Communication method and related apparatus

Abstract

A communication method and a related apparatus. In the method, a network device indicates to a terminal a data precision supported thereby, so that the terminal can perform quantization processing on collected data in combination with the indication of the network device and then transmit the collected data, thereby reducing transmission overhead of data collection.

Description

Communication method and related apparatus

[0001] The present application claims priority to the Chinese patent application No. 202410538387.X, filed on April 29, 2024, and entitled "Communication method and related apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, in particular to a communication method and related apparatus. BACKGROUND

[0003] Artificial intelligence (AI) is a technology that simulates human brain to perform complex calculations. AI is applied to wireless communication to improve network performance and user experience by intelligently collecting and analyzing data. AI model life cycle management mainly includes five parts: data collection, model training, inference, management and model storage. Data collection is an important part of AI model life cycle management, and the quality of the data set collected has a great influence on the performance of the model. The data collected at present is usually represented by floating point, but the data collected in floating point representation requires a large amount of transmission overhead. SUMMARY

[0004] The present application provides a communication method and related apparatus, which can reduce the transmission overhead of collected data.

[0005] The present application is described below from different aspects. It should be understood that the implementation and advantages of the different aspects below can be referred to each other.

[0006] In a first aspect, the present application provides a communication method, which can be executed by a first device. The first device can be a terminal, a communication module in the terminal, or a circuit or chip responsible for communication function in the terminal (such as a Modem chip, also known as a baseband chip, or a system on chip (SoC) chip or system in package (SIP) chip containing a modem core). That is, the method can be applied to the terminal side. The method comprises: receiving first indication information, and quantizing collected data according to the first indication information to obtain quantized collected data. Then, the quantized collected data is sent. The first indication information indicates a first data precision, and the first data precision is a data precision supported by a network device.

[0007] In the embodiments of the present application, the network device indicates the data precision supported by the network device to the terminal, so that the terminal quantizes the collected data according to the indication of the network device before transmission, which is beneficial to reduce the transmission overhead of the collected data.

[0008] In a possible implementation, the quantization processing of the collected data according to the first indication information to obtain the quantization-processed collected data includes: determining a quantization processing precision according to the first data precision and the second data precision, the second data precision being the data precision supported by the terminal; and quantizing the collected data according to the quantization processing precision to obtain the quantization-processed collected data.

[0009] In this implementation, the terminal determines the quantization processing precision to be finally used based on the data precision supported by the network device and the data precision supported by the terminal itself, so that the precision requirements of the terminal and the network device can be met as much as possible.

[0010] In a possible implementation, the method further includes: sending the quantization processing precision. In this implementation, the terminal sends the quantization processing precision to the network device, so that the network device can recover the received quantization-processed collected data based on the quantization processing precision.

[0011] In a possible implementation, the quantization processing precision is the smaller one of the first data precision and the second data precision. In this implementation, the device with lower processing capability can process the collected data under the quantization processing precision.

[0012] In a possible implementation, the network device is an access network device.

[0013] In a possible implementation, the first data precision is the minimum value of the data precisions supported by the plurality of network devices respectively. In this implementation, the minimum value of the data precisions supported by the plurality of network devices respectively is sent to the terminal, so that the transmission overhead can be reduced.

[0014] In a possible implementation, the first data precision includes the data precisions supported by the plurality of network devices. In this implementation, the data precisions supported by the plurality of network devices are all sent to the terminal, which is beneficial to the terminal to autonomously determine the quantization processing precision to be finally used, and the flexibility is higher.

[0015] In a possible implementation, the plurality of network devices include at least two of an access network device, a core network device, an operation and maintenance management device, and an Internet server.

[0016] In a possible implementation, the first indication information further indicates one or more of the following: uniform quantization, non-uniform quantization, transform domain quantization, or compression mode. In this implementation, the transmission overhead of the collected data can be further reduced.

[0017] In a possible implementation, the first indication information is a first function identity, a first model identity, or a first data set identity. The first function identity or the first model identity or the first data set identity is associated with the first data precision.

[0018] In this implementation, the first data precision is implicitly indicated by the first function identity, the first model identity, or the first data set identity, and the indication overhead of the first data precision can be reduced.

[0019] In a possible implementation, the first indication information is carried in a radio resource control connection reconfiguration message. In this implementation, the forward compatibility of the protocol is facilitated.

[0020] In a possible implementation, the quantized collected data is carried in a minimization of drive tests signaling. In this implementation, the forward compatibility of the protocol is facilitated.

[0021] In a possible implementation, the collected data includes one or more of the following: channel state information, modem data, or air interface received data. In this implementation, the collected data is more abundant, and the performance of the AI model is facilitated.

[0022] In a second aspect, a communication method is provided. The method can be performed by a second device, which can be a network device or a component (e.g., a circuit, a chip, or a chip system) in the network device. That is, the method can be applied to the network side (which can be the access network side). The method includes: sending first indication information, the first indication information indicating a first data precision, the first data precision being a data precision supported by the network device. Then, receiving quantized collected data.

[0023] In a possible implementation, the method further includes: receiving a quantization processing precision, the quantization processing precision being associated with the quantized collected data.

[0024] In a possible implementation, the method further includes: receiving second indication information, the second indication information indicating a third data precision, the third data precision being a data precision supported by a core network device, an operation and maintenance management, or an Internet server.

[0025] The sending the first indication information comprises: sending the first indication information according to the third data precision and a fourth data precision, wherein the first data precision is a smaller value of the third data precision and the fourth data precision, and the fourth data precision is a data precision supported by the access network device.

[0026] In a possible implementation, the method further includes: sending the collected data after the quantization processing to the core network device, the operation and maintenance management, or the Internet server.

[0027] In a possible implementation, the method further includes: sending the quantization processing precision associated with the collected data after the quantization processing to the core network device, the operation and maintenance management, or the Internet server.

[0028] In a possible implementation, the first indication information further indicates one or more of the following: uniform quantization, non-uniform quantization, transform domain quantization, or compression mode.

[0029] In a possible implementation, the first indication information is a first function identifier, a first model identifier, or a first data set identifier, wherein the first function identifier or the first model identifier or the first data set identifier is associated with the first data precision.

[0030] In a possible implementation, the first indication information is carried in a radio resource control connection reconfiguration message.

[0031] In a possible implementation, the collected data after the quantization processing is carried in a minimization of drive tests signaling.

[0032] In a possible implementation, the collected data includes one or more of the following: channel state information, modulation and demodulation data, or air interface receiving data.

[0033] In a third aspect, the present application provides a communication apparatus, which includes units or modules for performing the method in any of the first aspect to the second aspect, or the method shown in any possible implementation manner of any of the aspects.

[0034] In a fourth aspect, the present application provides a communication apparatus, which includes a processor and a transceiver. The processor and the transceiver are used to perform the method in any of the first aspect to the second aspect, or the method shown in any possible implementation manner of any of the aspects.

[0035] Optionally, the communication apparatus further comprises a memory, and the memory stores a computer program; the processor and the transceiver are configured to invoke the computer program in the memory, so that the communication apparatus executes the method in any of the first aspect to the second aspect, or the method in any possible implementation of any of the aspects.

[0036] In a possible design of the communication apparatus, the communication apparatus can be a chip or a device including the chip, which implements the method described above.

[0037] In a fifth aspect, the present application provides a communication apparatus, which comprises a processor and an interface circuit, the interface circuit is configured to receive a signal from another communication apparatus outside the communication apparatus and transmit the signal to the processor or send a signal from the processor to another communication apparatus outside the communication apparatus, and the processor is configured to implement the method in any of the first aspect to the second aspect, or the method in any possible implementation of any of the aspects, by means of logic circuit or executing code instructions.

