Data transmission method and device, and storage medium

Abstract

The present application discloses a data transmission method and apparatus, and a storage medium, belonging to the field of communications technology. In the present application, when sending an AI data request to a second network device, a first network device may include event information of a first AI event in the AI ​​data request, where the first AI event is an event that triggers the second network device to send AI data. In this way, when the second network device detects that the first AI event is met, it can timely send the AI ​​data required by the first network device based on the event information of the first AI event, thereby meeting the various data requirements of the first network device.

Description

[Technical Field]

[0001] The present application relates to the field of communication technology, and in particular to a data transmission method and apparatus, and a storage medium. [Background technology]

[0002] With the improvement of data storage and computing capabilities, artificial intelligence (AI) technology is increasingly being used. For example, in the 3rd generation partnership project (3GPP), AI technology is being applied to wireless communication systems, and it is proposed to improve network performance and user experience through intelligent collection and data analysis.

[0003] However, in wireless communication systems where AI technology is applied, there is currently no method for transmitting AI data between network devices, which makes it difficult for network devices to collect the AI ​​data they need in a timely manner. Summary of the Invention

[0004] The present application provides a data transmission method and apparatus, and a storage medium, so that network devices can collect the AI ​​data they need in a timely manner, thereby meeting various data requirements.

[0005] In order to achieve the above objectives, the following technical solutions are used in this application.

[0006] According to a first aspect, there is provided a data transmission method, which is applied to a first network device, and which includes: sending an AI data request to a second network device, where the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger the second network device to send AI data to the first network device; and receiving the AI ​​data.

[0007] In the present application, when sending an AI data request to a second network device, the first network device may include event information of a first AI event in the AI ​​data request, where the first AI event is an event that triggers the second network device to send AI data. In this way, when the second network device detects that the first AI event is met, it may send AI data to the first network device based on the event information of the first AI event. When triggered by a trigger event specified by the first network device, the second network device may return the AI ​​data required by the first network device in a timely manner, thereby satisfying the various data requirements of the first network device and improving the effectiveness of the first network device's AI model training, inference, or optimization.

[0008] In a first possible implementation, the event information of the first AI event includes an event identifier and configuration parameters of the first AI event, so that the second network device can directly return the AI ​​data required by the first network device based on the event identifier and configuration parameters of the first AI event.

[0009] In a second possible implementation, the event information for the first AI event includes an event identifier for the first AI event.

[0010] In this implementation, before sending an AI data request to the second network device, the first network device may pre-send an AI event information set to the second network device to instruct the second network device to store the AI ​​event information set, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes a first AI event. In other words, the first network device may pre-configure the event identifier of the AI ​​event and corresponding configuration parameters in the second network device. In this way, when acquiring AI data, the first network device includes the event identifier of the first AI event but not the configuration parameters in the AI ​​data request. The second network device obtains the configuration parameters of the first AI event from the event information of the AI ​​event pre-configured in the second network device based on the event identifier of the first AI event, and transmits the AI ​​data to the first network device based on the event identifier and configuration parameters of the first AI event. In this way, signaling overhead when the first network device requests AI data can be reduced.

[0011] Optionally, in the first possible implementation or the second possible implementation, the first network device may further send a configuration update request to the second network device, where the configuration update request includes an event identifier and update information of the first AI event, and the configuration update request is used to request the second network device to update configuration parameters of the first AI event; and receive a configuration update response to the configuration update request sent by the second network device, where the configuration update response indicates whether the second network device has successfully updated the configuration parameters of the first AI event or failed to update.

[0012] In this application, a first network device may use a configuration update request to update the configuration parameters of an AI event configured by the first network device in a second network device, thereby reducing erroneous or unnecessary data transmissions caused by changes in the configuration parameters of an AI event.

[0013] Optionally, the update information in the configuration update request comprises at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, and the update operation may include modifying, adding, and Removal Contains one of the following:

[0014] Optionally, in the present application, the first AI event comprises a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device. For example, the predictive trigger event may be an event that the AI ​​model prediction result of the second network device meets a specified condition of the first network device.

[0015] The predictive trigger event includes at least one of the following: the predicted value of a first measurement item being greater than a corresponding first specified threshold; and the predicted value of the first measurement item being less than a corresponding second specified threshold, where the first specified threshold is greater than the second specified threshold.

[0016] For example, the first measurement item may be a device load, a device energy consumption, or a terminal traffic.

[0017] If the first measurement item is device load, the predictive trigger event may include one or more of the following: the predicted value of the device load is greater than a corresponding first load threshold, and the predicted value of the device load is less than a corresponding second load threshold, where the first load threshold is greater than the second load threshold. In this case, the second network device can return AI data regarding the device load to the first network device based on the predictive trigger event, so that the AI ​​data is used by the first network device to implement an AI use case of load balancing.

[0018] If the first measurement item is device energy consumption, the predictive trigger event may be: the predicted value of the device energy consumption is greater than a corresponding first energy consumption threshold; and the predicted value of the device energy consumption is greater than a corresponding second energy consumption threshold. is less than where the first energy consumption threshold is greater than the second energy consumption threshold. In this case, the second network device can return AI data regarding device energy consumption to the first network device based on the predictive trigger event, so that the AI ​​data is used by the first network device to implement a network energy saving AI use case.

[0019] When the first measurement item is terminal traffic, the predictive trigger event may include one or more of the following: the predicted value of the terminal traffic is greater than a corresponding first traffic threshold; and the predicted value of the terminal traffic is less than a corresponding second traffic threshold, where the first traffic threshold is greater than the second traffic threshold. In this case, the second network device notifies the first network device based on the predictive trigger event. Terminal trafficThe first network device may return AI data related to the first measurement item, which may then be used by the first network device to implement the mobility optimization AI use case. Of course, the first measurement item may alternatively be another measurement item. Correspondingly, the predictive trigger event may alternatively include another event. This is not a limitation of the present application.

[0020] Optionally, in the present application, the first AI event may alternatively have a current measurement type trigger event, and the current measurement type trigger event includes a trigger event based on a current measurement result of the second network device.

[0021] The current measurement type trigger event includes at least one of the following: the current measurement value of the first measurement item is greater than a corresponding third specified threshold; the current measurement value of the first measurement item is less than a corresponding fourth specified threshold; the current measurement value of the second measurement item is different from a predicted value prior to the present time; the error rate between the current measurement value and the predicted value prior to the present time of the third measurement item is greater than a corresponding fifth specified threshold; and the error rate between the current measurement value and the predicted value prior to the present time of the third measurement item is less than a corresponding sixth specified threshold, where the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

[0022] Optionally, the first measurement item includes any one of device load, device energy consumption, and terminal traffic, the second measurement item includes terminal movement path or terminal service, and the third measurement item includes any one of device load, device energy consumption, and terminal traffic.

[0023] It should be noted that in this embodiment of the present application, if the second measurement item is a terminal movement path or a terminal service, the second network device can return AI data related to terminal handover to the first network device based on a current measurement-type trigger event, so that the AI ​​data is used by the first network device to implement the AI ​​use case of mobility optimization.

[0024] Optionally, if the first AI event has a predictive trigger event or a current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a duration of the first AI event. The indication information of the measurement item indicates the measurement item. For example, the indication information of the measurement item may be an identifier of the measurement item.

[0025] Optionally, in the present application, the first AI event may alternatively have a current action type trigger event, where the current action type trigger event includes a trigger event based on a current action of the second network device.

[0026] The current action type trigger event may include at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

[0027] If the first AI event includes a cell being enabled, the configuration parameters of the first AI event may include a cell identifier list and a duration of the first AI event. The second network device may return AI data about the target cell based on the cell being enabled AI event, so that the AI ​​data can be used by the first network device to implement an AI use case such as mobility optimization, load balancing, or the like, for example, to implement an AI model-based cell handover.

[0028] If the first AI event has at least one of the following: the terminal has been successfully handed over and the terminal is in handover, the configuration parameters of the first AI event may include a terminal identifier list and a duration. The second network device can return AI data related to the terminal handover based on the AI ​​event that the terminal has been successfully handed over or the terminal is in handover, so that the AI ​​data is used by the first network device to implement an AI use case of mobility optimization, for example, to implement an AI model-based terminal handover.

[0029] If the first AI event includes an AI use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration. The second network device can return AI data related to the executed AI use case based on the AI ​​event in which the AI ​​use case is being executed, so that the AI ​​data is used by the first network device to implement the corresponding AI use case.

[0030] According to a second aspect, there is provided a data transmission method that is applied to a second network device, the method comprising: receiving an AI data request sent by a first network device, where the AI ​​data request includes event information of a first AI event, the first AI event being used to trigger the second network device to send AI data to the first network device; and sending the AI ​​data to the first network device based on the event information of the first AI event.

[0031] In a first possible implementation, the event information of the first AI event includes an event identifier and configuration parameters of the first AI event. Correspondingly, the implementation process of the second network device sending AI data to the first network device based on the event information of the first AI event may be as follows: the second network device sends AI data to the first network device based on the event identifier and configuration parameters of the first AI event.

[0032] In a second possible implementation, the event information of the first AI event includes an event identifier of the first AI event. Correspondingly, an implementation process in which the second network device transmits AI data to the first network device based on the event information of the first AI event includes: obtaining configuration parameters for the first AI event based on the event identifier of the first AI event; and transmitting AI data to the first network device based on the event identifier and the configuration parameters of the first AI event.

[0033] In this implementation, before receiving the AI ​​data request sent by the first network device, the second network device may further receive an AI event information set sent by the first network device, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes the first AI event; and store the AI ​​event information set to complete the configuration of the AI ​​event.

[0034] Optionally, in the first possible implementation or the second possible implementation, the second network device may further receive a configuration update request sent by the first network device, where the configuration update request includes an event identifier and update information of the first AI event; update configuration parameters of the first AI event based on the event identifier and update information of the first AI event; and send a configuration update response to the first network device, where the configuration update response indicates whether the configuration parameters of the first AI event have been successfully updated or have failed to update. The update information includes at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, and the update operation may include modifying, adding, and Removal The configured event information of the AI ​​event is updated through interaction with the first network device, thereby avoiding erroneous or unnecessary AI data transmission caused by changes in the configuration parameters of the AI ​​event.

[0035] Optionally, in the present application, the first AI event has a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device.

[0036] The predictive trigger event includes at least one of the following: a predicted value of a first measurement item is greater than a corresponding first specified threshold, and a predicted value of the first measurement item is less than a corresponding second specified threshold, where the first specified threshold is greater than the second specified threshold. The first measurement item may be any one of a device load, a device energy consumption, and a terminal traffic.

[0037] Optionally, in the present application, the first AI event comprises a current measurement type trigger event, and the current measurement type trigger event includes a trigger event based on a current measurement result of the second network device.

