Communication method and device

Abstract

A communication method and device are used for improving the speed and accuracy of multipath prediction. The method comprises the following steps: receiving a first signal from network equipment; first information is determined, the first information comprises a receiving parameter of the first signal, or the first information comprises a sending parameter and a receiving parameter of the first signal, the first information is used for determining a first grid region corresponding to a path corresponding to the first signal in a preset geographic range, and the preset geographic range is divided into a plurality of grid regions; and sending a measurement result of the first signal to the network device, wherein the measurement result comprises the first information. According to the method, the multipath prediction model is trained by sending the data in the communication system to the network equipment, so that the multipath prediction model can learn the multipath rule in the communication system, the multipath prediction accuracy and prediction speed can be improved, multipath characteristics can be inferred in an unknown communication scene, and repeated channel measurement is avoided.

Description

Communication method and device Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0002] Multipath propagation refers to the phenomenon in which a signal in a wireless propagation environment travels two or more paths before reaching the receiving antenna. Reflection and diffraction of signals from objects in the environment cause multipath, resulting in signals traveling along different paths experiencing different delays and phases. The receiving antenna receives the superposition of these multipath signals. Multipath delay spread leads to inter-symbol interference, while multipath cancellation causes signal fading. Therefore, predicting multipath in wireless propagation environments is crucial for improving the service capabilities of communication systems. Multipath prediction involves predicting the potential multipath characteristics of a terminal device communicating with a network device at a specific spatial location, such as the number of paths, path strength, path angle, multipath delay spread, and multipath angular spread. One possible approach to multipath prediction is to model the real environment in a virtual physical world, recreating the size, position, and material of real-world objects as closely as possible. In this virtual physical world, network devices and terminal devices are placed at the locations where multipath prediction is desired, and ray tracing is used to simulate the multipath between them. However, ray tracing simulation methods suffer from slow speed and low accuracy, making them impractical.

[0003] Summary of the Invention

[0004] The present application provides a communication method and apparatus for improving the speed and accuracy of multipath prediction.

[0005] In a first aspect, a communication method is provided, wherein the executing subject of the method may be a terminal device or a chip, a chip system or a circuit located in the terminal device, and the method may be implemented by the following steps: receiving a first signal from a network device; determining first information, wherein the first information includes a receiving parameter of the first signal, or the first information includes a sending parameter and a receiving parameter of the first signal, and the first information is used to determine a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, wherein the preset geographical range is divided into multiple grid areas; and sending a measurement result of the first signal to the network device, wherein the measurement result includes the first information.

[0006] By sending data from the communication system to a network device, the embodiment of the present application enables the network device to train a multipath prediction model. This allows the multipath prediction model to learn the multipath patterns in the communication system's wireless propagation environment, thereby improving the accuracy and speed of multipath prediction. It can also infer multipath characteristics in unknown communication scenarios, avoiding repeated channel measurements. Furthermore, by deploying the multipath prediction model on the network device side and having the network device train the multipath prediction model, it is beneficial to improve the accuracy and speed of multipath prediction, and further contribute to improving the performance of the communication system.

[0007] In one possible design, the method further includes: determining a first reference point corresponding to the first signal based on the first information; determining a first grid area within a preset geographical range based on the first reference point corresponding to the first signal; and the measurement result of the first signal further including information indicating the first grid area. With this design, the grid area corresponding to the first signal can be used as training data for the multipath prediction model, thereby enabling the multipath prediction model to predict grid areas where multipath exists.

[0008] In one possible design, the method further includes: receiving second information from the network device, where the second information is used to indicate a method for determining the first reference point. This method can unify the method for determining the first reference point between the network device and the terminal device, thereby improving the accuracy of the multipath prediction model.

[0009] In one possible design, the method further includes receiving third information from the network device, the third information being used to indicate a method for dividing grid areas within a preset geographic area. This method allows the network device and the terminal device to unify the method for dividing grid areas, thereby enabling the network device and the terminal device to generate the same grid areas within the preset geographic range and assign the same identifier to each grid area, thereby improving the accuracy of the multipath prediction model.

[0010] In one possible design, the measurement result may not include the first information, and the measurement result may include indication information of the first grid area (e.g., an identifier of the first grid area). In the above approach, by reporting the first grid area, the multipath prediction model can predict the grid area where multipath exists. Not carrying the first information can save signaling overhead.

[0011] In one possible design, the transmission parameters of the first signal include a departure angle of the first signal.

[0012] In one possible design, the reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

[0013] In one possible design, the method further includes: receiving fourth information from the network device, the fourth information being used to indicate relevant information about multipath distribution within a preset geographical range during the first time period. This approach can assist the terminal device in beamforming decisions and addressing obstructions during a future period (i.e., the first time period), thereby improving communication performance.

[0014] In a second aspect, a communication method is provided, and the executor of the method can be a network device or a chip, chip system or circuit located in the network device. The method can be implemented by the following steps: sending a first signal to a terminal device; receiving a measurement result of the first signal from the terminal device, the measurement result including first information, the first information including a receiving parameter of the first signal, or the first information including a sending parameter and a receiving parameter of the first signal, the first information being used to determine a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, the preset geographical range being divided into multiple grid areas; training a multipath prediction model based on the measurement results, the multipath prediction model being used to predict the multipath characteristics of communication between the terminal device and the network device within the preset geographical range.

[0015] The embodiments of the present application train a multipath prediction model by sending data from the communication system to a network device. This allows the multipath prediction model to learn the multipath patterns in the communication system, thereby improving the accuracy and speed of multipath prediction. Furthermore, it can infer multipath characteristics in unknown communication scenarios, avoiding repeated channel measurements. Furthermore, by deploying the multipath prediction model on the network device side and having the network device train the multipath prediction model, it helps improve the accuracy and speed of multipath prediction, further contributing to improved communication system performance.

[0016] In one possible design, the measurement result of the first signal also includes indication information of the first grid area. Through the above design, the grid area corresponding to the first signal can be used as training data for the multipath prediction model, so that the multipath prediction model can predict the grid area where multipath exists.

[0017] In one possible design, the method further includes: sending third information to the terminal device, where the third information is used to indicate a division method of the grid areas in the preset geographic area. This method can unify the method for determining the first reference point between the network device and the terminal device, thereby improving the accuracy of the multipath prediction model.

[0018] In one possible design, the method further includes: sending second information to the terminal device, the second information being used to indicate a method for determining a first reference point of the first signal, the first reference point being used to be determined based on the first information, and the first reference point being used to determine a first grid area. The above method can unify the method for dividing grid areas for network devices and terminal devices, thereby enabling the network devices and terminal devices to generate the same grid area within a preset geographical range and having the same identifier for each grid area, which is beneficial to improving the accuracy of the multipath prediction model.

[0019] In one possible design, the first information includes receiving parameters of the first signal, and the method also includes: determining a second reference point corresponding to the first signal based on the sending parameters of the first signal; determining a second grid area within a preset geographical range based on the second reference point; determining a third grid area based on the first grid area and the second network area; and training a multipath prediction model based on the measurement results, including: training the multipath prediction model based on the first information in the measurement results and the third grid area.

[0020] If the first information includes reception parameters of the first signal but does not include transmission parameters of the first signal, that is, the terminal device has not obtained the beam configuration of the network device, in this case, the first grid area determined by the terminal device may be inaccurate. In the above method, the network device corrects the grid area determined by the terminal device based on the grid area determined by itself, which is conducive to improving the accuracy of the multipath prediction model.

[0021] In one possible design, the first information includes receiving parameters and sending parameters of the first signal, and the method also includes: determining a first reference point corresponding to the first signal based on the first information; determining a first grid area within a preset geographical range based on the first reference point; and training a multipath prediction model based on the measurement results, including: training the multipath prediction model based on the measurement results and the first grid area.

[0022] In the above method, the grid area corresponding to the first signal is determined by the network device, which can reduce signaling overhead compared to the method in which the terminal device reports the first grid area.

[0023] In one possible design, the transmission parameters of the first signal include a departure angle of the first signal.

[0024] In one possible design, the reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

[0025] In one possible design, the method further includes: determining the location information of the terminal device within a first time period based on the current location information of the terminal device and at least one historical location information, wherein the starting point of the first time period is no earlier than the current time; determining the multipath distribution within a preset geographical range within the first time period based on the location information of the terminal device within the first time period and a multipath prediction model; and sending fourth information to the terminal device, wherein the fourth information is used to indicate relevant information about the multipath distribution within the preset geographical range within the first time period. The above method can assist the terminal device in beam decision-making and occlusion response within a future period (i.e., the first time period), thereby improving communication performance.

[0026] In one possible design, the input data of the multipath prediction model includes at least one of the following: environmental information of a preset geographical range, location information of network equipment, and location information of terminal equipment; the output information of the multipath prediction model includes multipath information corresponding to each grid area within the preset geographical range.

[0027] In one possible design, the multipath information includes at least one of the following parameters for each path: confidence, signal departure angle, signal arrival angle, signal strength, or signal arrival time, where the confidence is used to indicate the probability of multipath existing in the corresponding grid area.

[0028] According to a third aspect, a communication method is provided, wherein the execution subject of the method may be a terminal device or a chip, a chip system or a circuit located in the terminal device, and the method may be implemented by the following steps: receiving a first signal from a network device; determining the sending parameters and receiving parameters of the first signal; determining a first grid area corresponding to a path corresponding to the first signal within a preset geographical range based on the sending parameters and receiving parameters of the first signal, wherein the preset geographical range is divided into multiple grid areas; training a multipath prediction model based on the sending parameters of the first signal, the receiving parameters of the first signal and the first grid area, wherein the multipath prediction model is used to predict the multipath characteristics of communication between the terminal device and the network device within the preset geographical range.

[0029] In the embodiments of the present application, the terminal device uses data from the communication system to train a multipath prediction model. This allows the multipath prediction model to learn the multipath patterns in the communication system, thereby improving the accuracy and speed of multipath prediction. Furthermore, the multipath characteristics can be inferred in unknown communication scenarios, avoiding repeated channel measurements. Furthermore, by deploying the multipath prediction model on the terminal device side and having the terminal device train the multipath prediction model, signaling overhead can be reduced.