[0038] In a sixth aspect, the present application provides a computer readable storage medium, which stores a computer program or instructions, when the computer program or instructions are executed by a computer, the method in any of the first aspect to the second aspect, or the method in any possible implementation of any of the aspects, is implemented.

[0039] In a seventh aspect, the present application provides a computer program product, when a computer reads and executes the computer program product, the computer executes the method in any of the first aspect to the second aspect, or the method in any possible implementation of any of the aspects.

[0040] In an eighth aspect, the present application provides a chip system, which comprises at least one processor and an interface, the processor is configured to read and execute instructions stored in a memory, when the instructions are executed, the chip executes the method in any of the first aspect or the second aspect, or the method in any possible implementation of any of the aspects.

[0041] In a ninth aspect, the present application provides a communication system, which can comprise a first apparatus and a second apparatus. The first apparatus is configured to execute the method in the first aspect or any possible implementation of the first aspect. The second apparatus is configured to execute the method in the second aspect or any possible implementation of the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0042] FIG. 1 is a schematic diagram of an architecture of a communication system to which embodiments of the present application are applied;

[0043] FIG. 2 is a schematic diagram of an AI application framework provided by the present application;

[0044] FIG. 3 is a schematic diagram of several data collection methods provided by the present application;

[0045] FIG. 4 is a flow diagram of a communication method provided by an embodiment of the present application;

[0046] FIG. 5 is another flow diagram of a communication method provided by an embodiment of the present application;

[0047] FIG. 6 is yet another flow diagram of a communication method provided by an embodiment of the present application;

[0048] FIG. 7 is a schematic diagram of processing collected data provided by an embodiment of the present application;

[0049] FIG. 8 is a schematic diagram of a structure of a possible communication device provided by an embodiment of the present application;

[0050] FIG. 9 is a schematic diagram of a structure of a possible communication device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0052] In the description of the present application, "first" and "second" are used only to distinguish different objects, and are not used to describe a specific order. In addition, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this document is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0053] The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device, etc. that includes a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or device, etc.

[0054] In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration." Any embodiment or design described in this application as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word exemplary is intended to present concepts in a concrete manner.

[0055] It should be understood that, in this application, "when", "if" and "whether" are used to indicate that the device will make corresponding processing under certain objective conditions, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0056] In this application, an element expressed by a singular form is intended to represent "one or more", rather than "one and only one", unless otherwise specified.

[0057] It should be understood that, in the embodiments of the present application, "A corresponding to B" means that A and B have a corresponding relationship, and B can be determined according to A. Determining B according to A does not mean that B is determined only according to A, but also can be determined according to A and / or other information.

[0058] In this application, "indication" can include direct indication, indirect indication, display indication, and implicit indication. When describing that certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the indication information is referred to as the to-be-indicated information. In the specific implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be only a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. In addition, the to-be-indicated information can be sent as a whole, or can be sent separately in multiple sub-information, and the sending period and / or sending opportunity of these sub-information can be the same or different.

[0059] In the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, which can include direct sending through the air interface, and also includes indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, which can include direct receiving from YY through the air interface, and also includes indirect receiving from YY through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can be carried out between devices, for example, between network devices and terminal devices, or can be carried out within a device, for example, between components, between modules, between chips, between software modules or hardware modules within a device through a bus, a wire or an interface.

[0060] In order to better understand the embodiments of the present application, first, the system architecture related to the embodiments of the present application will be introduced as follows:

[0061] Referring to Fig. 1, Fig. 1 is a schematic diagram of an architecture of a communication system to which embodiments of the present application are applied. It is noted that Fig. 1 is one possible, non-limiting example of a system. As shown in Fig. 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 10 can further include an Internet 300, which can include one or more Internet servers, such as over the top (OTT) servers. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in Fig. 1, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in Fig. 1, collectively referred to as 120). The RAN 100 can further include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Fig. 1). The terminal 120 is wirelessly connected to the RAN node 110. The RAN node 110 is connected to the core network 200 through wireless or wired connection. The core network device in the core network 200 and the RAN node 110 in the RAN 100 can be different physical devices respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the RAN, or can be a physical device integrated with the functions of part of the core network device and part of the RAN node 110. The terminals and the terminals, and the RAN nodes 110 and the RAN nodes 110 can be connected to each other through wired or wireless manner. Fig. 1 is only a schematic diagram, and the communication system 10 can further include other network devices, such as network management, wireless relay devices and wireless backhaul devices, etc., which are not shown in Fig. 1. The network management can divide the management of the network into three categories according to the actual needs of the operation of the operator network: operation (Operation), administration (Administration), and maintenance (Maintenance). The network management can also be referred to as operation administration and maintenance (OAM) network element, referred to as OAM. The operation mainly completes the analysis, prediction, planning and configuration of the daily network and services; the maintenance mainly includes the daily operation activities of testing and fault management of the network and services, and the network management can detect the running state of the network, optimize the network connection and performance, improve the stability of the network operation, and reduce the network maintenance cost.

[0062] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., a 4G, 5G mobile communication system, or a future oriented evolved system, e.g., a 6G mobile communication system. The RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system that combines two or more of the above systems.

[0063] The RAN nodes 110, which can also be referred to as radio access network devices, access network devices, RAN entities or access nodes, etc., form part of the communication system 100 and are configured to facilitate wireless access to the communication system 100 for terminals. The RAN nodes 110 in the communication system 100 can be nodes of the same type or nodes of different types. In some scenarios, the roles of the RAN nodes 110 and the terminals 120 are relative, e.g., the network element 120i in Figure 1 can be a helicopter or a drone, which can be configured to move as a mobile base station, to a terminal 120j accessing the RAN 100 via the network element 120i, the network element 120i is a base station; but to the base station 110a, the network element 120i is a terminal. The RAN nodes 110 and the terminals 120 are sometimes referred to as communication apparatuses, e.g., the network elements 110a and 110b in Figure 1 can be understood as communication apparatuses with base station functionality, and the network elements 120a-120j can be understood as communication apparatuses with terminal functionality.

[0064] In one possible scenario, the RAN node 110 can be a base station, an evolved Node B (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. The RAN node 110 can be a macro base station (e.g., 110a in Figure 1), a micro base station or an indoor station (e.g., 110b in Figure 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, the RAN node 110 can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, a wireless access network device in a vehicle to everything (V2X) technology can be a road side unit (RSU). All or part of the functions of the RAN node 110 in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform such as a cloud platform. The RAN node 110 in this application can also be a logical node, a logical module or software that can implement all or part of the functions of the RAN node 110.

[0065] In another possible scenario, a terminal is assisted by multiple RAN nodes 110 to implement wireless access, and different RAN nodes 110 respectively implement part of the functions of a base station. For example, the RAN node 110 can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a radio frequency remote unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0066] The CU (or CU-CP and CU-UP), DU or RU can also have different names in different systems, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0067] The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely applied to various scenarios, such as device-to-device (D2D) communication, vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, etc. Embodiments of this application do not limit the device form of the terminal.

[0068] For the convenience of description, the base station is taken as an example of the RAN node 110 in the following description. The base station and the terminal can be fixed in position or movable. The base station and the terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water surface; can also be deployed on airplanes, balloons and artificial satellites. Embodiments of this application do not limit the application scenarios of the base station and the terminal.

[0069] The roles of the base station and the terminal can be relative. For example, the helicopter or the drone 120i in FIG. 1 can be configured as a mobile base station, and for the terminal 120j that accesses the wireless access network 100 through the 120i, the terminal 120i is a base station; but for the base station 110a, the 120i is a terminal, that is, the 110a and the 120i communicate through a wireless air interface protocol. Of course, the 110a and the 120i can also communicate through a base station-to-base station interface protocol, and in this case, the 120i is also a base station relative to the 110a. Therefore, the base station and the terminal can be collectively referred to as a communication device, and the 110a and the 110b in FIG. 1 can be referred to as a communication device with a base station function, and the 120a-120j in FIG. 1 can be referred to as a communication device with a terminal function.

