Data transmission method, terminal and base station

By exchanging AI task control signaling and model parameters at the MAC layer between the base station and the terminal, and using multi-format MAC control packets for data transmission, the problems of high latency and poor reliability in AI data transmission are solved, thus realizing full utilization of terminal intelligence and ensuring data security.

CN115884206BActive Publication Date: 2026-08-04CHINA MOBILE COMM LTD RES INST +1
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA MOBILE COMM LTD RES INST
Filing Date
2021-08-03
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

The existing network architecture suffers from problems such as high data transmission latency, underutilization of terminal intelligence, and difficulty in ensuring data security when integrating AI with communication networks.

Method used

The base station interacts with the terminal via the MAC layer to exchange control signaling and model parameters for AI tasks. Data transmission is carried out using MAC control packets or MAC control units. Multiple formats of MAC control packets are introduced to adapt to different types of data, thereby achieving reliable data transmission and processing.

Benefits of technology

It reduces AI data transmission latency, improves data transmission reliability, and achieves the organic integration of model algorithms and wireless communication, enabling base station self-optimization and self-evolution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115884206B_ABST
    Figure CN115884206B_ABST
Patent Text Reader

Abstract

A data transmission method, a terminal and a base station, wherein the method comprises: a MAC layer of the base station interacting with the terminal through a MAC control package or a MAC control unit to transmit first data and / or second data, wherein the first data is control signaling of an artificial intelligence (AI) task, and the second data is an AI model parameter and / or data collection information. The embodiment of the application can reduce the time delay of AI data transmission and ensure the reliability of data transmission.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, specifically to a data transmission method, a terminal, and a base station. Background Technology

[0002] 5G and Artificial Intelligence (AI) are gradually integrating into people's lives and bringing new economic growth trends. With the rapid development of AI technology, future network architectures will increasingly integrate with AI. In the upcoming 6G era, AI will inevitably become an indispensable part of network architecture.

[0003] With the rapid development of AI technology, future network architectures will increasingly integrate with AI. Current AI models are trained on the network side, collecting data from the network or terminals to create AI models, which are then optimized based on the desired goals. In this approach, intelligent and network functions are relatively independent. This approach faces several challenges: 1) Increasing amounts of data need to be reported, consuming more network bandwidth. 2) Terminals are becoming increasingly intelligent, but current technology does not fully utilize their intelligence, failing to achieve end-to-end intelligence. 3) Data security is a sensitive factor in communication networks, and current technologies struggle to guarantee user data security.

[0004] It can be seen that the integration of existing network architecture with AI is still in the early stages of research. Many application scenarios have not yet been considered in the network architecture. For example, after introducing AI models with inherent intelligence, how to reduce the latency of AI data transmission and ensure the reliability of data transmission. Summary of the Invention

[0005] At least one embodiment of the present invention provides a data transmission method, a terminal, and a base station, which can reduce the latency of AI data transmission and ensure the reliability of data transmission.

[0006] According to one aspect of the present invention, at least one embodiment provides a data transmission method applied to a base station, comprising:

[0007] The MAC layer of the base station interacts with the terminal through MAC control packets or MAC control units to exchange first data and / or second data, wherein the first data is control signaling for artificial intelligence (AI) tasks, and the second data is AI model parameters and / or data acquisition information.

[0008] Furthermore, according to at least one embodiment of the present invention, the base station further includes a first AI function module, wherein the interaction of first data and / or second data with the terminal via a MAC control packet or a MAC control unit includes:

[0009] The MAC layer of the base station receives the first MAC control packet or MAC control unit sent by the terminal, obtains the first data and / or the second data encapsulated in the first MAC control packet or MAC control unit, and sends it to the first AI function module.

[0010] And / or,

[0011] The MAC layer of the base station receives first data and / or second data sent by the first AI function module, encapsulates the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit, and then sends it to the terminal.

[0012] Furthermore, according to at least one embodiment of the present invention, the first data includes at least one of the following categories:

[0013] AI connection establishment request signaling;

[0014] AI connection establishment signaling;

[0015] Signaling for establishing end-to-end AI tasks;

[0016] End-to-end AI task stop or interruption signaling;

[0017] Release signaling for AI connectivity;

[0018] Management signaling for AI models;

[0019] Configuration signaling for data acquisition;

[0020] The second data includes at least one of the following categories:

[0021] Synchronization information between base stations and terminals during AI model training;

[0022] Preprocessed collected data and / or tag information.

[0023] Furthermore, according to at least one embodiment of the present invention, the first MAC control package or MAC control unit and the second MAC control package or MAC control unit are both MAC control packages or MAC control units of a first format. The first format MAC control package or MAC control unit includes first format indication information, data length indication information, first data and / or second data, wherein the first format indication information is used to indicate that the MAC control package or MAC control unit to which it belongs carries the first data and / or the second data.

[0024] Furthermore, according to at least one embodiment of the present invention, obtaining the first data and / or second data encapsulated in the first MAC control package or MAC control unit includes: determining a first format according to the first format indication information in the first MAC control package or MAC control unit; and parsing the first MAC control package or MAC control unit according to the first format to obtain the first data and / or second data encapsulated therein.

[0025] The step of encapsulating the first data and / or the second data sent by the first AI function module into the second MAC control package or MAC control unit includes: encapsulating the first data and / or the second data sent by the first AI function module into the second MAC control package or MAC control unit according to the first format.

[0026] Furthermore, according to at least one embodiment of the present invention, the first MAC control package or MAC control unit and the second MAC control package or MAC control unit both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit.

[0027] Furthermore, according to at least one embodiment of the present invention, it further includes:

[0028] The step of obtaining the first data and / or the second data encapsulated in the first MAC control package or MAC control unit includes: determining a first target format according to the format indication information in the first MAC control package or MAC control unit; and parsing the first MAC control package or MAC control unit according to the first target format to obtain the first data and / or the second data encapsulated therein.

[0029] The step of encapsulating the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit includes: determining a corresponding second target format according to the type of the first data and / or second data packet sent by the first AI function module; and encapsulating the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit according to the second target format, wherein the format indication information in the second MAC control packet or MAC control unit indicates the second target format.

[0030] Furthermore, according to at least one embodiment of the present invention, the first target format is a second format, a fifth format, a sixth format, or an eighth format; the second target format is a third format, a fourth format, a fifth format, a sixth format, or a seventh format; wherein,

[0031] The second format corresponds to the AI ​​connection establishment request signaling;

[0032] The third format corresponds to the signaling for establishing an AI connection;

[0033] The fourth format corresponds to the signaling for establishing an end-to-end AI task;

[0034] The fifth format corresponds to the synchronization information between the base station and the terminal during the AI ​​model training process;

[0035] The sixth format corresponds to the preprocessed collected data and / or tag information;

[0036] The seventh format corresponds to the stop or interrupt signaling for end-to-end AI tasks;

[0037] The eighth format corresponds to the release signaling of the AI ​​connection.

[0038] Furthermore, according to at least one embodiment of the present invention, each format of MAC control packet or MAC control unit includes format indication information, data length indication information, the first data and / or the second data;

[0039] The third, fourth, fifth, sixth, seventh, and eighth formats also include a user identifier for indicating AI connection;

[0040] The fourth, fifth, sixth, and seventh formats also include a task ID for indicating the AI ​​task;

[0041] The sixth format also includes a data acquisition ID.