[0030] In one possible design, a multipath prediction model is trained based on the sending parameters of the first signal, the receiving parameters of the first signal, and the first grid area, including: inputting environmental information of a preset geographical range, location information of network equipment, and location information of a terminal device into the multipath prediction model to obtain output data of the multipath prediction model, the output data including at least one of the following parameters for each path in each grid area within the preset geographical range: confidence, signal sending parameters, or signal receiving parameters, the confidence being used to indicate the probability that multipath exists in the corresponding grid area; comparing the sending parameters of the first signal, the receiving parameters of the first signal, and the first grid area with the output data of the multipath prediction model to obtain a comparison result; and adjusting the multipath prediction model based on the comparison result.

[0031] Through the above design, the multipath prediction model can learn the multipath patterns in the communication system, thereby improving the accuracy of multipath prediction. It can also infer the multipath characteristics in unknown communication scenarios and avoid repeated channel measurements.

[0032] In one possible design, the method further includes receiving environmental information of a preset geographical range and / or location information of the network device from the network device. The above design enables the terminal device to obtain input data for the multipath prediction model, which is conducive to improving the accuracy of multipath prediction.

[0033] In one possible design, a first grid area corresponding to a path corresponding to the first signal within a preset geographical range is determined based on the sending parameters and receiving parameters of the first signal, including: determining a reference point corresponding to the first signal based on the sending parameters and receiving parameters of the first signal; and determining the first grid area based on the reference point corresponding to the first signal.

[0034] In one possible design, the method further includes: receiving first information from a network device, where the first information is used to indicate a method for determining a reference point. This method can unify the method for determining the first reference point between the network device and the terminal device, thereby improving the accuracy of the multipath prediction model.

[0035] In one possible design, the method further includes receiving second information from a network device, the second information being used to indicate a method for dividing grid areas within a preset geographic area. This method allows the network device and the terminal device to unify the method for dividing grid areas, thereby enabling the network device and the terminal device to generate the same grid areas within the preset geographic range and assigning the same identifier to each grid area, thereby improving the accuracy of the multipath prediction model.

[0036] In one possible design, the transmission parameters include a signal departure angle.

[0037] In one possible design, the receiving parameters include at least one of the following: signal arrival angle, signal arrival time, or signal strength.

[0038] In a fourth aspect, a communication method is provided, wherein the executing subject of the method may be a network device or a chip, chip system or circuit located in the network device, and the method may be implemented by the following steps: sending a first signal to a terminal device; sending at least one of the following items to the terminal device: environmental information of a preset geographical range, location information of the network device, first information, or second information, wherein the first information is used to indicate a method for determining a reference point, and the reference point is used to determine a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, and the second information is used to indicate a method for dividing grid areas in a preset geographical area.

[0039] The above method sends environmental information of a preset geographical range and location information of network devices to the terminal device, so that the terminal device can obtain input data of the multipath prediction model, which is conducive to improving the accuracy of multipath prediction.

[0040] By sending the first information to the terminal device, the network device and the terminal device can unify the method of determining the first reference point, which is conducive to improving the accuracy of the multipath prediction model.

[0041] By sending the second information to the terminal device, the network device and the terminal device can unify the grid area division method, so that the network device and the terminal device can generate the same grid area within the preset geographical range, and each grid area has the same identifier, which is conducive to improving the accuracy of the multipath prediction model.

[0042] In a fifth aspect, the present application further provides a communication device, which is a terminal device or a chip in a terminal device. The communication device has the function of implementing any of the methods provided in the first or third aspects above. The communication device can be implemented in hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more units or modules corresponding to the above functions.

[0043] In one possible design, the communication device includes: a processor configured to support the communication device in executing the corresponding functions of the method execution subject in the method described above. The communication device may also include a memory, which may be coupled to the processor and stores the necessary program instructions and data for the communication device. Optionally, the communication device also includes a communication interface, which is used to support communication between the communication device and a device such as a network device, such as the transmission and reception of data or signals. Exemplarily, the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.

[0044] In one possible design, the communication device includes corresponding functional modules for implementing the steps in the above method. The functions can be implemented by hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more modules corresponding to the above functions.

[0045] In one possible design, the structure of the communication device includes a processing unit (or processing module) and a communication unit (or communication module), which can perform the corresponding functions in the above method examples. Please refer to the description of the method provided in the first aspect or the third aspect for details, which will not be repeated here. As an example, the processing unit may be a processor, and the communication unit may be a transceiver or a communication interface. It can be understood that if the device is a terminal device, the transceiver can be implemented by an antenna, a feeder, and a codec in the device, or if the device is a chip (system) or circuit provided in the terminal device, the communication unit may be a communication interface, a communication circuit, or a pin, etc. of the chip (system) or circuit.

[0046] In a sixth aspect, the present application further provides a communication device, which is a network device or a chip in a network device. The communication device has the function of implementing any of the methods provided in the second or fourth aspects above. The communication device can be implemented in hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more units or modules corresponding to the above functions.

[0047] In one possible design, the communication device includes: a processor configured to support the communication device in executing the corresponding functions of the method execution subject in the method described above. The communication device may also include a memory, which may be coupled to the processor and stores the necessary program instructions and data for the communication device. Optionally, the communication device also includes a communication interface, which is used to support communication between the communication device and a terminal device, such as the transmission and reception of data or signals. Exemplarily, the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.

[0048] In one possible design, the communication device includes corresponding functional modules for implementing the steps in the above method. The functions can be implemented by hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more modules corresponding to the above functions.

[0049] In one possible design, the structure of the communication device includes a processing unit (or processing module) and a communication unit (or communication module), which can perform the corresponding functions in the above method examples. Please refer to the description of the method provided in the second aspect or the fourth aspect for details, which will not be repeated here. As an example, the processing unit can be a processor, and the communication unit can be a transceiver or a communication interface. It can be understood that if the device is a network device, the transceiver can be implemented by an antenna, a feeder, and a codec in the device, or if the device is a chip (system) or circuit provided in the network device, the communication unit can be a communication interface, a communication circuit, or a pin, etc. of the chip (system) or circuit.

[0050] In the seventh aspect, a communication device is provided, comprising a processor and an interface circuit, the interface circuit being used to receive signals from other communication devices outside the communication device and transmit them to the processor or to send signals from the processor to other communication devices outside the communication device, the processor being used to implement the methods in the aforementioned first aspect or third aspect and any possible design through logic circuits or execution code instructions.

[0051] In an eighth aspect, a communication device is provided, comprising a processor and an interface circuit, the interface circuit being used to receive signals from other communication devices outside the communication device and transmit them to the processor or to send signals from the processor to other communication devices outside the communication device, the processor being used to implement the methods in the aforementioned second aspect or fourth aspect and any possible design through logic circuits or execution code instructions.

[0052] In the ninth aspect, a computer-readable storage medium is provided, which stores a computer program or instruction. When the computer program or instruction is executed by a processor, the method of the aforementioned first aspect, second aspect, third aspect, or fourth aspect and any possible design is implemented.

[0053] In the tenth aspect, a computer program product storing instructions is provided, which, when executed by a processor, implements the method in the aforementioned first aspect, second aspect, third aspect, or fourth aspect and any possible design.

[0054] In an eleventh aspect, a chip system is provided, comprising a processor and possibly a memory, for implementing the methods of the first, second, third, or fourth aspects, and any possible designs. The chip system may be composed solely of a chip, or may include a chip and other discrete components.

[0055] In a twelfth aspect, a communication system is provided, which includes the device described in the first aspect (such as a terminal device) and the device described in the second aspect (such as a network device).

[0056] In a thirteenth aspect, a communication system is provided, which includes the device described in the third aspect (such as a terminal device) and the device described in the fourth aspect (such as a network device).

[0057] The technical effects that can be achieved by the technical solutions of any of the above-mentioned fifth to thirteenth aspects can be described with reference to the technical effects that can be achieved by the technical solutions of the above-mentioned first, second, third or fourth aspects, and repetitions will not be repeated. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] FIG1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present application;

[0059] FIG2 is a schematic diagram of a grid area division according to an embodiment of the present application;

[0060] FIG3 is a schematic diagram of the structure of a multipath prediction model according to an embodiment of the present application;

[0061] FIG4 is a schematic diagram of the structure of a multipath prediction model according to an embodiment of the present application;

[0062] FIG5 is a schematic diagram of a training method of a multipath prediction model according to an embodiment of the present application;

[0063] FIG6 is a flow chart of a communication method according to an embodiment of the present application;

[0064] FIG7A is a schematic diagram of a grid area division according to an embodiment of the present application;

[0065] FIG7B is a schematic diagram of the first two dimensions of an output tensor of a multipath prediction model according to an embodiment of the present application;

[0066] FIG7C is a schematic diagram of an output tensor of a multipath prediction model according to an embodiment of the present application;

[0067] FIG8 is a flow chart of a communication method according to an embodiment of the present application;

[0068] FIG9 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0069] FIG10 is a schematic structural diagram of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0071] The technology provided in the embodiments of the present application can be applied to various communication systems, for example, a fourth generation (4G) communication system (such as a long term evolution (LTE) system), a fifth generation (5G) communication system, a world-wide interoperability for microwave access (WiMAX) or a wireless local area network (WLAN) system, or a fusion system of multiple systems, or a future communication system, such as a sixth generation (6G) communication system. Among them, the 5G communication system can also be called a new radio (NR) system.

[0072] Referring to Figure 1, a communication system is provided in an embodiment of the present application. The communication system includes a network device and six terminal devices, namely UE1 to UE6. In this communication system, UE1 to UE6 can send uplink data to the network device, and the network device can receive uplink data sent by UE1 to UE6. In addition, UE4 to UE6 can also form a sub-communication system. The network device can send downlink information to UE1, UE2, UE3, and UE5, and UE5 can send downlink information to UE4 and UE6 based on device-to-device (D2D) technology.

[0073] It should be noted that the number and type of each device in the communication system shown in Figure 1 are for illustration only. The embodiments of the present application are not limited to this. In actual applications, the communication system may also include more terminal devices, more network devices, and other network elements, for example, core network elements, network management equipment such as operation administration and maintenance (OAM) network elements, etc.