[0070] The base station and the terminal, the base station and the base station, and the terminal and the terminal can communicate through a licensed spectrum, can communicate through an unlicensed spectrum, or can communicate through both the licensed spectrum and the unlicensed spectrum; can communicate through a spectrum below 6 gigahertz (GHz), can communicate through a spectrum above 6 GHz, or can communicate through both the spectrum below 6 GHz and the spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0071] In the embodiments of the present application, the functions of the base station can also be performed by a module (such as a chip) in the base station or by a control subsystem containing base station functions. The control subsystem containing base station functions herein can be a control center in the above-mentioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. The functions of the terminal can also be performed by a module (such as a chip or a modem) in the terminal or by a device containing terminal functions.

[0072] In the present application, the base station sends a downlink signal or downlink information to the terminal, and the downlink information is carried on a downlink channel; the terminal sends an uplink signal or uplink information to the base station, and the uplink information is carried on an uplink channel. In order to communicate with the base station, the terminal needs to establish a wireless connection on a cell controlled by the base station. The cell that establishes a wireless connection with the terminal is called a service cell of the terminal. When the terminal communicates with the service cell, it will also be interfered by signals from neighboring cells.

[0073] It should be noted that the AI model is a module with machine learning computing capability. The design of the AI model mainly includes a data collection link (e.g., collecting training data and / or inference data), a model training link, and a model inference link. Further, it can also include an inference result application link. See Figure 2 for an AI application framework. In the foregoing data collection link, the data source is used to provide the training data set and the inference data. In the model training link, the AI model is obtained by analyzing or training the training data provided by the data source. The AI model represents the mapping relationship between the input and the output of the model. The AI model learned by the model training node is equivalent to learning the mapping relationship between the input and the output of the model using the training data. In the model inference link, the AI model trained in the model training link is used to perform inference based on the inference data provided by the data source, and the inference result is obtained. This link can also be understood as: inputting the inference data into the AI model, and obtaining the output through the AI model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object, and / or the operation executed by the execution object. In the inference result application link, the inference result is published, for example, the inference result can be uniformly planned by an execution entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., core network equipment, access network equipment, or terminal equipment, etc.) to execute. For example, the execution entity can also feed back the performance of the model to the data source to facilitate subsequent implementation of model update training.

[0074] It can be understood that in the communication system, network elements with artificial intelligence functions can be included. The above-mentioned AI model design related links can be executed by one or more network elements with artificial intelligence functions. In one possible design, AI functions (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as training and / or inference of AI models. For example, the existing network element (or network device) can be an access network device (such as a base station), a core network device, a network management (such as OAM), or an Internet server (such as an OTT server), etc. For convenience of description, hereinafter, the network device is mainly taken as an access network device, a core network device, an OAM, and an Internet server for illustrative description.

[0075] It should be noted that the current 3GPP discusses the following several data collection methods, as shown in Figure 3:

[0076] One data collection method 1 is that the terminal directly sends the collected data to the Internet server, and then the Internet server performs AI model training and / or inference based on the received collected data.

[0077] A data collection manner 2 is that the terminal sends the collected data to an Internet server through the access network device and the core network device in turn, and then the Internet server trains and / or reasons an AI model based on the received collected data.

[0078] A data collection manner 3 is that the terminal sends the collected data to an Internet server through the access network device, and then the Internet server trains and / or reasons an AI model based on the received collected data.

[0079] A data collection manner 4 is that the terminal sends the collected data to an OAM / core network device through the access network device, and then the OAM / core network device trains and / or reasons an AI model based on the received collected data.

[0080] A data collection manner 5 is that the terminal directly sends the collected data to the access network device, and then the access network device trains and / or reasons an AI model based on the received collected data.

[0081] The communication method and the communication apparatus provided in the present application will be described in detail as follows:

[0082] Please refer to FIG. 4, which is a flowchart of the communication method provided in an embodiment of the present application. As shown in FIG. 4, the communication method can include the following steps S401-S403. The method execution subject shown in FIG. 4 can be the access network device / Internet server and the terminal. Alternatively, the method execution subject shown in FIG. 4 can be a chip in the access network device / Internet server and a chip in the terminal. For the convenience of description, the present application mainly takes the access network device / Internet server and the terminal as the execution subject for description. It should be understood that FIG. 4 mainly introduces the implementation scheme corresponding to the above-mentioned data collection manner 1 and data collection manner 5, and FIG. 4 is a schematic flowchart of the method embodiment of the present application, which shows the detailed communication steps or operations of the method, but these steps or operations are only examples, and the method embodiment of the present application can also execute other operations or variations of the various operations in FIG. 4. In addition, the various steps in FIG. 4 can be executed in different order from that presented in FIG. 4, and it is possible that not all the operations in FIG. 4 are executed.

[0083] S401, the access network device / Internet server sends first indication information to the terminal. Correspondingly, the terminal receives the first indication information from the access network device / Internet server.

[0084] The first indication information indicates a first data precision or the first indication information indicates a precision identifier of the first data precision, where one precision identifier is used to identify one data precision. It can be understood that the first data precision is a data precision supported by the access network device / internet server, or it can be understood that the first data precision is the highest data precision / maximum data precision supported by the access network device / internet server. For the convenience of description, the first data precision is described as the data precision supported by the access network device / internet server in the following. Alternatively, the data precision described in the embodiments of the present application can also be referred to as quantization precision, etc., and is not limited.

[0085] Generally, the access network device or the internet server can determine the data precision supported by the access network device or the internet server based on transmission overhead, model performance, etc. Alternatively, the precision determination on the access network device side can also be related to data bearer signaling or whether segmentation is performed or not. For example, if the access network device selects layer 1 (L1) signaling to bear the collected data, a smaller / lower data precision can be used because the amount of data that can be transmitted by the L1 signaling is small. For another example, if the access network device selects layer 3 (L3) signaling to bear the collected data, a larger / higher data precision can be used because the amount of data that can be transmitted by the L3 signaling is large. For another example, if the access network device supports segmentation, a larger / higher data precision can be used because the amount of data that can be transmitted by the segmented transmission is large.

[0086] Alternatively, the first indication information described above can also indicate one or more of the following: uniform quantization, non-uniform quantization, transform domain quantization, or compression mode. The uniform quantization refers to quantization in which the value range of the element to be quantized is divided equally. The non-uniform quantization refers to quantization in which the value range of the element to be quantized is not divided equally. The transform domain quantization refers to transforming a floating-point number to another domain, such as discrete fourier transform (DFT), or codebook, etc., and performing quantization in another domain. The compression mode can refer to whether compression is performed or not, or the compression mode can also refer to compression rate, etc., and is not limited.

[0087] In a possible design, the first indication information can be a display indication, for example, the first indication information can be a newly added field / bit in a message, which can indicate one or more of the data precision, uniform quantization, non-uniform quantization, transform domain quantization, or compression mode, etc.

[0088] For example, the first indication information indicates data precision, which can be 2 bits. When the value of the 2 bits is 00, it means no quantization; when the value of the 2 bits is 01, it means 16-bit quantization; when the value of the 2 bits is 10, it means 8-bit quantization; and when the value of the 2 bits is 11, it means 4-bit quantization.

[0089] For example, the first indication information indicates data precision, which can be a bitmap. One bit of the bitmap corresponds to one data precision. For example, assuming that the most significant bit (MSB) to the least significant bit (LSB) correspond to 16-bit quantization, 8-bit quantization, 4-bit quantization, and no quantization, respectively. When the bitmap is 1000, it means 16-bit quantization; when the bitmap is 0100, it means 8-bit quantization; when the bitmap is 0010, it means 4-bit quantization; and when the bitmap is 0001, it means no quantization.