[0042] Furthermore, according to at least one embodiment of the present invention, when the first target format determined based on the format indication information in the first MAC control package or MAC control unit is the second format, the method further includes:

[0043] The MAC layer of the base station assigns a user identifier to the terminal to indicate the AI ​​connection, and sends the user identifier and the AI ​​connection establishment request signaling to the first AI function module;

[0044] After receiving the AI ​​connection establishment signaling sent by the first AI function module, the MAC layer of the base station encapsulates a second MAC control packet or MAC control unit that includes the format indication information, the user identifier, the data length indication information, and the AI ​​connection establishment signaling.

[0045] According to another aspect of the present invention, at least one embodiment provides a data transmission method applied to a terminal, comprising:

[0046] The MAC layer of the terminal interacts with the base station with first data and / or second data through MAC control packets or MAC control units. The first data is control signaling for artificial intelligence (AI) tasks, and the second data is AI model parameters and / or data acquisition information.

[0047] Furthermore, according to at least one embodiment of the present invention, the terminal further includes a second AI function module, wherein the interaction of the first data and / or the second data with the base station via a MAC control packet or a MAC control unit includes:

[0048] The MAC layer of the terminal receives first data and / or second data sent by the second AI function module, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station.

[0049] And / or,

[0050] The MAC layer of the terminal receives the second MAC control packet or MAC control unit sent by the base station, obtains the first data and / or the second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module.

[0051] Furthermore, according to at least one embodiment of the present invention, the first data includes at least one of the following categories:

[0052] AI connection establishment request signaling;

[0053] AI connection establishment signaling;

[0054] Signaling for establishing end-to-end AI tasks;

[0055] End-to-end AI task stop or interruption signaling;

[0056] Release signaling for AI connectivity;

[0057] Management signaling for AI models;

[0058] Configuration signaling for data acquisition;

[0059] The second data includes at least one of the following categories:

[0060] Synchronization information between base stations and terminals during AI model training;

[0061] Preprocessed collected data and / or tag information.

[0062] Furthermore, according to at least one embodiment of the present invention, the first MAC control package or MAC control unit and the second MAC control package or MAC control unit are both MAC control packages or MAC control units of a first format. The first format MAC control package or MAC control unit includes first format indication information, data length indication information, first data and / or second data, wherein the first format indication information is used to indicate that the MAC control package or MAC control unit to which it belongs carries the first data and / or the second data.

[0063] Furthermore, according to at least one embodiment of the present invention, the step of encapsulating the first data and / or the second data sent by the second AI function module into the first MAC control package or MAC control unit includes: encapsulating the first data and / or the second data sent by the second AI function module into the first MAC control package or MAC control unit according to the first format;

[0064] The step of obtaining the first data and / or the second data encapsulated in the second MAC control package or MAC control unit includes: determining a first format according to the first format indication information in the second MAC control package or MAC control unit; and parsing the second MAC control package or MAC control unit according to the first format to obtain the first data and / or the second data encapsulated therein.

[0065] Furthermore, according to at least one embodiment of the present invention, the first MAC control package or MAC control unit and the second MAC control package or MAC control unit both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit.

[0066] Furthermore, according to at least one embodiment of the present invention, it further includes:

[0067] The step of encapsulating the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit includes: determining a corresponding first target format according to the type of the first data and / or the second data packet sent by the second AI function module; encapsulating the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit according to the first target format, wherein the format indication information in the first MAC control packet or MAC control unit indicates the first target format;

[0068] The step of obtaining the first data and / or the second data encapsulated in the second MAC control package or MAC control unit includes: determining a second target format according to the format indication information in the second MAC control package or MAC control unit; and parsing the second MAC control package or MAC control unit according to the second target format to obtain the first data and / or the second data encapsulated therein.

[0069] Furthermore, according to at least one embodiment of the present invention, the first target format is a second format, a fifth format, a sixth format, or an eighth format; the second target format is a third format, a fourth format, a fifth format, a sixth format, or a seventh format; wherein,

[0070] The second format corresponds to the AI ​​connection establishment request signaling;

[0071] The third format corresponds to the signaling for establishing an AI connection;

[0072] The fourth format corresponds to the signaling for establishing an end-to-end AI task;

[0073] The fifth format corresponds to the synchronization information between the base station and the terminal during the AI ​​model training process;

[0074] The sixth format corresponds to the preprocessed collected data and / or tag information;

[0075] The seventh format corresponds to the stop or interrupt signaling for end-to-end AI tasks;

[0076] The eighth format corresponds to the release signaling of the AI ​​connection.

[0077] Furthermore, according to at least one embodiment of the present invention, each format of MAC control packet or MAC control unit includes format indication information, data length indication information, the first data and / or the second data;

[0078] The third, fourth, fifth, sixth, seventh, and eighth formats also include a user identifier for indicating AI connection;

[0079] The fourth, fifth, sixth, and seventh formats also include a task ID for indicating the AI ​​task;

[0080] The sixth format also includes a data acquisition ID.

[0081] According to another aspect of the present invention, at least one embodiment provides a base station, comprising:

[0082] The first MAC layer module is used to interact with the terminal through a MAC control packet or a MAC control unit to exchange first data and / or second data, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0083] According to another aspect of the present invention, at least one embodiment provides a base station, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method described above.

[0084] According to another aspect of the present invention, at least one embodiment provides a terminal comprising:

[0085] The second MAC layer module is used to interact with the base station through a MAC control packet or a MAC control unit to exchange first data and / or second data, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0086] According to another aspect of the present invention, at least one embodiment provides a terminal comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method described above.

[0087] According to another aspect of the present invention, at least one embodiment provides a computer-readable storage medium on which a program is stored, which, when executed by a processor, implements the steps of the method described above.

[0088] Compared with existing technologies, the data transmission method, terminal and base station provided in this embodiment of the invention can reduce the latency of AI data transmission, ensure the reliability of data transmission, realize the organic integration of model algorithms, interaction processes and wireless communication, and achieve the purpose of base station self-optimization, self-evolution and self-generation. Attached Figure Description

[0089] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0090] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention;

[0091] Figure 2 A flowchart illustrating the data transmission method provided in this embodiment of the invention when applied to the base station side;

[0092] Figure 3 This is a schematic diagram of the interaction process between a base station and a terminal provided in an embodiment of the present invention;

[0093] Figure 4 This is a schematic diagram of a first-format MAC control packet or control unit according to an embodiment of the present invention;

[0094] Figure 5 This is a schematic diagram of a second-format MAC control packet or control unit according to an embodiment of the present invention;

[0095] Figure 6 This is a schematic diagram of a third-format MAC control packet or control unit according to an embodiment of the present invention;

[0096] Figure 7 This is a schematic diagram of a fourth format MAC control packet or control unit according to an embodiment of the present invention;

[0097] Figure 8 This is a schematic diagram of a fifth format MAC control packet or control unit according to an embodiment of the present invention;

[0098] Figure 9 This is a schematic diagram of a sixth format MAC control packet or control unit according to an embodiment of the present invention;

[0099] Figure 10 This is a schematic diagram of a seventh-format MAC control packet or control unit according to an embodiment of the present invention;

[0100] Figure 11 This is a schematic diagram of the eighth format MAC control packet or control unit according to an embodiment of the present invention;

[0101] Figure 12 A flowchart illustrating the application of the data transmission method provided in this embodiment of the invention to the terminal side;

[0102] Figure 13 This is a schematic diagram of a base station structure provided in an embodiment of the present invention;

[0103] Figure 14 This is a schematic diagram of another structure of a base station provided in an embodiment of the present invention;

[0104] Figure 15 A schematic diagram of a terminal provided in an embodiment of the present invention;

[0105] Figure 16 This is another structural schematic diagram of the terminal provided in an embodiment of the present invention. Detailed Implementation

[0106] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0107] The terms “first,” “second,” etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The terms “and / or” in the specification and claims indicate at least one of the connected objects.

