Communication method, communication apparatus and communication system

Abstract

Provided in the present application are a communication method, a communication apparatus, and a communication system. In the method, a first device determines, on the basis of a first model, whether collected sample data can be reported. Because the first model is obtained by training a large quantity of sample data, the model has a powerful function for analyzing sample data, thereby helping to improve the data acquisition efficiency and the data acquisition quality. In addition, using the first model to analyze sample data can filter out sample data which does not meet a reporting condition, that is, an output result is non-reporting of the sample data, such that the frequency of the first device reporting sample data which does not meet requirements can be reduced, thereby reducing the burden of data processing, and further improving the data acquisition efficiency and the data acquisition quality. The data collection solution is relatively flexible and efficient.

Description

Communication method, communication device and communication system

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on February 2, 2024, with application number 202410153398.6 and invention name "A communication method, communication device and communication system", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of wireless communication technology, and in particular to a communication method, a communication device, and a communication system. Background Art

[0004] In the field of wireless communications, more and more application scenarios require data analysis based on the massive amounts of data collected, and then performing corresponding operations based on the data analysis results, such as network load balancing based on the data analysis results.

[0005] However, how to improve data collection efficiency and quality remains to be solved. Summary of the Invention

[0006] The embodiments of the present application provide a communication method, a communication device, and a communication system to improve data collection efficiency and data collection quality.

[0007] In a first aspect, embodiments of the present application provide a communication method that can be executed by a first device or a module (e.g., a chip) in the first device. The method includes: receiving a first instruction, the first instruction including instruction information and an identifier of a first model, the instruction information indicating data reporting based on the first model; inputting collected sample data into the first model to obtain an output result, the output result indicating whether to report the sample data or not, and the data collection solution is relatively flexible and efficient.

[0008] In the above solution, the first device determines whether the collected sample data can be reported based on the first model. Because the first model is trained on a large amount of sample data, its sample data analysis capabilities are relatively powerful, thus helping to improve data collection efficiency and quality. Furthermore, by analyzing the sample data based on the first model, sample data that does not meet the reporting requirements can be filtered out, resulting in the output of "not reporting sample data." This reduces the frequency of reporting of sample data that does not meet the requirements, reduces the data processing burden, and further improves data collection efficiency and quality.

[0009] In one possible implementation method, when the sample data meets a first condition, the output result indicates that the sample data is to be reported, and the first condition includes at least one of the following: the characteristic value of at least one business feature in the sample data meets the characteristic value size requirement; the characteristic value of at least one business feature in the sample data meets the reporting period requirement, and the reporting period requirement is related to the degree of change of the characteristic value of the business feature within a set time period; the characteristic value of at least one business feature in the sample data meets the characteristic value distribution requirement corresponding to the business feature.

[0010] The above scheme associates the reporting period of the characteristic value of the business feature with the degree of change of the characteristic value of the business feature within a set time period, which can control the reporting frequency of the characteristic value and help reduce the redundancy of the reported characteristic values. For example, the smaller the degree of change, the higher the repetition (or redundancy) of the characteristic value of the business feature in the recent period, so the reporting frequency is lower (that is, the longer the reporting period), which helps to reduce the repeated reporting of the same or similar characteristic values, thereby improving data collection efficiency and data collection quality. In addition, the above scheme can also control the first device to collect the expected characteristic value by ensuring that the characteristic value of the business feature meets the characteristic value size requirement or the characteristic value distribution requirement corresponding to the business feature, so as to reduce the collection of invalid data (that is, unexpected characteristic values), thereby improving data collection efficiency.

[0011] In one possible implementation method, the degree of change of the characteristic value of the business feature within the set time period includes the variance, mean absolute error, autocorrelation coefficient, signal-to-noise ratio or peak detection of the characteristic value of the business feature within the set time period.

[0012] In one possible implementation method, the service characteristics include one or more of the following: performance data of the first device, measurement data of a single terminal device or measurement data of a group of terminal devices; wherein, when the first device includes a centralized unit (CU) or a distributed unit (DU), the performance data of the first device includes one or more of the following: coverage strength, coverage quality, number of switching, throughput, number of access attempts or number of dropped calls; when the first device includes a radio unit (RU), the performance data of the first device includes one or more of the following: transmission power, receiving level, background noise or bit error rate; the measurement data of the single terminal device includes one or more of the following: throughput, traffic volume, number of switching; the measurement data of the group of terminal devices includes one or more of the following: throughput, traffic volume, number of switching.

[0013] In a possible implementation method, the method further includes: when the output result indicates that the sample data is not to be reported, sending the sample data; or when the output result indicates that the sample data is not to be reported, discarding the sample data.

[0014] In a possible implementation method, the first instruction further includes an identifier of the first device.

[0015] In one possible implementation method, the first device includes a CU or a DU; the receiving of the first instruction includes: receiving the first instruction from the near real-time wireless access network intelligent controller through an interface between the first device and the near real-time wireless access network intelligent controller.

[0016] In a possible implementation method, the first device includes an RU; and the receiving of the first instruction includes: receiving the first instruction from a near real-time wireless access network intelligent controller through an interface between the RU and the DU.

[0017] In a possible implementation method, the method further includes: receiving a second instruction, where the second instruction includes file information of the first model.

[0018] In one possible implementation method, the first device includes a CU or a DU; the receiving the second instruction includes: receiving the second instruction from the near real-time wireless access network intelligent controller through an interface between the first device and the near real-time wireless access network intelligent controller.

[0019] In a possible implementation method, the first device includes an RU; and the receiving of the second instruction includes: receiving the second instruction from a near real-time wireless access network intelligent controller through an interface between the RU and the DU.

[0020] In one possible implementation method, the indication information also indicates the data collection type, and the data collection type is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

[0021] In a second aspect, embodiments of the present application provide a communication method that can be performed by a second device or a module (e.g., a chip) in the second device. The method includes: generating a first model; and sending a first instruction to the first device, the first instruction including instruction information and an identifier of the first model, the instruction information instructing data reporting based on the first model.

[0022] In the above solution, the second device instructs the first device to report data based on the first model, so that the first device determines whether the collected sample data can be reported based on the first model. Because the first model is trained based on a large amount of sample data, its sample data analysis function is relatively powerful, thus helping to improve data collection efficiency and quality. In addition, by analyzing the sample data based on the first model, sample data that does not meet the reporting conditions can be filtered out, that is, the output result is that the sample data is not reported. As a result, the first device reduces the frequency of reporting sample data that does not meet the requirements, reduces the burden of data processing, and can further improve data collection efficiency and quality.

[0023] In a possible implementation method, the method also includes: receiving sample data from the first device, the sample data meeting a first condition, the first condition including at least one of the following: the characteristic value of at least one business feature in the sample data meets the characteristic value size requirement; the characteristic value of at least one business feature in the sample data meets the reporting period requirement, and the reporting period requirement is related to the degree of change of the characteristic value of the business feature within a set time period; the characteristic value of at least one business feature in the sample data meets the characteristic value distribution requirement corresponding to the business feature.

[0024] In a possible implementation method, the first instruction further includes an identifier of the first device.

[0025] In one possible implementation method, generating the first model includes: receiving business requirements, wherein the business requirements indicate at least one of a first eigenvalue size requirement, a first eigenvalue quantity, a first eigenvalue distribution requirement, or a first reporting period requirement of the business feature to be collected, and the first reporting period requirement is related to the degree of change of the eigenvalue of the business feature within a set time period; generating the first model according to the business requirements.

[0026] The above scheme associates the reporting period of the characteristic value of the business feature with the degree of change of the characteristic value of the business feature within a set time period, which can control the reporting frequency of the characteristic value and help reduce the redundancy of the reported characteristic values. For example, the smaller the degree of change, the higher the repetition (or redundancy) of the characteristic value of the business feature in the recent period, so the reporting frequency is lower (that is, the longer the reporting period), which helps to reduce the repeated reporting of the same or similar characteristic values, thereby improving data collection efficiency and data collection quality. In addition, the above scheme can also control the first device to collect the expected characteristic value by ensuring that the characteristic value of the business feature meets the characteristic value size requirement or the characteristic value distribution requirement corresponding to the business feature, so as to reduce the collection of invalid data (that is, unexpected characteristic values), thereby improving data collection efficiency.

