, maintaining and releasing communication connections, performing user authentication and identity verification, managing the location and status of mobile devices, performing call forwarding and roaming operations. The purpose of signaling is to achieve the correct operation of the communication network and optimize the user experience. Signaling bearer refers to the channel or channel used to transmit signaling information. It carries signaling messages related to the control and management of the mobile communication network. These signaling messages usually have a low data volume and a high priority because they are critical to the normal operation of the network. Signaling bearers usually use low-latency and high-reliability transmission mechanisms to ensure the timely delivery and reliability of signaling messages.

[0063] For the signaling bearers corresponding to the communication services, 4 signaling radio bearers (SRBs) are supported, among which SRB0 is used for the sending and receiving of connection establishment request messages of the idle state user terminal before entering the connected state. It is responsible for transmitting key control messages, such as page requests and connection establishment messages, to facilitate effective communication between the user and the wireless access network. SRB1 is used for the sending and receiving of RRC-related signaling after the user terminal enters the connected state. It is used to transmit control messages related to the establishment, maintenance and release of the user plane (i.e., data channel), and is also responsible for transmitting messages related to the setting and release of the data channel and user equipment configuration. SRB2 is used for the sending and receiving of NAS signaling, and is used to transmit control messages related to the mobility of the user equipment. It is also responsible for transmitting messages related to the terminal, base station selection and other mobility-related functions. SRB3 is used for specific RRC messages when the UE is in EN-DC.

[0064] That is, each signaling bearer specifies when and what kind of signaling is transmitted.

[0065] However, the signaling bearer corresponding to the communication service may have the following problems:

[0066] 1) Only one SRB is supported for connected users, which cannot support differentiated QoS guarantees for task signaling and data. This is because AI task signaling and data also have different transmission priorities. For example, ultra-low latency and ultra-high reliability are required for actions such as model deployment, distribution, and training. For large amounts of data such as model gradients that need to be transmitted, high bandwidth and low transmission latency are used.

[0067] 2) Even if the current RRC supports cascading, the maximum length after cascading is still limited. Therefore, when AI task signaling is transmitted directly by reusing SRB, it is still impossible to carry large signaling.

[0068] 3) AI operations such as model compression / pruning / quantization / security, or data compression / de-privacy cannot be supported in the current SRB.

[0069] In order to avoid the above problems, an embodiment of the present application provides a second signaling bearer, namely, a signaling bearer corresponding to the AI ​​service.

[0070] The signaling information corresponding to the artificial intelligence service includes the transmission of artificial intelligence decision information, environmental status information, first model parameters and artificial intelligence operation information for the first model parameters.

[0071] Among them, artificial intelligence decision information may include: the final decision judgment obtained through reasoning, prediction results, or some additional explanatory information, etc., usually presented in the form of probability or score, the rules or logic used to generate output within the model, especially in models with strong interpretability and parameters learned during training, etc. Environmental state information may include: environmental state information in reinforcement learning. The first model parameter is the model parameter corresponding to the model of general data volume or the gradient information of the model parameter, such as a model matrix.

[0072] First, in some embodiments, the signaling bearer corresponding to the AI ​​service may include multiple sub-signaling bearers, each sub-signaling bearer has a different priority. Therefore, when the AI ​​service signaling is received, different signaling can be transmitted to different sub-signaling bearers based on the priorities of different signaling to achieve corresponding transmission according to the priority of the signaling.

[0073] Furthermore, compared with the signaling bearers corresponding to the above four communication services, the second signaling bearer has a larger data length. When the AI ​​service signaling is relatively large, such as when the AI ​​signaling is a model parameter, it can be smoothly transmitted through the second signaling bearer without using a data bearer to transmit the AI ​​service signaling.

[0074] In addition, the second signaling bearer can also support AI operations, such as model mobilization / deployment / inference / compression / encryption, etc.

[0075] If the AI ​​operation is model compression, the data volume of the signaling corresponding to the AI ​​service can be compressed to reduce the overhead of transmitting the signaling corresponding to the AI ​​service. If the AI ​​operation is model encryption, the security of the signaling corresponding to the AI ​​service can be increased. If the AI ​​operation is model mobilization / deployment / inference, the model can be trained and inferred during the signaling transmission process to realize the processing of AI services on local devices such as base stations.

[0076] Data bearer refers to the channel or passage used to transmit user data. It carries the transmission of voice, video, image and other data generated by users. The purpose of data bearer is to realize communication and information transmission between users. Data bearers usually have higher data volume and lower priority because they are mainly used to transmit large amounts of user data. Data bearers usually use high bandwidth and low transmission delay to meet users' demand for fast data transmission. Data bearers can be optimized for different types of data applications, such as streaming media, web browsing, file downloading, etc. For data bearers, one or more data radio bearers (DRBs) are supported to be established according to different Quality of Service (QoS) requirements, so as to provide differentiated QoS guarantees.