[0108] The technologies described in this document are not limited to NR systems and Long Time Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in various wireless communication systems such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" are often used interchangeably. CDMA systems can implement radio technologies such as CDMA2000 and Universal Terrestrial Radio Access (UTRA). UTRA includes Wideband Code Division Multiple Access (WCDMA) and other CDMA variants. TDMA systems can implement radio technologies such as the Global System for Mobile Communication (GSM). OFDMA systems can implement radio technologies such as Ultra Mobile Broadband (UMB), Evolution-UTRA (E-UTRA), IEEE 802.21 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, and Flash-OFDM. UTRA and E-UTRA are part of the Universal Mobile Telecommunications System (UMTS). LTE and more advanced versions of LTE (such as LTE-A) are newer UMTS versions using E-UTRA. UTRA, E-UTRA, UMTS, LTE, LTE-A, and GSM are described in documents from an organization called the 3rd Generation Partnership Project (3GPP). CDMA2000 and UMB are described in documents from an organization called 3rd Generation Partnership Project 2 (3GPP2).The techniques described herein can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. However, the following description describes NR systems for illustrative purposes, and NR terminology is used in most of the following description, although these techniques can also be applied to applications beyond NR systems.

[0109] The following description provides examples and is not intended to limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the function and arrangement of the elements discussed without departing from the spirit and scope of this disclosure. Various procedures or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with reference to certain examples may be combined in other examples.

[0110] Please see Figure 1 , Figure 1 This diagram illustrates a block diagram of a wireless communication system applicable to an embodiment of the present invention. The wireless communication system includes a terminal 11 and a network device 12. The terminal 11 can also be referred to as a user terminal or user equipment (UE). The terminal 11 can be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), mobile internet device (MID), wearable device, or in-vehicle device, etc. It should be noted that the specific type of terminal 11 is not limited in this embodiment of the present invention. Network device 12 can be a base station and / or a core network element. The base station can be a 5G or later version base station (e.g., gNB, 5G NR NB, etc.), or a base station in other communication systems (e.g., eNB, WLAN access point, or other access point, etc.). The base station can be referred to as a node B, evolved node B, access point, base transceiver station (BTS), radio base station, radio transceiver, basic service set (BSS), extended service set (ESS), B node, evolved B node (eNB), home B node, home evolved B node, WLAN access point, WiFi node, or any other suitable term in the field, as long as the same technical effect is achieved. The base station is not limited to specific technical terms. It should be noted that in the embodiments of the present invention, only the base station in the NR system is used as an example, but the specific type of base station is not limited.

[0111] The base station can communicate with terminal 11 under the control of a base station controller, which in various examples may be part of the core network or some base stations. Some base stations may communicate control information or user data with the core network via backhaul. In some examples, some of these base stations may communicate with each other directly or indirectly via backhaul links, which may be wired or wireless communication links. The wireless communication system may support operation on multiple carriers (waveform signals of different frequencies). A multi-carrier transmitter can transmit modulated signals on multiple carriers simultaneously. For example, each communication link may be a multi-carrier signal modulated according to various radio technologies. Each modulated signal may be transmitted on a different carrier and may carry control information (e.g., reference signals, control channels, etc.), overhead information, data, etc.

[0112] The base station can wirelessly communicate with terminal 11 via one or more access point antennas. Each base station can provide communication coverage for its respective coverage area. The coverage area of ​​an access point can be divided into sectors that constitute only a part of that coverage area. The wireless communication system may include different types of base stations (e.g., macro base stations, micro base stations, or pico base stations). Base stations may also utilize different radio technologies, such as cellular or WLAN radio access technologies. Base stations may be associated with the same or different access networks or operator deployments. The coverage areas of different base stations (including coverage areas of the same or different types of base stations, coverage areas using the same or different radio technologies, or coverage areas belonging to the same or different access networks) may overlap.

[0113] Communication links in a wireless communication system may include an uplink for carrying uplink (UL) transmissions (e.g., from terminal 11 to network device 12) or a downlink for carrying downlink (DL) transmissions (e.g., from network device 12 to terminal 11). UL transmissions may also be referred to as reverse link transmissions, and DL transmissions may also be referred to as forward link transmissions. Downlink transmissions may be carried out using licensed frequency bands, unlicensed frequency bands, or both. Similarly, uplink transmissions may be carried out using licensed frequency bands, unlicensed frequency bands, or both.

[0114] This invention introduces an intelligent, endogenous model parameter transmission method. By integrating intelligence as part of the base station and combining it with wireless data transmission functions, model parameters can be transmitted faster and more reliably. This achieves the organic integration of model algorithms, interaction processes, and wireless communication, enabling the base station to achieve self-optimization, self-evolution, and self-generation.

[0115] Specifically, this invention provides a method for transmitting AI-native data. The data to be transmitted includes two types, referred to as first data and second data, respectively. The first data is the control signaling for the AI ​​task (referred to as AI-C in this document), which may include configurations for establishing end-to-end AI, configurations for task interruption or termination, management information for the AI ​​model, configuration information for data acquisition, and other information controlling the correct operation of the end-to-end AI task. The second data is AI model parameters and / or data acquisition information (referred to as AI-U in this document), which may include synchronization information between the network and the terminal during AI model training, such as parameter updates under federated learning, model transfer information in transfer learning, or AI model transmission in the case of model segmentation in distributed AI, and also includes pre-processed data acquisition information and / or data labeling information.

[0116] Please refer to Figure 2 and Figure 3 The present invention provides a data transmission method, which, when applied to a base station, includes:

[0117] Step 21: The MAC layer of the base station interacts with the terminal through a MAC control packet or a MAC control unit to exchange first data and / or second data, wherein the first data is control signaling for the artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0118] Traditional AI data transmission involves the core network, access network, and terminal. However, in the case of AI being inherent, intelligence is ubiquitous in the network. The wireless side also possesses local intelligent agents. To improve the efficiency and reliability of AI data transmission, this invention employs a novel data transmission method.

[0119] Through the above steps, embodiments of the present invention can achieve reliable transmission of AI data by exchanging first data and / or second data between the terminal and the base station through a MAC control packet or MAC control unit.

[0120] like Figure 3 As shown, the base station also includes a first AI function module for implementing AI functions, and the first data and the second data may be generated by the first AI function module.

[0121] In step 21 above: the MAC layer of the base station receives the first MAC control packet or MAC control unit sent by the terminal, obtains the first data and / or the second data encapsulated in the first MAC control packet or MAC control unit, and sends it to the first AI function module;

[0122] And / or,

[0123] The MAC layer of the base station receives first data and / or second data sent by the first AI function module, encapsulates the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit, and then sends it to the terminal.