[0027] In a possible implementation method, the method also includes: determining update information based on the collected sample data and the business needs, the update information including at least one of the second eigenvalue size requirement, the second eigenvalue quantity, the second eigenvalue distribution requirement or the second reporting period requirement of the business feature to be collected, the second reporting period requirement being related to the degree of change of the eigenvalue of the business feature within a set time period; updating the first model according to the update information to obtain the second model; and sending the file information of the second model to the first device.

[0028] In the above scheme, the second device can dynamically update the first model based on the collected sample data to obtain the second model, and notify the first device to use the second model for data collection, which helps to achieve more accurate reporting of sample data and improve data collection efficiency and quality.

[0029] In one possible implementation method, the first device includes a CU or a DU, and the second device includes a near-real-time wireless access network intelligent controller; sending the first instruction to the first device includes: sending the first instruction to the first device through an interface between the first device and the second device.

[0030] In one possible implementation method, the first device includes an RU, and the second device includes a near real-time wireless access network intelligent controller; sending the first instruction to the first device includes: sending the first instruction to the first device through an interface between the second device and the DU.

[0031] In a possible implementation method, the method further includes: sending a second instruction to the first device, where the second instruction includes file information of the first model.

[0032] In one possible implementation method, the first device includes a CU or a DU, and the second device includes a near-real-time wireless access network intelligent controller; sending a second instruction to the first device includes: sending a second instruction to the first device through an interface between the first device and the second device.

[0033] In one possible implementation method, the first device includes an RU, and the second device includes a near real-time wireless access network intelligent controller; sending the second instruction to the first device includes: sending the second instruction to the first device through an interface between the second device and the DU.

[0034] In one possible implementation method, the indication information also indicates the data collection type, and the data collection type is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

[0035] In a third aspect, an embodiment of the present application provides a communication device, which may be a first device or a module (such as a chip) in the first device. The device has the function of implementing any implementation method of the first aspect described above. The function may be implemented by hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more modules corresponding to the above functions.

[0036] In a fourth aspect, an embodiment of the present application provides a communication device, which may be a second device or a module (such as a chip) in the second device. The device has the function of implementing any implementation method of the second aspect described above. The function may be implemented by hardware or by hardware executing corresponding software implementation. The hardware or software includes one or more modules corresponding to the above functions.

[0037] In a fifth aspect, an embodiment of the present application provides a communication device, comprising a unit or means for executing each step of any implementation method in the above-mentioned first to second aspects.

[0038] In a sixth aspect, an embodiment of the present application provides a communication device, comprising a processor and an interface circuit, wherein the processor is configured to communicate with other devices via the interface circuit and execute any of the implementation methods in the first to second aspects above. The processor comprises one or more.

[0039] Optionally, the communication device may further include a memory for storing computer instructions, the memory being coupled to a processor, and the processor executing the computer instructions stored in the memory so that the device executes any implementation method in the above-mentioned first to second aspects.

[0040] In the seventh aspect, an embodiment of the present application also provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run by a communication device, any implementation method in the above-mentioned first to second aspects is executed.

[0041] In an eighth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, which, when executed on a communication device, enables any implementation method in the above-mentioned first to second aspects to be executed.

[0042] In a ninth aspect, an embodiment of the present application further provides a chip system, comprising: a processor for executing any implementation method in the above-mentioned first to second aspects.

[0043] In the tenth aspect, an embodiment of the present application also provides a communication system, comprising: a first device for executing any implementation method in the above-mentioned first aspect, and a second device for executing any implementation method in the above-mentioned second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] FIG1( a ) is a schematic diagram of the architecture of a communication system used in an embodiment of the present application;

[0045] Figure 1(b) shows a schematic diagram of a network device;

[0046] Figure 2 is a schematic diagram of the architecture;

[0047] FIG3 is a flow chart of a communication method provided in an embodiment of the present application;

[0048] FIG4 is a schematic diagram of the architecture for data collection and reporting based on the model;

[0049] FIG5 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0050] FIG6 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] Figure 1(a) is a schematic diagram of the architecture of a communication system used in an embodiment of the present application. The communication system shown in Figure 1(a) includes a wireless access network 100 and a core network 200. Optionally, the communication system also includes the Internet 300. The wireless access network 100 may include at least one network device (such as 110a and 110b in Figure 1(a)) and may also include at least one terminal device (such as 120a-120j in Figure 1(a)). The terminal device is connected to the network device wirelessly, and the network device is connected to the core network wirelessly or by wire. The core network device and the network device may be independent and distinct physical devices, or the functions of the core network device and the logical functions of the network device may be integrated into the same physical device, or a physical device may integrate some of the functions of the core network device and some of the functions of the network device. Terminal devices and network devices may be connected to each other via wired or wireless connections. Figure 1(a) is merely a schematic diagram. The communication system may also include other network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in Figure 1(a).

[0052] A network device is an access device that a terminal device uses to access a communication system via a wired or wireless method. A network device may be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a fifth generation (5G) mobile communication system, a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system; it may also be a module or unit that performs some of the functions of a base station, for example, a centralized unit (CU), a distributed unit (DU), or a radio unit (RU). A network device may be a macro base station (such as 110a in FIG1(a)), a micro base station or an indoor station (such as 110b in FIG1(a)), a relay node or a donor node, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

[0053] A terminal device is a device with wireless transceiver capabilities that can send signals to or receive signals from a network device. Terminal devices include but are not limited to terminal devices, terminals, user equipment (UE), mobile stations, mobile terminals, etc. Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal device can specifically be a mobile phone, tablet computer, computer with wireless transceiver capabilities, wearable device, vehicle, aircraft, ship, robot, robotic arm, smart home device, etc. The embodiments of this application do not limit the specific technology and specific device form adopted by the terminal device.

[0054] Network devices and terminal devices can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed on aircraft, balloons, and artificial satellites. The embodiments of this application do not limit the application scenarios of network devices and terminal devices.

[0055] The roles of network devices and terminal devices can be relative. For example, the helicopter or drone 120i in Figure 1(a) can be configured as a mobile network device. For those terminal devices 120j that access the wireless access network 100 through 120i, the terminal device 120i is a network device; but for the network device 110a, 120i is a terminal device, that is, communication between 110a and 120i is carried out through the wireless air interface protocol. Of course, 110a and 120i can also communicate through the interface protocol between network devices. In this case, relative to 110a, 120i is also a network device. Therefore, network devices and terminal devices can be collectively referred to as communication devices. 110a and 110b in Figure 1(a) can be referred to as communication devices with network device functions, and 120a-120j in Figure 1(a) can be referred to as communication devices with terminal device functions. For ease of explanation, the embodiments of this application will be described later using UE as an example of a terminal device.

[0056] Communication between network devices and UEs, between network devices, and between UEs can be carried out through authorized spectrum, unauthorized spectrum, or both; communication can be carried out through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0057] In the embodiments of the present application, the functions of the network device may also be performed by a module (such as a chip) in the network device, or by a control subsystem that includes the network device functions. The control subsystem that includes the network device functions here may be a control center in the above-mentioned application scenarios such as smart grid, industrial control, smart transportation, and smart city. The functions of the UE may also be performed by a module (such as a chip or modem) in the UE, or by a device that includes the UE functions.

[0058] In this application, a network device sends downlink signals or downlink information to a UE, and the downlink information is carried on a downlink channel. The UE sends uplink signals or uplink information to the network device, and the uplink information is carried on an uplink channel. In order to communicate with the network device, the UE needs to establish a wireless connection with the cell controlled by the network device. The cell with which the UE has established a wireless connection is called the UE's serving cell.

[0059] Figure 1(b) shows a schematic diagram of a network device. As shown in Figure 1(b), the network device includes one or more CUs, one or more DUs, and one or more RUs. For clarity, Figure 1(b) shows only one CU, DU, and RU. The CU is connected to the core network and one or more DUs. Optionally, the CU may have some of the core network's functionality. The CU may include a CU-control plane (CP) and a CU-user plane (UP).

[0060] The CU and DU can be configured according to the protocol layer functions of the wireless network they implement: for example, the CU is configured to implement the functions of the packet data convergence protocol (PDCP) layer and the protocol layers above it (such as the radio resource control (RRC) layer and / or the service data adaptation protocol (SDAP) layer, etc.); the DU is configured to implement the functions of the protocol layers below the PDCP layer (such as the radio link control (RLC) layer, the medium access control (MAC) layer, and / or the physical (PHY) layer, etc.). For another example, the CU is configured to implement the functions of the protocol layers above the PDCP layer (such as the RRC layer and / or the SDAP layer), and the DU is configured to implement the functions of the PDCP layer and the protocol layers below it (such as the RLC layer, the MAC layer, and / or the PHY layer, etc.).