[0090] For example, the first indication information indicates uniform / non-uniform quantization, which can be 2 bits. When the value of the 2 bits is 00, it means no quantization; when the value of the 2 bits is 01, it means uniform quantization; when the value of the 2 bits is 10, it means non-uniform quantization; and “11” is a reserved bit (i.e., the value is not used).

[0091] For example, the first indication information indicates transform domain quantization, which can be 2 bits. When the value of the 2 bits is 00, it means no quantization; when the value of the 2 bits is 01, it means transform domain quantization; and “10” and “11” are reserved bits.

[0092] For example, the first indication information indicates compression mode, which can be 2 bits. When the value of the 2 bits is 0, it means no quantization; when the value of the 2 bits is 01, it means only quantization; when the value of the 2 bits is 10, it means quantization and compression; and “11” is a reserved bit.

[0093] It can be understood that when the first indication information is sent by the access network device to the terminal, the first indication information can be carried in a radio resource control connection reconfiguration (RRCconectionReconfiguration) message. For example, if the first indication information is added in the RRCconectionReconfiguration message, the RRCconectionReconfiguration::=SEQUENCE{

[0094] Data_quantify_ind, Data_method_ind, Data_transform_ind, Data_compress_ind are newly added fields in the RRCconectionReconfiguration message. Specifically, Data_quantify_ind indicates a field for indicating data precision, Data_method_ind indicates a field for indicating uniform / non-uniform quantization method, Data_transform_ind indicates a field for indicating transform domain quantization, and Data_compress_ind indicates a field for indicating compression method.

[0095] For another example, the RRCconectionReconfiguration message can be as follows: RRCconectionReconfiguration ::= SEQUENCE {

[0096] That is, the RRCconectionReconfiguration message can include one or more of the following information: Data_quantify_ind, Data_method_ind, Data_transform_ind, and Data_compress_ind, which are not limited in the present application.

[0097] In another possible design, the first indication information can be an implicit indication. For example, the first indication information is specifically a first functionality ID, a first model ID, or a first dataset ID. The first functionality ID or the first model ID or the first dataset ID is associated with the first data precision. That is, a correspondence between the functionality ID or the model ID or the dataset ID and the data precision can be predefined in advance, and thus the corresponding data precision can be determined based on the functionality ID or the model ID or the dataset ID carried in the message and the data precision.

[0098] For example, taking the implicit indication of the data precision by the functionality ID as an example, functionality ID1 can be predefined to correspond to 16-bit quantization, functionality ID2 can be predefined to correspond to 8-bit quantization, and functionality ID3 can be predefined to correspond to 4-bit quantization.

[0099] For example, Model ID can be used to implicitly indicate data precision. For example, Model ID1 can be used to indicate 16-bit quantization, Model ID2 can be used to indicate 8-bit quantization, and Model ID3 can be used to indicate 4-bit quantization.

[0100] For another example, functionality ID and Model ID can also be used in combination. Generally, one functionality ID can correspond to multiple Model IDs. For example, Model ID1, Model ID2 and Model ID3 can be used for functionality ID1. Model ID1 can be used to indicate 16-bit quantization, Model ID2 can be used to indicate 8-bit quantization, and Model ID3 can be used to indicate 4-bit quantization.

[0101] For another example, different data precision can be used for training different models. For example, Dataset ID1 can be used to indicate 16-bit quantization, Dataset ID2 can be used to indicate 8-bit quantization, and Dataset ID3 can be used to indicate 4-bit quantization.

[0102] S402, the terminal quantizes the collected data according to the first indication information to obtain quantized collected data.

[0103] In one possible implementation, the terminal quantizes the collected data according to the first indication information to obtain quantized collected data can be understood as: the terminal quantizes the collected data according to the first data precision indicated by the first indication information to obtain quantized collected data. That is, the first data precision is the quantization precision of the terminal. In another possible implementation, the terminal quantizes the collected data according to the first indication information to obtain quantized collected data can be understood as: the terminal determines the quantization precision according to the first data precision and the second data precision, and then quantizes the collected data according to the quantization precision to obtain quantized collected data. The second data precision is the data precision supported by the terminal, which is generally related to the capability of the terminal and the current resource state available to the terminal. That is, the terminal can determine the final quantization precision used by combining the data precision supported by the network side (i.e., the first data precision) and the data precision supported by the terminal itself (i.e., the second data precision). For example, the quantization precision can be the smaller one of the first data precision and the second data precision.

[0104] S403, the terminal sends the quantized collected data to the access network device / internet server. The access network device / internet server receives the quantized collected data from the terminal.

[0105] In some possible implementation, after the access network device / internet server receives the quantized collected data, the access network device / internet server can recover the collected data. In one design, if the quantization precision is the first data precision indicated by the first indication information, the access network device / internet server can recover the collected data from the quantized collected data according to the first data precision.

[0106] For example, assume that the first indication information sent by the access network device (or the internet server) to the terminal indicates that the data precision supported by the access network device (or the internet server) is 16-bit quantization, and the terminal performs quantization on the collected data using the data precision indicated by the first indication information (i.e., 16-bit quantization) to obtain the quantized collected data. Accordingly, after the access network device (or the internet server) obtains the quantized collected data, the access network device (or the internet server) can recover the collected data from the quantized collected data according to the 16-bit quantization, and then perform training and / or inference of the AI model based on the recovered collected data.

[0107] In another design, if the quantization precision is the smaller one of the first data precision and the second data precision, the terminal can send the quantization precision at the same time of sending the quantized collected data, or before sending the quantized collected data, or after sending the quantized collected data, so that the data receiving end (here, the data receiving end refers to the access network device or the internet server) can recover the collected data from the quantized collected data according to the quantization precision.

[0108] For example, assume that the first indication information sent by the access network device (or the internet server) to the terminal indicates that the data precision supported by the access network device (or the internet server) is 16-bit quantization, and the data precision supported by the terminal is 8-bit quantization, the terminal can determine that the final quantization precision is 8-bit quantization, and then perform quantization on the collected data using the 8-bit quantization to obtain the quantized collected data. Accordingly, after the access network device (or the internet server) obtains the quantized collected data, the access network device (or the internet server) can recover the collected data from the quantized collected data according to the 8-bit quantization, and then perform training and / or inference of the AI model based on the recovered collected data.

[0109] It can be understood that the collection data involved in the present application can be channel state information, modulation and demodulation data, or air interface receiving data, etc., which is not limited in the present application. Exemplarily, the dimension of the data structure of the channel state information can be the number of subbands, the number of resource blocks (RBs), the number of subcarriers, the number of symbols, the number of antennas, real and imaginary parts, etc., which is not limited in the present application. Exemplarily, the dimension of the data structure of the modulation and demodulation data can be the number of subbands, the number of RBs, the number of subcarriers, the number of symbols, the number of antennas, real and imaginary parts, etc., which is not limited in the present application. Exemplarily, the dimension of the data structure of the air interface receiving data can be the number of subbands, the number of RBs, the number of subcarriers, the number of symbols, the number of antennas, real and imaginary parts, etc., which is not limited in the present application.

[0110] It should be noted that the collection data sent by the terminal to the access network device in the present application can be unquantized, or the collection data sent by the terminal to the access network device can also be quantized. Alternatively, the collection data sent by the terminal to the access network device can also be processed by uniform quantization, non-uniform quantization, transform domain quantization, or compression, etc. Alternatively, the collection data sent by the terminal to the access network device can also be processed by dimension change, such as flatten processing. Alternatively, the collection data sent by the terminal to the access network device can also be processed by conversion into bytes, such as ToByte. It can be understood that the above various processing methods can be executed alone, or multiple processing methods can be executed in combination, and the execution order of the various processing methods is not limited when executed in combination. Correspondingly, the receiving end needs to restore the collection data according to the corresponding inverse transform processing method. For convenience of description, the embodiments of the present application are mainly described by way of example with the collection data sent by the terminal to the access network device being quantized.