[0124] In this embodiment of the invention, the MAC layer multiplexes the first and / or second data to be transmitted into a transport block (TB) and delivers it to the physical layer (PHY). The physical layer receives the first and / or second data sent by other devices, demultiplexes the first and / or second data, and submits it to the first AI function module. The MAC layer provides data transmission services for receiving the first and second data generated by the first AI function module. On the network side, for the first and / or second data generated by the first AI function module, the MAC layer forms MAC control packets or control units according to these data and sends them to the terminal side through the physical layer; the receiving terminal side receives the MAC control packets or control units through the physical layer, demultiplexes them, and submits them to the terminal's second AI function module. On the terminal side, for the first and / or second data generated by the second AI function module, the MAC layer forms MAC control packets or control units according to these data and sends them to the network side through the physical layer; the network side receives the MAC control packets or control units through the physical layer, demultiplexes them, and submits them to the network's first AI function module. This method effectively reduces the number of processing units involved in AI data transmission and reduces the latency of AI data transmission. Simultaneously, mechanisms such as HARQ in the MAC layer can also ensure data reliability.

[0125] Specifically, the first data includes at least one of the following categories of data packets:

[0126] a) AI connection establishment request signaling.

[0127] The AI ​​connection establishment request is usually a data packet sent by the terminal to the network. It is used by AI-capable terminals within the network to actively report the AI ​​capabilities they support, which is then used to establish an AI connection.

[0128] b) Signaling for establishing an AI connection.

[0129] This data packet is sent from the network to the terminal, and includes the terminal's user ID, used to establish an AI connection between the network and the terminal. The base station assigns a user ID to the terminal corresponding to the AI ​​connection; this user ID is a unique identifier that distinguishes the terminal from the AI's intrinsic module.

[0130] c) Signaling for establishing end-to-end AI tasks.

[0131] This data packet is sent from the network side to the terminal, instructing the terminal to establish the corresponding AI task according to the network side's requirements. The first data segment may contain one or more identifiers such as the task ID, AI model type, initial parameter configuration, user ID, data collection requirements and reporting configuration, and data preprocessing method. The task ID is used to distinguish different AI tasks; the task ID carried in this data packet represents the identifier of the end-to-end AI task to be established. The AI ​​model type and initial configuration parameter configuration indicate the model used by the current AI task. If the terminal does not have model information, it obtains the corresponding model by receiving the initial configuration. The user ID refers to the user ID used in establishing the AI ​​connection.

[0132] d) Stop or interrupt signaling for end-to-end AI tasks.

[0133] This type of MAC control packet or MAC control unit is a data packet sent from the network side to the terminal to instruct the terminal to stop ongoing AI tasks, including AI model calculations and data acquisition. The data packet includes information such as the task ID and user ID.

[0134] e) Release signaling for AI connection.

[0135] This type of MAC control packet or MAC control unit is a data packet sent by the terminal to the network to instruct the network that the UE wants to release the AI ​​connection. After receiving the AI ​​connection release message, the network stops the AI ​​task running for the user and releases the UE's user ID.

[0136] f) Management signaling for AI models.

[0137] g) Configuration signaling for data acquisition.

[0138] The second data includes at least one of the following categories:

[0139] a) Synchronization information between the base station and the terminal during AI model training.

[0140] This type of MAC control packet or control unit can be sent from the network to the terminal, or from the terminal to the network. It is used for real-time parameter synchronization between the network and the terminal. For example, in federated learning, the terminal reports local model parameters to the network, and the network generates global model parameters and sends them to the terminal.

[0141] b) Preprocessed collected data and / or tag information.

[0142] These MAC control packets or control units are sent from the terminal to the network, or vice versa. According to the data acquisition configuration in the end-to-end task setup, the terminal or network generates corresponding data acquisition packets and sends them to the peer. The data acquisition packets carry the task ID corresponding to the data acquisition, the model type, the user ID, and the data acquisition type ID (determined by the initial configuration in the end-to-end task setup). The terminal sends the data according to the data processing requirements and format. For example, data acquisition includes, but is not limited to, raw data reporting, pre-processed data reporting, and data that has undergone partial model processing.

[0143] In this embodiment of the invention, there are two transmission methods for MAC control packets or MAC control units. As the first transmission method, this embodiment introduces a format for MAC control packets or control units (referred to as the first format for ease of description). Both the first data and the second data are encapsulated in this format of MAC control packets or control units. When the MAC at the other end receives the first format MAC control packet or control unit, it parses out the corresponding first data and / or second data and submits it to the AI ​​function module.

[0144] Specifically, such as Figure 4 As shown, the MAC control package or MAC control unit of the first format includes first format indication information, data length indication information, first data and / or second data, wherein the first format indication information is used to indicate that the MAC control package or MAC control unit carries the first data and / or second data.

[0145] Thus, in step 21 above, the MAC layer of the base station can determine the first format according to the first format indication information in the first MAC control packet or MAC control unit; parse the first MAC control packet or MAC control unit according to the first format to obtain the first data and / or the second data encapsulated therein; and encapsulate the first data and / or the second data sent by the first AI function module into the second MAC control packet or MAC control unit according to the first format, and then send it out through the physical layer.

[0146] As a second transmission method, embodiments of the present invention can introduce corresponding MAC control packets or control units for different categories of first data / second data. In this case, both the first MAC control packet or MAC control unit and the second MAC control packet or MAC control unit include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or second data encapsulated in the respective MAC control packet or MAC control unit.

[0147] Thus, in step 21 above, the MAC layer of the base station can determine the first target format according to the format indication information in the first MAC control packet or MAC control unit; and parse the first MAC control packet or MAC control unit according to the first target format to obtain the first data and / or second data encapsulated therein.

[0148] In step 21 above, the MAC layer of the base station can also determine the corresponding second target format according to the type of the first data and / or the second data packet sent by the first AI function module; and encapsulate the first data and / or the second data sent by the first AI function module into a second MAC control packet or MAC control unit according to the second target format, wherein the format indication information in the second MAC control packet or MAC control unit indicates the second target format.

[0149] The following provides examples illustrating the format of the MAC control packet or MAC control unit involved in the second transmission method described above. Here, the second transmission method includes, for example... Figures 5 to 11 The seven formats shown are respectively called the second format, the third format, ... the eighth format.

[0150] A) The second format corresponds to the AI ​​connection establishment request signaling;

[0151] Here, the second-format MAC control packet or control unit is sent from the terminal to the network. The terminal receives the first message from the second AI function module (this message is used by the terminal to send an AI connection request to the base station), adds a second-format instruction, assembles a second-format MAC control packet or control unit, and sends it to the network through the physical layer. The network receives the TB block containing the second-format MAC control packet or control unit, demultiplexes it according to the second-format instruction to obtain the first message, and delivers it to the first AI function module.

[0152] B) The third format corresponds to the AI ​​connection establishment signaling.