[0061] The above configuration of CU and DU is only an example, and the functions of CU and DU can also be configured as needed. For example, the CU or DU can be configured to have the functions of more protocol layers, or the CU or DU can be configured to have partial processing functions of the protocol layer. For example, some functions of the RLC layer and the functions of the protocol layers above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set in the DU. For another example, the functions of the CU or DU can be divided according to the service type or other system requirements, such as by delay, and the functions whose processing time needs to meet the smaller delay requirement are set in the DU, and the functions that do not need to meet the delay requirement are set in the CU.

[0062] The DU and RU can work together to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways according to the design. For example, the DU is configured to implement the baseband function, and the RU is configured to implement the mid-RF function. For another example, the DU is configured to implement the high-layer functions in the PHY layer, and the RU is configured to implement the low-layer functions in the PHY layer or to implement the low-layer functions and the RF functions. The high-layer functions in the physical layer may include a part of the functions of the physical layer, which is closer to the MAC layer, and the low-layer functions in the physical layer may include another part of the functions of the physical layer, which is closer to the mid-RF side.

[0063] The CU and DU may be set separately, or may be included in the same network element, such as a baseband unit (BBU). The RU may be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU) or a remote radio head (RRH). In different systems, CU, DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (ORAN) system, CU may also be referred to as O-CU (open CU), DU may also be referred to as O-DU, and RU may also be referred to as O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0064] Figure 2 shows the architecture diagram. The architecture includes the CU / DU, the Non-Realtime RAN Intelligent Controller (Non-RT RIC), and the Near-Real-Time RAN Intelligent Controller (Near-RT RIC).

[0065] The CU / DU is used to collect data (eg, CU / DU data, RU data, or UE data), and report the data to the Non-RT RIC and / or the Near-RT RIC.

[0066] The Non-RT RIC is a logical function that supports the training of non-real-time AI models, saves the trained model file information, and provides the trained model file information to the Near-RT RIC. In specific implementations, the Non-RT RIC can be deployed on a different physical entity than the CU / DU, or it can be deployed on the same physical entity as the CU / DU.

[0067] Near-RT RIC is also a logical function that supports real-time AI model training and inference using AI models. In specific implementations, Near-RT RIC can be deployed on a different physical entity than the CU / DU, or on the same physical entity as the CU / DU. The primary goal of Near-RT RIC is to enhance and automate RAN management and optimization by introducing machine learning and AI algorithms.

[0068] In the embodiments of the present application, the artificial intelligence model may also be referred to as a machine learning (ML) model. For ease of explanation, it will be referred to as a model in the following.

[0069] Referring to FIG2 , the architecture may include at least one of the following operations:

[0070] 1) CU / DU collects data for offline training and sends the data for offline training to Non-RT RIC through the O1 interface.

[0071] 2) Non-RT RIC performs non-real-time offline training based on the data used for offline training to obtain a trained model.

[0072] 3) Non-RT RIC stores the file information of the trained model.

[0073] 4) CU / DU collects data for online training and sends the data for online training to Near-RT RIC through the E2 interface.

[0074] 5) Near-RT RIC performs real-time online training based on the data used for online training to obtain a trained model.

[0075] 6) Near-RT RIC downloads the model from Non-RT RIC, so that real-time online training can be performed based on the downloaded model and the collected data for online training.

[0076] 7) Near-RT RIC updates the file information of the model obtained by online training to Non-RT RIC for storage.

[0077] 8) Near-RT RIC deployment model for model reasoning.

[0078] 9) CU / DU collects data for model inference and sends the data for model inference to Near-RT RIC through the E2 interface.

[0079] 10) Near-RT RIC obtains the inference results based on the input data for model inference.

[0080] 11) Near-RT RIC provides performance feedback after model inference.

[0081] 12) Near-RT RIC sends the inference results to CU / DU through the E2 interface.

[0082] In the field of wireless communications, an increasing number of application scenarios require data analysis based on massive amounts of collected data, and then performing corresponding operations based on the data analysis results, such as network load balancing based on data analysis results. However, how to improve data collection efficiency and quality remains to be solved.

[0083] In current technology, a condition-based measurement method is used. Specifically, a data usage device (such as Near-RT RIC, Non-RT RIC, etc.) sends a data collection instruction to a data collection device (such as CU / DU / RU, etc.). The instruction contains a data filtering condition, which indicates that when the collected data reaches a certain threshold, the data is reported. For example, when the signal strength is lower than a certain threshold or the UE's moving speed exceeds a preset value, the data collection device reports the data. This method may not be flexible and efficient when dealing with complex scenarios and dynamic network environments.

[0084] To solve this problem, this application provides corresponding embodiments, which are described in detail below.

[0085] Figure 3 is a flow chart of a communication method provided in an embodiment of the present application. The method is executed by a first device or a module of the first device (such as a chip), and a second device or a module of the second device (such as a chip). The following description takes the execution of the method by the first device and the second device as an example. Among them, the first device can be a CU, DU, RU, base station or other types of devices, and the second device can be a near real-time wireless access network intelligent controller or other types of devices that need to obtain data (such as a network data analysis function (NWDAF) network element). This application does not limit the types of the first device and the second device.

[0086] The method comprises the following steps:

[0087] Step 301: The second device generates a first model.

[0088] Exemplarily, the second device receives a service requirement from a service application, and then generates a first model based on the service requirement. The service requirement indicates at least one of a first eigenvalue size requirement, a first eigenvalue quantity requirement, a first eigenvalue distribution requirement, or a first reporting period requirement for the service features to be collected. The service application may be a service application within the second device, for example, a visualization interface installed on the second device, where a network administrator triggers the service application to send the service requirement by operating the service application on the visualization interface. The service application may also be a service application external to the second device.

[0089] For example, when a service application needs to perform cell-level handover optimization, cell-level load balancing, or user group-level live broadcast optimization, the service application can send the service requirement.

[0090] Exemplarily, the service characteristics include one or more of the following: performance data of the first device, measurement data of a single UE, or measurement data of a group of UEs. Wherein, when the first device includes a CU or a DU, the performance data of the first device includes one or more of the following: coverage strength, coverage quality, number of switching, throughput, number of access attempts, or number of dropped calls. When the first device includes an RU, the performance data of the first device includes one or more of the following: transmit power, receive level, background noise, or bit error rate. The measurement data of a single UE includes one or more of the following: throughput, traffic volume, number of switching. The measurement data of a group of UEs includes one or more of the following: throughput, traffic volume, number of switching. Wherein, the number of switching is the number of times a single UE switches to or out of the first device.

[0091] The first characteristic value can be understood as the value of a certain service characteristic. For example, when the service characteristic is the number of handovers, the first characteristic value of the service characteristic is the number of times the UE has handed over to the first device. Other similarities are omitted for clarity.

[0092] The first eigenvalue size requirement of a service feature indicates a requirement that the eigenvalue of the service feature must meet. For example, the eigenvalue of the service feature must be greater than a eigenvalue threshold. This method controls the first device to collect the desired eigenvalue by ensuring that the eigenvalue of the service feature meets the corresponding eigenvalue size requirement, thereby reducing the collection of invalid data (i.e., unexpected eigenvalues) and improving data collection efficiency.

[0093] The number of first characteristic values ​​of a service feature is used to indicate the required number of characteristic values ​​for the service feature. For example, the required number of characteristic values ​​for the service feature is 500. This method controls the first device to collect the desired characteristic values ​​based on whether the characteristic values ​​of the service feature meet the required number of characteristic values ​​corresponding to the service feature, thereby reducing the collection of invalid data (i.e., unexpected characteristic values) and improving data collection efficiency.

[0094] The first eigenvalue distribution requirement of the business feature is used to indicate the relationship between the size of the eigenvalue of the business feature and the number of eigenvalues. For example, the first eigenvalue distribution requirement is a normal distribution requirement. For another example, for the eigenvalue of the business feature, 100 eigenvalues ​​are required with values ​​between 1 and 50, 150 eigenvalues ​​are required with values ​​between 50 and 100, 50 eigenvalues ​​are required with values ​​between 100 and 150, and so on. This method controls the first device to collect the expected eigenvalues ​​by ensuring that the eigenvalues ​​of the business feature meet the eigenvalue distribution requirements corresponding to the business feature, so as to reduce the collection of invalid data (i.e., unexpected eigenvalues), thereby improving the efficiency of data collection.