[0077] The following problems exist in data carrying of communication services:

[0078] 1) Although it currently supports multiple DRBs and differentiated QoS guarantees, it does not support QoS for AI services. 2) Similar to SRB, it currently does not support some specific operations of AI, such as model compression / pruning / quantization / security.

[0079] In order to avoid the above problems, an embodiment of the present application provides a second data bearer, namely, a data bearer corresponding to the AI ​​service.

[0080] In some embodiments, the communication data corresponding to the artificial intelligence service includes training data corresponding to the artificial intelligence service, second model parameters, and artificial intelligence operation information for the second model parameters.

[0081] Among them, the second model parameters are parameters corresponding to the ultra-large model with a large amount of data. Due to the large amount of data, the transmission of the second model parameters cannot be carried even through the second signaling bearer. Therefore, it is necessary to transmit through the second data bearer. The artificial intelligence operation information of the second model parameters includes model mobilization / deployment / inference / compression / encryption, etc.

[0082] First, in some embodiments, the data bearer corresponding to the AI ​​service may include multiple sub-data bearers. Therefore, when the AI ​​service data and the QoS of the AI ​​service are received, the data can be transmitted to different sub-data bearers to achieve the QoS of the AI ​​service.

[0083] In other embodiments, the data bearer corresponding to the AI ​​service may be configurable, and when the AI ​​service data and the QoS of the AI ​​service are received, the data bearer may be configured to transmit the data to the configured data bearer to achieve the QoS of the AI ​​service.

[0084] Furthermore, the second data bearer can also support AI operations, such as model mobilization / deployment / inference / compression / encryption, etc.

[0085] If the AI ​​operation is model compression, the data volume of the super-large model parameters corresponding to the AI ​​service can be compressed to reduce the overhead of transmitting the data corresponding to the AI ​​service. If the AI ​​operation is model encryption, the security of the data corresponding to the AI ​​service can be increased. If the AI ​​operation is model mobilization / deployment / inference, the model can be trained and inferred during the data transmission process to realize the processing of AI services on local devices such as base stations.

[0086] The present disclosure proposes a wireless interface protocol stack architecture for AI service enhancement, which includes: a wireless bearer; a wireless bearer includes a signaling bearer and a data bearer; a signaling bearer includes a first signaling bearer and a second signaling bearer; a data bearer includes a first data bearer and a second data bearer; the first signaling bearer is used to transmit signaling information corresponding to the communication service; the second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; the first data bearer is used to transmit data corresponding to the communication service; the second data bearer is used to transmit data corresponding to the artificial intelligence service. The embodiments of the present application use different bearers to transmit the signaling and data of different services respectively, so as to provide corresponding connection control and data transmission support for the artificial intelligence service in a targeted manner, so as to efficiently transmit the data corresponding to the artificial intelligence service.

[0087] In some embodiments, the architecture further includes:

[0088] Enhanced radio resource control layer;

[0089] The enhanced wireless resource control layer is used to receive signaling information; determine the service to which the signaling information belongs; when it is determined that the service to which the signaling information belongs is a communication service, transmit the signaling information to the first signaling bearer; when it is determined that the service to which the signaling information belongs is an artificial intelligence service, transmit the signaling information to the second signaling bearer.

[0090] The signaling information may be control plane signaling information of the access network.

[0091] In some embodiments, in order to ensure that each wireless signaling bearer can transmit corresponding signaling information, the enhanced wireless resource control layer can determine the service to which the received signaling information belongs. For example, it can determine the service to which the signaling information belongs based on the identifier of the signaling information, where the identifier can be an identifier related to the AI ​​service and an identifier related to the communication service.

[0092] When it is determined that the service to which the signaling information belongs is a communication service, the signaling information is transmitted to the first signaling bearer; when it is determined that the service to which the signaling information belongs is an artificial intelligence service, the signaling information is transmitted to the second signaling bearer.

[0093] In an optional embodiment, the corresponding signaling bearer can also be determined based on the function of the signaling information. For example, if the signaling information is a preamble code, then the corresponding signaling bearer is the first signaling bearer, specifically the physical random access channel of the first signaling bearer.

[0094] In some embodiments, the architecture further includes:

[0095] Enhanced service data adaptation protocol layer;

[0096] The enhanced service data adaptation protocol layer is used to receive communication data; determine the service to which the communication data belongs; when it is determined that the service to which the communication data belongs is a communication service, transmit the communication data to the first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, transmit the communication data to the second data bearer.