[0038] The current measurement type trigger event includes at least one of the following: the current measurement value of the first measurement item is greater than a corresponding third specified threshold; the current measurement value of the first measurement item is less than a corresponding fourth specified threshold; the current measurement value of the second measurement item is different from a predicted value prior to the present time; the error rate between the current measurement value and the predicted value prior to the present time of the third measurement item is greater than a corresponding fifth specified threshold; and the error rate between the current measurement value and the predicted value prior to the present time of the third measurement item is less than a corresponding sixth specified threshold, where the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

[0039] The first measurement item includes any one of device load, device energy consumption, and terminal traffic, the second measurement item includes terminal movement path or terminal service, and the third measurement item includes any one of device load, device energy consumption, and terminal traffic.

[0040] Optionally, if the first AI event has a predictive trigger event or a current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a duration of the first AI event. In this case, an implementation process of the second network device sending AI data to the first network device based on the event identifier and configuration parameters of the first AI event may include: detecting the first AI event based on the event identifier of the first AI event, indication information of the measurement item, and / or a specified threshold corresponding to the measurement item; and if the first AI event is continuously detected within the duration, sending AI data to the first network device.

[0041] Optionally, in the present application, the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device.

[0042] The current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

[0043] If the first AI event includes a cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event. An implementation process for sending AI data to the first network device based on the event identifier and configuration parameters of the first AI event may include: detecting an enabled / disabled state of the target cell based on the event identifier of the first AI event, where the cell identifier of the target cell is any cell identifier in the cell identifier list; and sending AI data to the first network device if it is detected that the target cell is in an enabled state within the duration.

[0044] If the first AI event indicates that the terminal has been successfully handed over, the configuration parameters of the first AI event include a terminal identifier list and a duration of the first AI event. An implementation process for sending AI data to the first network device based on the event identifier and configuration parameters of the first AI event may include: detecting a camped state of the target terminal based on the event identifier of the first AI event, where the identifier of the target terminal is any identifier in the terminal identifier list, and the target terminal is a terminal that has been handed over to the second network device; and sending AI data to the first network device if it is detected that the target terminal is continuously camped on the second network device within the duration.

[0045] If the first AI event includes an AI use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration of the first AI event. An implemented process for sending AI data to a first network device based on an event identifier and the configuration parameters of the first AI event may include: detecting a status of execution of the AI ​​use case by a second network device based on the event identifier of the first AI event; and if it is detected that the second network device is executing the AI ​​use case within the duration, sending the AI ​​data to the first network device.

[0046] According to a third aspect, there is provided a data transmission device, comprising at least one module configured to perform the data transmission method according to the first or second aspect.

[0047] According to a fourth aspect, there is provided a data transmission apparatus, comprising a processor configured to execute at least one program instruction or code stored in a memory to implement the data transmission method according to the first or second aspect.

[0048] The data transmission device according to the third or fourth aspect may be a network device or a device used within the network device, such as a chip or a device configured to implement some of the functions of the network device.

[0049] According to a fifth aspect, there is provided a data transmission system, comprising a first network device and a second network device, the first network device configured to perform the data transmission method according to the first aspect, and the second network device configured to perform the data transmission method according to the second aspect.

[0050] According to a sixth aspect, there is provided a computer-readable storage medium having stored thereon instructions that, when executed on a network device, enable the network device to perform the data transmission method according to the first or second aspect.

[0051] According to a seventh aspect, there is provided a computer program product comprising instructions which, when executed on a computer, enable the computer to perform the data transmission method according to the first or second aspect.

[0052] The technical effects obtained in the second to seventh aspects are the same as those obtained by the corresponding technical means in the first aspect, and the details will not be described again here. [Brief explanation of the drawings]

[0053] [Figure 1] FIG. 1 is a diagram of a system architecture for a data transmission method according to an embodiment of the present application.

[0054] [Figure 2] 1 is a diagram of the structure of a base station in an architecture with separated central and distributed units according to one embodiment of the present application;

[0055] [Figure 3] 1 is a structural diagram of a data transmission device according to an embodiment of the present application;

[0056] [Figure 4] 1 is a flowchart of a data transmission method according to an embodiment of the present application;

[0057] [Figure 5] 4 is a flowchart of another data transmission method according to an embodiment of the present application;

[0058] [Figure 6]4 is a flowchart of yet another data transmission method according to an embodiment of the present application;

[0059] [Figure 7] FIG. 10 is a structural diagram of another data transmission device according to an embodiment of the present application;

[0060] [Figure 8] FIG. 10 is a structural diagram of yet another data transmission device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0061] To make the objectives, technical solutions and advantages of the embodiments of the present application more apparent, the implementation of the present application is described in more detail below with reference to the accompanying drawings.

[0062] Before the embodiments of the present application are described in detail, application scenarios for the embodiments of the present application are first described.

[0063] In a wireless communication system using AI technology, a first network device may collect execution data from an access network device, a core network device, a terminal, or another management device to train an AI model. The trained AI model may perform predictions based on the execution data from a second network device and then perform policy adjustments for the second network device based on the prediction results. The first network device may then obtain the adjusted AI data from the second network device and continue optimizing the AI ​​model.

[0064] For example, in a first possible application scenario, AI techniques may be used to implement network energy saving. For example, in this scenario, a first network device may collect data from a RAN to train an AI model. Then, using the trained AI model, the energy efficiency and load state of a second network device in the RAN are predicted, and an energy saving policy of the second network device is configured based on the predicted energy efficiency and load state to maintain a balance between network performance and energy efficiency while reducing energy consumption. Thereafter, the second network device with the configured energy saving policy may feed back data to the first network device to optimize the AI ​​model.

[0065] In a second possible application scenario, AI technology can be used to implement network load balancing. For example, a first network device may collect measurement data, feedback data, historical data, and the like of network devices such as terminals or base stations to train an AI model. The cell load of a second network device is predicted using the trained AI model, and terminal handover procedures or handover parameters are optimized based on the predicted cell load to improve load balancing performance and enhance user experience. The second network device may then feedback data to the first network device to optimize the AI ​​model.

[0066] In a third possible application scenario, mobility optimization can be implemented using AI technology. For example, a first network device collects terminal data from a RAN to train an AI model. Using the trained AI model, a movement path of the terminal is predicted, and radio resource management actions are performed based on the predicted movement path of the terminal, such as selecting a target cell for handover. In this way, a second network device corresponding to a target cell to be selected later can feed back data to the first network device to optimize the AI ​​model.

[0067] The above application scenarios are multiple possible application scenarios in which the AI ​​technology described in the embodiments of the present application is applied to NR. Obviously, in NR, AI technology can also be used to implement other network optimizations. The data transmission method provided in the embodiments of the present application can be used to implement AI data transmission between network devices in NR to which AI technology is applied. AI data is data collected by network devices in the various scenarios described above and used for training, inference, and optimization of AI models.

[0068] 1 is a diagram of a system architecture for a data transmission method according to an embodiment of the present application. As shown in FIG. 1, the system architecture includes a first network device 101 and a second network device 102. A communication connection is established between the first network device 101 and the second network device 102.

[0069] The system architecture may be applicable to multiple communication networks, for example, a fifth generation (5G) mobile communication system such as a long term evolution (LTE) network, an enhanced long term evolution (eLTE) network, or a new radio (NR) network, or a sixth generation (6G) communication system, or another future-oriented communication system. In addition, the communication system provided herein may be used in a terrestrial network (TN) and / or a non-terrestrial network (NTN). This is not limited thereto.

[0070] The first network device 101 may collect AI data from the second network device 102 and use the collected AI data to train, infer, or optimize an AI model. For example, the first network device 101 may send an AI data request to the second network device 102, where the AI ​​data request includes event information of a first AI event. The first AI event may be used to trigger the second network device to send AI data to the first network device. After receiving the AI ​​data request, the second network device 102 sends AI data to the first network device based on the event information of the first AI event.

[0071] In a possible implementation, the AI ​​model may be deployed on the first network device 101. In this case, the first network device 101 may send an AI data request to the second network device 102 when the AI ​​model of the first network device 101 requires training data, inference data, or optimization data. After receiving the AI ​​data request, the second network device 102 may detect a first AI event based on the event information of the first AI event in the AI ​​data request. If it is detected that the first AI event is satisfied, the AI ​​data required by the first network device is returned to the first network device 101.

[0072] Optionally, the AI ​​model may also be deployed on the second network device 102. In this case, the second network device 102 may detect the first AI event based on the prediction result of the AI ​​model deployed on the second network device 102.

[0073] In one example, the first network device 101 or the second network device 102 may be an access network device in a radio access network (RAN). In this application, the access network device may be various types of base stations, such as an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB), or another base station in a future-oriented communication system. In addition, if an eNB is connected to a 5G core network (5G Core network, 5GC), the LTE eNB may also be referred to as an eLTE eNB, and the eLTE eNB may also be considered a base station device in an NR system; the access network device may alternatively be a device such as a radio relay node or a radio backhaul node. The base station may be a macro base station, a micro base station, an indoor base station, or the like. The access network device may alternatively be a module or unit that completes some of the functions of a base station. For example, the access network device may further include a central unit (CU) and / or a distributed unit (DU). For example, the first network device 101 or the second network device 102 may be a base station in an architecture in which the central unit (CU) and the distributed unit (DU) are separated. For example, Figure 2 is a diagram of the structure of a base station in a CU-DU separated architecture. As shown in Figure 2, the base station includes a CU 201 and a DU 202.

[0074] The CU 201 includes a central unit-control plane (CU-CP) 2011 and a central unit-user plane (CU-UP) 2012. The CU-CP 2011 and CU-UP 2012 communicate with each other through an E1 interface. The CU-CP 2011 is configured to implement RRC and control plane packet data convergence protocol-control (PDCP-C) functions. The CU-UP 2012 is configured to implement service data adaptation protocol (SDAP) functions and user plane packet data convergence protocol-user (PDCP-U) functions.

[0075] The DU 202 may communicate with the CU-CP 2011 through an F1-C interface and with the CU-UP 2012 through an F1-U interface. The DU 202 is configured to implement radio link control (RLC), medium access control (MAC), and physical (PHY) layer functions.

[0076] In different systems, the CU (including the CU-CP and the CU-UP) or the DU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (O-RAN) system, the CU may also be referred to as an O-CU (open CU), the DU may also be referred to as an O-DU, the CU-CP may also be referred to as an O-CU-CP, and the CU-UP may also be referred to as an O-CU-UP. For ease of explanation, the CU, CU-CP, CU-UP, and DU are used as examples for explanation in this application. Note that the O-RAN is an intelligent and open access network, and the O-RAN architecture integrates a modular base station software stack on current hardware, allowing baseband components and radio unit components from different vendors to run seamlessly together. The O-RAN architecture is mainly characterized by the separation of software and hardware and implements network function virtualization and hardware standardization.

[0077] In one example, the first network device 101 or the second network device 102 may alternatively be a terminal. As used herein, a terminal may be one of various devices that provide voice and / or data connectivity for a user and may communicate with one or more core networks through a radio access network (RAN). A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, or the like. The terminal may be used in various communication scenarios, such as device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self-driving, telemedicine, smart grid, smart furniture, smart office, smart clothing, smart transportation, or smart city. The terminal device may be a mobile phone, a tablet computer (pad), a computer with wireless transceiver function, a wearable device, an aerospace device, an unmanned aerial vehicle device, or the like. The chip used in the above-mentioned device may also be referred to as a terminal.