[0095] The first reporting period requirement of a service feature is used to indicate the reporting period of the characteristic value of the service feature, and the first reporting period requirement of the service feature is related to the degree of change of the characteristic value of the service feature within a set time period. For example, the degree of change of the characteristic value of the service feature within the set time period can be variance, mean absolute deviation (MAD), autocorrelation coefficient (Autocorrelation Coefficient), signal-to-noise ratio (SNR) or peak detection, etc. These implementation methods are described below.

[0096] 1) The degree of change of the characteristic value of a business feature within a set time period is the variance.

[0097] Variance measures the degree of deviation between a data point and its mean, reflecting the magnitude of data fluctuation. High variance indicates a wide distribution of data points, while low variance indicates a relatively concentrated distribution. This method is suitable for scenarios where data volatility needs to be monitored. For example, in network key performance indicators (KPIs) or temperature monitoring, if temperature fluctuations are large (high variance), more frequent data collection may be necessary to capture these changes.

[0098] 2) The degree of change of the characteristic value of the business characteristic within the set time period is the mean absolute error.

[0099] Mean absolute error (MAE) is the average of the absolute differences between the observed values ​​and their mean. It provides another measure of data volatility, being less sensitive to outliers than the variance. This measure is useful when the data may contain outliers but still needs to measure the magnitude of the fluctuation. MAE can help filter out unusual fluctuations and focus on more stable trends.

[0100] 3) The degree of change of the characteristic value of the business characteristic within a set time period is the autocorrelation coefficient.

[0101] The autocorrelation coefficient measures the correlation between previous and subsequent data points in a sequence. High autocorrelation means the current data is highly similar to the previous data, while low autocorrelation indicates independence between data points. This method is suitable for time series data analysis, such as wireless channel measurement and meteorological data analysis. In these scenarios, if the data exhibits high autocorrelation, the acquisition frequency can be reduced without losing important information.

[0102] 4) The degree of change of the characteristic value of the service characteristic within a set time period is the signal-to-noise ratio.

[0103] The signal-to-noise ratio (SNR) measures the ratio of the strength of the desired signal to the background noise. A high SNR indicates a clearly discernible signal, while a low SNR may indicate that the signal is drowned out by noise. This method is suitable for signal acquisition in noisy environments, such as audio signal processing and wireless air interfaces. If the SNR is low, technical measures may be needed to improve signal quality or increase acquisition frequency to ensure signal availability.

[0104] 5) The degree of change of the characteristic value of the business characteristic within a set time period is peak detection.

[0105] Peak detection aims to identify the maximum value points in the data, which is particularly important for capturing transient events. This method is suitable for scenarios where key information in the data is reflected in the peak value, such as wireless RF power amplifiers. In these applications, timely and accurate peak detection is crucial for data analysis and decision-making.

[0106] As a specific example, if the variance of the characteristic value of the business feature in the last 10 seconds is D1, the reporting period is T1; if the variance of the characteristic value of the business feature in the last 10 seconds is D2, the reporting period is T3; if the variance of the characteristic value of the business feature in the last 10 seconds is D3, the reporting period is T3, and so on. And the variance is inversely proportional to the reporting period, that is, the smaller the variance, the larger the reporting period; the larger the variance, the smaller the reporting period. For example, the smaller the variance, the higher the repetition (or redundancy) of the characteristic value of the business feature in the recent period, so the reporting frequency is lower, which helps to reduce the repeated reporting of the same or similar characteristic values, thereby improving data collection efficiency and data collection quality. Based on this method, the reporting period of the characteristic value of the business feature is associated with the degree of change of the characteristic value of the business feature within a set time period, which can achieve the control of the reporting frequency of the characteristic value and help reduce the redundancy of the reported characteristic values.

[0107] It should be noted that the second device may receive service requirements corresponding to one or more service features from a single service application, or may receive service requirements corresponding to multiple service features from multiple service applications. For example, the second device may receive service requirement 1 corresponding to service feature 1 and service requirement 2 corresponding to service feature 2 from service application 1, and may also receive service requirement 3 corresponding to service feature 3 from service application 2.

[0108] Exemplarily, when the business requirements include requirements for the size of the first eigenvalue of a business feature, the number of the first eigenvalues ​​of a business feature, or the distribution of the first eigenvalues ​​of a business feature, the first model generated based on the business requirements can be a deep neural network (DNN) model, etc., or it can be understood that the first model is any other model with the functions of a DNN model.

[0109] Exemplarily, when the business demand includes a first reporting cycle requirement for business features, the first model generated based on the business demand may be a timing model, which may be, for example, a recursive neural network (RNN) model or a long short-term memory (LSTM) model, or it may be understood that the first model has the functions of an RNN model or an LSTM model.

[0110] Step 302: The second device sends a first instruction to the first device. Correspondingly, the first device receives the first instruction.

[0111] The first instruction includes indication information and an identifier of a first model, where the identifier of the first model is used to identify the first model, and the indication information indicates that data reporting is performed based on the first model.

[0112] Exemplarily, the indication information is further used to indicate a data collection type, where the data collection type is used to indicate the source and / or type of the collected data. For example, the data collection type indicates collection of performance data of a first device, collection of performance data and / or network data of a single UE, or collection of performance data and / or network data of a group of UEs.

[0113] Optionally, the first instruction further includes an identifier of the first device, and the first instruction instructs the first device to collect and report data.

[0114] Exemplarily, if the second device is a near-real-time radio access network intelligent controller and the first device includes a CU, the second device may send the first instruction to the CU via an interface between the near-real-time radio access network intelligent controller and the CU. If the second device is a near-real-time radio access network intelligent controller and the first device includes a DU, the second device may send the first instruction to the DU via an interface between the near-real-time radio access network intelligent controller and the DU. If the second device is a near-real-time radio access network intelligent controller and the first device includes an RU, the second device may send the first instruction to the DU via an interface between the near-real-time radio access network intelligent controller and the DU, and the DU may then forward the first instruction to the RU via an interface between the DU and the RU.

[0115] In one implementation method, the first instruction also includes file information of the first model, for example, the file information of the first model includes network structure information, weight information, etc. of the first model. The network structure information is used to indicate the association relationship between each node in the first model. The weight information is used to indicate the weight size between different nodes. Based on the network structure information and weight information, the first device can determine the complete information of the first model, that is, determine the first model that can be used. The first device can then use the first model to determine whether to report the collected sample data.

[0116] In another implementation method, the second device may send a second instruction to the first device before or after step 302, wherein the second instruction includes the file information of the first model. For details of the file information of the first model, refer to the above description.

[0117] That is to say, the second device can inform the first device of the file information about the first model in different ways, and there may be other ways, which will not be described in detail in this application.

[0118] Exemplarily, the method for sending the second instruction may refer to the method for sending the first instruction described above, and will not be described in detail.

[0119] In one implementation method, if the embodiment of Figure 3 is applied in the scenario shown in Figure 2, the first device includes DU, DU or RU, and the second device is a Near-RT RIC, then the first instruction can be a control instruction in a subscription procedure (for example, ric subscription procedure), and the control instruction includes a model identifier (ID) and a RIC style type (style Type), and the RIC style Type is a specific example of the above-mentioned indication information.

[0120] For example, when the first instruction is a control instruction of a ric subscription procedure, a manner of carrying the model identifier in the control instruction may be: modifying label informaiton or teset informaiton in the control instruction to the model identifier.

[0121] Exemplarily, the RIC style Type may be any of the following:

[0122] 1) Model-based E2 Node Measurement

[0123] This type indicates that E2 nodes (i.e., CUs and / or CUs) collect and report sample data based on a model and measures the performance and status of E2 nodes. This type of measurement is used to assess the overall health and performance of E2 nodes to optimize network performance and resource utilization.

[0124] 2) Model-based, E2 Node Measurement for a single UE

[0125] This type of measurement indicates that the E2 node collects and reports sample data based on a model and measures the performance and status of a single UE. This type of measurement is used to diagnose the UE and optimize the user experience.

[0126] 3) Model-based, UE-level E2 Node Measurement

[0127] This type indicates that the E2 node collects and reports sample data based on the model and indicates that the network performance at the UE level is measured. This type of measurement is used to optimize the UE's network status and resource usage.

[0128] 4) Common Model-based, UE-level E2 Node Measurement

[0129] This type of measurement indicates that the E2 node collects and reports sample data based on a model and indicates the conditions that affect the UE level. This type of measurement is used to resolve network issues that have a wide impact on user experience.