[0111] It can be understood that when the terminal sends the quantized collection data to the access network device, the quantized collection data can be carried in the minimization drive test (MDT) signaling. In a possible design, the collection data quantized by the terminal (or the collection data without quantization) can be carried through a newly added field in the MDT signaling, for example, the newly added field is an Mx field, and the measurement description corresponding to the Mx field can be that the collection data on the terminal side includes but is not limited to channel state information, modulation and demodulation data, or air interface receiving data, etc., which is not limited in the present application, or the measurement description corresponding to the Mx field can be that the collection data on the terminal side can be uplink (UL) / downlink (DL) signals.

[0112] Optionally, the MDT signaling can further indicate other measurements on the terminal side. For example, the field related to the terminal measurement in the MDT signaling can further include M1 field, M2 field, M6 field, M8 field, and M9 field. Specifically, the measurement description corresponding to the M1 field can be the quality of the downlink signal (DL signal quantity) measured by the terminal, such as the reference signal received power (RSRP), the reference signal received quality (RSRQ), and the signal to interference plus noise ratio (SINR); the measurement description corresponding to the M2 field can be the power headroom; the measurement description corresponding to the M6 field can be the uplink delay (UL delay); and the measurement description corresponding to the M8 / 9 field can be the wireless fidelity (WIFI) / Bluetooth measurement.

[0113] Optionally, the MDT signaling can further indicate measurements on the network side. For example, the field related to the network measurement in the MDT signaling can include M4 field, M5 field, M6 field, and M7 field. Specifically, the measurement description corresponding to the M4 field can be the data volume for the downlink and uplink; the measurement description corresponding to the M5 field can be the scheduled IP throughput for the downlink and uplink; the measurement description corresponding to the M6 field can be the uplink / downlink delay; and the measurement description corresponding to the M7 field can be the packet loss rate for the downlink and uplink.

[0114] In the embodiments of the present application, the access network device / Internet server indicates the data precision supported by the terminal, so that the terminal quantizes the collected data according to the indication of the access network device / Internet server before transmission, which is beneficial to reduce the transmission overhead of the collected data.

[0115] Please refer to FIG. 5, which is another flow diagram of the communication method provided in the embodiments of the present application. As shown in FIG. 5, the communication method can include the following steps S501-S505. The method execution subject shown in FIG. 5 can be an access network device / core network device / operation and maintenance management / internet server and a terminal. Alternatively, the method execution subject shown in FIG. 5 can be a chip in the access network device / core network device / operation and maintenance management / internet server and a chip in the terminal. For the convenience of description, the present application mainly takes the access network device / core network device / operation and maintenance management / internet server and the terminal as the execution subject for description. It should be understood that FIG. 5 mainly introduces the implementation scheme corresponding to the above-mentioned data collection mode 3 and data collection mode 4, and FIG. 5 is a schematic flow diagram of the method embodiments of the present application, which shows the detailed communication steps or operations of the method, but these steps or operations are only examples, and the method embodiments of the present application can also perform other operations or variations of the various operations in FIG. 5. In addition, the various steps in FIG. 5 can be executed in different order from that presented in FIG. 5, and it is possible that not all the operations in FIG. 5 are executed. Among them:

[0116] S501, the core network device / operation and maintenance management / internet server sends second indication information to the access network device. Correspondingly, the access network device receives the second indication information from the core network device / operation and maintenance management / internet server.

[0117] The second indication information indicates the third data precision or the second indication information indicates the precision identifier of the third data precision, wherein one precision identifier is used to identify one data precision. It can be understood that the third data precision is the data precision supported by the core network device, operation and maintenance management, or internet server, or the third data precision is the highest data precision / maximum data precision supported by the core network device, operation and maintenance management, or internet server. Generally, the core network device / operation and maintenance management / internet server can determine the supported data precision based on its own transmission overhead, model performance, etc.

[0118] Optionally, the second indication information can indicate the third data precision in a displayed or implicit manner. The manner in which the second indication information indicates the third data precision can refer to the description of the manner in which the first indication information indicates the first data precision in the foregoing corresponding embodiments of FIG. 4, and will not be described here.

[0119] S502, the access network device sends the first indication information to the terminal. Correspondingly, the terminal receives the first indication information from the access network device.

[0120] In some possible implementation manners, after receiving the second indication information, the access network device can send the first indication information based on the third data precision and a fourth data precision. The first indication information indicates the first data precision or the first indication information indicates an accuracy identifier of the first data precision, where one accuracy identifier is used to identify one data precision.

[0121] In a possible design, the first data precision is a smaller one of the third data precision and a fourth data precision, and the fourth data precision is a data precision supported by the access network device.

[0122] In another possible design, the first data precision includes the third data precision and a fourth data precision, and the fourth data precision is a data precision supported by the access network device.

[0123] In yet another possible design, the first data precision is the third data precision.

[0124] It should be noted that the implementation manner of how the first indication information indicates the first data precision can refer to the related description in the foregoing corresponding embodiments of FIG. 4, and will not be described herein again.

[0125] Exemplarily, when the implicit indication manner is adopted, the second indication information can be a function identifier, and the function identifier is associated with the third data precision. The first indication information can be a model identifier under the function identifier, and the model identifier under the function identifier is associated with the first data precision.

[0126] S503, the terminal performs quantization processing on the collected data according to the first indication information, to obtain quantization-processed collected data.

[0127] In some possible implementation manners, when the first data precision is the third data precision, the terminal performing quantization processing on the collected data according to the first indication information, to obtain quantization-processed collected data can be understood as: the terminal performs quantization processing on the collected data according to the third data precision, to obtain quantization-processed collected data. That is, the data precision supported by the core network device or the operation and maintenance management or the Internet server (i.e., the third data precision) is the quantization processing precision used by the terminal.

[0128] Optionally, the terminal quantizes the collected data according to the first indication information, and the collected data after the quantization can also be understood as: the terminal determines a quantization precision according to the first data precision and the second data precision, and then quantizes the collected data according to the quantization precision to obtain the collected data after the quantization. The second data precision is a data precision supported by the terminal, and generally, the data precision supported by the terminal is related to the capability of the terminal and the current resource state available to the terminal. That is, the terminal can comprehensively determine the final quantization precision used in combination with the data precision supported by the network side (i.e., the first data precision) and the data precision supported by the terminal itself (i.e., the second data precision).

[0129] Exemplarily, the quantization precision can be the minimum value of the first data precision and the second data precision. For example, assuming that the first data precision is the smaller value of the third data precision and the fourth data precision, the quantization precision can be the smaller value of the first data precision and the second data precision. For another example, assuming that the first data precision includes the third data precision and the fourth data precision, the quantization precision can be the minimum value of the third data precision, the fourth data precision and the second data precision.

[0130] S504, the terminal sends the collected data after the quantization to the access network device. The access network device receives the collected data after the quantization from the terminal.

[0131] In some possible implementation manners, the collected data after the quantization sent by the terminal to the access network device can be carried in MDT signaling or other messages, which is not limited. Optionally, the terminal can also send the quantization precision associated with the collected data after the quantization to the access network device at the same time of sending the collected data after the quantization, or before sending the collected data after the quantization, or after sending the collected data after the quantization.

[0132] S505, the access network device sends the collected data after the quantization to the core network device / operation and maintenance management / internet server. Correspondingly, the core network device / operation and maintenance management / internet server receives the collected data after the quantization from the access network device.

[0133] In some possible implementation manners, after the access network device obtains the collected data after the quantization, the access network device can further send the collected data after the quantization to the core network device / operation and maintenance management / internet server, and then the core network device / operation and maintenance management / internet server recovers the collected data from the collected data after the quantization. Optionally, the access network device can also send the quantization precision associated with the collected data after the quantization to the core network device / operation and maintenance management / internet server.