[0097] The communication data may be user plane communication data of the access network.

[0098] Based on the same principle, the enhanced service data adaptation protocol layer can determine the business to which the received communication data belongs. For example, it can determine the business to which the communication data belongs based on the identifier of the communication data, where the identifier can be an identifier related to the AI ​​business and an identifier related to the communication business.

[0099] When it is determined that the service to which the signaling information belongs is a communication service, the signaling information is transmitted to the first signaling bearer; when it is determined that the service to which the signaling information belongs is an artificial intelligence service, the signaling information is transmitted to the second signaling bearer.

[0100] In some embodiments, the enhanced service data adaptation protocol layer is further used to receive quality of service of the communication data;

[0101] When it is determined that the service to which the communication data belongs is a communication service, based on the quality of service, the communication data is transmitted to at least one first target data bearer of the first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, based on the quality of service, the communication data is transmitted to at least one second target data bearer of the second data bearer.

[0102] As mentioned above, the second data bearer needs to support the QoS corresponding to the AI ​​service. Therefore, the enhanced service data adaptation protocol layer is also used to receive the service quality of the communication data, and the service quality of the communication data includes the QoS of the communication service and the QoS of the AI ​​service.

[0103] When it is determined that the service to which the communication data belongs is a communication service, based on the QoS of the communication service, the communication data is transmitted to at least one first target data bearer of the first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, based on the QoS of the AI ​​service, the communication data is transmitted to at least one second target data bearer of the second data bearer.

[0104] In some embodiments, the above architecture further includes: Figure 1 The enhanced-Medium Access Control (e-MAC) layer, the Radio Link Control (RLC) layer, and the Packet Data Convergence Protocol (PDCP) layer are shown, wherein the data link layer is divided into 4 sublayers, including the e-MAC layer, the RLC layer, the PDCP layer, and the enhanced-Service Data Adaptation Protocol (e-SDAP) layer.

[0105] Among them, compared with the MAC layer of the 5G system, the e-MAC layer, in addition to the traditional wireless resource scheduling function, adds scheduling and real-time collaboration functions for new resources such as computing power, algorithms, data, and models for AI services.

[0106] The proposed e-SDAP layer is only located in the enhanced user plane. Compared with the SDAP layer of the 5G system, in addition to the original mapping function between QoS flow and data radio bearer (DRB), a mapping mechanism between QoAIS flow and AI dedicated data radio bearer (DRB-AI) is added for AI services.

[0107] The three sublayers of the e-MAC layer, RLC layer, and PDCP layer are located in the enhanced control plane and the enhanced user plane at the same time. They are responsible for the transmission, encryption, and integrity protection of wireless bearer signaling information in the control plane, and for the transmission and encryption of user service data in the user plane.

[0108] The network layer refers to the enhanced-Radio Resource Control (e-RRC) layer proposed in the present disclosure, which is located in the control plane of the access network. Compared with the RRC layer of the 5G system, in addition to being responsible for completing the processing of all traditional communication control signaling information (system messages, admission control, security management, measurement and reporting, switching and mobility, NAS message transmission, wireless resource management, etc.) interacting between the access network and the terminal, it also adds AI control signaling information (model mobilization / deployment / inference / compression / pruning / quantization / security / data compression / deprivacy / data enhancement, etc.) required for AI operations and execution for artificial intelligence (AI) services.

[0109] In some embodiments, Figure 2 A data transmission method provided by an embodiment of the present disclosure is shown. The method is applied to Figure 1 The wireless interface protocol stack architecture enhanced for AI services is shown.

[0110] The data transmission method of the embodiment of the present disclosure may include the following steps:

[0111] S21. Receive signaling information or communication data.

[0112] S22. Determine the service to which the signaling information belongs and the service to which the communication data belongs.

[0113] S23. When it is determined that the signaling information service is a communication service, the signaling information is transmitted to the first signaling bearer; when it is determined that the service to which the signaling information belongs is an artificial intelligence service, the signaling information is transmitted to the second signaling bearer.

[0114] S24. When it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to a first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to a second data bearer.

[0115] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0116] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0117] The first data bearer is used to transmit data corresponding to the communication service;

[0118] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0119] The signaling information may be control plane signaling information of the access network, and the communication data may be user plane communication data of the access network.

[0120] The above S21-S24 is the process of the base station sending signaling and data, and the process of receiving signaling and data is the opposite process, which will not be repeated here.