[0130] 5) Model-based, E2 Node Measurement for multiple UEs

[0131] This type of measurement indicates that the E2 node collects and reports sample data based on a model and measures the performance and status of multiple UEs. This type of measurement is used to obtain a more comprehensive view of network interactions and performance from the perspective of a group of UEs, allowing for trend analysis, identification of common issues, and optimization of network performance for multiple users.

[0132] In step 303 , the first device inputs the sample data into the first model to obtain an output result, where the output result indicates whether to report the sample data or not.

[0133] The sample data includes characteristic values ​​of one or more service characteristics. For example, the first device collects characteristic values ​​of N service characteristics and generates sample data based on the collected characteristic values ​​in a predefined sample data format. The sample data includes characteristic values ​​of N service characteristics, where N is a positive integer. The sample data format defines which service characteristic values ​​are included in the sample data and the order in which the characteristic values ​​of different service characteristics are arranged. Taking N=3 as an example, sample data 1 is generated at time T1. The sample data 1 includes characteristic value 1 of service characteristic 1, characteristic value 1 of service characteristic 2, and characteristic value 1 of service characteristic 3. Sample data 2 is generated at time T2. The sample data 2 includes characteristic value 2 of service characteristic 1, characteristic value 2 of service characteristic 2, and characteristic value 2 of service characteristic 3. Sample data 3 is generated at time T3. The sample data 3 includes characteristic value 3 of service characteristic 1, characteristic value 3 of service characteristic 2, and characteristic value 3 of service characteristic 3. And so on. For example, the above-mentioned service characteristics 1, service characteristics 2, and service characteristics 3 are the coverage strength of the CU, the coverage quality of the CU, and the throughput rate of the CU, respectively. For another example, the service feature 1, service feature 2, and service feature 3 are the transmit power of the RU, the receive level of the RU, and the noise floor of the RU, respectively.

[0134] After the first device collects the sample data, it can input the sample data into the first model to obtain the output result every time it receives sample data, or it can input a set number of sample data (for example, 100) into the first model to obtain the output result, and obtain the output result corresponding to each sample data, or it can input the collected sample data into the first model at intervals (for example, 10 seconds) to obtain the output result, and obtain the output result corresponding to each sample data.

[0135] When the output result indicates that the sample data should be reported, the first device sends the sample data to the second device. When the output result indicates that the sample data should not be reported, the first device does not report the sample data, for example, it may discard the sample data.

[0136] In one implementation method, after sample data is input into a first model, if the sample data satisfies a first condition, an output result of the first model indicates reporting the sample data, wherein the first condition includes at least one of the following:

[0137] 1) The characteristic value of at least one business characteristic in the sample data meets the first characteristic value size requirement of the business characteristic.

[0138] In one implementation method, when the characteristic value of any business feature in the sample data meets the first characteristic value size requirement of the business feature, it indicates that the sample data contains valid characteristic values, and therefore the sample data meets the first condition. Taking the above-mentioned sample data 1 as an example, if the characteristic value 1 of business feature 1 in sample data 1 is greater than the characteristic value threshold corresponding to business feature 1, then sample data 1 meets the first condition; or if the characteristic value 1 of business feature 2 in sample data 1 is greater than the characteristic value threshold corresponding to business feature 2, then sample data 1 meets the first condition; or if the characteristic value 1 of business feature 3 in sample data 1 is greater than the characteristic value threshold corresponding to business feature 3, then sample data 1 meets the first condition.

[0139] In another implementation, when the eigenvalues ​​of any two business characteristics in the sample data meet the first eigenvalue requirement for that business characteristic, the sample data contains at least two valid eigenvalues, and thus the sample data meets the first condition. Compared to the aforementioned method, which only requires that at least one eigenvalue in the sample data meet the first eigenvalue requirement, this method is more rigorous in determining whether the first condition is met, and accordingly, fewer sample data that meet the first condition are screened out. Taking the above-mentioned sample data 1 as an example, if the feature value 1 of the business feature 1 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 1, and the feature value 1 of the business feature 2 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 2, then the sample data 1 meets the first condition; or if the feature value 1 of the business feature 1 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 1, and the feature value 1 of the business feature 3 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 3, then the sample data 1 meets the first condition; or if the feature value 1 of the business feature 2 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 2, and the feature value 1 of the business feature 3 in the sample data 1 is greater than the feature value threshold corresponding to the business feature 3, then the sample data 1 meets the first condition.

[0140] Of course, it can also be stipulated that when the feature values ​​of any three or more business features in the sample data meet the first feature value requirement of the business feature, the sample data meets the first condition. Taking the above-mentioned sample data 1 as an example, if the feature value 1 of business feature 1 in sample data 1 is greater than the feature value threshold corresponding to business feature 1, the feature value 1 of business feature 2 in sample data 1 is greater than the feature value threshold corresponding to business feature 2, and the feature value 1 of business feature 3 in sample data 1 is greater than the feature value threshold corresponding to business feature 3, then sample data 1 meets the first condition.

[0141] 2) The characteristic value of at least one service characteristic in the sample data meets the first reporting period requirement of the service characteristic.

[0142] The first reporting period requirement for a service feature is related to the degree of change in the service feature's characteristic value within a set duration. For example, if the variance of the characteristic value of a service feature within the last 10 seconds is D1, the reporting period is T1, meaning that the characteristic value of service feature 1 is reported every T1 duration. If the variance of the characteristic value of a service feature within the last 10 seconds is D2, the reporting period is T2, meaning that the characteristic value of service feature 2 is reported every T2 duration, and so on.

[0143] In one implementation method, when the characteristic value of any service feature in the sample data meets the first reporting period requirement of the service feature, it indicates that the sample data contains a valid characteristic value, and therefore the sample data meets the first condition. Taking the above-mentioned sample data 1 as an example, if the characteristic value 1 of service feature 1 in sample data 1 meets the first reporting period requirement of service feature 1, then sample data 1 meets the first condition; or if the characteristic value 1 of service feature 2 in sample data 1 meets the first reporting period requirement of service feature 2, then sample data 1 meets the first condition; or if the characteristic value 1 of service feature 3 in sample data 1 meets the first reporting period requirement of service feature 3, then sample data 1 meets the first condition.

[0144] In another implementation, when the characteristic values ​​of any two business characteristics in the sample data meet the first reporting period requirement for that business characteristic, the sample data contains at least two valid characteristic values, and therefore the sample data meets the first condition. Compared to the above method, which only requires that at least one characteristic value in the sample data meet the first characteristic value requirement for the business characteristic, this method is more rigorous in determining whether the first condition is met, and accordingly, fewer sample data that meet the first condition are screened out. Taking the above-mentioned sample data 1 as an example, if the feature value 1 of the business feature 1 in the sample data 1 meets the first reporting period requirement of the business feature 1, and the feature value 1 of the business feature 2 in the sample data 1 meets the first reporting period requirement of the business feature 2, then the sample data 1 meets the first condition; or if the feature value 1 of the business feature 1 in the sample data 1 meets the first reporting period requirement of the business feature 1, and the feature value 1 of the business feature 3 in the sample data 1 meets the first reporting period requirement of the business feature 3, then the sample data 1 meets the first condition; or if the feature value 1 of the business feature 2 in the sample data 1 meets the first reporting period requirement of the business feature 2, and the feature value 1 of the business feature 3 in the sample data 1 meets the first reporting period requirement of the business feature 3, then the sample data 1 meets the first condition.

[0145] Of course, it can also be stipulated that if the feature values ​​of any three or more service features in the sample data meet the first reporting period requirement of the service feature, the sample data meets the first condition. Taking the above sample data 1 as an example, if feature value 1 of service feature 1 in sample data 1 meets the first reporting period requirement of service feature 1, feature value 1 of service feature 2 in sample data 1 meets the first reporting period requirement of service feature 2, and feature value 1 of service feature 3 in sample data 1 meets the first reporting period requirement of service feature 3, then sample data 1 meets the first condition.

[0146] 3) The characteristic value of at least one business characteristic in the sample data meets the first characteristic value distribution requirement of the business characteristic.

[0147] For example, assuming that for a certain business feature, 100 feature values ​​between 1 and 50 are required, 150 feature values ​​between 50 and 100 are required, and 50 feature values ​​between 100 and 150 are required. If the number of feature values ​​of the business feature that have been reported has been met, the feature value of the business feature in the newly collected sample data does not meet the first feature value distribution requirement. For example, for business feature 1, the number of reported feature values ​​between 1 and 50 has reached 100, and the feature value of the business feature 1 in the subsequently collected sample data is 45, then this feature value does not meet the first feature value distribution requirement.