[0134] In one design, if the quantization processing precision is the third data precision, the access network device / Internet server can recover the collected data from the quantization-processed collected data according to the third data precision.

[0135] For example, assume that the second indication information sent by the core network device (or the operation and maintenance management, or the Internet server) to the access network device indicates that the data precision supported by the core network device (or the operation and maintenance management, or the Internet server) is 16-bit quantization, and the first indication information sent by the access network device to the terminal indicates that the data precision is the same as that indicated by the second indication information, i.e., 16-bit quantization. In this case, the terminal can perform quantization processing on the collected data in the 16-bit quantization manner to obtain the quantization-processed collected data. Correspondingly, after the core network device (or the operation and maintenance management, or the Internet server) obtains the quantization-processed collected data, the core network device (or the operation and maintenance management, or the Internet server) can recover the collected data from the quantization-processed collected data according to the 16-bit quantization manner, and further perform training and / or inference of the AI model based on the recovered collected data.

[0136] In another design, if the quantization processing precision is the minimum of the first data precision and the second data precision, the data receiving end (here, the data receiving end refers to the core network device or the operation and maintenance management or the Internet server) can recover the collected data from the quantization-processed collected data according to the quantization processing precision.

[0137] For example, assume that the second indication information sent by the core network device (or the operation and maintenance management, or the Internet server) to the access network device indicates that the data precision supported by the core network device (or the operation and maintenance management, or the Internet server) is 16-bit quantization, and the first indication information sent by the access network device to the terminal indicates that the data precision is the same as that indicated by the second indication information, i.e., 16-bit quantization. In this case, the terminal can perform quantization processing on the collected data in the 16-bit quantization manner to obtain the quantization-processed collected data. Correspondingly, after the core network device (or the operation and maintenance management, or the Internet server) obtains the quantization-processed collected data, the core network device (or the operation and maintenance management, or the Internet server) can recover the collected data from the quantization-processed collected data according to the 16-bit quantization manner, and further perform training and / or inference of the AI model based on the recovered collected data.

[0138] For another example, assuming that the second indication information sent by the core network device (or operation and maintenance management, or an Internet server) to the access network device indicates that the data precision supported by the core network device (or operation and maintenance management, or an Internet server) is 16-bit quantization, and the data precision supported by the access network device itself is 8-bit quantization, the data precision indicated by the first indication information sent by the access network device to the terminal can be 16-bit quantization and 8-bit quantization. Assuming that the data precision supported by the terminal itself is 4-bit quantization, the terminal can determine that the final quantization processing precision is 4-bit quantization (that is, the minimum value in 16-bit quantization, 8-bit quantization, and 4-bit quantization), and then use the 4-bit quantization manner to perform quantization processing on the collected data to obtain quantization-processed collected data. Correspondingly, after the core network device (or operation and maintenance management, or an Internet server) obtains the quantization-processed collected data, the collected data can be recovered from the quantization-processed collected data according to the 4-bit quantization manner, and then the training and / or inference of the AI model is performed based on the recovered collected data.

[0139] The understanding of the collected data can refer to the related description in the foregoing embodiment of FIG. 4, and will not be described here.

[0140] In this embodiment, the network device indicates the data precision supported by the network device to the terminal, so that the terminal transmits the collected data after quantization processing according to the indication of the network device, which is beneficial to reduce the transmission overhead of the collected data.

[0141] Please refer to FIG. 6, which is another flowchart of a communication method provided by an embodiment of the present application. As shown in FIG. 6, the communication method can include the following steps S601-S607. The method execution subject shown in FIG. 6 can be an access network device / core network device / operation and maintenance management / Internet server and a terminal. Alternatively, the method execution subject shown in FIG. 6 can be a chip in the access network device / core network device / operation and maintenance management / Internet server and a chip in the terminal. For the convenience of description, the present application mainly takes the access network device / core network device / operation and maintenance management / Internet server and the terminal as the execution subject for description. It should be understood that FIG. 6 mainly introduces the implementation scheme corresponding to the above-described data collection manner 2, and FIG. 6 is a schematic flowchart of the method embodiment of the present application, which shows the detailed communication steps or operations of the method, but these steps or operations are only examples, and other operations or variations of the operations in FIG. 6 can also be performed by the embodiment of the present application. In addition, the steps in FIG. 6 can be executed in different order from that presented in FIG. 6, and it is possible that not all the operations in FIG. 6 are executed. Among them:

[0142] S601. The Internet server sends third indication information to the core network device / operation and maintenance management. Accordingly, the core network device / operation and maintenance management receives the third indication information from the Internet server.

[0143] The third indication information indicates the fifth data precision or the third indication information indicates an accuracy identifier of the fifth data precision, where one accuracy identifier is used to identify one data precision. It can be understood that the fifth data precision is a data precision supported by the Internet server, or the fifth data precision is the highest data precision / maximum data precision supported by the Internet server.

[0144] Optionally, the third indication information can indicate the fifth data precision in a displayed or implicit manner. The manner in which the third indication information indicates the fifth data precision can be referred to the description of the manner in which the first indication information indicates the first data precision in the first embodiment of FIG. 4, which will not be described herein.

[0145] S602. The core network device / operation and maintenance management sends second indication information to the access network device. Accordingly, the access network device receives the second indication information from the core network device / operation and maintenance management.

[0146] The second indication information indicates the third data precision or the second indication information indicates an accuracy identifier of the third data precision, where one accuracy identifier is used to identify one data precision.

[0147] In a possible design, the third data precision is the smaller one of the fifth data precision and a sixth data precision. The sixth data precision is a data precision supported by the core network device or the operation and maintenance management, or the sixth data precision is the highest data precision / maximum data precision supported by the core network device or the operation and maintenance management. Generally, the core network device / operation and maintenance management can determine the supported data precision based on its own transmission overhead, model performance, and the like.

[0148] In another possible design, the third data precision includes the fifth data precision and the sixth data precision. The sixth data precision is a data precision supported by the core network device or the operation and maintenance management.

[0149] In yet another possible design, the third data precision is the fifth data precision.

[0150] Optionally, the second indication information can indicate the third data precision in a displayed or implicit manner. The manner in which the second indication information indicates the third data precision can be referred to the description of the manner in which the first indication information indicates the first data precision in the first embodiment of FIG. 4, which will not be described herein.

[0151] S603, the access network device sends first indication information to the terminal. Correspondingly, the terminal receives the first indication information from the access network device.

[0152] In some possible implementation manners, after receiving the second indication information, the access network device can send the first indication information based on the third data precision and the fourth data precision. The first indication information indicates the first data precision, or the first indication information indicates an accuracy identifier of the first data precision, where one accuracy identifier is used to identify one data precision.

[0153] In a possible design, the first data precision is the smaller one of the third data precision and the fourth data precision. In this design, the third data precision is the smaller one of the fifth data precision and the sixth data precision, and the fourth data precision is the data precision supported by the access network device.

[0154] In another possible design, the first data precision includes the third data precision and the fourth data precision, and the fourth data precision is the data precision supported by the access network device. In this design, the third data precision includes the fifth data precision and the sixth data precision, and the fourth data precision is the data precision supported by the access network device. That is, the first data precision includes the fourth data precision, the fifth data precision, and the sixth data precision.

[0155] In yet another possible design, the first data precision is the fifth data precision.

[0156] It should be noted that the implementation manner of how the first indication information indicates the first data precision can refer to the related description in the foregoing corresponding embodiments of FIG. 4, and will not be described herein.

[0157] S604, the terminal performs quantization processing on the collected data according to the first indication information, to obtain quantization-processed collected data.