[0078] In one example, the first network device 101 or the second network device 102 may alternatively be a core network device or a network device with AI capabilities, such as an operation, administration, and maintenance (OAM) device. This is not specifically limited in the embodiments of the present application. The core network device may include one or more core network elements. A 5G core network is used as an example. The 5G core network includes an access and mobility management function (AMF) network element responsible for mobility management, access management, and other services, a session management function (SMF) network element responsible for session management, a user plane function (UPF) network element responsible for user plane data packet routing and forwarding and quality of service (QoS) control, a policy control function (PCF) network element, and the like. The core network elements may act independently or may be combined together to implement several control functions. For example, the AMF, SMF, and PCF may be combined together to function as a core network device.

[0079] FIG. 3 is a structural diagram of a data transmission device according to an embodiment of the present application.

[0080] The data transmission device may be a network device, or a device used in the network device, such as a chip, or a device used to implement some functions of the network device, such as a CU or DU in a separate base station. The network device in this application may be an access network device, a terminal, or a core network device.

[0081] As shown in Fig. 3, the data transmission device may include at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304. It should be noted that the device structure shown in Fig. 3 does not constitute a limitation on the data transmission device. The data transmission device may include more or fewer components than those shown in the figure, or may combine some components, or may have a different component arrangement. This is not limited to the embodiments of the present application. The components of the data transmission device will be described in detail below with reference to Fig. 3.

[0082] The processor 301 is the central control center of the data transmission device and may be a single processor or a collective term for multiple processing elements. For example, the processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to control program execution of the solutions herein, such as one or more microprocessors (digital signal processors (DSPs)), or one or more field programmable gate arrays (FPGAs). The processor 301 may execute software programs stored in the memory 303 and perform various functions of the data transmission device by accessing data stored in the memory 303. For example, in the embodiments shown in FIGS. 4 to 6, actions of the first network device or the second network device may be performed by the corresponding processor accessing data in the memory.

[0083] In one embodiment, processor 301 may include one or more CPUs, for example, CPU0 and CPU1 in FIG.

[0084] In one embodiment, the data transmission device may include multiple processors, such as processor 301 and processor 305 shown in Figure 3. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may be one or more devices, circuits, and / or processing cores configured to process data (e.g., computer program instructions).

[0085] The communication bus 302 may include a channel for transferring information between the aforementioned components. The communication bus 302 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. Buses may be categorized as address buses, data buses, control buses, and the like. For ease of presentation, only one bold line represents a bus in FIG. 3, but this does not imply that only one bus or only one type of bus is present.

[0086] The memory 303 may be a read-only memory (ROM) or another type of static storage device capable of storing static information and instructions, a random access memory (RAM) or another type of dynamic storage device capable of storing information and instructions, or may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other compact disc storage, an optical disc storage (including a compact optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, or the like), a magnetic disc storage medium or other magnetic storage device, or a storage medium capable of storing the desired program code in the form of instructions or data structures. retention or any other medium accessible by a computer that can be used to store data. However, the memory is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 through the communication bus 302. Alternatively, the memory 303 may be integrated with the processor 301. The memory 303 is configured to store a software program for executing the solutions provided in the embodiments of the present application, and the processor 301 controls the execution of the software program.

[0087] The communication interface 304 is configured to communicate with another device or a communication network, such as an Ethernet, a RAN, or a wireless local area network (WLAN), and may include a receiving unit for implementing a receiving function and a transmitting unit for implementing a transmitting function.

[0088] When the data transmission device is a network device, the network device may be a general-purpose network device or a dedicated network device, for example, a desktop computer, a portable computer, or a network server, which is not limited in the embodiments of the present application.

[0089] A data transmission method provided in an embodiment of the present application is described in detail below. It can be understood that the method provided in the present application can be performed by a network device or by a module (e.g., a chip) used in a network device. In the following, the data transmission method provided in the present application is described by using network devices (first network device and second network device) as an execution body.

[0090] FIG. 4 is a flowchart of a data transmission method according to an embodiment of the present application; as shown in FIG. 4, the method includes the following steps:

[0091] Step 401: A first network device sends an AI data request to a second network device, where the AI ​​data request includes event information of a first AI event.

[0092] The first network device and the second network device are applicable to the system architecture shown in Fig. 1. For example, both the first network device and the second network device are access network devices; or the first network device is an access network device, and the second network device is a core network device or a terminal; or the first network device is a core network device, and the second network device is an access network device. This is not limited to this embodiment of the present application.

[0093] In this embodiment of the present application, data related to various operations of applying an AI model, such as training, inference, optimization, or the like, may be collectively referred to as AI data. For example, corresponding to different operations, AI data may be classified into training data corresponding to training an AI model, inference data corresponding to inference of the AI ​​model, and feedback data corresponding to optimization of the AI ​​model. When a first network device needs to obtain training data to train an AI model, when the first network device needs to obtain inference data to perform inference by using an AI model, or when the first network device needs to obtain feedback data of a second network device to optimize an AI model, the first network device may send an AI data request to the second network device to request the required AI data.

[0094] The AI ​​data request may carry event information of a first AI event. The first AI event is an event that triggers the second network device to transmit AI data. In addition, the first AI event may be associated with an AI use case being executed by the first network device. The AI ​​use case is an item for adjusting a policy by applying the inference results of an AI model. For example, the AI ​​use case may include at least one of network energy saving, load balancing, and mobility optimization, which are described in the above application scenarios.

[0095] In some implementations, the first AI event may include a predictive trigger event. The predictive trigger event is a trigger event based on an AI model prediction result of the second network device. For example, the predictive trigger event may be an event in which the AI ​​model prediction result of the second network device meets a specified condition of the first network device.

[0096] For example, the predictive trigger event may include at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and a predicted value of the first measurement item being less than a corresponding second specified threshold, where the first specified threshold is greater than the second specified threshold and the first measurement item refers to an object specified by a first network device and actually measured by a second network device.

[0097] For example, the first measurement item includes a device load. Correspondingly, the predictive trigger event may include: the predicted value of the device load being greater than a corresponding first load threshold, and / or the predicted value of the device load being less than a corresponding second load threshold, where the first load threshold is greater than the second load threshold. As another example, the first measurement item includes a device energy consumption. Correspondingly, the predictive trigger event may include: the predicted value of the device energy consumption being greater than a corresponding first energy consumption threshold, and / or the predicted value of the device energy consumption being less than a corresponding second energy consumption threshold, where the first energy consumption threshold is greater than the second energy consumption threshold. As another example, the first measurement item includes a terminal traffic. Correspondingly, the predictive trigger event may include: the predicted value of the terminal traffic being greater than a corresponding first traffic threshold, and the predicted value of the terminal traffic being less than a corresponding second traffic threshold, where the first traffic threshold is greater than the second traffic threshold. Of course, the first measurement item may alternatively be another measurement item, and correspondingly, the predictive trigger event may alternatively include another event, which is not limited in this embodiment of the present application.

[0098] In some implementations, the first AI event may alternatively include a currently measured trigger event, which is a trigger event based on a current measurement result of the second network device. For example, the currently measured trigger event may mean that a current measurement value of the second network device satisfies a specified condition of the first network device.

[0099] For example, a current measurement type trigger event may include at least one of the following: a current measurement value of a first measurement item being greater than a corresponding third specified threshold; a current measurement value of a first measurement item being less than a corresponding fourth specified threshold; a current measurement value of a second measurement item being different from a predicted value prior to the present time; an error rate between a current measurement value and a predicted value prior to the present time of a third measurement item being greater than a corresponding fifth specified threshold; and an error rate between a current measurement value and a predicted value prior to the present time of a third measurement item being less than a corresponding sixth specified threshold, where the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

[0100] A predicted value of a measurement item prior to the current time may be a value at the current time and a value obtained through prediction prior to the current time. For example, if the current time is T1, a predicted value prior to the current time may be a value at time T1 and a value obtained through prediction at time T2, where time T2 is prior to time T1.

[0101] In addition, the first measurement item may include any one of device load, device energy consumption, and terminal traffic, the second measurement item may include terminal movement path or terminal service, and the third measurement item may include any one of device load, device energy consumption, and terminal traffic.

[0102] For example, the first measurement item may include a device load. Correspondingly, the current measurement-type trigger event may include: a current measurement value of the device load being greater than a corresponding third load threshold, and / or a current measurement value of the device load being less than a corresponding fourth load threshold, where the third load threshold is greater than the fourth load threshold. As another example, the first measurement item may include a device energy consumption. Correspondingly, the current measurement-type trigger event may include: a current measurement value of the device energy consumption being greater than a corresponding third energy consumption threshold, and / or a current measurement value of the device energy consumption being less than a corresponding fourth energy consumption threshold, where the third energy consumption threshold is greater than the fourth energy consumption threshold. As another example, the second measurement item may include a terminal movement path. Correspondingly, the current measurement-type trigger event may include: a current measurement value of the terminal movement path is different from a predicted value of the terminal movement path prior to the present time. As another example, the second measurement item may include a terminal service. Correspondingly, the current measurement trigger event may include: a current measurement value of the terminal service differs from a predicted value of the terminal service prior to the present time. As another example, the third measurement item may include terminal traffic. Correspondingly, the current measurement trigger event may include: an error rate between a current measurement value of the terminal traffic and a predicted value prior to the present time being greater than a corresponding fifth specified threshold; and / or Terminal traffic the error rate between the current measurement and the predicted value prior to the current time is less than a corresponding sixth specified threshold, where the fifth specified threshold is greater than the sixth specified threshold.

[0103] In some implementations, the first AI event may alternatively include a current-action trigger event, which is a trigger event based on a current action of the second network device. For example, the current-action trigger event may be an event in which a current action of the second network device satisfies a specified condition of the first network device.

[0104] For example, the current action type trigger event may include one or more of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

[0105] In a possible implementation, the event information of the first AI event in the AI ​​data request may include an event identifier and configuration parameters of the first AI event, where the event identifier identifies the AI ​​event and the configuration parameters are used to configure parameters required to detect the corresponding event. In the following cases, the configuration parameters of the AI ​​event may vary based on different AI events.

[0106] In the first case, the first AI event includes any of the predictive trigger events described above.

[0107] In this case, the configuration parameters of the first AI event may include a specified threshold corresponding to a measurement item and a duration of the first AI event. The duration of the first AI event is required by the first network device, and the second network device detects the first AI event within the duration. In this embodiment of the present application, the duration of the first AI event is also referred to as the time to trigger.

[0108] Optionally, the configuration parameters of the first AI event further include a prediction accuracy corresponding to the measurement item, which is a prediction accuracy that the second network device must meet for the predicted value of the corresponding measurement item. The prediction accuracy may be accuracy, precision, recall, or the like. Accuracy is the ratio of the number of samples correctly predicted by the AI ​​model to the total number of samples in the sample set, and represents the specific number of samples correctly predicted by the AI ​​model in the sample set. Precision is the ratio of the number of positive samples correctly predicted by the AI ​​model to the number of all positive samples predicted by the AI ​​model, and represents the specific number of correctly predicted samples among the positive samples predicted by the AI ​​model. Recall is the ratio of the number of positive samples correctly predicted by the AI ​​model to the number of positive samples included in the sample set, and represents the specific number of correctly predicted samples among the positive samples included in the sample set.