[0074] A network device may be a base station (BS). It may also be referred to as an access network device, an access node (AN), or a radio access node (RAN). Base stations may take various forms, such as macro base stations, micro base stations, relay stations, or access points. Network devices may connect to a core network (such as the LTE core network or the 5G core network) and provide wireless access services to terminal devices. The network equipment includes, for example, but is not limited to, at least one of the following: a base station in 5G, such as a transmission reception point (TRP) or a next generation node B (gNB), a network device in an open radio access network (O-RAN) or a module included in the network device, an evolved node B (eNB), a radio network controller (RNC), a node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (for example, a home evolved node B, or a home node B, HNB), a base band unit (BBU), a transmitting and receiving point (TRP), a transmitting point (TP), and / or a mobile switching center, etc. Alternatively, the network device may be a radio unit (RU), a centralized unit (CU), a distributed unit (DU), a centralized unit control plane (CU-CP) node, or a centralized unit user plane (CU-UP) node. Alternatively, the network device may be an in-vehicle device, a wearable device, or a network device in a future-evolved public land mobile network (PLMN). In some deployments of network devices, the network device may also be an open radio access network (ORAN) architecture, etc. For example, the network device shown in the embodiment of the present application may be an access network device in the ORAN, or a module in the access network device, etc.In the ORAN system, CU may also be referred to as open (O)-CU, DU may also be referred to as O-DU, CU-DU may also be referred to as O-CU-DU, CU-UP may also be referred to as O-CU-UP, and RU may also be referred to as O-RU.

[0075] In the embodiments of the present application, the communication device used to implement the network device function can be a network device, or a network device that has some of the functions of a network device, or a device that can support the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The communication device can be installed in the network device or used in combination with the network device. In the method of the embodiments of the present application, the communication device used to implement the network device function is described as an example of a network device.

[0076] Terminal equipment is also called terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), etc. Terminal equipment can be a device that provides voice and / or data connectivity to users. Terminal equipment can communicate with one or more core networks through network equipment. Terminal equipment can be deployed on land, including indoors, outdoors, handheld, and / or vehicle-mounted; it can also be deployed on the water (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.). Terminal equipment includes handheld devices with wireless connection capabilities, other processing equipment connected to wireless modems, or vehicle-mounted equipment, etc. Terminal equipment can be portable, pocket-sized, handheld, built-in computer or vehicle-mounted mobile devices. Some examples of terminal devices include: personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), wireless network cameras, mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices such as smart watches, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, terminals in vehicle networking systems, wireless terminals in self-driving, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities such as smart gas pumps, terminal devices on high-speed railways, and wireless terminals in smart homes such as smart speakers, smart coffee machines, and smart printers.

[0077] In the embodiments of the present application, the communication device for realizing the functions of the terminal device can be a terminal device, or a terminal device with some terminal functions, or a device capable of supporting the terminal device to realize the functions, such as a chip system. The communication device can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the technical solutions provided in the embodiments of the present application, the communication device for realizing the functions of the terminal device is described as an example of a terminal device.

[0078] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person skilled in the art will appreciate that, with the evolution of the network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems.

[0079] It should be noted that in this application, the phrases "sending information / data to A" and "sending information / data" simply indicate the direction of information / data transmission, with A being the destination. This does not limit "sending information / data to A" to transmission over an air interface. "Sending information / data to A" includes both direct and indirect transmission of information / data to A. Therefore, "sending information / data to A" can also be understood as the processing unit's communication interface "outputting information / data destined for A." Similarly, "sending information / data" can also be understood as "outputting information / data."

[0080] Similarly, "receiving information / data from A" and "receiving information / data" only indicate the direction of information / data transmission. "From A" means that the source of the information / data is A, including receiving information / data directly from A and indirectly receiving information / data from A. Therefore, "receiving information / data from A" can also be understood as the communication interface of the processing unit "inputting information / data from A"; similarly, "receiving information / data" can also be understood as "inputting information / data".

[0081] The following describes the technical features involved in the embodiments of this application.

[0082] Multipath propagation refers to the phenomenon in which a signal in a wireless propagation environment travels two or more paths before reaching the receiving antenna. Reflection and diffraction of signals from objects in the environment cause multipath, resulting in signals traveling along different paths experiencing different delays and phases. The receiving antenna receives the superposition of these multipath signals. Multipath delay spread leads to inter-symbol interference, while multipath cancellation causes signal fading. Therefore, predicting multipath in wireless propagation environments is crucial for improving the service capabilities of communication systems. Multipath prediction involves predicting the potential multipath characteristics of a terminal device communicating with a network device at a specific spatial location, such as the number of paths, path strength, path angle, multipath delay spread, and multipath angular spread. One possible approach to multipath prediction is to model the real environment in a virtual physical world, recreating the size, position, and material of real-world objects as closely as possible. In the virtual physical world, network devices and terminal devices are placed at the locations where multipath prediction is desired, and ray tracing is used to simulate the multipath between them. However, ray tracing simulation methods suffer from computational complexity and slow speed, and the simulated multipath can differ from the multipath in the real wireless propagation environment.

[0083] Based on this, embodiments of the present application provide a communication method and apparatus for improving the speed and accuracy of multipath prediction. The method and apparatus are based on the same inventive concept. Since the method and apparatus solve similar problems, the implementation of the apparatus and method can refer to each other, and any repetitions will not be repeated.

[0084] The embodiments of the present application use data actually collected by the communication system to learn the mapping relationship between the wireless propagation environment and the multipath in a data-driven manner. The data-driven approach described here can be to use neural networks, such as artificial intelligence (AI) / machine learning (ML), and other methods based on a large amount of real collected data to learn the hidden patterns in the data. Specifically, in the present application, the multipath characteristics of the wireless propagation environment are inferred by learning the mapping from the wireless propagation environment to the multipath through a neural network model. For ease of description, the above-mentioned neural network model will be referred to as a multipath prediction model below. It should be understood that the multipath prediction model is only an exemplary name for the model, and the present application does not limit the naming of the model.

[0085] Optionally, the multipath prediction model in the present application may also be trained in conjunction with data collected over non-air interfaces, such as simulation data. For example, the multipath prediction model may be pre-trained using data collected over non-air interfaces, such as simulation data, and then further trained based on real data collected. The aforementioned method of combining real data collected over the air interface with simulation data collected over non-air interface for training can reduce the computing and measurement overhead of the device compared to a method of training using only real data collected over the air interface.

[0086] The multipath prediction model in this application is introduced below.

[0087] The multipath prediction model can output multiple vectors, which can be mapped one by one to multiple grid areas divided within a preset geographic range. For example, the preset geographic range can be a predefined area, such as a rectangular area on the ground that is 300 meters long and 500 meters wide, or a circular area on the ground with a radius of 200 meters centered at a certain point, or an area surrounded by any geometric shape on the ground, etc. The preset geographic range covers as many potential propagation paths between network devices and terminal devices as possible. As shown in Figure 2, the preset geographic range is divided into a 3*3 grid, with a total of 9 grid cells. For each grid cell, the multipath prediction model can predict the characteristics of N paths, where N is an integer greater than 0. Therefore, if the preset geographic range is divided into X*Y grid cells, the multipath prediction model can predict the characteristics of up to X*Y*N paths, where X and Y are integers greater than 0, and X and Y can be the same or different, and are not specifically limited here. It should be noted that, here, only the case where the number of paths predicted by the multipath prediction model for each grid area is the same is used as an example for description, and this application does not limit whether the number of paths predicted for each grid area is the same.

[0088] Optionally, the preset geographical range can also be a three-dimensional spatial area, such as a rectangular area on the ground that is 300 meters long, 500 meters wide, and 30 meters high, or an area surrounded by any three-dimensional geometric shape. Similarly, the three-dimensional preset geographical range can be divided into X*Y*Z three-dimensional grid areas. X*Y represents the number of grid areas divided on the ground, and Z represents the number of grids divided in the height direction. Therefore, there are a total of X*Y*Z three-dimensional grid areas. The multipath prediction model can predict the characteristics of up to X*Y*Z*N paths, where X, Y, and Z are integers greater than 0, and X, Y, and Z can be the same or different, and are not specifically limited here. It should be noted that when Z is equal to 1, the preset geographical range is not distinguished in the height direction and can be regarded as a two-dimensional area. Here, only Z equal to one is used as an example for illustration, and this application does not limit the value of Z.

[0089] The multipath prediction model may adopt a multi-layer convolutional neural network (CNN) structure. For example, as shown in FIG3 , the multipath prediction model may adopt a six-layer CNN structure. It should be understood that the present application does not limit the neural network structure adopted by the multipath prediction model.

[0090] In the present application, the input data for the multipath prediction model may include at least one of the following: environmental information within a preset geographic range, location information of a network device, or location information of a terminal device. It may also include other parameters of the terminal device and / or network device, such as operating frequency and antenna orientation, which are not specifically limited herein. Exemplarily, the environmental information corresponds to the preset geographic range.

[0091] Environmental information may include the outlines of objects within a preset geographical range, such as building outlines, natural landscape outlines such as mountains and rivers, outlines of objects such as flowers, plants and trees, outlines of objects in the environment perceived by the network or terminal equipment, etc. It may also include information such as building materials, reflection coefficient of signals, or other information that affects signal transmission, which will not be listed here one by one.

[0092] Environmental information can be image data, such as aerial images, radar sensing images, satellite remote sensing images, terminal perception images, terminal-photographed images, network device perception images, etc. Alternatively, environmental information can also be data in the form of a schematic diagram, which can include information such as building layout and object outlines. Alternatively, environmental information can also be data in the form of a map, which can include relevant information such as roads, water systems, and trees. Alternatively, environmental information can also be multidimensional tensor data, where the dimensions of the tensor data can be c*x*y*z, where x, y, and z correspond to the maximum ranges of the x-axis, y-axis, and z-axis of the environment in space, respectively, and c corresponds to different types of environmental information. The values ​​of the tensor data are descriptions of environmental information at different spatial locations and different types. Alternatively, environmental information can also be point cloud data, and so on.

[0093] In one example, the location of the network device and / or terminal device can be reflected in the environmental information using latitude and longitude coordinates. The operating frequency and antenna orientation of the network device and / or terminal device can also be reflected in the environmental information. For example, the operating frequency can be represented by the size of a sector, and the sector orientation can represent the cell antenna orientation.

[0094] The output information of the multipath prediction model may include multipath information corresponding to each grid area within a preset geographical range. For example, the multipath information includes at least one of the following parameters for each path: confidence, departure angle, arrival angle, signal strength, arrival time (delay), etc.

[0095] The confidence level indicates the probability that the path exists. For example, the confidence level can range from 0 to 1. The higher the confidence level, the greater the likelihood that the path exists. For example, 0 indicates that the path does not exist, and 1 indicates that the path exists.

[0096] The departure angle may include at least one of the azimuth angle and the pitch angle; the departure angle may also be called the departure angle of the path, the departure angle of the path, the departure angle of the signal, the sending angle of the signal, the angle of the sending beam of the signal, etc.

[0097] The angle of arrival may include at least one of an azimuth angle and an elevation angle. The angle of arrival may also be referred to as the angle of arrival of a signal, the angle of arrival of a path, the receiving angle of a signal, the angle of a receiving beam of the signal, etc.