[0158] In some possible implementation manners, when the first data precision is the fifth data precision, the terminal performing quantization processing on the collected data according to the first indication information, to obtain quantization-processed collected data can be understood as: the terminal performing quantization processing on the collected data according to the fifth data precision, to obtain quantization-processed collected data. That is, the data precision supported by the Internet server (i.e., the fifth data precision) is the quantization processing precision used by the terminal.

[0159] For example, assuming that the third indication information sent by the Internet server to the core network device / operation and maintenance management indicates that the data precision supported by the Internet server is 16-bit quantization, and the second indication information sent by the core network device / operation and maintenance management to the access network device and the first indication information sent by the access network device to the terminal indicate that the data precision is the same as that indicated by the third indication information, that is, 16-bit quantization, the terminal can perform quantization processing on the collected data in the 16-bit quantization manner to obtain quantization-processed collected data. Correspondingly, after the Internet server obtains the quantization-processed collected data, the Internet server can recover the collected data from the quantization-processed collected data according to the 16-bit quantization manner, and then perform training and / or inference of the AI model based on the recovered collected data.

[0160] Alternatively, the terminal performing quantization processing on the collected data according to the first indication information to obtain quantization-processed collected data can also be understood as: the terminal determines quantization processing precision according to the first data precision and the second data precision, and then performs quantization processing on the collected data according to the quantization processing precision to obtain quantization-processed collected data. The second data precision is the data precision supported by the terminal. Generally, the data precision supported by the terminal is related to the capability of the terminal and the current resource state available to the terminal. That is, the terminal can comprehensively determine the final quantization processing precision in combination with the data precision supported by the network side (that is, the first data precision) and the data precision supported by the terminal itself (that is, the second data precision).

[0161] For example, the quantization processing precision can be the minimum value of the first data precision and the second data precision. For example, assuming that the first data precision is the smaller value of the third data precision and the fourth data precision, the quantization processing precision can be the smaller value of the first data precision and the second data precision. For example, assuming that the third indication information sent by the Internet server to the core network device / operation and maintenance management indicates that the data precision supported by the Internet server is 16-bit quantization, and the data precision supported by the core network device / operation and maintenance management itself is 16-bit quantization, the second indication information sent by the core network device / operation and maintenance management to the access network device indicates that the data precision is 16-bit quantization. Assuming that the data precision supported by the access network device itself is 8-bit quantization, the first indication information sent by the access network device to the terminal indicates that the data precision can be the smaller value of 16-bit quantization and 8-bit quantization, i.e., 8-bit quantization. Assuming that the data precision supported by the terminal itself is 4-bit quantization, the terminal can determine that the final quantization processing precision is 4-bit quantization (i.e., the smaller value of 8-bit quantization and 4-bit quantization), and then uses the 4-bit quantization manner to perform quantization processing on the collected data to obtain quantization-processed collected data. Correspondingly, after the Internet server obtains the quantization-processed collected data, the collected data can be recovered from the quantization-processed collected data according to the 4-bit quantization manner, and then the training and / or inference of the AI model is performed based on the recovered collected data.

[0162] For example, assuming that the first data precision includes the fourth data precision, the fifth data precision, and the sixth data precision, the quantization processing precision can be the minimum value of the second data precision, the fourth data precision, the fifth data precision, and the sixth data precision. For example, assuming that the third indication information sent by the Internet server to the core network device / operation and maintenance management indicates that the data precision supported by the Internet server is 16-bit quantization, and the data precision supported by the core network device / operation and maintenance management itself is 16-bit quantization, the second indication information sent by the core network device / operation and maintenance management to the access network device indicates that the data precision is 16-bit quantization. Assuming that the data precision supported by the access network device itself is 8-bit quantization, the first indication information sent by the access network device to the terminal indicates that the data precision can be 16-bit quantization and 8-bit quantization. Assuming that the data precision supported by the terminal itself is 4-bit quantization, the terminal can determine that the final quantization processing precision is 4-bit quantization (i.e., the smaller value of 16-bit quantization, 8-bit quantization, and 4-bit quantization), and then uses the 4-bit quantization manner to perform quantization processing on the collected data to obtain quantization-processed collected data. Correspondingly, after the Internet server obtains the quantization-processed collected data, the collected data can be recovered from the quantization-processed collected data according to the 4-bit quantization manner, and then the training and / or inference of the AI model is performed based on the recovered collected data.

[0163] S605, the terminal sends the quantized collected data to the access network device. The access network device receives the quantized collected data from the terminal.

[0164] In some possible implementation manners, the quantized collected data sent by the terminal to the access network device can be carried in MDT signaling or other messages, which is not limited. Alternatively, the terminal can also send the quantization precision associated with the quantized collected data to the access network device at the same time of sending the quantized collected data, or before sending the quantized collected data, or after sending the quantized collected data.

[0165] S606, the access network device sends the quantized collected data to the core network device / operation and maintenance management. Correspondingly, the core network device / operation and maintenance management receives the quantized collected data from the access network device.

[0166] Alternatively, the access network device can also send the quantization precision associated with the quantized collected data to the core network device / operation and maintenance management.

[0167] S607, the core network device / operation and maintenance management sends the quantized collected data to the Internet server. Correspondingly, the Internet server receives the quantized collected data from the core network device / operation and maintenance management.

[0168] In some possible implementation manners, when the Internet server obtains the quantized collected data, the Internet server can recover the collected data from the quantized collected data.

[0169] In one design, if the quantization precision is the fifth data precision, the access network device can recover the collected data from the quantized collected data according to the fifth data precision.

[0170] In another design, if the quantization precision is the minimum value of the first data precision and the second data precision, the data receiving end (here, the data receiving end refers to the Internet server) can recover the collected data from the quantized collected data according to the quantization precision.

[0171] The understanding of the collected data can refer to the related description in the foregoing corresponding embodiment of FIG. 4, which is not repeated here.

[0172] In this embodiment, the network device indicates the data precision supported by the network device to the terminal, so that the terminal performs quantization processing on the collected data according to the indication of the network device before transmission, which is beneficial to reduce the transmission overhead of the collected data.

[0173] Exemplarily, as shown in FIG. 7, a schematic diagram of collecting data processing is shown. For the terminal, after the terminal receives the data precision indicated by the network device, the terminal can quantize the original collected data in combination with the indication of the network device to obtain quantized collected data, and send the obtained quantized collected data to the network device. Correspondingly, after the network device receives the quantized collected data, the original collected data can be recovered based on the inverse transform, and then the training and / or inference of the AI model is performed based on the recovered collected data.

[0174] The communication apparatus provided by the present application will be described in detail below with reference to FIGS. 8-9.

[0175] It can be understood that, in order to implement the functions in the above embodiments, the communication apparatus includes hardware structures and / or software modules corresponding to the functions. Those skilled in the art should easily understand that, in combination with the units and method steps of the examples described in the embodiments disclosed in the present application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application scenarios and design constraints of the technical solutions.

[0176] FIGS. 8 and 9 are structural schematic diagrams of possible communication apparatuses provided by the embodiments of the present application. These communication apparatuses can be used to implement the functions of the terminal or the network device (such as the access network device or the core network device or the Internet server or the operation and maintenance management) 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 apparatus can be one of the terminals 120a-120j as shown in FIG. 1, or can be the RAN node 110a or 110b as shown in FIG. 1, or can be the core network device in the CN 200 as shown in FIG. 1, or can be the Internet server in the Internet 300 as shown in FIG. 1, or can be the operation and maintenance management in the communication system 10 as shown in FIG. 1. Alternatively, it can also be a module (such as a chip) applied to a terminal or a wireless access network device or a core network device or an Internet server or an operation and maintenance management.

[0177] As shown in FIG. 8, the communication apparatus 800 includes a processing unit 810 and a transceiver unit 820. The communication apparatus 800 is used to implement the functions of the terminal or the network device in the above method embodiments shown in FIGS. 4-6.