[0109] Optionally, the configuration parameters of the first AI event may further include a hysteresis parameter, which indicates an allowable hysteresis range of the predicted value of the measurement item. For example, if the hysteresis parameter is a and the specified threshold corresponding to the measurement item is b, the allowable hysteresis range of the predicted value of the measurement item is (ba, b+a). If the second network device detects that the predicted value of the measurement item is within the hysteresis range, it may determine that the first AI event has been detected.

[0110] For example, if the first AI event has a predicted value of the device load being greater than a corresponding first load threshold, the configuration parameters of the first AI event may include the first load threshold corresponding to the device load, a time to trigger, a hysteresis parameter, and a prediction accuracy.

[0111] The device load may be represented by using different load sub-items. Accordingly, the configuration parameters of the first AI event may include load thresholds corresponding to the different load sub-items. For example, the device load may be represented by one or more load sub-items: throughput, physical resource block (PRB) utilization, number of active terminals, number of radio resource control (RRC) connections, composite available capacity group, transport network layer (TNL) capacity indicator, and slice available capacity. Correspondingly, the configuration parameters of the first AI event may include load thresholds for one or more of the above-mentioned load sub-items. The number of active terminals is the number of terminals in an active state.

[0112] If the configuration parameters of the first AI event include load thresholds for the above-mentioned multiple load sub-items, assuming that the event identifier of the AI ​​event whose predicted device load value is greater than the corresponding first load threshold is AI event A1, the event information of the first AI event carried in the AI ​​data request may be one example in Table 1. Table 1 Event information for the first AI event [Table 1]

[0113] The symbols ">", ">>", and ">>>" in Table 1 represent the level of an information element. For example, ">" represents a first-level information element, ">>" represents a second-level information element, ">>>" represents a third-level information element, and so on. Information elements at various levels have a nesting relationship based on the level. For example, second-level information elements are included in first-level information elements, and third-level information elements are included in second-level information elements. It can be understood that both second-level information elements and third-level information elements are included in first-level information elements. In the examples of information element designs in this application, when the above-mentioned symbols such as ">" appear, the meaning of the symbols is the same as in Table 1. Details will not be described again.

[0114] In the second case, the first AI event comprises the currently measured trigger event described above.

[0115] In this case, the configuration parameters of the first AI event may include a specified threshold corresponding to a measurement and / or a measurement, and the configuration parameters of the first AI event further include a time to trigger.

[0116] For example, if the first AI event has one or more current measurement-type trigger events corresponding to the first measurement item or the third measurement item, the configuration parameters of the first AI event may include a specified threshold and time to trigger corresponding to the first measurement item or the third measurement item.

[0117] Optionally, the configuration parameters of the first AI event further include a hysteresis parameter. For a related description of the hysteresis parameter, please refer to the related description in the first case above. The details will not be described again.

[0118] Optionally, if the measurement item of the first AI event relates to a device other than the second network device, for example, to a terminal, the configuration parameters of the first AI event may further include an identifier of a measurement object, which is an object to be measured by the second network device.

[0119] For example, if the first AI event has a current measurement value of the device load being greater than a corresponding third load threshold, the configuration parameters of the first AI event may include the third load threshold corresponding to the device load, a time to trigger, and a hysteresis parameter. The device load may include one or more load sub-items described in the first case above. Correspondingly, the configuration parameters of the first AI event may include load thresholds of one or more load sub-items.

[0120] If the configuration parameters of the first AI event include load thresholds for multiple load sub-items, assuming that the event identifier of the AI ​​event in which the current measurement value of the device load is greater than the corresponding third load threshold is AI event B1, the event information of the first AI event carried in the AI ​​data request may be an example in Table 2. Table 2 Event information for the first AI event [Table 2]

[0121] As another example, if the first AI event has an error rate between a current measurement value of terminal traffic and a predicted value prior to the present time being greater than a corresponding fifth specified threshold, the configuration parameters of the first AI event may include a terminal identifier list, the fifth specified threshold, a time to trigger, and a hysteresis parameter. The terminal identifier list includes at least one terminal identifier, and the at least one terminal identifier indicates a terminal on which measurement is to be performed. Specifically, the terminal identified by the at least one terminal identifier is a measurement target corresponding to the terminal traffic.

[0122] The terminal traffic may include at least one of uplink traffic and downlink traffic. Based on this, the fifth specified threshold may include at least one of an uplink traffic threshold and a downlink traffic threshold. In addition, an error rate between a current measurement value and a previous predicted value of the terminal traffic may be equal to (current measurement value - previous predicted value) / predicted value or may be equal to (current measurement value - previous predicted value) / current measurement value.

[0123] If the configuration parameters of the first AI event include an uplink traffic threshold and a downlink traffic threshold, assuming that the event identifier of the AI ​​event in which the error rate between the current measurement value of terminal traffic and the predicted value prior to the present time is greater than the corresponding fifth specified threshold is AI event C3, the event information of the first AI event carried in the AI ​​data request may be an example in Table 3. Table 3 Event information for the first AI event [Table 3]

[0124] In some other implementations, if the first AI event has a current measurement value of a second measurement item in a current measurement type trigger event that is different from a predicted value prior to the present time, the configuration parameters of the first AI event may include indication information of the measurement item and a time to trigger.

[0125] Optionally, if the measurement item of the first AI event relates to a device other than the second network device, for example, to a terminal, the configuration parameters of the first AI event may further include an identifier of a measurement object, which is an object to be measured by the second network device.

[0126] For example, if the current measurement value of a terminal service included in the first AI event is different from the predicted value prior to the present time, the configuration parameters of the first AI event may include a terminal identifier list, a service type identifier, and a time to trigger. The terminal identifier list includes at least one terminal identifier, and the at least one terminal identifier indicates the terminal on which the measurement will be performed, i.e., the measurement target. The service type identifier indicates the service to be measured, and specifically, the service type identifier is indication information of the measurement item.

[0127] There may be multiple terminal service types, such as conversational voice, real-time games, process automation monitoring, mission-critical service video user plane, low-latency enhanced mobile broadband (eMBB) application augmented reality, and intelligent transportation system. Based on this, the configuration parameters of the first AI event may include identifiers of one or more of the above-mentioned service types.

[0128] If the configuration parameters of the first AI event include the identifiers of the above-mentioned multiple service types, assuming that the event identifier of the AI ​​event in which the current measurement value of the terminal service differs from the predicted value prior to the present time is AI event C2, the event information of the first AI event carried in the AI ​​data request may be one example in Table 4. Table 4 Event information for the first AI event [Table 4]

[0129] In the third case, the first AI event has the current action type trigger event described above.

[0130] For example, if the first AI event includes a cell being enabled, the configuration parameters of the first AI event may include a cell identifier list and a time to trigger. The cell identifier list includes at least one cell identifier, where the at least one cell identifier indicates a cell on which a measurement is to be performed, specifically, the at least one cell identifier indicates a cell to be measured by the second network device. In other words, the second network device may detect the first AI event by detecting the enabled / disabled state of a cell identified by the at least one cell identifier.

[0131] If the first AI event has at least one of the following: the terminal is successfully handed over, and the terminal is in handover, the configuration parameters of the first AI event include a terminal identifier list and a time to trigger. The terminal identifier list includes at least one terminal identifier, and the at least one terminal identifier indicates a terminal on which measurement will be performed. In other words, the at least one terminal identifier indicates a terminal on which measurement will be performed by the second network device. The second network device may detect the first AI event by detecting a handover state of the terminal identified by the at least one terminal identifier.

[0132] For example, if the first AI event has the terminal being successfully handed over, assuming that the event identifier of the AI ​​event for which the terminal is being successfully handed over is AI event E1, the event information of the first AI event included in the AI ​​data request may be an example in Table 5. Table 5 Event information for the first AI event [Table 5]

[0133] If the first AI event includes an AI use case being executed, the configuration parameters of the first AI event may include an AI use case and a time to trigger. The AI ​​use case may include at least one of network energy saving, load balancing, and mobility optimization, which are described in the above application scenarios.

[0134] For example, if the configuration parameters of the first AI event include the multiple AI use cases described above, assuming that the event identifier of the AI ​​event in which the AI ​​use case is being executed is AI event F1, the event information of the first AI event carried in the AI ​​data request may be one example in Table 6. Table 6 Event information for the first AI event [Table 6]

[0135] It should be noted that after the first network device sends an AI data request carrying the event identifier and configuration parameters of the first AI event to the second network device, the second network device may correspondingly store the received event identifier and configuration parameters of the first AI event to implement the configuration of the event information of the first AI event. Then, the second network device may send an AI data response to the first network device, where the AI ​​data response carries first instruction information, and the first instruction information indicates whether the second network device has successfully configured the event information of the first AI event or failed to configure it. If the configuration fails, the first instruction information may further indicate the cause of the configuration failure.

[0136] It can be understood that the examples in Tables 1 to 6 are merely possible implementations of information element structures used when the event information of the first AI event is transmitted by using an AI data request, and do not constitute any limitations on the transmission method or information element structure of the event information of the first AI event.

[0137] Optionally, when storing the event identifier and configuration parameters of the first AI event, the second network device may correspondingly store the event identifier and configuration parameters of the first AI event and the device identifier of the first network device to distinguish between different AI events configured by different network devices.

[0138] In another possible implementation, the event information of the first AI event in the AI ​​data request may include an event identifier of the first AI event, but not include configuration parameters of the first AI event.

[0139] In this case, before sending the AI ​​data request to the second network device, the first network device may further send an AI event information set to the second network device to instruct the second network device to store the AI ​​event information set, where the AI ​​event information set includes an event identifier and configuration parameters of at least one AI event, and the at least one AI event includes the event identifier of the first AI event.

[0140] For example, the first network device may include the AI ​​event information set by using an AI event configuration request. The AI ​​event configuration request may be a request specialized for transmitting the AI ​​event information set. Alternatively, the AI ​​event configuration request may reuse another request between the first network device and the second network device. For example, the AI ​​event configuration request may be an Xn link establishment request (Xn establishment request). In other words, the first network device may include the AI ​​event information set in the Xn link establishment request sent to the second network device. For implementation of the event identifier and configuration parameters of at least one AI event in the AI ​​event information set, please refer to the related description above. In this embodiment of the present application, details will not be described again here.

[0141] After receiving the AI ​​event information set, the second network device may correspondingly store the event identifiers and configuration parameters of all AI events in the AI ​​event information set to complete the configuration of the event information of the AI ​​events. Then, the second network device may send second instruction information to the first network device, where the second instruction information indicates whether the second network device has successfully configured or failed to configure the event information of some or all of the AI ​​events in the AI ​​event information set. Optionally, if there are AI events that have failed to be configured, the second instruction information may further indicate the cause of the configuration failure.

[0142] For example, when a first network device carries an AI event information set using an AI event configuration request, the second network device may send an AI event configuration response to the first network device, where the AI ​​event configuration response carries second instruction information.