[0153] Here, after receiving the second-format control packet or control unit identifier, the MAC on the network side adds a third-format identifier and / or assigns a user identifier for AI connection to the terminal, and notifies the first AI function module of the identifier. The first AI function module then sends a second message (used by the network to initiate AI connection establishment to the terminal) to the MAC. The third-format MAC control packet or control unit is sent from the network to the terminal. Upon receiving the second message from the first AI function module, the network adds a third-format instruction to assemble a third-format MAC control packet or control unit, which is then sent to the terminal through the physical layer. The terminal receives the TB block containing the third-format MAC control packet or control unit, demultiplexes it according to the third-format instruction to obtain the second message, and delivers it to the second AI function module.

[0154] C) The fourth format corresponds to the establishment signaling of the end-to-end AI task.

[0155] Here, the fourth-format MAC control packet or control unit is sent from the network to the terminal. On the network side, the MAC receives the third message (used for terminal task AI establishment) from the first AI function module, adds the fourth-format identifier and / or the user identifier for AI connection and / or the task identifier / data length marker, forming the fourth-format MAC control packet or control unit, which is then sent to the terminal through the physical layer. The terminal receives the TB block containing the fourth-format MAC control packet or control unit, demultiplexes it according to the fourth-format instructions to obtain the third message, and delivers it to the second AI function module.

[0156] D) The fifth format corresponds to the synchronization information between the base station and the terminal during the AI ​​model training process.

[0157] Here, the fifth-format MAC control packet or control unit can be sent from the network to the terminal, or from the terminal to the network. At the sending end, the MAC receives the fourth message (used for model and parameter synchronization, e.g., in federated learning, the terminal reports local model parameters to the network, which then generates global model parameters and sends them to the terminal) from its local AI function module. It adds a fifth-format identifier and / or a user identifier for AI connection and / or a task identifier and / or data length marker to form a fifth-format MAC control packet or control unit, which is then sent to the receiving end through the physical layer. The receiving end MAC receives the TB block containing the fifth-format MAC control packet or control unit, demultiplexes it according to the fifth-format instructions to obtain the fourth message, and delivers it to its local AI function module.

[0158] E) The sixth format corresponds to the preprocessed acquired data and / or tag information.

[0159] Here, the sixth-format MAC control packet or control unit can be sent from the network to the terminal, or from the terminal to the network. At the sending end, the MAC receives the fifth message (used to transmit data acquisition results) from its local AI function module, adds a sixth-format identifier and / or a user identifier for AI connection and / or a task identifier and / or a data acquisition identifier and / or data length to form a sixth-format MAC control packet or control unit, and sends it to the receiving end through the physical layer. The receiving end MAC receives the TB block containing the sixth-format MAC control packet or control unit, demultiplexes it according to the sixth-format instructions to obtain the fifth message, and delivers it to its local AI function module.

[0160] F) The seventh format corresponds to the stop or interrupt signaling for end-to-end AI tasks.

[0161] Here, the seventh-format MAC control packet or control unit is sent from the network to the terminal. At the sending end, the MAC receives the sixth message from the first module (used to stop ongoing AI tasks such as model calculations or data acquisition), adds a seventh-format identifier and / or a user identifier for AI connection and / or a task identifier and / or data length marker, assembles a seventh-format MAC control packet or control unit, and sends it to the receiving end through the physical layer. The receiving end MAC receives the TB block containing the seventh-format MAC control packet or control unit, demultiplexes it according to the seventh-format instructions to obtain the sixth message, and delivers it to the first module.

[0162] G) The eighth format corresponds to the release signaling of the AI ​​connection.

[0163] Here, the eighth-format MAC control packet or control unit is sent from the terminal to the network. At the sending end, the MAC receives the seventh message from the first module (e.g., used to instruct the network that the UE wants to release the ongoing AI task such as model calculation or data acquisition), adds the eighth-format identifier and / or the user identifier and / or data length for the AI ​​connection, assembles the eighth-format MAC control packet or control unit, and sends it to the receiving end through the physical layer. The receiving end MAC receives the TB block containing the eighth-format MAC control packet or control unit, demultiplexes it according to the eighth-format instructions to obtain the seventh message, and delivers it to the first module. After receiving the eighth-format MAC control packet or control unit data, the first module stops the AI ​​task running for that user and releases the UE's user ID.

[0164] For example, the first target format can be a second format, a fifth format, a sixth format, or an eighth format; the second target format can be a third format, a fourth format, a fifth format, a sixth format, or a seventh format.

[0165] from Figures 5 to 11 It can be seen that each format of MAC control packet or MAC control unit includes format indication information, data length indication information, the first data and / or the second data; wherein, the third, fourth, fifth, sixth, seventh and eighth formats also include a user identifier for indicating AI connection; the fourth, fifth, sixth and seventh formats also include a task ID for indicating AI task; the sixth format also includes a data acquisition ID.

[0166] In addition, in the second transmission method described above, if the first target format is determined to be the second format based on the format indication information in the first MAC control packet or MAC control unit, the MAC layer of the base station can also assign a user identifier to the terminal to indicate the AI ​​connection, and send the user identifier and the AI ​​connection establishment request signaling to the first AI function module; and after receiving the AI ​​connection establishment signaling sent by the first AI function module, the MAC layer of the base station encapsulates the second MAC control packet or MAC control unit including the format indication information, the user identifier, the data length indication information and the AI ​​connection establishment signaling, and then sends it to the peer device through the physical layer.

[0167] As can be seen from the above, the data transmission method provided by the embodiments of the present invention can reduce the latency of AI data transmission and ensure the reliability of data transmission. In addition, the architecture can make full use of the AI ​​capabilities of the terminal and improve the end-to-end AI capabilities.

[0168] Please refer to Figure 12 The present invention provides a data transmission method, which, when applied to a terminal, includes:

[0169] Step 121: The MAC layer of the terminal interacts with the base station with first data and / or second data through a MAC control packet or a MAC control unit, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0170] Through the above steps, this embodiment of the invention reduces the latency of AI data transmission and ensures the reliability of data transmission.

[0171] like Figure 3 As shown, the terminal also includes a second AI function module, wherein the interaction of the first data and / or the second data with the base station via the MAC control packet or the MAC control unit includes:

[0172] The MAC layer of the terminal receives first data and / or second data sent by the second AI function module, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station.

[0173] And / or,

[0174] The MAC layer of the terminal receives the second MAC control packet or MAC control unit sent by the base station, obtains the first data and / or the second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module.

[0175] In the first transmission method described above, in step 121, the MAC layer of the terminal can encapsulate the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit according to the first format; and determine the first format according to the first format indication information in the second MAC control packet or MAC control unit; and parse the second MAC control packet or MAC control unit according to the first format to obtain the first data and / or the second data encapsulated therein.

[0176] In the first transmission method described above, in step 121, the MAC layer of the terminal can determine the corresponding first target format based on the type of the first data and / or second data packet sent by the second AI function module; according to the first target format, encapsulate the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, wherein the format indication information in the first MAC control packet or MAC control unit indicates the first target format; and, according to the format indication information in the second MAC control packet or MAC control unit, determine a second target format; according to the second target format, parse the second MAC control packet or MAC control unit to obtain the first data and / or second data encapsulated therein.

[0177] For information on the categories of the first and second data, as well as the formats of the MAC control packets or MAC control units used under different transmission methods, please refer to the above description; further details will not be provided here.

[0178] The various methods of the embodiments of the present invention have been described above. Apparatus for implementing the above methods will now be provided.