[0178] In an implementation manner, when the communication apparatus 800 is used to implement the functions of the terminal in the method embodiments shown in FIG. 3:

[0179] The transceiver unit 820 is configured to receive first indication information, the first indication information indicating a first data precision, the first data precision being a data precision supported by the network device; the processing unit 810 is configured to perform quantization processing on the collected data according to the first indication information to obtain quantization-processed collected data; and the transceiver unit 820 is configured to send the quantization-processed collected data.

[0180] When the communication apparatus 800 is configured to implement the functions of the network device in the method embodiment shown in FIG. 3, the processing unit 810 is configured to perform the following steps:

[0181] The processing unit 810 is configured to send first indication information, the first indication information indicating a first data precision, the first data precision being a data precision supported by the network device; and the processing unit 810 is configured to receive quantization-processed collected data.

[0182] For more detailed description of the processing unit 810 and the transceiver unit 820, refer to the related description in the method embodiments shown in FIG. 4 to FIG. 6.

[0183] As shown in FIG. 9, the communication apparatus 900 includes a processor 910 and an interface circuit 920. The processor 910 and the interface circuit 920 are coupled with each other. It can be understood that the interface circuit 920 can be a transceiver or an input / output interface. Optionally, the communication apparatus 900 can further include a memory 930 configured to store instructions executed by the processor 910 or store input data required by the processor 910 to execute instructions or store data generated after the processor 910 executes instructions.

[0184] When the communication apparatus 900 is configured to implement the methods shown in FIG. 4 to FIG. 6, the processor 910 is configured to implement the functions of the processing unit 810, and the interface circuit 920 is configured to implement the functions of the transceiver unit 820.

[0185] When the communication apparatus is a terminal chip, the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receives information sent by the radio access network device to the terminal through other modules (such as a radio frequency module or an antenna) in the terminal; or the terminal chip sends information to other modules (such as a radio frequency module or an antenna) in the terminal, and the information is sent by the terminal to the radio access network device.

[0186] When the communication device is a module applied to a radio access network device, the radio access network device module implements the functions of the radio access network device in the method embodiments. The radio access network device module receives information from other modules (such as a radio frequency module or an antenna) in the radio access network device, and the information is sent by the terminal to the radio access network device; or the radio access network device module sends information to other modules (such as a radio frequency module or an antenna) in the radio access network device, and the information is sent by the radio access network device to the terminal. The radio access network device module can be a baseband chip of the radio access network device, or a CU, a DU or other modules, or a device under the open radio access network (O-RAN) architecture, such as an open CU, an open DU, etc.

[0187] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0188] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions executable by a processor. The software instructions can be composed of corresponding software modules, which can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a 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. 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 a radio access network device or a terminal. The processor and the storage medium can also exist as discrete components in the radio access network device or the terminal.

[0189] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; an optical medium, such as a digital video disc; and a semiconductor medium, such as a solid state disk. The computer readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile storage media.

[0190] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0191] It can be understood that various numerical numbers involved in the embodiments of the present application are only used for differentiation for convenience of description, and are not used to limit the scope of the embodiments of the present application. The size of the serial number of the above processes does not mean the execution order, and the execution order of the processes should be determined according to their functions and inherent logic.

Claims

1. A communication method characterized by comprising: The method comprises: receiving first indication information, the first indication information indicating a first data precision, the first data precision being a data precision supported by a network device; quantizing collected data according to the first indication information to obtain quantized collected data; sending the quantized collected data.

2. The method of claim 1, wherein, The quantizing collected data according to the first indication information to obtain quantized collected data comprises: determining a quantization precision according to the first data precision and a second data precision, the second data precision being a data precision supported by a terminal; quantizing the collected data according to the quantization precision to obtain quantized collected data.

3. The method of claim 2, wherein, The method further comprises: sending the quantization precision.

4. The method according to claim 2 or 3, characterized in that, The quantization precision is a smaller one of the first data precision and the second data precision.

5. The method according to any one of claims 1 to 4, characterized in that, The network device is an access network device.

6. The method according to any one of claims 1 to 4, characterized in that, The first data precision is a minimum value of data precisions supported by a plurality of network devices.

7. The method according to any one of claims 1 to 4, characterized in that, The first data precision comprises data precisions supported by a plurality of network devices.

8. The method according to claim 6 or 7, characterized in that, The plurality of network devices comprise at least two of an access network device, a core network device, an operation and maintenance management, and an Internet server.

9. The method according to any one of claims 1 to 8, characterized in that, The first indication information further indicates one or more of the following: uniform quantization, non-uniform quantization, transform domain quantization, or compression mode.

10. The method according to any one of claims 1 to 9, characterized in that, The first indication information is a first function identifier, a first model identifier, or a first data set identifier; wherein the first function identifier or the first model identifier or the first data set identifier is associated with the first data precision.

11. The method according to any one of claims 1 to 10, characterized in that, The first indication information is carried in a radio resource control connection reconfiguration message.

12. The method according to any one of claims 1 to 11, characterized in that, The quantized collected data is carried in a minimization of drive tests signaling.

13. The method according to any one of claims 1 to 12, characterized in that, The collected data comprises one or more of the following: channel state information, modulation and demodulation data, or air interface received data.

14. A communication method, comprising: The method comprises: sending first indication information, the first indication information indicating a first data precision, the first data precision being a data precision supported by a network device; receiving quantized collected data.

15. The method of claim 14, wherein, The method further comprises: receiving a quantization precision, the quantization precision being associated with the quantized collected data.

16. The method according to claim 14 or 15, characterized in that The method further comprises: receiving second indication information, the second indication information indicating a third data precision, the third data precision being a data precision supported by a core network device, an operation and maintenance management, or an Internet server; The sending first indication information comprises: sending first indication information according to the third data precision and a fourth data precision, wherein the first data precision is a smaller one of the third data precision and the fourth data precision, and the fourth data precision is a data precision supported by an access network device.

17. The method of claim 16, wherein, The method further comprises: sending the quantized collected data to the core network device, the operation and maintenance management, or the Internet server.

18. The method of claim 16 or 17, wherein, The method further comprises: sending the quantization precision to the core network device, the operation and maintenance management, or the Internet server, the quantization precision being associated with the quantized collected data.

19. The method according to any one of claims 14-18, characterized by, The first indication information further indicates one or more of the following: Uniform quantization, non-uniform quantization, transform domain quantization, or compression mode.

20. The method according to any one of claims 14-19, characterized by, The first indication information is a first function identifier, a first model identifier, or a first data set identifier; wherein the first function identifier or the first model identifier or the first data set identifier is associated with the first data precision.

21. The method according to any one of claims 14-20, characterized by, The first indication information is carried in a radio resource control connection reconfiguration message.

22. The method according to any one of claims 14-21, characterized by, The quantized collected data is carried in a minimization of drive test signaling.

23. The method according to any one of claims 14-22, characterized by, The collected data includes one or more of the following: Channel state information, modulation and demodulation data, or air interface receiving data.

24. A communications device, characterized by A unit or module for performing the method of any one of claims 1-13, or a unit or module for performing the method of any one of claims 14-23.

25. A communications device, characterized by A processor and an interface circuit for receiving signals from other communication devices outside the communication device and transmitting signals to the processor or sending signals from the processor to other communication devices outside the communication device, the processor being used to implement the method of any one of claims 1-13 or the method of any one of claims 14-23 through a logic circuit or an execution code instruction.

26. A computer readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method of any one of claims 1-13 or the method of any one of claims 14-23.

27. A computer program product, characterised in that, Computer program code for implementing the method of any one of claims 1-13 or the method of any one of claims 14-23.

28. A communication system, characterized by A terminal for implementing the method of any one of claims 1-13 or a network device for implementing the method of any one of claims 14-23.

Images