[0143] If the AI ​​event configuration request is a request specialized for transmitting an AI event information set, the AI ​​event configuration response is also a response specialized for the AI ​​event configuration request. If the AI ​​event configuration request reuses another request between the first network device and the second network device, the AI ​​event configuration response is a response to the corresponding request. For example, if the AI ​​event configuration request is an Xn link establishment request, the AI ​​event configuration response may be an Xn link establishment response (Xn establishment response).

[0144] Optionally, when storing the AI ​​event information set, the second network device may correspondingly store the device identifier and the AI ​​event information set of the first network device to distinguish AI event information sets from different network devices.

[0145] Optionally, when sending an AI data request to the second network device, the first network device may further send third instruction information to the second network device, where the third instruction information indicates the AI ​​data items requested by the first network device. The AI ​​data items requested by the first network device may include one or more of predicted values, current measurement values, and other related data of measurement items included in the first AI event, or may include other data of the second network device. This is not limited to this embodiment of the present application.

[0146] Note that the AI ​​data item requested by the first network device may be associated with an AI use case being performed by the first network device. For example, if the first network device performs AI model-based load balancing, the AI ​​data item requested by the first network device may be AI data related to device load predicted or currently measured by the second network device.

[0147] In addition, the third instruction information may be conveyed by using a separate message different from the AI ​​data request, or may be conveyed by using the AI ​​data request. In addition, the transmission opportunities for the third instruction information and the AI ​​data request may be in any order.

[0148] In addition, the AI ​​data request may be a message specifically for requesting AI data, or may reuse another request between the first network device and the second network device. For example, the AI ​​data request may be a handover request sent by the first network device to the second network device. The first network device may include event information of the first AI event in the handover request sent to the second network device.

[0149] Step 402: The second network device sends AI data to the first network device based on the event information of the first AI event.

[0150] After receiving the AI ​​data request sent by the first network device, the second network device may send AI data to the first network device based on the event information of the first AI event carried in the AI ​​data request.

[0151] In a possible implementation, if the event information of a first AI event carried in the AI ​​data request is the event identifier and configuration parameters of the first AI event, the second network device may send AI data to the first network device based on the event identifier and configuration parameters of the first AI event.

[0152] From the above description, it can be seen that if the first AI event has a predictive trigger event or a current measurement trigger event, the configuration parameters of the first AI event include a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a time to trigger. In this case, after receiving the event identifier and the configuration parameters of the first AI event, the second network device can detect the first AI event based on the event identifier of the first AI event, the indication information of the measurement item, and / or the specified threshold corresponding to the measurement item, and can transmit AI data to the first network device if the first AI event is continuously detected within the time to trigger.

[0153] In one example, if the first AI event has a predicted value of a first measurement item in a predictive trigger event that is greater than a corresponding first specified threshold, the second network device may detect whether the predicted value of the first measurement item is greater than the corresponding first specified threshold based on the event identifier of the first AI event, and may transmit AI data to the first network device if it detects that the predicted value of the first measurement item is greater than the first specified threshold and that the predicted value of the first measurement item is continuously greater than the first specified threshold within the time until the trigger. The predicted value of the first measurement item is a value obtained by the second network device through prediction using an AI model.

[0154] Optionally, when the configuration parameters of the first AI event further include a hysteresis parameter and a prediction accuracy, the second network device may detect, based on the event identifier of the first AI event, whether the predicted value of the first measurement item satisfies the prediction accuracy. If the predicted value satisfies the prediction accuracy, the second network device detects, based on the hysteresis parameter and a first specified threshold corresponding to the first measurement item, whether the predicted value of the first measurement item is within a hysteresis range, and transmits AI data to the first network device if it detects that the predicted value of the first measurement item is continuously within the hysteresis range within the time until the trigger.

[0155] The second network device may return all of the AI ​​data of the second network device to the first network device. Alternatively, if the first network device sends third instruction information to the second network device indicating the data items requested by the first network device, the second network device may return corresponding AI data based on the third instruction information.

[0156] For example, when the first AI event has a predicted value of the device load being greater than a corresponding first load threshold, and the configuration parameters of the AI ​​event are indicated in step 401, if the second network device detects that one or more predicted values ​​of the throughput, the PRB utilization rate, the number of active terminals, the number of RRC connections, the composite available capacity group, the TNL capacity indicator, and the slice available capacity meet the prediction accuracy and are within the corresponding hysteresis range within the time to the trigger, 3 For example, when the first network device performs AI model-based load balancing, the second network device may return the AI ​​data to the first network device under the instruction of the third instruction information. For example, when the first network device performs AI model-based load balancing, the second network device may return the predicted value of the above-mentioned load sub-item obtained through current prediction or the current measured value of the above-mentioned load sub-item under the instruction of the third instruction information, so that the first network device may perform training, inference, or optimization of the AI ​​model based on the AI ​​data.

[0157] In another example, if the first AI event has a current measurement value of the second measurement item that is different from a predicted value before the current time, the second network device may compare the current measurement value of the second measurement item with the predicted value before the current time based on the event identifier of the first AI event, and if the current measurement value of the second measurement item does not match the predicted value before the current time within the time until the trigger, return AI data to the first network device. For implementations of returning AI data to the first network device, see the above example.

[0158] For example, if the first AI event has a current measurement value of a terminal service that differs from a predicted value prior to the current time, and the configuration parameters of the AI ​​event are indicated in step 401, the second network device may detect whether the current measurement value of the service of the terminal identified by at least one terminal identifier in the terminal identifier list matches the predicted value prior to the current time, in other words, whether the service of the at least one terminal at the current time matches the predicted service of the at least one terminal prior to the current time. If the second network device detects that the two do not always match within the time until the trigger, the second network device may return AI data associated with the at least one terminal to the first network device. For example, the AI ​​data may include the type of service currently being performed by the terminal, throughput, packet loss rate, transmission delay, and the like.

[0159] In another example, if the first AI event has a current-action trigger event, for example, if the first AI event includes a cell being enabled and the configuration parameters of the first AI event include a cell identifier list and a time to trigger, the second network device may detect the enabled / disabled state of the target cell based on the event identifier of the first AI event, where the cell identifier of the target cell is any cell identifier in the cell identifier list; and if the target cell is detected to be in an enabled state within the duration, send AI data to the first network device. The AI ​​data may be data related to the target cell measured by the second network device, and the AI ​​data may be used by the first network device to implement AI model-based network energy saving.

[0160] As another example, if the first AI event indicates that a terminal has been successfully handed over and the configuration parameters of the AI ​​event include a terminal identifier list and a time to trigger, the second network device may detect the stationing status of the target terminal based on the event identifier of the first AI event, where the identifier of the target terminal is any identifier in the terminal identifier list, and the target terminal is a terminal handed over to the second network device; and if it is detected that the target terminal is continuously stationed on the second network device within the time to trigger, it may send AI data to the first network device. The AI ​​data may be data associated with the target terminal, such as handover parameters of the target terminal. In addition, the AI ​​data may be used by the first network device to implement AI model-based mobility optimization.

[0161] As another example, if the first AI event includes an AI use case being executed, and the configuration parameters of the AI ​​event include the AI ​​use case and the time to trigger described in step 401, the second network device may detect the status of the execution of the AI ​​use case by the second network device based on the event identifier of the first AI event; and if it detects that the second network device is executing any one of the above-mentioned AI use cases within the time to trigger, it may send AI data to the first network device. The AI ​​data may be data related to the AI ​​use case being executed by the second network device. For example, if the second network device performs load balancing within the time to trigger, the second network device may return data related to load balancing, such as values ​​of different load sub-items predicted or currently measured by the second network device, to the first network device.

[0162] In another possible implementation, if the event information of the first AI event carried in the AI ​​data request includes an event identifier of the first AI event, the second network device may obtain configuration parameters of the first AI event based on the event identifier of the first AI event, and then send AI data to the first network device based on the event identifier and configuration parameters of the first AI event.

[0163] If the AI ​​data request carries the event identifier of the first AI event but does not carry the configuration parameters, the first network device pre-sends an AI event information set including the event identifier and configuration parameters of the first AI event to the second network device, and instructs the second network device to store the AI ​​event information set. Based on this, after receiving the AI ​​data request, the second network device can search the stored AI event information set based on the event identifier of the first AI event to obtain the configuration parameters of the first AI event.

[0164] After obtaining the configuration parameters of the first AI event, the second network device can send AI data to the first network device based on the event identifier and the configuration parameters of the first AI event. For related implementations, see the related description in step 402.

[0165] Optionally, in this implementation, the first network device pre-sends an AI event information set to the second network device to configure an AI event, and then the first network device may further update the configuration parameters of the pre-configured AI event in the AI ​​event information set.

[0166] For example, a first network device may send a configuration update request to a second network device, where the configuration update request includes an event identifier and update information of the first AI event, and the configuration update request is used to request the second network device to update the configuration parameters of the first AI event. After receiving the configuration update request, the second network device updates the configuration parameters of the first AI event based on the event identifier and update information of the first AI event carried in the configuration update request. Then, the second network device sends a configuration update response to the first network device, where the configuration update response indicates whether the configuration parameters of the first AI event were successfully updated or the update failed. If the configuration parameters of the first AI event failed to update, the configuration update response may further indicate the cause of the update failure.

[0167] The update information carried in the configuration update request may include at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, and the update operation may include modify, add, and Removal Contains one of the following:

[0168] In response to this, the second network device may search for configuration parameters of the first AI event stored in the second network device based on the event identifier of the first AI event, and then perform corresponding update operations on the configuration parameters of the first AI event stored in the second network device based on the configuration parameters and corresponding update operations carried in the update information.

[0169] For example, if the first AI event is that the predicted value of the device load is greater than a corresponding first specified threshold, and the first network device intends to modify the throughput threshold in the configuration parameters of the first AI event, the information carried in the configuration update request may be an example in Table 7. Table 7. Information in a configuration update request [Table 7]

[0170] The throughput thresholds shown in Table 7 are modified throughput thresholds determined by the first network device. After receiving the configuration update request, the second network device may modify the throughput thresholds stored in the second network device to the throughput thresholds in Table 7.

[0171] As another example, if the first AI event is that the predicted value of the device load is greater than the corresponding first specified threshold, the configuration parameters of the first AI event stored in the second network device do not include the threshold for the number of active terminals. In addition, the first network device intends to add the threshold for the number of active terminals to the configuration parameters of the first AI event. In this case, the information carried in the configuration update request may be an example in Table 8. Table 8. Information in a configuration update request [Table 8]

[0172] The threshold value of the number of active terminals in Table 8 is a threshold value item to be added by the first network device. In this case, the second network device may add the threshold value of the number of active terminals carried in the configuration update request to the configuration parameters of the first AI event stored in the second network device.

[0173] As another example, the first AI event is that the predicted value of the device load is greater than a corresponding first specified threshold, and the first network device sets a threshold for the number of RRC connections in the configuration parameters of the first AI event stored in the second network device. Removal If so, the information carried in the configuration update request may be an example in Table 9. Table 9. Information in a configuration update request [Table 9]

[0174] The thresholds for the number of RRC connections in Table 9 are set by the first network device. Removal In this example, the second network device sets the threshold value of the number of RRC connections in the configuration parameters of the first AI event stored in the second network device. Removal possible.