[0179] The embodiments of the present invention provide Figure 13 The base station shown includes:

[0180] The first MAC layer module 131 is used to interact with the terminal through a MAC control packet or a MAC control unit to exchange first data and / or second data, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0181] Optionally, the first MAC layer module 131 is further configured to:

[0182] Receive the first MAC control packet or MAC control unit sent by the terminal, obtain the first data and / or second data encapsulated in the first MAC control packet or MAC control unit, and send them to the first AI function module;

[0183] And / or,

[0184] The system receives first data and / or second data sent by the first AI function module, encapsulates the first data and / or second data sent by the first AI function module into a second MAC control package or MAC control unit, and then sends it to the terminal.

[0185] Optionally, the first MAC layer module 131 is further configured to:

[0186] Based on the first format indication information in the first MAC control packet or MAC control unit, determine the first format; according to the first format, parse the first MAC control packet or MAC control unit to obtain the first data and / or second data encapsulated therein;

[0187] According to the first format, the first data and / or the second data sent by the first AI function module are encapsulated into the second MAC control package or MAC control unit.

[0188] Optionally, the first MAC layer module 131 is further configured to:

[0189] Based on the format indication information in the first MAC control packet or MAC control unit, determine the first target format; according to the first target format, parse the first MAC control packet or MAC control unit to obtain the first data and / or the second data encapsulated therein;

[0190] Based on the type of the first data and / or second data packet sent by the first AI function module, a corresponding second target format is determined; according to the second target format, the first data and / or second data sent by the first AI function module are encapsulated into a second MAC control packet or MAC control unit, wherein the format indication information in the second MAC control packet or MAC control unit indicates the second target format.

[0191] Optionally, the first MAC layer module 131 is further configured to, when the first target format determined according to the format indication information in the first MAC control packet or MAC control unit is the second format:

[0192] The terminal is assigned a user identifier to indicate an AI connection, and the user identifier and the AI ​​connection establishment request signaling are sent to the first AI function module.

[0193] After receiving the AI ​​connection establishment signaling sent by the first AI function module, a second MAC control packet or MAC control unit is encapsulated, which includes the format indication information, the user identifier, the data length indication information, and the AI ​​connection establishment signaling.

[0194] It should be noted that the device in this embodiment is the same as the one described above. Figure 2 The devices corresponding to the methods shown are all applicable to the embodiments of the above-described devices, and can achieve the same technical effects. It should be noted that the devices provided in this embodiment can implement all the method steps implemented in the above-described method embodiments and achieve the same technical effects. Therefore, the parts and beneficial effects that are the same as those in the method embodiments will not be described in detail here.

[0195] Please refer to Figure 14 This invention provides a schematic diagram of a base station structure, including: a processor 1401, a transceiver 1402, a memory 1403, and a bus interface, wherein:

[0196] In this embodiment of the invention, the base station further includes: a program stored on a memory 1403 and executable on a processor 1401, wherein the program, when executed by the processor 1401, performs the following steps:

[0197] The terminal interacts with first and / or second data via a MAC control package or MAC control unit, wherein the first data is control signaling for the artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0198] Optionally, when the processor executes the program, it further implements the following steps:

[0199] The base station receives a first MAC control packet or MAC control unit sent by the terminal through the MAC layer, obtains the first data and / or second data encapsulated in the first MAC control packet or MAC control unit, and sends it to the first AI function module.

[0200] And / or,

[0201] The base station receives first data and / or second data sent by the first AI function module through the MAC layer, encapsulates the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit, and then sends it to the terminal.

[0202] Optionally, when the processor executes the program, it further implements the following steps:

[0203] The base station's MAC layer determines a first format based on the first format indication information in the first MAC control packet or MAC control unit; and according to the first format, it parses the first MAC control packet or MAC control unit to obtain the first data and / or second data encapsulated therein.

[0204] Through the MAC layer of the base station, the first data and / or the second data sent by the first AI function module are encapsulated into a second MAC control packet or MAC control unit in the first format.

[0205] Optionally, when the processor executes the program, it further implements the following steps:

[0206] The base station's MAC layer determines a first target format based on the format indication information in the first MAC control packet or MAC control unit; and according to the first target format, it parses the first MAC control packet or MAC control unit to obtain the first data and / or second data encapsulated therein.

[0207] The MAC layer of the base station determines the corresponding second target format based on the type of the first data and / or second data packet sent by the first AI function module; according to the second target format, the first data and / or second data sent by the first AI function module are encapsulated into a second MAC control packet or MAC control unit, wherein the format indication information in the second MAC control packet or MAC control unit indicates the second target format.

[0208] Optionally, when the processor executes the program, it further implements the following steps:

[0209] If, through the MAC layer of the base station, the first target format is determined to be the second format based on the format indication information in the first MAC control packet or MAC control unit:

[0210] The terminal is assigned a user identifier to indicate an AI connection, and the user identifier and the AI ​​connection establishment request signaling are sent to the first AI function module.

[0211] After receiving the AI ​​connection establishment signaling sent by the first AI function module, a second MAC control packet or MAC control unit is encapsulated, which includes the format indication information, the user identifier, the data length indication information, and the AI ​​connection establishment signaling.

[0212] Understandably, in this embodiment of the invention, the computer program executed by the processor 1401 can achieve the above-mentioned functions. Figure 2 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0213] exist Figure 14In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, including one or more processors represented by processor 1401 and memory represented by memory 1403. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1402 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium.

[0214] The processor 1401 is responsible for managing the bus architecture and general processing, while the memory 1403 can store the data used by the processor 1401 when performing operations.

[0215] It should be noted that the terminal in this embodiment is the same as the one described above. Figure 2 The device corresponding to the method shown above, and the implementation methods in each embodiment above, are all applicable to the embodiments of this terminal, and can achieve the same technical effect. In this device, the transceiver 1402 and the memory 1403, as well as the transceiver 1402 and the processor 1401, can be connected for communication via a bus interface. The function of the processor 1401 can also be implemented by the transceiver 1402, and the function of the transceiver 1402 can also be implemented by the processor 1401. It should be noted that the device provided by the embodiments of the present invention can implement all the method steps implemented in the above method embodiments and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail.

[0216] In some embodiments of the present invention, a computer-readable storage medium is also provided, on which a program is stored, which, when executed by a processor, performs the following steps:

[0217] The terminal interacts with first and / or second data via a MAC control package or MAC control unit, wherein the first data is control signaling for the artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0218] When executed by the processor, this program can implement all the above-mentioned data transmission methods applied to the base station and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0219] Please refer to Figure 15 This invention provides a terminal, comprising:

[0220] The second MAC layer module 151 is used to interact with the base station with first data and / or second data through a MAC control packet or a MAC control unit, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0221] Optionally, the second MAC layer module 151 is further configured to:

[0222] The terminal receives first data and / or second data sent by the second AI function module through the MAC layer, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station.

[0223] And / or,

[0224] The MAC layer of the terminal receives the second MAC control packet or MAC control unit sent by the base station, obtains the first data and / or the second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module.

[0225] Optionally, the second MAC layer module 151 is further configured to:

[0226] According to the first format, the first data and / or the second data sent by the second AI function module are encapsulated into the first MAC control packet or MAC control unit;

[0227] Based on the first format indication information in the second MAC control package or MAC control unit, determine the first format; according to the first format, parse the second MAC control package or MAC control unit to obtain the first data and / or second data encapsulated therein.