[0148] In one implementation method, when the characteristic value of any business feature in the sample data meets the first characteristic value distribution requirement of the business feature, it indicates that the sample data contains valid characteristic values, and therefore the sample data meets the first condition. Taking the above-mentioned sample data 1 as an example, if characteristic value 1 of business feature 1 in sample data 1 meets the first characteristic value distribution requirement of business feature 1, then sample data 1 meets the first condition; or if characteristic value 1 of business feature 2 in sample data 1 meets the first characteristic value distribution requirement of business feature 2, then sample data 1 meets the first condition; or if characteristic value 1 of business feature 3 in sample data 1 meets the first characteristic value distribution requirement of business feature 3, then sample data 1 meets the first condition.

[0149] In another implementation, when the eigenvalues ​​of any two business characteristics in the sample data meet the first eigenvalue distribution requirement for that business characteristic, the sample data contains at least two valid eigenvalues, and thus the sample data meets the first condition. Compared to the aforementioned method, which only requires that at least one eigenvalue in the sample data meet the first eigenvalue size requirement for the business characteristic, this method is more rigorous in determining whether the first condition is met, and accordingly, fewer sample data that meet the first condition are screened out. Taking the above-mentioned sample data 1 as an example, if the feature value 1 of the business feature 1 in the sample data 1 meets the first feature value distribution requirement of the business feature 1, and the feature value 1 of the business feature 2 in the sample data 1 meets the first feature value distribution requirement of the business feature 2, then the sample data 1 meets the first condition, or if the feature value 1 of the business feature 1 in the sample data 1 meets the first feature value distribution requirement of the business feature 1, and the feature value 1 of the business feature 3 in the sample data 1 meets the first feature value distribution requirement of the business feature 3, then the sample data 1 meets the first condition, or if the feature value 1 of the business feature 2 in the sample data 1 meets the first feature value distribution requirement of the business feature 2, and the feature value 1 of the business feature 3 in the sample data 1 meets the first feature value distribution requirement of the business feature 3, then the sample data 1 meets the first condition.

[0150] Of course, it can also be stipulated that when the feature values ​​of any three or more business features in the sample data meet the first feature value distribution requirement of the business features, the sample data meets the first condition. Taking the above-mentioned sample data 1 as an example, if feature value 1 of business feature 1 in sample data 1 meets the first feature value distribution requirement of business feature 1, feature value 1 of business feature 2 in sample data 1 meets the first feature value distribution requirement of business feature 2, and feature value 1 of business feature 3 in sample data 1 meets the first feature value distribution requirement of business feature 3, then sample data 1 meets the first condition.

[0151] In one implementation method, if the characteristic value of at least one business feature in the sample data meets the first characteristic value size requirement of the business feature, the sample data meets the first condition, so the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0152] In another implementation method, if the characteristic value of at least one business feature in the sample data meets the first reporting period requirement of the business feature, the sample data meets the first condition, so the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0153] In another implementation method, if the characteristic value of at least one business feature in the sample data meets the first characteristic value distribution requirement of the business feature, the sample data meets the first condition, so the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0154] In another implementation method, if the characteristic value of at least one business feature in the sample data meets the first characteristic value size requirement of the business feature, and the characteristic value of at least one business feature in the sample data meets the first reporting period requirement of the business feature, then the sample data meets the first condition, and therefore the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0155] In another implementation method, if the eigenvalue of at least one business feature in the sample data meets the first eigenvalue size requirement of the business feature, and the eigenvalue of at least one business feature in the sample data meets the first eigenvalue distribution requirement of the business feature, then the sample data meets the first condition, and therefore the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0156] In another implementation method, if the characteristic value of at least one business feature in the sample data meets the first reporting period requirement of the business feature, and the characteristic value of at least one business feature in the sample data meets the first characteristic value distribution requirement of the business feature, then the sample data meets the first condition, and therefore the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0157] In another implementation method, if the characteristic value of at least one business feature in the sample data meets the first characteristic value size requirement of the business feature, the characteristic value of at least one business feature in the sample data meets the first reporting period requirement of the business feature, and the characteristic value of at least one business feature in the sample data meets the first characteristic value distribution requirement of the business feature, then the sample data meets the first condition, and therefore the output result obtained after the sample data is input into the first model indicates the above-mentioned sample data.

[0158] In one implementation method, the second device can determine the update information based on the sample data that has been received and the business requirements from the business application, and the second device updates the first model according to the update information to obtain the second model. The second device sends the file information of the second model to the first device. The update information includes at least one of the second eigenvalue size requirement, the second eigenvalue quantity, the second eigenvalue distribution requirement or the second reporting period requirement of the business feature to be collected, and the second reporting period requirement is related to the degree of change of the eigenvalue of the business feature within a set time period. Exemplarily, the second device divides the eigenvalue interval for each feature in the sample data that has been received, and then determines the entropy value corresponding to each eigenvalue interval based on the eigenvalues ​​received in each eigenvalue interval, and then determines the redundancy of each eigenvalue interval based on the entropy value corresponding to each eigenvalue interval, and determines the above-mentioned update information based on the entropy value corresponding to each eigenvalue interval and the business requirements.

[0159] In one implementation method, the first device includes a CU, and the sample data collected by the CU may be from at least one of the CU, the RU, or the UE. The CU determines whether to report the sample data based on the first model, and if it determines to report the sample data, reports the sample data to the second device.

[0160] In another implementation method, the first device includes a DU, and the sample data collected by the DU may be from at least one of the DU, RU, or UE. The DU determines whether to report the sample data based on the first model, and if it determines to report the sample data, reports the sample data to the second device.

[0161] In another implementation method, the first device includes an RU, and the sample data collected by the RU may be from the RU and / or the UE. The RU determines whether to report the sample data based on the first model. If it determines to report the sample data, it reports the sample data to the DU, which then forwards the sample data to the second device.

[0162] In the above solution, the first device determines whether the collected sample data can be reported based on the first model. Because the first model is trained based on a large amount of sample data, its sample data analysis capabilities are relatively powerful, thus helping to improve data collection efficiency and quality. Furthermore, by analyzing the sample data based on the first model, sample data that does not meet the reporting conditions can be filtered out, that is, the output result is that the sample data is not reported. This allows the first device to reduce the frequency of reporting sample data that does not meet the requirements, reduce the burden of data processing, and further improve data collection efficiency and quality. Furthermore, this data collection solution is relatively flexible and efficient.

[0163] More specifically, compared to condition-based measurement, model-based measurement introduces models to replace traditional conditional logic. This approach's core advantage lies in its ability to leverage extensive historical data to learn and identify the optimal timing and conditions for data reporting, enabling more intelligent and adaptive network management. The following are some of the advantages of model-based measurement:

[0164] First, it can handle complex logic: The model can handle logic and patterns that are more complex than traditional conditional judgments, including nonlinear relationships and multi-variable interactions, thereby making more accurate judgments in changing network conditions and complex user behavior patterns.

[0165] Second, adaptive feature distribution: Model-based methods can automatically adjust reporting strategies based on the feature distribution of collected samples, making data reporting more efficient. Especially when network status changes rapidly, the model can identify the features that have the greatest impact on network performance and optimize the data collection and reporting process accordingly.

[0166] Third, time series model support: By introducing time series models, such as RNN models or LSTM models, model-based measurement methods can take into account the changing trends of data over time and provide support for data reporting based on the degree of change. This means that the system can dynamically adjust the reporting frequency and granularity based on the rate and pattern of data change.

[0167] Fourth, dynamic optimization: The model can continuously learn from new data and optimize its judgment criteria. This enables model-based measurement methods to adapt to long-term changes in network conditions and emerging usage patterns, achieving continuous performance optimization.

[0168] Fifth, personalized and granular control: Model-based approaches can provide personalized measurement and reporting strategies for different UEs, service types, or network conditions, enabling more fine-grained network management and optimization.

[0169] In summary, model-based measurement approaches demonstrate greater creativity and novelty compared to traditional condition-based methods in handling complex network environments, enabling adaptive network management, and optimizing data collection and reporting. This approach can provide a more efficient and flexible solution for intelligent wireless access networks.

[0170] The embodiment of FIG. 3 is described below with reference to the specific example of FIG. 4 .

[0171] Figure 4 shows the architecture for model-based data collection and reporting. The Near-RT RIC includes the collection controller, model training unit, and business applications, while the CU, DU, and RU all include collectors.