[0175] For example, the configuration update request may further carry a device identifier of the first network device to instruct the second network device to update configuration parameters of a first AI event pre-transmitted by the first network device.

[0176] It can be understood that the examples in Tables 7 to 9 are merely possible implementations of information element structures used when update information for the first AI event is transmitted by using a configuration update request, and do not constitute any limitations on the transmission method or information element structure of update information for the first AI event.

[0177] It should be noted that the configuration update request and the configuration update response may be signaling specialized for updating configuration parameters of an AI event. Optionally, the configuration update request and the configuration update response may alternatively reuse another request and corresponding response between the first network device and the second network device. For example, the configuration update request may be an Xn link establishment request, and the configuration update response may be an Xn link establishment response. Alternatively, the configuration update request may be a handover request, and the configuration update response may be a handover request response.

[0178] In the above, updating the configuration parameters of the first AI event is used as an example for explanation. Obviously, the first network device can further update the configuration parameters of the corresponding AI event pre-configured in the second network device by including the event identifier of another AI event and corresponding update information in the configuration update request. The details will not be described again.

[0179] It should be noted that if the AI ​​data request directly carries the event identifier and configuration parameters of the first AI event, the configuration parameters of the AI ​​event on the second network device can also be updated by using the method described above. For example, after receiving the AI ​​data returned by the second network device based on the AI ​​data request, the first network device can also send a configuration update request to the second network device to update the configuration parameters of the AI ​​event previously sent by the first network device to the second network device. The details will not be described again.

[0180] According to the data transmission method provided herein, when sending an AI data request to a second network device, a first network device may include event information of a first AI event in the AI ​​data request, where the first AI event is an event that triggers the second network device to send AI data. In this way, when the second network device detects that the first AI event is met, it may send AI data to the first network device based on the event information of the first AI event. When triggered by a trigger event specified by the first network device, the second network device may return the AI ​​data required by the first network device in a timely manner, thereby satisfying the various data requirements of the first network device and improving the effectiveness of AI model training, inference, or optimization by the first network device.

[0181] Based on the above description, if the AI ​​data request carries the event identifier and configuration parameters of the first AI event, in one example, as shown in FIG. 5, the data transmission method may include the following steps:

[0182] Step 501: A first network device sends an AI data request to a second network device, where the AI ​​data request includes an event identifier and configuration parameters of a first AI event.

[0183] Step 502: The second network device sends an AI data response to the first network device, where the AI ​​data response includes first instruction information, and the first instruction information indicates whether the second network device has successfully configured or failed to configure event information of the first AI event.

[0184] Step 503: The second network device sends AI data to the first network device based on the event identifier and the configuration parameters of the first AI event.

[0185] For the implementation of steps 501 to 503, please refer to the implementation of the related steps in the embodiment shown in Fig. 4. The details will not be described again.

[0186] 5 is used, the first network device may directly include the event identifier and configuration parameters of the first AI event in the AI ​​data request. In this way, both the configuration of the event information of the AI ​​event and the request for AI data are implemented, thereby reducing signaling overhead between network devices.

[0187] If the AI ​​data request carries the event identifier of the first AI event but does not carry the configuration parameters of the first AI event, in one example, as shown in FIG. 6, the data transmission method may include the following steps.

[0188] Step 601: A first network device sends an AI event configuration request to a second network device, where the AI ​​event configuration request includes an AI event information set.

[0189] Step 602: The second network device stores the AI ​​event information set.

[0190] Step 603: The second network device sends an AI event configuration response to the first network device, where the AI ​​event configuration response includes second instruction information, which indicates whether the stored event information of the AI ​​event has been successfully configured or failed to be configured.

[0191] Step 604: The first network device sends an AI data request to the second network device, where the AI ​​data request includes the event identifier of the first AI event.

[0192] Step 605: The second network device obtains configuration parameters of the first AI event based on the event identifier of the first AI event.

[0193] Step 606: The second network device sends AI data to the first network device based on the event identifier and the configuration parameters of the first AI event.

[0194] Step 607: The first network device sends a configuration update request to the second network device, where the configuration update request includes the event identifier and update information of the first AI event.

[0195] Step 608: The second network device updates the configuration parameters of the first AI event based on the event identifier and the update information of the first AI event.

[0196] Step 609: The second network device sends a configuration update response to the first network device, where the configuration update response indicates whether the configuration parameters of the first AI event have been updated successfully or failed.

[0197] For the implementation of steps 601 to 609, please refer to the relevant description in the embodiment shown in Figure 4. The details will not be described again.

[0198] 6 is used, the first network device may pre-configure event information of an AI event in the second network device through steps 601 to 603. Then, when AI data needs to be obtained, the first network device may include the event identifier of the AI ​​event in the AI ​​data request to instruct the second network device to return the AI ​​data when the corresponding AI event is met, thereby reducing signaling overhead.

[0199] In addition, the first network device and the second network device may, through steps 607 to 609, update the configuration parameters of the AI ​​event pre-configured in the second network device by the first network device, to reduce erroneous or unnecessary data transmission caused by changes in the configuration parameters of the AI ​​event.

[0200] The data transmission device provided in the embodiment of the present application will be described below.

[0201] 7 is a structural diagram of another data transmission device 700 according to an embodiment of the present application. This device can be deployed in the first network device in the above-mentioned embodiment. As shown in FIG. 7, the data transmission device includes a sending module 701 and a receiving module 702.

[0202] The sending module 701 is configured to perform step 401 in the above-mentioned embodiments. In some examples, the sending module is configured to perform step 501 or step 604 in the above-mentioned embodiments.

[0203] The receiving module 702 is configured to receive the AI ​​data returned by the second network device.

[0204] For example, the event information for a first AI event includes an event identifier and configuration parameters for the first AI event.

[0205] For example, the event information for the first AI event includes an event identifier for the first AI event.

[0206] For example, the sending module 701 is further configured to: send an AI event information set to a second network device and instruct the second network device to store the AI ​​event information set, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes the first AI event.

[0207] For example, the sending module 701 is further configured to send a configuration update request to the second network device, where the configuration update request includes an event identifier and update information of the first AI event, and the configuration update request is used to request the second network device to update the configuration parameters of the first AI event; and the receiving module 702 is further configured to receive a configuration update response to the configuration update request sent by the second network device, where the configuration update response indicates whether the second network device has successfully updated the configuration parameters of the first AI event or failed to update.

[0208] For example, the update information includes at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, and the update operation may include modifying, adding, and Removal Contains one of the following:

[0209] For example, the first AI event includes a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device.

[0210] For example, the predictive trigger event may include at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and a predicted value of the first measurement item being less than a corresponding second specified threshold, where the first specified threshold is greater than the second specified threshold.

[0211] For example, the first AI event includes a current measurement type trigger event, which includes a trigger event based on a current measurement result of the second network device.

[0212] For example, current measurement type trigger events include at least one of the following: the current measurement value of a first measurement item being greater than a corresponding third specified threshold; the current measurement value of the first measurement item being less than a corresponding fourth specified threshold; the current measurement value of a second measurement item being different from a predicted value prior to the present time; the error rate between the current measurement value and the predicted value prior to the present time of a third measurement item being greater than a corresponding fifth specified threshold; and the error rate between the current measurement value and the predicted value prior to the present time of a third measurement item being less than a corresponding sixth specified threshold, where the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

[0213] For example, the first measurement item includes any one of device load, device energy consumption, and terminal traffic, the second measurement item includes terminal movement path or terminal service, and the third measurement item includes any one of device load, device energy consumption, and terminal traffic.

[0214] For example, if the first AI event has a predictive trigger event or a current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include the duration of the first AI event.

[0215] For example, the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device.

[0216] For example, the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

[0217] For example, if the first AI event includes a cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event; if the first AI event includes at least one of the following: a terminal being successfully handed over and a terminal being in handover, the configuration parameters of the first AI event include a terminal identifier list and a duration; if the first AI event includes an AI use case being executed, the configuration parameters of the first AI event include an AI use case and a duration.

[0218] According to the data transmission device provided in the present application, when sending an AI data request to a second network device, a first network device may include event information of a first AI event in the AI ​​data request, where the first AI event is an event that triggers the second network device to send AI data. In this way, when the second network device detects that the first AI event is met, it may send AI data to the first network device based on the event information of the first AI event. When triggered by a trigger event specified by the first network device, the second network device may return the AI ​​data required by the first network device in a timely manner, thereby satisfying the various data requirements of the first network device and improving the effectiveness of AI model training, inference, or optimization by the first network device.

[0219] 8 is a structural diagram of another data transmission device according to an embodiment of the present application. The data transmission device can be deployed in the second network device in the above embodiment. As shown in FIG. 8, the data transmission device 800 includes a receiving module 801 and a sending module 802.

[0220] The receiving module 801 is configured to receive an AI data request sent by a first network device, where the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger a second network device to send AI data to the first network device.

[0221] The sending module 802 is configured to perform step 402 in the above embodiment.

[0222] In some examples, the sending module 802 is configured to perform steps 502 and 503 in the above-described embodiments.

[0223] In some other examples, the sending module 802 is configured to perform steps 605 and 606 in the above-described embodiments.

[0224] In this case, see Figure 8. The apparatus 800 may further include a storage module 803. The transmission module 802 is further configured to receive an AI event information set transmitted by a first network device, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes a first AI event. The storage module 803 is configured to store the AI ​​event information set.

[0225] 8, for example. The apparatus 800 may further include an update module 804. The receiving module 801 is further configured to receive a configuration update request sent by a first network device, where the configuration update request includes an event identifier and update information of the first AI event; the update module 804 is configured to update configuration parameters of the first AI event based on the event identifier and update information of the first AI event; and the sending module 802 is further configured to send a configuration update response to the first network device, where the configuration update response indicates whether the configuration parameters of the first AI event have been successfully updated or have failed to be updated.

[0226] For example, the update information includes at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, and the update operation may include modifying, adding, and Removal Contains one of the following:

[0227] For example, the first AI event includes a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device.

[0228] For example, the predictive trigger event may include at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and a predicted value of the first measurement item being less than a corresponding second specified threshold, where the first specified threshold is greater than the second specified threshold.

[0229] For example, the first AI event includes a current measurement type trigger event, which includes a trigger event based on a current measurement result of the second network device.

[0230] For example, current measurement type trigger events include at least one of the following: the current measurement value of a first measurement item being greater than a corresponding third specified threshold; the current measurement value of the first measurement item being less than a corresponding fourth specified threshold; the current measurement value of a second measurement item being different from a predicted value prior to the present time; the error rate between the current measurement value and the predicted value prior to the present time of a third measurement item being greater than a corresponding fifth specified threshold; and the error rate between the current measurement value and the predicted value prior to the present time of a third measurement item being less than a corresponding sixth specified threshold, where the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

[0231] For example, the first measurement item includes any one of device load, device energy consumption, and terminal traffic, the second measurement item includes terminal movement path or terminal service, and the third measurement item includes any one of device load, device energy consumption, and terminal traffic.