[0228] Optionally, the second MAC layer module 151 is further configured to:

[0229] Based on the type of the first data and / or the second data packet sent by the second AI function module, determine the corresponding first target format; according to the first target format, encapsulate the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit, wherein the format indication information in the first MAC control packet or MAC control unit indicates the first target format;

[0230] Based on the format indication information in the second MAC control package or MAC control unit, determine the second target format; according to the second target format, parse the second MAC control package or MAC control unit to obtain the first data and / or the second data encapsulated therein.

[0231] It should be noted that the device in this embodiment is the same as the one described above. Figure 12 The devices corresponding to the methods shown are all applicable to the embodiments of the above-described devices, and can achieve the same technical effects. The devices provided by the embodiments of the present invention can implement all the method steps implemented in the above-described method embodiments and can achieve the same technical effects. Therefore, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail here.

[0232] Please refer to Figure 16 The present invention provides a schematic diagram of the structure of a terminal, which includes: a processor 1601, a transceiver 1602, a memory 1603, a user interface 1604, and a bus interface.

[0233] In this embodiment of the invention, the terminal further includes a program stored on memory 1603 and executable on processor 1601.

[0234] When the processor 1601 executes the program, it performs the following steps:

[0235] The system interacts with the base station via a MAC control packet or MAC control unit, where the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0236] Optionally, when the processor executes the program, it further implements the following steps:

[0237] The terminal receives first data and / or second data sent by the second AI function module through the MAC layer, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station.

[0238] And / or,

[0239] The MAC layer of the terminal receives the second MAC control packet or MAC control unit sent by the base station, obtains the first data and / or the second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module.

[0240] Optionally, when the processor executes the program, it further implements the following steps:

[0241] Through the MAC layer of the terminal, the first data and / or the second data sent by the second AI function module are encapsulated into the first MAC control packet or MAC control unit according to the first format;

[0242] Based on the first format indication information in the second MAC control package or MAC control unit, determine the first format; according to the first format, parse the second MAC control package or MAC control unit to obtain the first data and / or second data encapsulated therein.

[0243] Optionally, when the processor executes the program, it further implements the following steps:

[0244] The terminal's MAC layer determines the corresponding first target format based on the type of the first data and / or second data packet sent by the second AI function module; according to the first target format, the first data and / or second data sent by the second AI function module are encapsulated into a first MAC control packet or MAC control unit, wherein the format indication information in the first MAC control packet or MAC control unit indicates the first target format;

[0245] Based on the format indication information in the second MAC control package or MAC control unit, determine the second target format; according to the second target format, parse the second MAC control package or MAC control unit to obtain the first data and / or the second data encapsulated therein.

[0246] Understandably, in this embodiment of the invention, the computer program executed by the processor 1601 can achieve the above-mentioned functions. Figure 12 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0247] exist Figure 16 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, such as one or more processors represented by processor 1601 and memory represented by memory 1603. The bus architecture can also link together various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1602 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. For different user equipment, the user interface 1604 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0248] The processor 1601 is responsible for managing the bus architecture and general processing, while the memory 1603 can store the data used by the processor 1601 when performing operations.

[0249] It should be noted that the device in this embodiment is the same as the one described above. Figure 12The device corresponding to the method shown above is applicable to the embodiments of this device and can achieve the same technical effect. In this device, the transceiver 1602 and the memory 1603, as well as the transceiver 1602 and the processor 1601, can be connected via a bus interface. The functions of the processor 1601 can also be implemented by the transceiver 1602, and vice versa. It should be noted that the device provided in this embodiment can implement all the method steps of the above method embodiments and achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiments will not be described in detail here.

[0250] In some embodiments of the present invention, a computer-readable storage medium is also provided, on which a program is stored, which, when executed by a processor, performs the following steps:

[0251] The system interacts with the base station via a MAC control packet or MAC control unit, where the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information.

[0252] When executed by the processor, this program can implement all the above-mentioned data transmission methods applied to the terminal side and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0253] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0254] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0255] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0256] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0257] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0258] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0259] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A data transmission method applied to a base station, characterized in that, include: The MAC layer of the base station interacts with the terminal with first data and / or second data through MAC control packets or MAC control units, wherein the first data is control signaling for artificial intelligence (AI) tasks, and the second data is AI model parameters and / or data acquisition information. The base station further includes a first AI function module, wherein the interaction of first data and / or second data with the terminal via a MAC control packet or MAC control unit includes: The MAC layer of the base station receives the first MAC control packet or MAC control unit sent by the terminal, obtains the first data and / or the second data encapsulated in the first MAC control packet or MAC control unit, and sends it to the first AI function module. And / or, The MAC layer of the base station receives first data and / or second data sent by the first AI function module, encapsulates the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit, and then sends it to the terminal. The first data includes: AI connection establishment request signaling; The first MAC control package or MAC control unit, and the second MAC control package or MAC control unit, both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit; The step of obtaining the first data and / or the second data encapsulated in the first MAC control package or MAC control unit includes: determining a first target format according to the format indication information in the first MAC control package or MAC control unit; and parsing the first MAC control package or MAC control unit according to the first target format to obtain the first data and / or the second data encapsulated therein.

2. The method as described in claim 1, characterized in that, The first data also includes the following category: AI connection establishment signaling; Signaling for establishing end-to-end AI tasks; End-to-end AI task stop or interruption signaling; Release signaling for AI connectivity; Management signaling for AI models; Configuration signaling for data acquisition; The second data includes at least one of the following categories: Synchronization information between base stations and terminals during AI model training; Preprocessed collected data and / or tag information.

3. The method as described in claim 1 or 2, characterized in that, The first MAC control packet or MAC control unit and the second MAC control packet or MAC control unit are both MAC control packets or MAC control units of a first format. The first format MAC control packet or MAC control unit includes first format indication information, data length indication information, first data and / or second data, wherein the first format indication information is used to indicate that the MAC control packet or MAC control unit carries the first data and / or the second data.

4. The method as described in claim 3, characterized in that, The step of obtaining the first data and / or the second data encapsulated in the first MAC control package or MAC control unit includes: determining a first format according to the first format indication information in the first MAC control package or MAC control unit; and parsing the first MAC control package or MAC control unit according to the first format to obtain the first data and / or the second data encapsulated therein. The step of encapsulating the first data and / or the second data sent by the first AI function module into the second MAC control package or MAC control unit includes: encapsulating the first data and / or the second data sent by the first AI function module into the second MAC control package or MAC control unit according to the first format.

5. The method as described in claim 1, characterized in that, Also includes: The step of encapsulating the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit includes: determining a corresponding second target format according to the type of the first data and / or second data packet sent by the first AI function module; and encapsulating the first data and / or second data sent by the first AI function module into a second MAC control packet or MAC control unit according to the second target format, wherein the format indication information in the second MAC control packet or MAC control unit indicates the second target format.

6. The method as described in claim 5, characterized in that, The first target format is a second, fifth, sixth, or eighth format; the second target format is a third, fourth, fifth, sixth, or seventh format; wherein, The second format corresponds to the AI ​​connection establishment request signaling; The third format corresponds to the signaling for establishing an AI connection; The fourth format corresponds to the signaling for establishing an end-to-end AI task; The fifth format corresponds to the synchronization information between the base station and the terminal during the AI ​​model training process; The sixth format corresponds to the preprocessed collected data and / or tag information; The seventh format corresponds to the stop or interrupt signaling for end-to-end AI tasks; The eighth format corresponds to the release signaling of the AI ​​connection.