[0098] Signal strength can also be referred to as path signal strength, reference signal received power (RSRP), signal-to-noise ratio (SNR), path loss, etc. Time of arrival can also be referred to as signal arrival time, signal delay, or time of flight (TOF) of the signal on the propagation path.

[0099] The input data and output data of the multipath prediction model may be in the form of tensors, that is, multi-dimensional data.

[0100] In one possible implementation, when multiple paths exist within a grid area, assuming that the multipath prediction model predicts the characteristics of one path for the grid area (i.e., N=1), the multipath prediction model may predict the path with the highest signal strength within the grid area and discard other paths. Similarly, if the multipath prediction model predicts the characteristics of two paths for the grid area (i.e., N=2), the multipath prediction model may only predict the two paths with the highest signal strength within the grid area, and so on.

[0101] For ease of understanding, the multipath prediction model is illustrated by taking the structure shown in FIG3 as an example.

[0102] Assume that the input data of the multipath prediction model includes environmental information of a preset geographic range, location information of network devices, and location information of terminal devices. For example, taking 256*256 image data of the environmental information of the preset geographic range as an example, the input data of the multipath prediction model can be 256*256*3, where 3 represents three channels of environmental information of the preset geographic range, one channel representing the environmental information within the preset geographic range, one channel representing the location of the network device within the preset geographic range, and one channel representing the location of the terminal device within the preset geographic range.

[0103] Assuming that the preset geographic range is divided into 8*8 grid areas, i.e., X=8, Y=8, the multipath prediction model predicts the multipath information of one path (i.e., N=1) for each grid area. Taking the multipath information including five parameters, namely, confidence, departure angle, arrival angle, signal strength, and arrival time, as an example, the output data dimension of the multipath prediction model can be 8*8*5. It should be noted that the above example takes the departure angle including azimuth or elevation, and the arrival angle including azimuth or elevation as an example. If the departure angle includes both azimuth and elevation, and the arrival angle includes azimuth or elevation, the multipath information includes six parameters, namely, confidence, departure azimuth, departure elevation, arrival angle, signal strength, and arrival time, and the output data dimension of the multipath prediction model can be 8*8*6. Similarly, if the departure angle includes the two parameters of azimuth and pitch angle, the arrival angle can include the two parameters of azimuth and pitch angle. The multipath information includes 7 parameters, namely confidence, departure azimuth, departure pitch angle, arrival azimuth, arrival pitch angle, signal strength, and arrival time. The output data dimension of the multipath prediction model can be 8*8*7.

[0104] For example, the parameters of the first layer CNN of the structure shown in Figure 3 can be (3, 64, 7, 4, 3), where 3 is the number of input channels, 64 is the number of output channels, 7 is the size of the convolution kernel, 4 is the stride, and 3 is padding. After the input data is processed by the first layer CNN, the dimension becomes 64*64*64. The parameters of the second layer CNN can be (64, 128, 3, 2, 1), and after being processed by the second layer CNN, the dimension becomes 32*32*128. The parameters of the third layer CNN can be (128, 256, 3, 2, 1), and after being processed by the third layer CNN, the dimension becomes 16*16*256. The parameters of the fourth layer CNN can be (256, 256, 3, 2, 1), and after being processed by the fourth layer CNN, the dimension becomes 8*8*256. The parameters of the fifth layer CNN can be (256, 5, 3, 1, 1), and after being processed by the fifth layer CNN, the dimension becomes 8*8*5. In this way, after the multipath prediction model processes the 256*256 environmental information, it outputs 8*8 feature vectors (one-to-one corresponding to the 8*8 grid area). The length of each feature vector is 5, corresponding to the multipath characteristics of the corresponding grid area, namely confidence, departure angle, arrival angle, signal strength, and arrival time.

[0105] It should be understood that the above parameters are only examples. This application does not limit the neural network structure of the multipath prediction model, and may include convolutional neural networks, recurrent neural networks (RNN), residual networks (ResNet), and deformation networks (Transformer). Specifically, the number of network layers, the connection relationship between layers, and the parameters of each layer are not limited.

[0106] In the present application, the multipath prediction model can be trained by multiple sets of training data, and any set of training data may include input data and label data. Among them, the input data may include environmental information of a preset geographical range, location information of the network device, and location information of the terminal device. The label data may include information on the path corresponding to the reference signal (such as an uplink reference signal or a downlink reference signal, in order to facilitate the understanding of the solution, this application will be explained by taking the downlink reference signal as an example) transmitted by the network device to the terminal device, as well as information on the grid area corresponding to the path. The information on the path corresponding to the reference signal may include the confidence, departure angle, arrival angle, signal strength, arrival time, etc. of the path corresponding to the reference signal. Among them, the grid area corresponding to the path can be determined based on the information of the path, and the specific determination method will be explained below. For example, taking the downlink reference signal as an example, if the terminal device correctly parses the reference signal transmitted on a path, it can be understood that the path exists and the confidence is 1.

[0107] In one possible implementation, the label data can be processed into the same format as the output data of the multipath prediction model. For example, the output data of the multipath prediction model can be a three-dimensional tensor: X*Y*(N*M), where X*Y represents the division of the preset geographic area into X*Y grid areas, and N*M represents the output of N paths with a length of M, each of which is a feature vector. Each feature vector represents the multipath characteristics of the corresponding path, namely, confidence, departure angle, arrival angle, signal strength, and arrival time.

[0108] For example, the feature vectors of the N paths may be sorted according to predefined rules, such as by signal strength, such as sorting from smallest to largest signal strength, or sorting from largest to smallest signal strength, etc. This application does not specifically limit the predefined rules.

[0109] For a grid area with no paths or a grid area with fewer than N paths, the confidence values ​​in the vectors of the paths that do not exist in this grid area are all 0, indicating that the paths do not exist. The values ​​of other multipath characteristics can be arbitrary. For example, for a grid area with no paths, the confidence values ​​in all N feature vectors of this grid area are all 0, indicating that there are no paths in this grid area. The values ​​of other multipath characteristics can be arbitrary. For another example, for a grid area with n paths, where n is an integer greater than 0 and less than N, the confidence values ​​in all n feature vectors of this grid area are all 1, indicating that there are paths in this grid area. The values ​​of other multipath characteristics are the values ​​corresponding to the paths. If the confidence values ​​in all Nn feature vectors of this grid area are all 0, it indicates that there are no paths in this grid area. The values ​​of other multipath characteristics can be arbitrary. In one possible implementation, these n feature vectors can be sorted before the aforementioned Nn feature vectors during output. Furthermore, these n feature vectors can be sorted according to predefined rules.

[0110] By inputting input data into the multipath prediction model, the output data of the multipath prediction model is obtained. The output data of the multipath prediction model is compared with the label data, so that the multipath prediction model can learn the mapping from input to output through stochastic gradient descent (SGD). Exemplarily, the training of the multipath prediction model can first calculate the loss value of the output data and the label data, calculate the gradient based on this loss value, and update the parameters of the neural network using the stochastic gradient descent method. After multiple rounds of training and updates, the output data of the multipath prediction model and the label data become closer and closer, the loss value becomes smaller and smaller, and the multipath prediction model gradually converges. When the loss value meets the preset conditions, the training of the multipath prediction model is completed.

[0111] Taking the multipath prediction model as an example in the previous article, the output data dimension of the multipath prediction model is 8*8*5, that is, it outputs 8*8 feature vectors (corresponding to 8*8 grid areas), and the length of each feature vector is 5. The 5-dimensional feature vector can include: [Confidence, Angle of Departure (AOD), Angle of Arrival (AOA), Signal Strength (Strength), Time of Arrival (TOA)].

[0112] Exemplarily, the calculation of the loss value can be shown in the following formula, which consists of three parts. Loss1 is the mean-square error (MSE) of the output data corresponding to the grid area with a confidence level of 1 in the label data and the 4-dimensional feature vector of the label data (i.e., [departure angle AoD, arrival angle AoA, signal strength Strength, arrival time ToA]), where the number of samples input into the neural network each time is B, called the batch size (batch size) B. When calculating the mean square error, the mean square error is calculated for these B samples. Loss2 is the mean square error of the output data corresponding to the grid area with a confidence level of 1 in the label data and the confidence level of the label data. Loss3 is the mean square error of the output data corresponding to the grid area with a confidence level of 0 in the label data and the confidence level of the label data. The total loss value is the sum of these three loss values. The gradient is calculated based on the total loss value to complete the parameter update of the multipath prediction model.

[0113] loss1: MSE difference of ([AoD, AoA, Strength, ToA]|confidence==1);

[0114] loss2:MSE difference of(confidence|confidence==1);

[0115] loss3:MSE difference of(confidence|confidence==0);

[0116] loss=loss1+loss2+loss3.

[0117] This application can divide the preset geographical range into smaller and more numerous grid areas by increasing the X / Y values, thereby predicting more paths.

[0118] In one possible implementation, the last layer of the multipath prediction model may include multiple parallel modules, wherein each module corresponds to a division method of the grid area. For example, the last layer of the multipath prediction model includes three parallel modules, wherein the dimension of the output data of module 1 is 8*8*N*M, indicating that the preset geographical range is divided into 8*8 grid areas through the multipath prediction model, and each grid area outputs N feature vectors of length M, representing the multipath characteristics of the N paths in the grid area, namely, confidence, departure angle, arrival angle, signal strength, and arrival time. The dimension of the output data of module 2 is 3*3*N*M, indicating that the preset geographical range is divided into 3*3 grid areas through the multipath prediction model, and each grid area outputs N feature vectors of length M, representing the multipath characteristics of the N paths in the grid area, namely, confidence, departure angle, arrival angle, signal strength, and arrival time. The output data from module 3 has a dimension of 5*5*N*M, indicating that the pre-set geographic area is divided into 5*5 grid areas using the multipath prediction model. Each grid area outputs N feature vectors of length M, representing the multipath characteristics of the N paths within the grid area, namely, confidence, departure angle, arrival angle, signal strength, and arrival time. For example, combining the structure shown in Figure 3, the structure of the multipath prediction model can be shown in Figure 4.

[0119] Alternatively, the present application may also increase the value of N so that the multipath prediction model can predict more paths for each grid area, thereby avoiding some paths from being discarded, thereby improving the accuracy of multipath prediction.