[0232] For example, if the first AI event has a predictive trigger event or a current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include the duration of the first AI event.

[0233] In this case, the transmission module 802 is mainly configured to: detect a first AI event based on an event identifier of the first AI event, indication information of a measurement item, and / or a specified threshold corresponding to the measurement item; and transmit AI data to a first network device if the first AI event is continuously detected within a duration.

[0234] For example, the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device.

[0235] For example, the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

[0236] For example, if the first AI event includes a cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event. In this case, the sending module 802 is mainly configured to: detect the enabled / disabled state of the target cell based on the event identifier of the first AI event, where the cell identifier of the target cell is any cell identifier in the cell identifier list; and send AI data to the first network device if the target cell is detected to be in an enabled state within the duration.

[0237] For example, if the first AI event indicates that the terminal has been successfully handed over, the configuration parameters of the first AI event include a terminal identifier list and a duration of the first AI event. In this case, the sending module 802 is mainly configured to: detect the residence status of the target terminal based on the event identifier of the first AI event, where the identifier of the target terminal is any identifier in the terminal identifier list, and the target terminal is a terminal that has been handed over to the second network device; and send AI data to the first network device if it is detected that the target terminal is continuously residence on the second network device within the duration.

[0238] For example, if the first AI event includes an AI use case being executed, the configuration parameters of the first AI event include the AI ​​use case and the duration of the first AI event. In this case, the sending module 802 is mainly configured to: detect the status of the execution of the AI ​​use case by the second network device based on the event identifier of the first AI event; and send AI data to the first network device if it is detected that the second network device is executing the AI ​​use case within the duration.

[0239] According to the data transmission device provided in the present application, a second network device receives an AI data request sent by a first network device, where the AI ​​data request carries event information of a first AI event. If the second network device detects that the first AI event is met, it can send AI data to the first network device based on the event information of the first AI event. When triggered by a trigger event specified by the first network device, the second network device can timely return the AI ​​data required by the first network device, thereby satisfying the various data requirements of the first network device and improving the effectiveness of AI model training, inference, or optimization by the first network device.

[0240] It should be noted that the module division in the various data transmission devices in the above-described embodiments is merely an example and represents a logical functional division. In actual implementation, other division schemes may exist. In addition, the functional modules in the embodiments of the present application may be integrated into one processor, and each module may exist physically independently, or two or more modules may be integrated into one module. The integrated module may be implemented in the form of hardware or in the form of a software functional module.

[0241] When the integrated module is implemented in the form of a software function module and sold or used as an independent product, the integrated module may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application may be essentially implemented in the form of a software product, or a portion of the technical solutions, or all or a portion of the technical solutions, may be implemented in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for instructing a network device (which may be a router or a switch) or a processor to perform all or a portion of the steps of the method described in the embodiments of the present application. The above-mentioned storage medium includes various media capable of storing program code. For example, the storage medium may be a computer-readable storage medium, any available medium accessible by a computer, or a data storage device such as a server or a data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk drive, or a tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)). As another example, the storage medium may be a read-only memory (ROM) or a random access memory (RAM). In addition, the data transmission device and the data transmission method provided in the above embodiments are based on the same concept. For the specific implementation process of the device, please refer to the method embodiment. Details will not be described again here.

[0242] An embodiment of the present application further provides a data transmission system. The data transmission system includes a first network device and a second network device. The first network device may be configured to perform the steps performed by the first network device in the method embodiment shown in Figure 4, Figure 5, or Figure 6. The second network device may be configured to perform the steps performed by the second network device in the method embodiment shown in Figure 4, Figure 5, or Figure 6. Details will not be described again.

[0243] All or part of the above-described embodiments may be implemented by software, hardware, firmware, or any combination thereof. When software is used to implement an embodiment, all or part of the embodiment may be implemented in the form of a computer program product. The computer program product comprises one or more computer instructions. When the computer instructions are loaded onto a computer and executed thereon, the procedures or functions according to the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, radio, or microwave) transmission.

[0244] In various embodiments of the present application, unless otherwise specified or logically contradictory, the terms and / or descriptions in different embodiments are consistent and may be cross-referenced, and technical features in different embodiments may be combined based on their internal logical relationships to form new embodiments. In this application, "at least one" means one or more, and "multiple" means two or more. The term "and / or" describes a relational relationship between associated objects and indicates that three relationships may exist. For example, A and / or B may represent the following: the case where only A exists, the case where both A and B exist, and the case where only B exists, where A and B may be singular or plural. In the text description of the present application, the character " / " generally represents an "or" relationship between associated objects. In this application, "first," "second," and various numbers are used for differentiation to facilitate description and are not used to limit the scope of the embodiments of the present application, for example, to distinguish different messages, but are not intended to describe a specific order or sequence.

[0245] It can be understood that various numbers in the embodiments of the present application are used only for differentiation to facilitate description, and are not used to limit the scope of the embodiments of the present application. The order numbers of the above processes do not mean the order of execution, and the order of execution of the processes should be determined based on the functions and internal logic of the processes. (Other possible items) (Item 1) 1. A data transmission method, the method being applied to a first network device, the method comprising: sending an AI data request to a second network device, where the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger the second network device to send AI data to the first network device; and receiving the AI ​​data A method comprising: (Item 2) Item 10. The method of item 1, wherein the event information of the first AI event includes an event identifier and configuration parameters of the first AI event. (Item 3) 2. The method of claim 1, wherein the event information for the first AI event includes an event identifier for the first AI event. (Item 4) Prior to sending the AI ​​data request to the second network device, the method includes: sending an AI event information set to the second network device to instruct the second network device to store the AI ​​event information set, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes the first AI event; Item 4. The method of item 3, further comprising: (Item 5) The method comprises: sending a configuration update request to the second network device, where the configuration update request includes the event identifier and update information of the first AI event, and the configuration update request is used to request the second network device to update the configuration parameters of the first AI event; and receiving a configuration update response to the configuration update request sent by the second network device, wherein the configuration update response indicates whether the second network device successfully updated the configuration parameter of the first AI event or failed to update; 5. The method according to any one of items 1 to 4, further comprising: (Item 6) 6. The method of claim 5, wherein the update information comprises at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, the update operation including one of modify, add, and delete. (Item 7) 7. The method according to any one of items 2 and 4 to 6, wherein the first AI event has a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device. (Item 8) 8. The method of claim 7, wherein the predictive trigger event includes at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and a predicted value of the first measurement item being less than a corresponding second specified threshold, wherein the first specified threshold is greater than the second specified threshold. (Item 9) The method according to any one of items 2 and 4 to 6, wherein the first AI event has a currently measured trigger event, and the currently measured trigger event includes a trigger event based on a current measurement result of the second network device. (Item 10) The current measurement type trigger event includes at least one of the following: a current measurement value of a first measurement item being greater than a corresponding third specified threshold; a current measurement value of the first measurement item being less than a corresponding fourth specified threshold; a current measurement value of a second measurement item being different from a predicted value prior to the present time; a rate of error between a current measurement value of a third measurement item and a predicted value prior to the present time being greater than a corresponding fifth specified threshold; and a rate of error between a current measurement value of the third measurement item and the predicted value prior to the present time being less than a corresponding sixth specified threshold, wherein the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold. (Item 11) Item 11. The method according to item 10, wherein the first measurement item includes any one of a device load, a device energy consumption, and a terminal traffic, the second measurement item includes a terminal movement path or a terminal service, and the third measurement item includes any one of a device load, a device energy consumption, and a terminal traffic. (Item 12) 12. The method of any one of items 8, 10, and 11, wherein, when the first AI event has the predictive trigger event or the current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a duration of the first AI event. (Item 13) The method according to any one of items 2 and 4 to 6, wherein the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device. (Item 14) Item 14. The method of item 13, wherein the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed. (Item 15) If the first AI event includes the cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event; If the first AI event has at least one of the following: the terminal is successfully handed over, and the terminal is in handover, the configuration parameters of the first AI event include a terminal identifier list and a duration; or If the first AI event has the AI ​​use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration. Item 15. The method according to item 14. (Item 16) 1. A data transmission method, the method being applied to a second network device, the method comprising: receiving an AI data request sent by a first network device, where the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger the second network device to send AI data to the first network device; and transmitting the AI ​​data to the first network device based on the event information of the first AI event; A method comprising: (Item 17) The event information of the first AI event includes an event identifier and configuration parameters of the first AI event; The step of the second network device transmitting the AI ​​data to the first network device based on the event information of the first AI event includes: the second network device transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event. Item 17. The method according to Item 16, comprising: (Item 18) The event information of the first AI event includes an event identifier of the first AI event; Transmitting the AI ​​data to the first network device based on the event information of the first AI event includes: obtaining configuration parameters of the first AI event based on the event identifier of the first AI event; and transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event. Item 17. The method according to Item 16, comprising: (Item 19) Prior to receiving the AI ​​data request sent by the first network device, the method includes: receiving an AI event information set transmitted by the first network device, where the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes the first AI event; and Storing the AI ​​event information set. Item 19. The method of item 18, further comprising: (Item 20) The method comprises: receiving a configuration update request sent by the first network device, wherein the configuration update request includes the event identifier and update information of the first AI event; updating the configuration parameters of the first AI event based on the event identifier of the first AI event and the update information; and sending a configuration update response to the first network device, wherein the configuration update response indicates whether the configuration parameters of the first AI event were successfully updated or whether the update failed; 20. The method according to any one of items 16 to 19, further comprising: (Item 21) 21. The method of claim 20, wherein the update information comprises at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, the update operation including one of modify, add, and delete. (Item 22) 20. The method according to any one of items 17 to 19, wherein the first AI event has a predictive trigger event, and the predictive trigger event includes a trigger event based on an AI model prediction result of the second network device. (Item 23) 23. The method of claim 22, wherein the predictive trigger event includes at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and a predicted value of the first measurement item being less than a corresponding second specified threshold, wherein the first specified threshold is greater than the second specified threshold. (Item 24) 20. The method according to any one of items 17 to 19, wherein the first AI event comprises a current measurement type trigger event, and the current measurement type trigger event comprises a trigger event based on a current measurement result of the second network device. (Item 25) The current measurement type trigger event includes at least one of the following: a current measurement value of a first measurement item being greater than a corresponding third specified threshold; a current measurement value of the first measurement item being less than a corresponding fourth specified threshold; a current measurement value of a second measurement item being different from a predicted value prior to the present time; a rate of error between a current measurement value of a third measurement item and a predicted value prior to the present time being greater than a corresponding fifth specified threshold; and a rate of error between a current measurement value of the third measurement item and the predicted value prior to the present time being less than a corresponding sixth specified threshold, wherein the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold. (Item 26) Item 26. The method according to item 25, wherein the first measurement item includes any one of a device load, a device energy consumption, and a terminal traffic, the second measurement item includes a terminal movement path or a terminal service, and the third measurement item includes any one of a device load, a device energy consumption, and a terminal traffic. (Item 27) 27. The method of any one of items 23, 25, and 26, wherein, when the first AI event has the predictive trigger event or the current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include the duration of the first AI event. (Item 28) Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting the first AI event based on the event identifier of the first AI event, the indication of the measurement, and / or the specified threshold corresponding to the measurement; and transmitting the AI ​​data to the first network device if the first AI event is continuously detected within the duration. 28. The method of claim 27, comprising: (Item 29) 20. The method according to any one of items 17 to 19, wherein the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device. (Item 30) 30. The method of claim 29, wherein the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed. (Item 31) If the first AI event comprises the cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting an enabled / disabled state of a target cell based on the event identifier of the first AI event, where the cell identifier of the target cell is any cell identifier in the cell identifier list; and transmitting the AI ​​data to the first network device if the target cell is detected to be in the enabled state within the duration. Item 31. The method according to Item 30, comprising: (Item 32) If the first AI event includes that the terminal is successfully handed over, the configuration parameters of the first AI event include a terminal identifier list and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting a stationary state of a target terminal based on the event identifier of the first AI event, where the identifier of the target terminal is any identifier in the terminal identifier list, and the target terminal is a terminal that has been handed over to the second network device; and transmitting the AI ​​data to the first network device if the target terminal is detected to be continuously stationed on the second network device within the duration. Item 31. The method according to Item 30, comprising: (Item 33) If the first AI event has the AI ​​use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: detecting a status of execution of the AI ​​use case by the second network device based on the event identifier of the first AI event; and transmitting the AI ​​data to the first network device if the second network device is detected to be executing the AI ​​use case within the duration. Item 31. The method according to Item 30, comprising: (Item 34) A data transmission device comprising at least one module, the at least one module being configured to execute the data transmission method according to any one of items 1 to 16 or items 17 to 33. (Item 35) A data transmission device comprising a processor, the processor being configured to execute at least one program instruction or code stored in a memory to implement the data transmission method described in any one of items 1 to 16 or items 17 to 33. (Item 36) A computer-readable storage medium storing instructions that, when executed on a network device, enable the network device to perform the data transmission method described in any one of items 1 to 16 or items 17 to 33.