7. The method as described in claim 6, characterized in that, Each format of MAC control packet or MAC control unit includes format indication information, data length indication information, the first data and / or the second data; The third, fourth, fifth, sixth, seventh, and eighth formats also include a user identifier for indicating AI connection; The fourth, fifth, sixth, and seventh formats also include a task ID for indicating the AI ​​task; The sixth format also includes a data acquisition ID.

8. The method as described in claim 6, characterized in that, If the first target format is determined to be the second format based on the format indication information in the first MAC control packet or MAC control unit, the method further includes: The MAC layer of the base station assigns a user identifier to the terminal to indicate the AI ​​connection, and sends the user identifier and the AI ​​connection establishment request signaling to the first AI function module; After receiving the AI ​​connection establishment signaling sent by the first AI function module, the MAC layer of the base station encapsulates a second MAC control packet or MAC control unit that includes the format indication information, the user identifier, the data length indication information, and the AI ​​connection establishment signaling.

9. A data transmission method applied to a terminal, characterized in that, include: The MAC layer of the terminal interacts with the base station with first data and / or second data through MAC control packets or MAC control units, wherein the first data is control signaling for artificial intelligence (AI) tasks, and the second data is AI model parameters and / or data acquisition information. The terminal further includes a second AI function module, wherein the interaction of first data and / or second data with the base station via a MAC control packet or MAC control unit includes: The MAC layer of the terminal receives first data and / or second data sent by the second AI function module, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station. And / or, The MAC layer of the terminal receives the second MAC control packet or MAC control unit sent by the base station, obtains the first data and / or the second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module. The first data includes: AI connection establishment request signaling; The first MAC control package or MAC control unit and the second MAC control package or MAC control unit both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit.

10. The method as described in claim 9, characterized in that, The first data also includes the following category: AI connection establishment signaling; Signaling for establishing end-to-end AI tasks; End-to-end AI task stop or interruption signaling; Release signaling for AI connectivity; Management signaling for AI models; Configuration signaling for data acquisition; The second data includes at least one of the following categories: Synchronization information between base stations and terminals during AI model training; Preprocessed collected data and / or tag information.

11. The method as described in claim 9 or 10, characterized in that, The first MAC control packet or MAC control unit and the second MAC control packet or MAC control unit are both MAC control packets or MAC control units of a first format. The first format MAC control packet or MAC control unit includes first format indication information, data length indication information, first data and / or second data, wherein the first format indication information is used to indicate that the MAC control packet or MAC control unit carries the first data and / or the second data.

12. The method as described in claim 11, characterized in that, The step of encapsulating the first data and / or the second data sent by the second AI function module into the first MAC control package or MAC control unit includes: encapsulating the first data and / or the second data sent by the second AI function module into the first MAC control package or MAC control unit according to the first format; The step of obtaining the first data and / or the second data encapsulated in the second MAC control package or MAC control unit includes: determining a first format according to the first format indication information in the second MAC control package or MAC control unit; and parsing the second MAC control package or MAC control unit according to the first format to obtain the first data and / or the second data encapsulated therein.

13. The method as described in claim 9, characterized in that, Also includes: The step of encapsulating the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit includes: determining a corresponding first target format according to the type of the first data and / or the second data packet sent by the second AI function module; encapsulating the first data and / or the second data sent by the second AI function module into a first MAC control packet or MAC control unit according to the first target format, wherein the format indication information in the first MAC control packet or MAC control unit indicates the first target format; The step of obtaining the first data and / or the second data encapsulated in the second MAC control package or MAC control unit includes: determining a second target format according to the format indication information in the second MAC control package or MAC control unit; and parsing the second MAC control package or MAC control unit according to the second target format to obtain the first data and / or the second data encapsulated therein.

14. The method as described in claim 13, characterized in that, The first target format is a second, fifth, sixth, or eighth format; the second target format is a third, fourth, fifth, sixth, or seventh format; wherein, The second format corresponds to the AI ​​connection establishment request signaling; The third format corresponds to the signaling for establishing an AI connection; The fourth format corresponds to the signaling for establishing an end-to-end AI task; The fifth format corresponds to the synchronization information between the base station and the terminal during the AI ​​model training process; The sixth format corresponds to the preprocessed collected data and / or tag information; The seventh format corresponds to the stop or interrupt signaling for end-to-end AI tasks; The eighth format corresponds to the release signaling of the AI ​​connection.

15. The method as described in claim 14, characterized in that, Each format of MAC control packet or MAC control unit includes format indication information, data length indication information, the first data and / or the second data; The third, fourth, fifth, sixth, seventh, and eighth formats also include a user identifier for indicating AI connection; The fourth, fifth, sixth, and seventh formats also include a task ID for indicating the AI ​​task; The sixth format also includes a data acquisition ID.

16. A base station, characterized in that, include: The first MAC layer module is used to interact with the terminal through a MAC control packet or a MAC control unit to exchange first data and / or second data, wherein the first data is control signaling for an artificial intelligence (AI) task, and the second data is AI model parameters and / or data acquisition information; The base station also includes a first AI function module; The first MAC layer module is also used for: Receive the first MAC control packet or MAC control unit sent by the terminal, obtain the first data and / or second data encapsulated in the first MAC control packet or MAC control unit, and send them to the first AI function module; And / or, Receive first data and / or second data sent by the first AI function module, encapsulate the first data and / or second data sent by the first AI function module into a second MAC control package or MAC control unit, and then send it to the terminal. The first data includes: AI connection establishment request signaling; The first MAC control package or MAC control unit, and the second MAC control package or MAC control unit, both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit; The step of obtaining the first data and / or the second data encapsulated in the first MAC control package or MAC control unit includes: determining a first target format according to the format indication information in the first MAC control package or MAC control unit; and parsing the first MAC control package or MAC control unit according to the first target format to obtain the first data and / or the second data encapsulated therein.

17. A base station, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method as described in any one of claims 1 to 8.

18. A terminal, characterized in that, include: The second MAC layer module is used to interact with the base station with first data and / or second data through MAC control packets or MAC control units, wherein the first data is control signaling for artificial intelligence (AI) tasks, and the second data is AI model parameters and / or data acquisition information; The terminal also includes a second AI function module; The second MAC layer module is also used for: The terminal receives first data and / or second data sent by the second AI function module through the MAC layer, encapsulates the first data and / or second data sent by the second AI function module into a first MAC control packet or MAC control unit, and then sends it to the base station. And / or, The terminal receives a second MAC control packet or MAC control unit sent by the base station through the MAC layer, obtains the first data and / or second data encapsulated in the second MAC control packet or MAC control unit, and sends it to the second AI function module. The first data includes: AI connection establishment request signaling; The first MAC control package or MAC control unit and the second MAC control package or MAC control unit both include format indication information; the format indicated by the format indication information corresponds to the category of the first data and / or the second data encapsulated in the respective MAC control package or MAC control unit.

19. A terminal, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method as described in any one of claims 9 to 15.

20. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 15.