[0120] In the embodiments of this application, the multipath prediction model can be either a single-sided model or a double-sided model, which is not specifically limited in this application. A single-sided model refers to a multipath prediction model deployed on either the network device or the terminal device side, while a double-sided model refers to a multipath prediction model where some modules are deployed on the network device side and others on the terminal device side. Deploying the multipath prediction model on the network device side is more conducive to improving the accuracy and speed of multipath prediction, and thus, the performance of the communication system, due to the greater processing power of the network device. The following describes the training process of the multipath prediction model using a single-sided model as an example.

[0121] The training data of the multipath prediction model can be data collected by the air interface, data collected by non-air interface, or data collected by the air interface and data collected by non-air interface, and this application does not make specific restrictions. Among them, air interface collection refers to the measurement data of signal reception and transmission between the terminal device and the network device, and non-air interface collection refers to simulation data or test field data, etc. Among them, the data collected by the air interface can improve the accuracy of multipath prediction compared with simulation data or test field data collected by non-air interface, which is beneficial for the terminal device or network device to update the multipath prediction model as needed to adapt to diverse and changing channel environments. In one example, data collected by non-air interface can be used to pre-train the multipath prediction model and provide an initial value for the neural network parameters and weights of the multipath prediction model. In this way, based on the pre-trained multipath prediction model, the model is fine-tuned using a small amount of data collected by the air interface, which allows the model to converge quickly and reduces the overhead of air interface collection data.

[0122] The multipath prediction model can be trained online or offline, and this application does not impose any specific restrictions. Online training refers to training the multipath prediction model each time some training data is collected. Offline training refers to training the multipath prediction model after sufficient training data has been collected.

[0123] Exemplarily, the training method of the multipath prediction model may be as shown in FIG5 .

[0124] The above describes the multipath prediction model. Deploying this model in a communication system requires collecting training data. This data is then used to train the multipath prediction model. Once the multipath prediction model is obtained, it can be used to predict multipath characteristics, helping to improve communication system performance. The following describes the training process and application scenarios of the multipath prediction model in communication systems.

[0125] Example 1:

[0126] Taking the multipath prediction model deployed on the network device side as an example, as shown in Figure 6, a communication method is provided in an embodiment of the present application. This method can be applied to the communication system shown in Figure 1. For ease of understanding, this embodiment is described from the perspectives of both the terminal device and the network device. It should be understood that this does not constitute a limitation of the present application. The present application has improvements on either side of the terminal device and the network device. Specifically, the method can be applied to the terminal device and the network device, or it can also be applied to the chip or chipset / chip system of the terminal device and the network device. The following is an example of application to the terminal device and the network device. The communication method may specifically include:

[0127] S601: A network device sends a first signal to a terminal device. Correspondingly, the terminal device receives the first signal from the network device.

[0128] In one possible implementation, the network device may transmit signals using beam scanning. The terminal device may also receive signals using beam scanning. For example, if the network device has 64 candidate beams and the terminal device has 4 candidate beams, a complete beam scan requires 256 passes, requiring the transmission of 256 signals. The first signal may be a signal transmitted by the network device using a transmit beam and received by the terminal device using a receive beam.

[0129] The beam can be considered a resource. Beamforming not only provides gain but also determines the departure and arrival angles of the propagation path based on the beam selected by the terminal device, thereby inferring the location of the terminal device.

[0130] Exemplarily, the first signal may be a channel state information reference signal (CSI-RS), or the first signal may be a positioning reference signal (PRS), or other reference signals, which are not specifically limited here.

[0131] S602: The terminal device determines the first information.

[0132] The first information includes reception parameters of the first signal. In one possible scenario, the terminal device does not obtain the relevant configuration of the network device for sending the first signal, such as the beam configuration. In this scenario, the first information may include reception parameters of the first signal but not transmission parameters of the first signal.

[0133] Alternatively, the first information includes the sending parameters and receiving parameters of the first signal. In one possible scenario, the terminal device pre-acquires the relevant configuration of the network device for sending the first signal, such as the beam configuration, etc. In this scenario, the first information includes the receiving parameters and sending parameters of the first signal.

[0134] Exemplarily, the transmission parameter of the first signal may include a departure angle of the first signal.

[0135] The reception parameter of the first signal may include at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

[0136] As an optional solution, the terminal device can determine the departure angle of the first signal by the angle of the transmit beam of the first signal, and determine the arrival angle of the first signal by the angle of the receive beam of the first signal. The angle of the transmit beam of the first signal can be determined based on the identifier of the transmit beam carried by the first signal and the beam configuration of the network device. The angle of the receive beam of the first signal can be determined based on the identifier of the receive beam of the first signal and the beam configuration of the terminal device.

[0137] In an exemplary description, when narrow beam scanning is used, if multiple paths can be distinguished in the time domain, only the path with the strongest signal strength (strongest tap) can be retained. The path corresponding to the first signal can be the path with the strongest signal, and the departure angle or arrival angle is the beam angle corresponding to the narrow beam. The "retaining the path with the strongest signal strength" means that only the characteristics of this path (such as arrival time, signal strength, departure angle, arrival angle, etc.) are used in subsequent calculations. When wide beam scanning is used, if multiple paths can be distinguished simultaneously in the angle domain and the time domain, the characteristics of each path (such as arrival time, signal strength, departure angle, arrival angle) can be calculated and retained for subsequent calculations.

[0138] The first information is used to determine a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, where the preset geographical range is divided into a plurality of grid areas.

[0139] The network device and the terminal device can unify the division method of the grid area within the preset geographical range, so that the network device and the terminal device can generate the same grid area within the preset geographical range and have the same ID for each grid area.

[0140] In one possible implementation, the division method of the grid areas within the preset geographical range may be determined by network equipment, terminal equipment, protocol definition, or preconfigured in other ways, which is not specifically limited here.

[0141] If the division method of the grid area is determined by the network device, the network device may send third information to the terminal device, where the third information is used to indicate the division method of the grid area in the preset geographical area.

[0142] In one possible implementation, the network device and the terminal device may pre-store the same division rule table, where the division rule table may include one or more division methods for grid areas and corresponding IDs. Thus, the network device may indicate the division method for the grid areas in a preset geographical area by indicating the IDs in the division rule table. The terminal device may obtain the corresponding division method for the grid areas by looking up the table.

[0143] For example, the division rule table may be as shown in Table 1.

[0144] Table 1

[0145] The network device can indicate the ID in Table 1 to the terminal device, and the terminal device can obtain the longitude and latitude range corresponding to the indicated ID and the number of divided grid areas by looking up the table, so that the grid areas can be divided according to the longitude and latitude directions. Optionally, the network device and the terminal device can evenly divide the grid areas according to the number of grid areas in the longitude and latitude directions. Non-uniform division schemes require additional instructions. Exemplarily, the network device and the terminal device can arrange the identification (ID) of the grid areas in a manner that first gradually increases from west to east along the longitude direction, and then gradually increases from north to south along the latitude direction. For example, as shown in Figure 7A.

[0146] S603: The terminal device sends a measurement result of the first signal to the network device. Correspondingly, the network device receives the measurement result from the terminal device.

[0147] The following two examples illustrate the contents of the measurement results.

[0148] Example 1: The measurement result of the first signal includes first information.

[0149] In this example, the training data of the multipath prediction model may include the first information. That is, the network device may use the first information as training data to train the multipath prediction model. Accordingly, the output data of the multipath prediction model includes parameters corresponding to the first information. For example, the first information includes one or more of the angle of arrival of the first signal, the time of arrival of the first signal, and the signal strength of the first signal. The corresponding output data of the multipath prediction model may include one or more of the angle of arrival, time of arrival, and signal strength of the signal. In other words, the multipath prediction model can predict one or more of the angle of arrival, time of arrival, and signal strength of the path.

[0150] The first grid area is described below in conjunction with two implementation methods of the first information.

[0151] Implementation method 1: The first information includes a reception parameter of the first signal and a transmission parameter of the first signal.

[0152] In Example 1, the terminal device may determine the first grid area based on the first information, i.e., the reception parameters of the first signal and the transmission parameters of the first signal, and report indication information of the first grid area to the network device. For example, the measurement result of the first signal may further include indication information of the first grid area (e.g., an identifier of the first grid area, etc.).

[0153] Exemplarily, the measurement result may include first information and information indicating the first grid area. Exemplarily, the first information may include: {Path 1: [DL-AoD#1, DL-AoA#1, DL-PRS-RSRP#1, ToA#1]}, where Path 1 is the path for transmitting the first signal, DL-AoD#1 is the departure angle of the first signal, DL-AoA#1 is the arrival angle of the first signal, DL-PRS-RSRP#1 is the signal strength of the first signal, and ToA#1 is the arrival time of the first signal. Assume that the first grid area is grid area 4, and the confidence level of grid area 4 is 1, indicating that a path exists in grid area 4.

[0154] Optionally, the terminal device may determine the first grid area in the following manner: the terminal device determines the first reference point corresponding to the first signal based on the first information; the terminal device determines the first grid area within a preset geographical range based on the first reference point corresponding to the first signal.

[0155] In the above method, the method for determining the first reference point may be indicated by the network device. For example, the network device may send second information to the terminal device, where the second information indicates the method for determining the first reference point. Alternatively, the method for determining the first reference point may be determined by the terminal device and indicated to the network device, or may be preconfigured in other ways.

[0156] In one possible implementation, the network device and the terminal device may pre-store the same determination method table, where the determination method table may include one or more reference point determination methods and corresponding IDs. Thus, the network device can indicate the determination method for the first reference point by indicating the ID in the determination method table. The terminal device can obtain the corresponding determination method by looking up the table.

[0157] For example, the determination method table may be as shown in Table 2.

[0158] Table 2

[0159] Among them, aoa x is the angle of arrival of the path identified as x, TOA x is the arrival time of the signal transmitted by the path marked as x, aod x is the departure angle of the path identified by x, BS pos Is the location of the network equipment, UE pos The location of the terminal device.

[0160] In Table 2, calculation method ID 1 indicates that starting from the terminal device's location, the route travels half the distance along the arrival angle to reach point A. Starting from the network device's location, the route travels half the distance along the departure angle to reach point B. The midpoint between points A and B is then taken to obtain the reference point of the path. Calculation method ID 2 considers only the network device's location and departure angle (this method can be applied in scenarios where the terminal device's location and arrival angle are not readily available). Starting from the network device's location, the route travels half the distance along the departure angle to reach point B, which serves as the reference point of the path.

[0161] The above method can unify the reference point determination method of network equipment and terminal equipment, which is beneficial to the accuracy of multipath prediction.