[0121] The data receiving process is explained below based on a specific example. Figure 3 As shown, it is a specific implementation process of applying the method in the embodiment of the present disclosure to receive data in an Android system.

[0122] Step a: The control plane signaling information flow enters the e-RRC layer. In addition to being responsible for processing all traditional communication control signaling information (system messages, admission control, security management, measurement and reporting, switching and mobility, NAS message transmission, wireless resource management, etc.) interacting between the access network and the terminal, the e-RRC is also responsible for processing the AI ​​control signaling information required for AI operation and execution (model mobilization / deployment / inference / compression / pruning / quantization / security / data compression / deprivacy / data enhancement, etc.) for AI services.

[0123] Step b: AI service-related control signaling information is transmitted through the SRB-AI bearer. This signaling information is mainly used to manage and control AI-related tasks and data flows. At the same time, traditional control signaling information is transmitted through traditional SRB bearers to manage the control process of traditional communication services.

[0124] Step c: The user plane data flow enters the e-SDAP layer, which is responsible for managing the mapping of quality of service (QoS) flows and QoAIS flows to business data bearers. This includes mapping data flows of different priorities to appropriate business data bearers to meet the performance requirements of various applications. At the same time, the e-SDAP layer is also responsible for mapping QoAIS (AI-related quality of service) flows to dedicated AI-dedicated business data bearers (DRB-AI) to ensure efficient processing and transmission of AI tasks.

[0125] Step d: AI service data is transmitted via the DRB-AI bearer, which involves data flows related to tasks and models processed by AI. Traditional service data is transmitted via the traditional DRB bearer, which is used for regular communication data transmission.

[0126] (Steps ab and cd are executed in parallel)

[0127] Step e: Data enters the PDCP layer, which is responsible for handling the transmission of IP data packets. The PDCP layer improves transmission efficiency and ensures the security of data transmission through data compression and security protection measures to protect the integrity and privacy of user data.

[0128] Step f: Data enters the RLC layer, which is responsible for data segmentation and reassembly, as well as confirmation and retransmission control. These functions include data segmentation, reassembly during transmission, confirmation of received data packets, retransmission when necessary, and implementation of flow control strategies to ensure reliable data transmission and smooth data flow.

[0129] Step g: The data enters the e-MAC layer, which is responsible for scheduling traditional wireless resources and data, models, and computing resources related to AI services. This includes dynamic allocation and scheduling of traditional wireless resources and AI service-related resources to meet different service quality requirements and optimize the utilization efficiency of network resources.

[0130] Step h: The data is processed by the PHY layer, which is responsible for the modulation and demodulation of the physical signal. This includes functions such as channel coding and decoding, multiplexing, etc., to ensure that the data can be transmitted efficiently and reliably during wireless transmission, and communicate effectively with the physical layer PHY device at the receiving end.

[0131] Corresponding to the implementation of the above data transmission method, the embodiment of the present disclosure further provides a data transmission device, which is used to perform the above Figure 2 The data transmission method of any embodiment is shown. Figure 4 As shown, the data transmission device includes:

[0132] A receiving unit 41 receives signaling information or communication data;

[0133] A determination unit 42, configured to determine the service to which the signaling information belongs and the service to which the communication data belongs;

[0134] A transmission unit 43 is configured to transmit the signaling information to a first signaling bearer when it is determined that the service to which the signaling information belongs is a communication service; and to transmit the signaling information to a second signaling bearer when it is determined that the service to which the signaling information belongs is an artificial intelligence service;

[0135] If it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to the first data bearer; if it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to the second data bearer;

[0136] The first signaling bearer is used to transmit signaling information corresponding to the communication service;

[0137] The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service;

[0138] The first data bearer is used to transmit data corresponding to the communication service;

[0139] The second data bearer is used to transmit data corresponding to the artificial intelligence service.

[0140] The data transmission device provided by the above-mentioned embodiment of the present disclosure and the data transmission method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0141] The present disclosure also provides an electronic device for executing the above data transmission method. Figure 5 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 5 As shown, the electronic device includes: a processor 900, a memory 901, a bus 902 and a communication interface 903, wherein the processor 900, the communication interface 903 and the memory 901 are connected via the bus 902; the memory 901 stores a computer program that can be run on the processor 900, and the processor 900 executes the aforementioned Figure 2 The data transmission method provided by any of the illustrated embodiments.

[0142] The memory 901 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 903 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0143] The bus 902 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 901 is used to store programs. After receiving the execution instruction, the processor 900 executes the program. Figure 2 The data transmission method disclosed in any of the illustrated embodiments may be applied to the processor 900 or implemented by the processor 900 .