[0172] Data collection and reporting mainly include the following operations:

[0173] 1) The business application sends a business requirement to the model training unit, where the business requirement is used to indicate the feature value required by the business application.

[0174] For the meaning of the business requirements, please refer to the description in the aforementioned step 301.

[0175] 2) The model training unit generates a first model according to business requirements and sends the file information of the first model to the acquisition controller.

[0176] 3) The acquisition controller sends the file information of the first model to the CU / DU, and the DU may also forward the file information of the first model to the RU.

[0177] 4) When the CU / DU receives the first instruction from the Near-RT RIC, if the first instruction instructs the CU / DU to collect and report data, the CU / DU collects sample data based on the first model and sends the sample data that meets the first condition to the Near-RT RIC acquisition controller. If the first instruction instructs the RU to collect and report data, the DU forwards the first instruction to the RU. The RU collects sample data based on the first model and sends the sample data that meets the first condition to the DU. The DU then sends the sample data to the Near-RT RIC acquisition controller.

[0178] The acquisition controller sends the feature values ​​of the business features related to the business application in the sample data to the business application, and the acquisition controller can also send the sample data to the model training unit.

[0179] 5) The model training unit can determine whether the first model needs to be updated based on the collected sample data and the first model. If a second model is obtained, the acquisition controller can send the file information of the second model to the CU / DU. The DU can also forward the file information of the second model to the RU.

[0180] It is understandable that in order to implement the functions in the above embodiments, the first device or the second device includes hardware structures and / or software modules corresponding to the execution of each function. It should be readily apparent to those skilled in the art that, in combination with the units and method steps of each example described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in hardware or in a computer software-driven hardware manner depends on the specific application scenario and design constraints of the technical solution.

[0181] Figures 5 and 6 are schematic diagrams of the structures of possible communication devices provided in embodiments of the present application. These communication devices can be used to implement the functions of the first device or the second device in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments. In the embodiments of the present application, the communication device can be the first device or the second device, or can also be a module (such as a chip) applied to the first device or the second device.

[0182] The communication device 500 shown in Figure 5 includes a processing unit 510 and a transceiver unit 520. The communication device 500 is used to implement the functions of the first device or the second device in the above method embodiment.

[0183] When the communication device 500 is used to implement the function of the first device in the above method embodiment, the transceiver unit 520 is used to receive a first instruction, which includes indication information and an identifier of a first model, and the indication information indicates that data is reported based on the first model; the processing unit 510 is used to input the collected sample data into the first model to obtain an output result, and the output result indicates whether to report the sample data or not.

[0184] In one possible implementation method, when the sample data meets a first condition, the output result indicates that the sample data is to be reported, and the first condition includes at least one of the following: the characteristic value of at least one business feature in the sample data meets the characteristic value size requirement; the characteristic value of at least one business feature in the sample data meets the reporting period requirement, and the reporting period requirement is related to the degree of change of the characteristic value of the business feature within a set time period; the characteristic value of at least one business feature in the sample data meets the characteristic value distribution requirement corresponding to the business feature.

[0185] In one possible implementation method, the degree of change of the characteristic value of the business feature within the set time period includes the variance, mean absolute error, autocorrelation coefficient, signal-to-noise ratio or peak detection of the characteristic value of the business feature within the set time period.

[0186] In a possible implementation method, the service characteristics include one or more of the following: performance data of the first device, measurement data of a single terminal device or measurement data of a group of terminal devices; wherein, when the first device includes a CU or a DU, the performance data of the first device includes one or more of the following: coverage strength, coverage quality, number of switching, throughput, number of access attempts or number of dropped calls; when the first device includes an RU, the performance data of the first device includes one or more of the following: transmission power, receiving level, background noise or bit error rate; the measurement data of the single terminal device includes one or more of the following: throughput, traffic volume, number of switching; the measurement data of the group of terminal devices includes one or more of the following: throughput, traffic volume, number of switching.

[0187] In a possible implementation method, the transceiver unit 520 is further used to send the sample data when the output result indicates that the sample data is to be reported; or the processing unit 510 is further used to discard the sample data when the output result indicates that the sample data is not to be reported.

[0188] In a possible implementation method, the first instruction further includes an identifier of the first device.

[0189] In one possible implementation method, the first device includes a CU or a DU; the transceiver unit 520 is used to receive a first instruction, specifically including: receiving the first instruction from the near real-time wireless access network intelligent controller through the interface between the first device and the near real-time wireless access network intelligent controller.

[0190] In one possible implementation method, the first device includes an RU; a transceiver unit 520, used to receive a first instruction, specifically including: receiving the first instruction from a near real-time wireless access network intelligent controller through an interface between the RU and the DU.

[0191] In a possible implementation method, the transceiver unit 520 is further configured to receive a second instruction, where the second instruction includes file information of the first model.

[0192] In one possible implementation method, the first device includes a CU or a DU; the transceiver unit 520 is used to receive a second instruction, specifically including: receiving the second instruction from the near real-time wireless access network intelligent controller through the interface between the first device and the near real-time wireless access network intelligent controller.

[0193] In one possible implementation method, the first device includes an RU; a transceiver unit 520, used to receive a second instruction, specifically including: receiving the second instruction from a near real-time wireless access network intelligent controller through an interface between the RU and the DU.

[0194] In one possible implementation method, the indication information also indicates the data collection type, and the data collection type is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

[0195] When the communication device 500 is used to implement the function of the second device in the above method embodiment, the processing unit 510 is used to generate a first model; the transceiver unit 520 is used to send a first instruction to the first device, wherein the first instruction includes indication information and an identifier of the first model, and the indication information indicates that data reporting is performed based on the first model.

[0196] In one possible implementation method, the transceiver unit 520 is further used to receive sample data from the first device, and the sample data meets a first condition, which includes at least one of the following items: the characteristic value of at least one business feature in the sample data meets the characteristic value size requirement; the characteristic value of at least one business feature in the sample data meets the reporting period requirement, and the reporting period requirement is related to the degree of change of the characteristic value of the business feature within a set time period; the characteristic value of at least one business feature in the sample data meets the characteristic value distribution requirement corresponding to the business feature.

[0197] In a possible implementation method, the first instruction further includes an identifier of the first device.

[0198] In one possible implementation method, the processing unit 510 is used to generate a first model, specifically including: receiving business requirements through the transceiver unit 520, wherein the business requirements indicate at least one of the first eigenvalue size requirement, the first eigenvalue quantity, the first eigenvalue distribution requirement or the first reporting period requirement of the business feature to be collected, and the first reporting period requirement is related to the degree of change of the eigenvalue of the business feature within a set time period; generating the first model according to the business requirements.

[0199] In one possible implementation method, the processing unit 510 is also used to determine update information based on the collected sample data and the business needs, and the update information includes at least one of the second eigenvalue size requirement, the second eigenvalue quantity, the second eigenvalue distribution requirement or the second reporting period requirement of the business feature to be collected, and the second reporting period requirement is related to the degree of change of the eigenvalue of the business feature within a set time period; according to the update information, the first model is updated to obtain the second model; the transceiver unit 520 is also used to send file information of the second model to the first device.

[0200] In one possible implementation method, the first device includes a CU or DU, and the second device includes a near-real-time wireless access network intelligent controller; the transceiver unit 520 is used to send a first instruction to the first device, specifically including: sending the first instruction to the first device through the interface between the first device and the second device.

[0201] In one possible implementation method, the first device includes an RU, and the second device includes a near-real-time wireless access network intelligent controller; the transceiver unit 520 is used to send a first instruction to the first device, specifically including: sending the first instruction to the first device through the interface between the second device and the DU.

[0202] In a possible implementation method, the transceiver unit 520 is further configured to send a second instruction to the first device, where the second instruction includes file information of the first model.

[0203] In one possible implementation method, the first device includes a CU or DU, and the second device includes a near-real-time wireless access network intelligent controller; the transceiver unit 520 is used to send a second instruction to the first device, specifically including: sending a second instruction to the first device through the interface between the first device and the second device.

[0204] In one possible implementation method, the first device includes an RU, and the second device includes a near real-time wireless access network intelligent controller; the transceiver unit 520 is used to send a second instruction to the first device, specifically including: sending the second instruction to the first device through the interface between the second device and the DU.

[0205] In one possible implementation method, the indication information also indicates a data collection type, which is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

[0206] For a more detailed description of the processing unit 510 and the transceiver unit 520, reference can be made to the relevant description in the above method embodiment, which will not be repeated here.