[0162] In the calculation method described in Table 2, when the terminal device determines the first grid area, it needs to know the position of the network device, the beam information of the network device and the position of the terminal device. The position of the network device and the beam information of the network device can be sent by the network device to the terminal device. The position of the terminal device can be obtained in a variety of ways, such as the terminal device is a positioning reference unit (PRU) device with a known position, or the terminal device can obtain position information through a global positioning system (GPS) and other devices. Alternatively, the terminal device can estimate its own position using the NR positioning method. Alternatively, the network device can calculate the position of the terminal device and send it to the terminal device. In order to obtain accurate multipath delay measurement results, the terminal device can also obtain synchronization and timing errors of the network device.

[0163] Optionally, the terminal device may further determine the first grid area by: determining grid area A based on the reception parameters of the first signal in the first information, determining grid area B based on the transmission parameters of the first signal in the first information, and determining the first grid area based on grid area A and grid area B. Grid area A and grid area B may be the same or different. The first grid area may be the same or different from grid area A. The first grid area may be the same or different from grid area B.

[0164] For example, the terminal device determines the corresponding grid area according to the reception parameters of signal 1, signal 2 and signal 3, as shown in Table 3.

[0165] Table 3

[0166] The terminal device determines the corresponding grid area according to the transmission parameters of signal 1, signal 2 and signal 3, as shown in Table 4.

[0167] Table 4

[0168] The terminal device can determine the grid areas corresponding to signals 1 to 3 based on the grid areas in Table 3 and Table 4, as shown in Table 5.

[0169] Table 5

[0170] In the above example, the first signal may be any one of signals 1 to 3.

[0171] If the first signal is signal 1, grid area A is the grid area determined based on the reception parameters of the first signal, as shown in Table 3, which is grid area 4. Grid area B is the grid area determined based on the transmission parameters of the first signal, as shown in Table 4, which is grid area 4. The first grid area is determined based on grid area A and grid area B, as shown in Table 5, which is grid area 4.

[0172] If the first signal is signal 2, grid area A is the grid area determined based on the reception parameters of the first signal, as shown in Table 3, and is grid area 2. Grid area B is the grid area determined based on the transmission parameters of the first signal, as shown in Table 4, and is grid area 8. The first grid area is determined based on grid area A and grid area B, as shown in Table 5, and is grid area 5.

[0173] If the first signal is signal 3, grid area A is the grid area determined based on the reception parameters of the first signal, as shown in Table 3, which is grid area 3. Grid area B is the grid area determined based on the transmission parameters of the first signal, as shown in Table 4, which is grid area 7. The first grid area is determined based on grid area A and grid area B, as shown in Table 5, which is grid area 6.

[0174] Exemplarily, the manner in which the terminal device determines grid area A based on the reception parameters of the first signal in the first information may be similar to the manner in which the terminal device determines the first grid area based on the reception parameters and transmission parameters of the first signal. The manner in which the terminal device determines grid area B based on the transmission parameters of the first signal in the first information may be similar to the manner in which the terminal device determines the first grid area based on the reception parameters and transmission parameters of the first signal. Please refer to the previous description for details and will not be repeated here.

[0175] For example, after the network device and the terminal device have completed all beam combination scans (for example, the network device has 64 beams and the terminal device has 4 beams, then a total of 64*4=256 scans have been performed, i.e., the first signal sent a reference signal 256 times and was measured 256 times), there are 3 beam combinations whose signal strength exceeds the preset threshold (i.e., there are only 3 paths in the 256 beam combinations, and the signal strength on the other paths is lower than the preset threshold). The terminal device obtains the departure angle and arrival angle of the above three beam combinations based on the IDs of the three beam combinations and the beam configuration. The terminal device determines the first grid area based on the departure angle and arrival angle of the above three beam combinations, the signal strength and arrival time of the first signal.

[0176] Optionally, the multipath prediction model can be trained using the measurement results of sending the first signal multiple times (for example, when all beams are fully scanned, that is, sending the first signal 256 times). Compared with training the multipath prediction model using the measurement results of sending the first signal once, the accuracy of the multipath prediction model can be improved.

[0177] In embodiment 2, the network device may determine the first grid area according to the first information, ie, the reception parameter of the first signal and the transmission parameter of the first signal.

[0178] Optionally, the way in which the network device determines the first grid area is similar to the way in which the terminal device determines the first grid area, and please refer to the above description for details.

[0179] In the two aforementioned embodiments, the training data for the multipath prediction model can also include information indicating the first grid area. That is, the network device can use the information indicating the first grid area as training data to train the multipath prediction model. Accordingly, the output data of the multipath prediction model also includes information about the grid area. That is, the multipath prediction model can also predict grid areas where paths exist. One possible implementation is to set N*M equal to 1, meaning the output dimensions of the multipath prediction model are X*Y*1. The output value represents whether X*Y grids contain multipath, ranging from 0 to 1. The closer the value is to 1, the more certain the grid is that multipath exists.

[0180] Implementation method 2: The first information includes the receiving parameters of the first signal, but does not include the sending parameters of the first signal, that is, the terminal device does not obtain the beam configuration of the network device (that is, does not obtain the sending parameters of the first signal).

[0181] In a first implementation, the terminal device may determine the first grid area according to the reception parameter of the first signal, and send the first grid area to the network device. For example, the measurement result of the first signal may further include indication information of the first grid area.

[0182] Optionally, the above implementation method can refer to the process in which the terminal device determines the grid area A according to the reception parameters of the first signal, which will not be repeated here.

[0183] In a second implementation, the network device may determine the first grid area according to a reception parameter of the first signal.

[0184] Optionally, the above implementation method can refer to the process in which the terminal device determines the grid area A according to the reception parameters of the first signal, which will not be repeated here.

[0185] In the two aforementioned implementations, the first grid area may be inaccurate. Based on this, as a further option, the network device can determine a second reference point corresponding to the first signal based on the transmission parameters of the first signal; determine a second grid area within a preset geographical range based on the second reference point; and determine a third grid area based on the first and second grid areas. The second grid area may be the same as or different from the first grid area. The third grid area may be the same as or different from the first grid area. The third grid area may be the same as or different from the second grid area.

[0186] Taking the first embodiment described above as an example, the terminal device determines the corresponding grid area according to the reception parameters of signal 1, signal 2 and signal 3, as shown in Table 3 above.

[0187] The network device determines the corresponding grid area according to the transmission parameters of signal 1, signal 2, and signal 3, as shown in Table 4 above.

[0188] The network device may determine the grid areas corresponding to signals 1 to 3 based on the grid areas determined by itself and the grid areas determined by the terminal device, as shown in Table 5 above.

[0189] In the above example, the first signal may be any one of signals 1 to 3.

[0190] If the first signal is signal 1, the first grid area is the grid area determined by the terminal device, as shown in Table 3, which is grid area 4. The second grid area is the grid area determined by the network device, as shown in Table 4, which is grid area 4. The third grid area is determined by the network device based on the first grid area and the second grid area, as shown in Table 5, which is grid area 4.

[0191] If the first signal is signal 2, the first grid area is the grid area determined by the terminal device, as shown in Table 3, which is grid area 2. The second grid area is the grid area determined by the network device, as shown in Table 4, which is grid area 8. The third grid area is determined by the network device based on the first grid area and the second grid area, as shown in Table 5, which is grid area 5.

[0192] If the first signal is signal 3, the first grid area is the grid area determined by the terminal device, as shown in Table 3, which is grid area 3. The second grid area is the grid area determined by the network device, as shown in Table 4, which is grid area 7. The third grid area is determined by the network device based on the first grid area and the second grid area, as shown in Table 5, which is grid area 6.

[0193] In a third implementation, the network device may determine the third grid area according to the sending parameters of the first signal and the first information.

[0194] Optionally, the process by which the network device determines the third grid area based on the sending parameters of the first signal and the first information is similar to the process by which the network device determines the first grid area based on the sending parameters of the first signal and the receiving parameters of the first signal, and is not repeated here.

[0195] Based on the above three implementations, when training the multipath prediction model, the network device can train the multipath prediction model based on the first information in the measurement results and the third grid area. That is, the training data of the multipath prediction model can also include indication information of the third grid area. In other words, the network device can also use the indication information of the third grid area as training data to train the multipath prediction model.

[0196] In Example 2, the measurement result of the first signal includes information indicating the first grid area. In this Example 2, the measurement result of the first signal may not include the first information. The specific method for determining the first grid area can be found in the relevant description of Example 1, Implementation Method 1, above, and will not be repeated here.

[0197] In some embodiments, the terminal device may send the measurement result in the following manner: the terminal device may associate the first information with the indication information of the first grid area, and then send the result to the network device through a radio resource control (RRC) message.

[0198] Exemplarily, the measurement results may also include layer 1 reference signal received power (L1-RSRP), time domain channel impulse response (CIR), channel frequency response (CFR), power delay profile (PDP), etc.

[0199] S604: The network device trains the multipath prediction model according to the measurement results. The specific training process can be found in the description of the multipath prediction model above, and will not be repeated here.

[0200] Optionally, after receiving the measurement result, the network device may convert the measurement result into the form of an output tensor of the multipath prediction model. For example, taking the measurement result including the content of Table 5 above as an example, the network device may convert the measurement result into data with a dimension of 3*3*5.

[0201] As shown in Figure 7B, the preset geographic range shown in Figure 7B includes three grid areas horizontally and three grid areas vertically, representing the first two dimensions of the output tensor of the multipath prediction model, namely 3*3. According to the measurement results shown in Table 5 above, the corresponding feature vectors of length 5 are filled in at the tensor positions numbered 4, 5, and 6 (corresponding to the grid areas marked 4, 5, and 6, respectively). For example, the feature vector at the tensor position numbered 4 (corresponding to the grid area marked 4) is [1, 120 / a, -60 / a, -80 / b, 300 / c]. Here, a, b, and c are preset values ​​used for data normalization to avoid values ​​that are too large. For example, a = 180, b = 100, and c = 1000. Similar processing is performed on the tensor positions numbered 5 and 6. Tensor positions without paths (e.g., positions 0, 1, 2, 3, 7, and 8) can be filled with [0, 0, 0, 0, 0], with the first value being 0 and the remaining four values ​​being arbitrary. Through the above processing, a 3*3*5 tensor can be obtained. For example, using a=180, b=100, and c=1000, the contents of Table 5 can be converted into the output tensor of the multipath prediction model, as shown in Figure 7C.

[0202] After the multipath prediction model training is completed, the network device can use the trained multipath prediction model to predict the multipath characteristics of the network device and the terminal device within a preset geographical range.