[0144] The processor 900 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 900 or the instruction in the form of software. The above processor 900 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 901, and the processor 900 reads the information in the memory 901 and completes the steps of the above method in combination with its hardware.

[0145] The electronic device provided by the embodiment of the present disclosure and the data transmission method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0146] The present disclosure also provides a computer-readable storage medium corresponding to the data transmission method provided in the above embodiment. Figure 6 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the data transmission method provided by any of the aforementioned embodiments will be executed.

[0147] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0148] The computer-readable storage medium provided by the above-mentioned embodiments of the present disclosure and the data transmission method provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0149] It should be noted that:

[0150] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0151] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed disclosure requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present disclosure.

[0152] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of this disclosure and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0153] The above is only a preferred specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A wireless interface protocol stack architecture for AI service enhancement, characterized in that: The architecture includes: Radio bearer; The radio bearer includes a signaling bearer and a data bearer; The signaling bearer includes a first signaling bearer and a second signaling bearer; The data bearer includes a first data bearer and a second data bearer; The first signaling bearer is used to transmit signaling information corresponding to the communication service; The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; The first data bearer is used to transmit data corresponding to the communication service; The second data bearer is used to transmit data corresponding to the artificial intelligence service.

2. The architecture according to claim 1, characterized in that The signaling information corresponding to the artificial intelligence service includes transmission of artificial intelligence decision information, environmental information report information, first model parameters and artificial intelligence operation information for the first model parameters.

3. The architecture according to claim 1, characterized in that The communication data corresponding to the artificial intelligence service includes training data corresponding to the artificial intelligence service, second model parameters and artificial intelligence operation information for the second model parameters.

4. The architecture according to claim 1, characterized in that The architecture also includes: Enhanced radio resource control layer; The enhanced wireless resource control layer is used to receive signaling information; determine the service to which the signaling information belongs; when it is determined that the service to which the signaling information belongs is a communication service, transmit the signaling information to the first signaling bearer; when it is determined that the service to which the signaling information belongs is an artificial intelligence service, transmit the signaling information to the second signaling bearer.

5. The architecture according to claim 1, characterized in that The architecture also includes: Enhanced service data adaptation protocol layer; The enhanced service data adaptation protocol layer is used to receive communication data; determine the service to which the communication data belongs; when it is determined that the service to which the communication data belongs is a communication service, transmit the communication data to the first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, transmit the communication data to the second data bearer.

6. The architecture according to claim 1, characterized in that: The enhanced service data adaptation protocol layer is also used to receive the quality of service of the communication data; When it is determined that the service to which the communication data belongs is a communication service, based on the service quality, the communication data is transmitted to at least one first target data bearer of the first data bearer; when it is determined that the service to which the communication data belongs is an artificial intelligence service, based on the service quality, the communication data is transmitted to at least one second target data bearer of the second data bearer.

7. A data transmission method, characterized in that: The method applied to the wireless interface protocol stack architecture for AI service enhancement according to any one of claims 1 to 6 includes: receiving signaling information or communication data; Determine the service to which the signaling information belongs and the service to which the communication data belongs; When it is determined that the service described in the signaling information is a communication service, the signaling information is transmitted to the first signaling bearer; when it is determined that the service described in the signaling information is an artificial intelligence service, the signaling information is transmitted to the second signaling bearer; If it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to the first data bearer; if it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to the second data bearer; The first signaling bearer is used to transmit signaling information corresponding to the communication service; The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; The first data bearer is used to transmit data corresponding to the communication service; The second data bearer is used to transmit data corresponding to the artificial intelligence service.

8. A data transmission device, characterized in that: A wireless interface protocol stack architecture for AI service enhancement applied to any one of claims 1 to 6, the device comprising: A receiving unit, receiving signaling information or communication data; A determination unit, configured to determine the service to which the signaling information belongs and the service to which the communication data belongs; a transmission unit, configured to transmit the signaling information to a first signaling bearer when it is determined that the service to which the signaling information belongs is a communication service; and to transmit the signaling information to a second signaling bearer when it is determined that the service to which the signaling information belongs is an artificial intelligence service; If it is determined that the service to which the communication data belongs is a communication service, the communication data is transmitted to the first data bearer; if it is determined that the service to which the communication data belongs is an artificial intelligence service, the communication data is transmitted to the second data bearer; The first signaling bearer is used to transmit signaling information corresponding to the communication service; The second signaling bearer is used to transmit signaling information corresponding to the artificial intelligence service; The first data bearer is used to transmit data corresponding to the communication service; The second data bearer is used to transmit data corresponding to the artificial intelligence service.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the computer program to implement the method according to claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to claim 7.

Images