[0207] The communication device 600 shown in Figure 6 includes a processor 610 and an interface circuit 620. The processor 610 and the interface circuit 620 are coupled to each other. It is understood that the interface circuit 620 can be a transceiver or an input / output interface. Optionally, the communication device 600 may also include a memory 630 for storing instructions executed by the processor 610, or storing input data required by the processor 610 to execute instructions, or storing data generated after the processor 610 executes instructions.

[0208] When the communication device 600 is used to implement the above method embodiment, the processor 610 is used to implement the functions of the above processing unit 510 , and the interface circuit 620 is used to implement the functions of the above transceiver unit 520 .

[0209] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0210] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, mobile hard disks, compact disc read-only memory (CD-ROM) or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in the first device or the second device. Of course, the processor and the storage medium can also exist as discrete components in the access network device or the terminal.

[0211] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. A computer program refers to a set of instructions that instruct an electronic computer or other device with message processing capabilities to perform each step of the action, usually written in a certain programming language and running on a certain target architecture. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer program or instruction can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0212] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0213] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In the text description of this application, the character " / " generally indicates that the previous and next related objects are in an "or" relationship; in the formulas of this application, the character " / " indicates that the previous and next related objects are in a "division" relationship.

[0214] It is understood that the various numbers used in the embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily imply a specific order of execution; the order of execution of the processes should be determined by their functions and inherent logic.

Claims

1. A communication method, characterized in that: Applied to a first device or a module of the first device, the method includes: receiving a first instruction, the first instruction including instruction information and an identifier of a first model, the instruction information instructing data reporting based on the first model; The collected sample data is input into the first model to obtain an output result, wherein the output result indicates whether to report the sample data or not.

2. The method according to claim 1, wherein When the sample data satisfies a first condition, the output result indicates reporting the sample data, where the first condition includes at least one of the following: The characteristic value of at least one business characteristic in the sample data meets the characteristic value size requirement; The characteristic value of at least one service characteristic in the sample data meets a reporting period requirement, where the reporting period requirement is related to the degree of change of the characteristic value of the service characteristic within a set period of time; The characteristic value of at least one business characteristic in the sample data meets the characteristic value distribution requirement corresponding to the business characteristic.

3. The method according to claim 2, wherein The degree of change of the characteristic value of the service feature within the set time period includes the variance, mean absolute error, autocorrelation coefficient, signal-to-noise ratio or peak detection of the characteristic value of the service feature within the set time period.

4. The method according to claim 2 or 3, wherein: The business characteristics include one or more of the following: performance data of the first device, measurement data of a single terminal device, or measurement data of a group of terminal devices; Wherein, when the first device includes a centralized unit or a distributed unit, the performance data of the first device includes one or more of the following: coverage strength, coverage quality, number of handovers, throughput, number of access attempts, or number of dropped calls; When the first device includes a radio frequency unit, the performance data of the first device includes one or more of the following: transmit power, receive level, noise floor, or bit error rate; The measurement data of the single terminal device includes one or more of the following: throughput, traffic volume, and number of handovers; The measurement data of the group of terminal devices includes one or more of the following: throughput rate, traffic volume, and number of switching times.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: When the output result indicates that the sample data is to be reported, sending the sample data; or, When the output result indicates that the sample data is not to be reported, the sample data is discarded.

6. The method according to any one of claims 1 to 5, characterized in that The first instruction also includes an identification of the first device.

7. The method according to any one of claims 1 to 6, characterized in that The first device includes a centralized unit or a distributed unit; The receiving of the first instruction includes: The first instruction from the near real-time wireless access network intelligent controller is received through an interface between the first device and the near real-time wireless access network intelligent controller.

8. The method according to any one of claims 1 to 6, characterized in that The first device includes a radio frequency unit; The receiving of the first instruction includes: The first instruction is received from the near real-time wireless access network intelligent controller through the interface between the radio frequency unit and the distributed unit.

9. The method according to any one of claims 1 to 6, characterized in that The method further comprises: A second instruction is received, where the second instruction includes file information of the first model.

10. The method according to claim 9, wherein The first device includes a centralized unit or a distributed unit; The receiving of the second instruction comprises: The second instruction from the near real-time wireless access network intelligent controller is received through an interface between the first device and the near real-time wireless access network intelligent controller.

11. The method according to claim 9, wherein The first device includes a radio frequency unit; The receiving of the second instruction comprises: The second instruction is received from the near real-time wireless access network intelligent controller through the interface between the radio frequency unit and the distributed unit.

12. The method according to any one of claims 1 to 11, characterized in that The indication information also indicates a data collection type, which is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

13. A communication method, characterized in that: Applied to the second device or a module of the second device, the method includes: generating a first model; A first instruction is sent to a first device, where the first instruction includes instruction information and an identifier of a first model, and the instruction information indicates that data reporting is performed based on the first model.

14. The method according to claim 13, wherein The method further comprises: Receive sample data from the first device, where the sample data satisfies a first condition, where the first condition includes at least one of the following: The characteristic value of at least one business characteristic in the sample data meets the characteristic value size requirement; The characteristic value of at least one service characteristic in the sample data meets a reporting period requirement, where the reporting period requirement is related to the degree of change of the characteristic value of the service characteristic within a set period of time; The characteristic value of at least one business characteristic in the sample data meets the characteristic value distribution requirement corresponding to the business characteristic.

15. The method according to claim 13 or 14, characterized in that The first instruction also includes an identification of the first device.

16. The method according to any one of claims 13 to 15, characterized in that The generating of the first model comprises: receiving a service requirement, where the service requirement indicates at least one of a first characteristic value size requirement, a first characteristic value quantity requirement, a first characteristic value distribution requirement, or a first reporting period requirement for a service feature to be collected, where the first reporting period requirement is related to a degree of change of a characteristic value of the service feature within a set period; Generate the first model according to the business requirements.

17. The method according to claim 16, wherein The method further comprises: Determining update information based on the collected sample data and the service requirements, the update information including at least one of a second eigenvalue size requirement, a second eigenvalue quantity requirement, a second eigenvalue distribution requirement, or a second reporting period requirement of the service feature to be collected, where the second reporting period requirement is related to a degree of change in the eigenvalue of the service feature within a set period; updating the first model according to the update information to obtain a second model; Send file information of the second model to the first device.

18. The method according to any one of claims 13 to 17, characterized in that The first device comprises a centralized unit or a distributed unit, and the second device comprises a near real-time wireless access network intelligent controller; The sending the first instruction to the first device includes: The first instruction is sent to the first device through an interface between the first device and the second device.

19. The method according to any one of claims 13 to 17, wherein The first device includes a radio frequency unit, and the second device includes a near real-time wireless access network intelligent controller; The sending the first instruction to the first device includes: The first instruction is sent to the first device through an interface between the second device and the distributed unit.

20. The method according to any one of claims 13 to 17, wherein The method further comprises: A second instruction is sent to the first device, where the second instruction includes file information of the first model.

21. The method according to claim 20, wherein The first device comprises a centralized unit or a distributed unit, and the second device comprises a near real-time wireless access network intelligent controller; The sending a second instruction to the first device includes: A second instruction is sent to the first device through an interface between the first device and the second device.

22. The method according to claim 20, wherein The first device includes a radio frequency unit, and the second device includes a near real-time wireless access network intelligent controller; The sending a second instruction to the first device includes: The second instruction is sent to the first device through an interface between the second device and the distributed unit.

23. The method according to any one of claims 13 to 22, characterized in that The indication information also indicates a data collection type, which is collecting performance data of the first device, collecting performance data and / or network data of a single terminal device, or collecting performance data and / or network data of a group of terminal devices.

24. A communication device, characterized in that: The method comprises a unit for performing the method according to any one of claims 1 to 12, or a unit for performing the method according to any one of claims 13 to 23.

25. A computer program product, characterized in that The computer program product comprises instructions, which, when executed on a processor, cause the processor to execute the method according to any one of claims 1 to 12 or the method according to any one of claims 13 to 23.

26. A computer-readable storage medium, characterized in that The storage medium stores a computer program or instruction. When the computer program or instruction is executed by the communication device, the method described in any one of claims 1 to 12 or the method described in any one of claims 13 to 23 is implemented.

27. A communication system, characterized in that: The method comprises a first device for executing the method according to any one of claims 1 to 12, and a second device for executing the method according to any one of claims 13 to 23.

Images