[0203] In one application scenario, network equipment can use a trained multipath prediction model to predict delay spread, beam direction, key grid areas, etc., and adjust communication parameters based on the output data of the multipath prediction model. For example, channel prediction, Doppler compensation, timing advance (TA) compensation, adjustment of reference signal measurement period, adjustment of the transmit / receive beam of the network equipment, adjustment of the transmit / receive beam of the terminal equipment, etc.

[0204] In a specific application scenario, a network device may determine the location information of a terminal device within a first time period based on the terminal device's current location information and at least one piece of historical location information, where the starting point of the first time period is no earlier than the current time. The network device determines the multipath distribution within a preset geographic range within the first time period based on the terminal device's location information within the first time period and a multipath prediction model. The network device sends fourth information to the terminal device, the fourth information being used to indicate relevant information about the multipath distribution within the preset geographic range within the first time period, such as information about each path in each grid area within the preset geographic range, identification of key grid areas, etc.

[0205] Illustratively, the aforementioned key grid area may be an identifier of a grid area within a preset geographic range where a path exists. Alternatively, the key grid area may be an identifier of a grid area within a preset geographic range where no path exists. Alternatively, the key grid area may be an identifier of a grid area within a preset geographic range where a path with a signal strength greater than a threshold exists, etc. Alternatively, the key grid area may be an identifier of a grid area within a preset geographic range where a path with a signal strength not greater than a threshold exists, etc. Alternatively, the key grid area may be an identifier of a grid area within a preset geographic range where a path with the strongest signal and / or an identifier of a grid area within a preset geographic range where a path with the weakest signal exists, etc.

[0206] The above method can assist the terminal device in beam decision-making and occlusion response in the future period (i.e., the first time period), thereby improving communication performance.

[0207] The embodiments of the present application collect data from commercial, diverse network deployment equipment and complex and diverse environments, so that the multipath prediction model has excellent performance, scenario scalability, and robustness to environmental changes.

[0208] Compared to ray tracing, the solution provided by the embodiments of this application offers faster prediction speeds. Furthermore, ray tracing is based on a virtual environment, and the difference between it and the real environment is affected by modeling accuracy. Inputting environmental information into a neural network (i.e., a multipath prediction model) in the form of tensors can ensure the integrity of environmental information as much as possible.

[0209] In addition, by utilizing environmental prior information (i.e., collected training data), the efficiency of the communication system can be improved. By fully utilizing the objective laws of the physical world, the neural network (i.e., the multipath prediction model) can learn these laws and infer the multipath characteristics in unknown scenarios, avoiding repeated channel measurements and pre-adjusting network parameters, thus realizing the replacement of passive networks with active networks.

[0210] In addition, by deploying the multipath prediction model on the network device side and having the network device train the multipath prediction model, it is beneficial to improve the accuracy and prediction speed of multipath prediction, and is more conducive to improving the performance of the communication system.

[0211] Example 2: The difference between Example 2 and Example 1 is that in Example 1, the multipath prediction model is deployed on the network device side. After the terminal device collects relevant data of the first signal (such as the first information, etc.), it sends the data to the network device, and the network device trains the multipath prediction model. In Example 2, the multipath prediction model is deployed on the terminal device side. After the terminal device collects relevant data of the first signal (such as the first information, etc.), the multipath prediction model is trained without sending the data to the network device. In addition, in Example 1, since the network device can obtain environmental information of a preset geographical range, the location of the network device, and other information, it can directly obtain input data for the multipath prediction model. In Example 2, the terminal device can obtain environmental information of a preset geographical range, the location of the network device, and other information from the network device, thereby obtaining input data for the multipath prediction model.

[0212] Taking the multipath prediction model deployed on the terminal device side as an example, as shown in Figure 8, a communication method is provided in an embodiment of the present application. This method can be applied to the communication system shown in Figure 1. For ease of understanding, this embodiment is described from the perspectives of both the terminal device and the network device. It should be understood that this does not constitute a limitation of the present application. The present application has improvements on either side of the terminal device and the network device. Specifically, the method can be applied to the terminal device and the network device, or it can also be applied to the chip or chipset / chip system of the terminal device and the network device. The following is an example of application to the terminal device and the network device. The communication method may specifically include:

[0213] S801: A network device sends a first signal to a terminal device. Correspondingly, the terminal device receives the first signal from the network device.

[0214] For details, please refer to the relevant instructions of S601, which will not be repeated here.

[0215] S802: The terminal device determines the sending parameters and receiving parameters of the first signal.

[0216] For details, please refer to the relevant description of the terminal device determining the sending parameters and receiving parameters of the first signal in S602, which will not be repeated here.

[0217] S803, the terminal device determines a first grid area corresponding to a path corresponding to the first signal within a preset geographical range according to the sending parameters and receiving parameters of the first signal, where the preset geographical range is divided into multiple grid areas.

[0218] In one implementation, the terminal device can determine the first grid area in the following manner: the terminal device determines the first reference point corresponding to the first signal based on the sending parameters and receiving parameters of the first signal; the terminal device determines the first grid area within a preset geographical range based on the first reference point corresponding to the first signal.

[0219] In the above manner, the first test point may be determined by the network device, or may be determined by the terminal device and indicated to the network device, or may be pre-configured in other ways.

[0220] Among them, the implementation scheme of the method for determining the first test point indicated by the network device to the terminal device can be specifically referred to the relevant description in the method described in Figure 6.

[0221] Optionally, in this manner, the network device and the terminal device may unify the division method of the grid areas within the preset geographical range, so that the network device and the terminal device may generate the same grid areas within the preset geographical range and have the same ID for each grid area.

[0222] In one possible implementation, the division method of the grid areas within the preset geographic range may be determined by the network device, may be determined by the terminal device, may be defined by a protocol, or may be pre-configured in other ways, without specific limitation herein. If the division method of the grid areas is determined by the network device, the network device indicates the division method of the grid areas to the terminal device. For specific indication methods, please refer to the relevant description of the method described in FIG6 .

[0223] S804: The terminal device trains the multipath prediction model according to the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area. The specific training process can be found in the description of the multipath prediction model above, and will not be repeated here.

[0224] Optionally, the terminal device can obtain environmental information of a preset geographical range and / or location information of the network device from the network device, and the obtained environmental information of the preset geographical range and / or location information of the network device can be used as input data of the multipath prediction model to train the multipath prediction model.

[0225] After the multipath prediction model training is completed, the terminal device can use the trained multipath prediction model to predict the multipath characteristics of the network device and the terminal device within a preset geographical range. Specific application scenarios can refer to the relevant descriptions in the embodiments, which will not be repeated here.

[0226] The embodiments of the present application collect data from commercial, diverse network deployment equipment and complex and diverse environments, so that the multipath prediction model has excellent performance, scenario scalability, and robustness to environmental changes.

[0227] Compared to ray tracing, the solution provided by the embodiments of this application offers faster prediction speeds. Furthermore, ray tracing is based on a virtual environment, and the difference between it and the real environment is affected by modeling accuracy. Inputting environmental information into a neural network (i.e., a multipath prediction model) in the form of tensors can ensure the integrity of environmental information as much as possible.

[0228] In addition, by utilizing environmental prior information (i.e., collected training data), the efficiency of the communication system can be improved. By fully utilizing the objective laws of the physical world, the neural network (i.e., the multipath prediction model) can learn these laws and infer the multipath characteristics in unknown scenarios, avoiding repeated channel measurements and pre-adjusting network parameters, thus realizing the replacement of passive networks with active networks.

[0229] In addition, by deploying the multipath prediction model on the terminal device side and having the terminal device train the multipath prediction model, signaling overhead can be saved.

[0230] Based on the same inventive concept as the method embodiment, an embodiment of the present application provides a communication device, the structure of which may be as shown in FIG. 9 , including a communication unit 301 and a processing unit 302 .

[0231] In one embodiment, the communication device can be specifically used to implement the method executed by the terminal device in the embodiment of Figure 6. The device can be the terminal device itself, or it can be a chip or chipset in the terminal device, or a part of the chip used to execute the function of the relevant method. Among them, the communication unit 301 is used to receive a first signal from the network device; the processing unit 302 is used to determine the first information, the first information includes the receiving parameters of the first signal, or the first information includes the sending parameters and the receiving parameters of the first signal, and the first information is used to determine the first grid area corresponding to the path corresponding to the first signal within a preset geographical range, and the preset geographical range is divided into multiple grid areas; the communication unit 301 is also used to send the measurement result of the first signal to the network device, and the measurement result includes the first information.

[0232] Optionally, the processing unit 302 is further used to: determine a first reference point corresponding to the first signal based on the first information; determine a first grid area within a preset geographical range based on the first reference point corresponding to the first signal; and the measurement result of the first signal also includes indication information of the first grid area.

[0233] Optionally, the communication unit 301 is further used to: receive second information from the network device, where the second information is used to indicate a method for determining the first reference point.

[0234] Optionally, the communication unit 301 is further configured to: receive third information from a network device, where the third information is used to indicate a division method of grid areas in a preset geographical area.

[0235] Exemplarily, the transmission parameter of the first signal includes a departure angle of the first signal.

[0236] Exemplarily, the reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

[0237] Optionally, the communication unit 301 is further configured to: receive fourth information from the network device, where the fourth information is used to indicate relevant information about multipath distribution within a preset geographical range within the first time period.

[0238] In one embodiment, the communication device can be specifically used to implement the method executed by the network device in the embodiment of Figure 6. The device can be the network device itself, or it can be a chip or chipset in the network device, or a part of the chip used to execute the function of the relevant method. Among them, the communication unit 301 is used to send a first signal to the terminal device; and receive the measurement result of the first signal from the terminal device, the measurement result includes first information, the first information includes the receiving parameters of the first signal, or the first information includes the sending parameters and the receiving parameters of the first signal, the first information is used for the first grid area corresponding to the path corresponding to the first signal within the preset geographical range, and the preset geographical range is divided into multiple grid areas; the processing unit 302 is used to train the multipath prediction model according to the measurement results, and the multipath prediction model is used to predict the multipath characteristics of the terminal device and the network device communicating within the preset geographical range.

[0239] Exemplarily, the measurement result of the first signal further includes indication information of the first grid area.

[0240] Optionally, the communication unit 301 is also used to: send second information to the terminal device, the second information is used to indicate a method for determining the first reference point of the first signal, the first reference point is used to be determined based on the first information, and the first reference point is used to determine the first grid area.