Claims

1. 1. A data transmission method, the method being applied to a first network device, the method comprising: sending an AI data request to a second network device, wherein the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger the second network device to send AI data to the first network device; and receiving the AI ​​data A method comprising:

2. The method of claim 1 , wherein the event information for the first AI event includes an event identifier and configuration parameters for the first AI event.

3. The method of claim 1 , wherein the event information for the first AI event includes an event identifier for the first AI event.

4. Prior to sending the AI ​​data request to the second network device, the method includes: sending an AI event information set to the second network device to instruct the second network device to store the AI ​​event information set, wherein the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, and the at least one AI event includes the first AI event. The method of claim 3 further comprising:

5. The method comprises: sending a configuration update request to the second network device, wherein the configuration update request includes the event identifier and update information of the first AI event, and the configuration update request is used to request the second network device to update the configuration parameters of the first AI event; and receiving a configuration update response to the configuration update request sent by the second network device, wherein the configuration update response indicates whether the second network device successfully updated the configuration parameters of the first AI event or failed to update. The method of any one of claims 1 to 4, further comprising:

6. The method of claim 5 , wherein the update information comprises at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, the update operation comprising one of modify, add, and delete.

7. 7. The method of claim 2, wherein the first AI event comprises a predictive trigger event, and the predictive trigger event comprises a trigger event based on an AI model prediction result of the second network device.

8. 8. The method of claim 7, wherein the predictive trigger event comprises at least one of the following: a predicted value of a first measurement item being greater than a corresponding first specified threshold; and the predicted value of the first measurement item being less than a corresponding second specified threshold, wherein the first specified threshold is greater than the second specified threshold.

9. The method of any one of claims 2 and 4 to 6, wherein the first AI event comprises a current measurement-type trigger event, and the current measurement-type trigger event comprises a trigger event based on a current measurement result of the second network device.

10. 10. The method of claim 9, wherein the current measurement-type trigger event includes at least one of the following: a current measurement value of a first measurement item being greater than a corresponding third specified threshold; the current measurement value of the first measurement item being less than a corresponding fourth specified threshold; the current measurement value of a second measurement item being different from a predicted value prior to the present time; a rate of error between a current measurement value and a predicted value prior to the present time of a third measurement item being greater than a corresponding fifth specified threshold; and the rate of error between the current measurement value and the predicted value prior to the present time of the third measurement item being less than a corresponding sixth specified threshold, wherein the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

11. 11. The method of claim 10, wherein the first measurement item includes any one of a device load, a device energy consumption, and a terminal traffic, the second measurement item includes a terminal movement path or a terminal service, and the third measurement item includes any one of a device load, a device energy consumption, and a terminal traffic.

12. 12. The method of claim 8, wherein when the first AI event has the predictive trigger event or the current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a duration of the first AI event.

13. The method of any one of claims 2 and 4 to 6, wherein the first AI event has a current action type trigger event, and the current action type trigger event includes a trigger event based on a current action of the second network device.

14. 14. The method of claim 13, wherein the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

15. If the first AI event comprises the cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event; If the first AI event has at least one of the following: the terminal is successfully handed over, and the terminal is in handover, the configuration parameters of the first AI event include a terminal identifier list and a duration; or If the first AI event has the AI ​​use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration.

15. The method of claim 14.

16. 1. A data transmission method, the method being applied to a second network device, the method comprising: receiving an AI data request sent by a first network device, wherein the AI ​​data request includes event information of a first AI event, and the first AI event is used to trigger the second network device to send AI data to the first network device; and transmitting the AI ​​data to the first network device based on the event information of the first AI event. A method comprising:

17. The event information for the first AI event includes an event identifier and configuration parameters for the first AI event; The step of the second network device transmitting the AI ​​data to the first network device based on the event information of the first AI event includes: the second network device transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event.

17. The method of claim 16, comprising:

18. the event information for the first AI event includes an event identifier for the first AI event; Transmitting the AI ​​data to the first network device based on the event information of the first AI event includes: obtaining configuration parameters of the first AI event based on the event identifier of the first AI event; and transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event.

17. The method of claim 16, comprising:

19. Prior to receiving the AI ​​data request sent by the first network device, the method includes: receiving an AI event information set transmitted by the first network device, wherein the AI ​​event information set includes configuration parameters and an event identifier of at least one AI event, the at least one AI event including the first AI event; and Storing the AI ​​event information set.

20. The method of claim 18, further comprising:

20. The method comprises: receiving a configuration update request sent by the first network device, wherein the configuration update request includes the event identifier and update information for the first AI event; updating the configuration parameters of the first AI event based on the event identifier of the first AI event and the update information; and sending a configuration update response to the first network device, wherein the configuration update response indicates whether the configuration parameters of the first AI event were successfully updated or whether the update failed; The method of any one of claims 16 to 19, further comprising:

21. 21. The method of claim 20, wherein the update information comprises at least one configuration parameter and an update operation corresponding to each of the at least one configuration parameter, the update operation comprising one of modify, add, and delete.

22. 20. The method of claim 17, wherein the first AI event comprises a predictive trigger event, and the predictive trigger event comprises a trigger event based on an AI model prediction result of the second network device.

23. 23. The method of claim 22, wherein the predictive trigger event comprises at least one of the following: a predicted value of a first measurement being greater than a corresponding first specified threshold; and the predicted value of the first measurement being less than a corresponding second specified threshold, wherein the first specified threshold is greater than the second specified threshold.

24. 20. The method of claim 17, wherein the first AI event comprises a current measurement-type trigger event, and the current measurement-type trigger event comprises a trigger event based on a current measurement result of the second network device.

25. 25. The method of claim 24, wherein the current measurement-type trigger event comprises at least one of the following: a current measurement value of a first measurement item being greater than a corresponding third specified threshold; the current measurement value of the first measurement item being less than a corresponding fourth specified threshold; the current measurement value of a second measurement item being different from a predicted value prior to the present time; a rate of error between a current measurement value and a predicted value prior to the present time of a third measurement item being greater than a corresponding fifth specified threshold; and the rate of error between the current measurement value and the predicted value prior to the present time of the third measurement item being less than a corresponding sixth specified threshold, wherein the third specified threshold is greater than the fourth specified threshold and the fifth specified threshold is greater than the sixth specified threshold.

26. 26. The method of claim 25, wherein the first measurement item includes any one of a device load, a device energy consumption, and a terminal traffic, the second measurement item includes a terminal movement path or a terminal service, and the third measurement item includes any one of a device load, a device energy consumption, and a terminal traffic.

27. 27. The method of claim 23, wherein when the first AI event has the predictive trigger event or the current measurement trigger event, the configuration parameters of the first AI event include indication information of a measurement item and / or a specified threshold corresponding to the measurement item, and the configuration parameters of the first AI event further include a duration of the first AI event.

28. Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting the first AI event based on the event identifier of the first AI event, the indication of the measurement, and / or the specified threshold corresponding to the measurement; and transmitting the AI ​​data to the first network device if the first AI event is continuously detected within the duration.

28. The method of claim 27, comprising:

29. 20. The method of claim 17, wherein the first AI event comprises a current action type trigger event, and the current action type trigger event comprises a trigger event based on a current action of the second network device.

30. 30. The method of claim 29, wherein the current action type trigger event includes at least one of the following: a cell is activated, a terminal is successfully handed over, a terminal is in handover, and an AI use case is being executed.

31. If the first AI event comprises the cell being enabled, the configuration parameters of the first AI event include a cell identifier list and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting an enabled / disabled state of a target cell based on the event identifier of the first AI event, where the cell identifier of the target cell is any cell identifier in the cell identifier list; and transmitting the AI ​​data to the first network device if the target cell is detected to be in the valid state within the duration.

31. The method of claim 30, comprising:

32. If the first AI event comprises the terminal being successfully handed over, the configuration parameters of the first AI event include a terminal identifier list and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting a stationary state of a target terminal based on the event identifier of the first AI event, where the identifier of the target terminal is any identifier in the terminal identifier list, and the target terminal is a terminal handed over to the second network device; and transmitting the AI ​​data to the first network device if the target terminal is detected to be continuously stationed on the second network device within the duration.

31. The method of claim 30, comprising:

33. If the first AI event has the AI ​​use case being executed, the configuration parameters of the first AI event include the AI ​​use case and a duration of the first AI event; Transmitting the AI ​​data to the first network device based on the event identifier and the configuration parameters of the first AI event includes: Detecting a status of execution of the AI ​​use case by the second network device based on the event identifier of the first AI event; and transmitting the AI ​​data to the first network device if the second network device is detected to be executing the AI ​​use case within the duration.

31. The method of claim 30, comprising:

34. A data transmission device comprising at least one module, said at least one module being configured to perform the data transmission method according to any one of claims 1 to 16 or 17 to 33.

35. 34. A data transmission device comprising a processor, the processor configured to execute at least one program instruction or code stored in a memory to implement the data transmission method of any one of claims 1 to 16 or claims 17 to 33.

36. 34. A computer-readable storage medium having stored thereon instructions that, when executed on a network device, enable the network device to perform the data transmission method of any one of claims 1 to 16 or claims 17 to 33.

Images