[0241] Optionally, the communication unit 301 is further used to: send third information to the terminal device, where the third information is used to indicate a division method of grid areas in the preset geographical area.

[0242] Optionally, the first information includes receiving parameters of the first signal, and the processing unit 302 is further used to: determine a second reference point corresponding to the first signal based on the sending parameters of the first signal; determine a second grid area within a preset geographical range based on the second reference point; determine a third grid area based on the first grid area and the second network area; when training the multipath prediction model based on the measurement results, the processing unit 302 is specifically used to: train the multipath prediction model based on the first information in the measurement results and the third grid area.

[0243] Optionally, the first information includes receiving parameters and sending parameters of the first signal, and the processing unit 302 is also used to: determine the first reference point corresponding to the first signal based on the first information; determine the first grid area within a preset geographical range based on the first reference point; the processing unit 302, when training the multipath prediction model based on the measurement results, is specifically used to: train the multipath prediction model based on the measurement results and the first grid area.

[0244] Exemplarily, the transmission parameter of the first signal includes a departure angle of the first signal.

[0245] Exemplarily, the reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

[0246] Optionally, the processing unit 302 is also used to: determine the location information of the terminal device within a first time period based on the current location information of the terminal device and at least one historical location information, where the starting point of the first time period is not earlier than the current time; and determine the multipath distribution within a preset geographical range within the first time period based on the location information of the terminal device within the first time period and the multipath prediction model.

[0247] The communication unit 301 is further configured to send fourth information to the terminal device, where the fourth information is used to indicate relevant information about multipath distribution within a preset geographical range within a time period.

[0248] Exemplarily, the input data of the multipath prediction model includes at least one of the following: environmental information of a preset geographical range, location information of network equipment, and location information of terminal equipment; the output information of the multipath prediction model includes multipath information corresponding to each grid area within the preset geographical range.

[0249] Exemplarily, the multipath information includes at least one of the following parameters for each path: confidence, signal departure angle, signal arrival angle, signal strength, or signal arrival time, where the confidence is used to indicate the probability of multipath existing in the corresponding grid area.

[0250] In one embodiment, the communication device can be specifically used to implement the method executed by the terminal device in the embodiment of Figure 8. The device can be the terminal device itself, or it can be a chip or chipset in the terminal device, or a part of the chip used to execute the function of the relevant method. Among them, the communication unit 301 is used to receive a first signal from the network device; the processing unit 302 is used to determine the transmission parameters and reception parameters of the first signal; and, based on the transmission parameters and reception parameters of the first signal, determine the first grid area corresponding to the path corresponding to the first signal within a preset geographical range, where the preset geographical range is divided into multiple grid areas; and, based on the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area, train a multipath prediction model, and the multipath prediction model is used to predict the multipath characteristics of the terminal device and the network device when communicating within the preset geographical range.

[0251] The processing unit 302, when training the multipath prediction model based on the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area, can be specifically used to: input environmental information of a preset geographical range, location information of the network device, and location information of the terminal device into the multipath prediction model to obtain output data of the multipath prediction model, where the output data includes at least one of the following parameters for each path in each grid area within the preset geographical range: confidence, signal transmission parameters, or signal reception parameters, where the confidence is used to indicate the probability that multipath exists in the corresponding grid area; compare the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area with the output data of the multipath prediction model to obtain a comparison result; and adjust the multipath prediction model based on the comparison result.

[0252] Optionally, the communication unit 301 is further configured to receive environmental information of a preset geographical range from the network device and / or location information of the network device.

[0253] Optionally, the processing unit 302, when determining the first grid area corresponding to the path corresponding to the first signal within a preset geographical range based on the sending parameters and receiving parameters of the first signal, is specifically used to: determine the reference point corresponding to the first signal based on the sending parameters and receiving parameters of the first signal; and determine the first grid area based on the reference point corresponding to the first signal.

[0254] Optionally, the communication unit 301 is further used to: receive first information from a network device, where the first information is used to indicate a method for determining a reference point.

[0255] Optionally, the communication unit 301 is further configured to: receive second information from a network device, where the second information is used to indicate a division method of grid areas in a preset geographical area.

[0256] Exemplarily, the transmission parameters include a signal departure angle.

[0257] Exemplarily, the receiving parameter includes at least one of the following: signal arrival angle, signal arrival time, or signal strength.

[0258] In one embodiment, the communication device can be specifically used to implement the method executed by the network device in the embodiment of Figure 8. The device can be the network device itself, or a chip or chipset in the network device, or a part of the chip used to execute the function of the relevant method. Among them, the communication unit 301 is used to communicate with the terminal device; the processing unit 302 is used to send a first signal to the terminal device through the communication unit 301; and at least one of the following is sent to the terminal device through the communication unit 301: environmental information of a preset geographical range, location information of the network device, first information, or second information, the first information is used to indicate a method for determining a reference point, the reference point is used to determine a first grid area corresponding to a path corresponding to the first signal within the preset geographical range, and the second information is used to indicate a method for dividing grid areas in the preset geographical area.

[0259] The division of modules in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods. In addition, the functional modules in the various embodiments of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. It is understood that the functions or implementations of the various modules in the embodiments of the present application may be further described with reference to the relevant descriptions of the method embodiments.

[0260] In one possible embodiment, a communication device may be as shown in FIG10 . The device may be a communication device or a chip within the communication device, wherein the communication device may be a terminal device or a network device in the above embodiments. The device includes a processor 401 and a communication interface 402, and may also include a memory 403. The processing unit 302 may be the processor 401. The communication unit 301 may be the communication interface 402. Optionally, the processor 401 and the memory 403 may be integrated.

[0261] The processor 401 may be a CPU, a digital processing unit, or the like. The communication interface 402 may be a transceiver, an interface circuit such as a transceiver circuit, or a transceiver chip, or the like. The apparatus further includes a memory 403 for storing programs executed by the processor 401. The memory 403 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory (volatile memory), such as a random-access memory (RAM). The memory 403 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0262] The processor 401 is used to execute the program code stored in the memory 403, specifically to execute the actions of the processing unit 302, which will not be described in detail in this application. The communication interface 402 is specifically used to execute the actions of the communication unit 301, which will not be described in detail in this application.

[0263] The specific connection medium between the communication interface 402, processor 401, and memory 403 is not limited in the embodiments of the present application. In Figure 10, the memory 403, processor 401, and communication interface 402 are connected via bus 404. The bus is represented by a bold line in Figure 10. The connection methods between other components are only for schematic illustration and are not limiting. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, only one bold line is used in Figure 10, but this does not mean that there is only one bus or one type of bus.

[0264] An embodiment of the present invention further provides a computer-readable storage medium for storing computer software instructions required to be executed by the above-mentioned processor, which includes a program required to be executed by the above-mentioned processor.

[0265] An embodiment of the present application also provides a communication system, including a communication device for implementing the terminal device function in the embodiment of Figure 6 and a communication device for implementing the network device function in the embodiment of Figure 6.

[0266] An embodiment of the present application also provides a communication system, including a communication device for implementing the terminal function in the embodiment of Figure 8 and a communication device for implementing the network device function in the embodiment of Figure 8.

[0267] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0268] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each flow and / or box in the flow chart and / or block diagram, as well as the combination of the flow chart and / or box in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more flow charts and / or one or more boxes in the block diagram.

[0269] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0270] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0271] Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of protection of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A communication method, characterized in that: The method comprises: receiving a first signal from a network device; Determine first information, where the first information includes a receiving parameter of the first signal, or the first information includes a sending parameter and a receiving parameter of the first signal, and the first information is used to determine a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, where the preset geographical range is divided into a plurality of grid areas; A measurement result of the first signal is sent to the network device, where the measurement result includes the first information.

2. The method according to claim 1, characterized in that The method further comprises: determining a first reference point corresponding to the first signal according to the first information; Determine the first grid area within the preset geographical range according to the first reference point corresponding to the first signal; The measurement result of the first signal also includes indication information of the first grid area.

3. The method according to claim 2, characterized in that The method further comprises: Second information is received from the network device, where the second information is used to indicate a method for determining the first reference point.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Receive third information from the network device, where the third information is used to indicate a division method of grid areas in the preset geographical area.

5. The method according to any one of claims 1 to 4, characterized in that: The transmission parameters of the first signal include a departure angle of the first signal.

6. The method according to any one of claims 1 to 5, characterized in that: The reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Fourth information is received from the network device, where the fourth information is used to indicate relevant information about multipath distribution within the preset geographical range within a first time period.

8. A communication method, characterized in that: The method comprises: Sending a first signal to a terminal device; Receiving a measurement result of the first signal from the terminal device, the measurement result comprising first information, the first information comprising a reception parameter of the first signal, or the first information comprising a transmission parameter and a reception parameter of the first signal, the first information being used for a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, the preset geographical range being divided into a plurality of grid areas; A multipath prediction model is trained according to the measurement results, and the multipath prediction model is used to predict multipath characteristics of the terminal device and the network device communicating within the preset geographical range.

9. The method according to claim 8, characterized in that The measurement result of the first signal also includes indication information of the first grid area.

10. The method according to claim 8 or 9, characterized in that The method further comprises: Sending second information to the terminal device, the second information is used to indicate a method for determining a first reference point of the first signal, the first reference point is used to be determined based on the first information, and the first reference point is used to determine the first grid area.

11. The method according to any one of claims 8 to 10, characterized in that: The method further comprises: Sending third information to the terminal device, where the third information is used to indicate a division method of grid areas in the preset geographical area.

12. The method according to any one of claims 9 to 11, characterized in that: The first information includes a reception parameter of the first signal, and the method further includes: determining a second reference point corresponding to the first signal according to a sending parameter of the first signal; Determine a second grid area within the preset geographical range according to the second reference point; Determine a third grid area according to the first grid area and the second network area; The training of the multipath prediction model according to the measurement result includes: A multipath prediction model is trained according to the first information in the measurement result and the third grid area.

13. The method according to claim 8, characterized in that The first information includes a receiving parameter and a sending parameter of the first signal, and the method further includes: determining a first reference point corresponding to the first signal according to the first information; Determine the first grid area within the preset geographical range according to the first reference point; The training of the multipath prediction model according to the measurement result includes: The multipath prediction model is trained according to the measurement result and the first grid area.

14. The method according to any one of claims 8 to 13, characterized in that: The transmission parameters of the first signal include a departure angle of the first signal.

15. The method according to any one of claims 8 to 14, characterized in that: The reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

16. The method according to any one of claims 8 to 15, characterized in that: The method further comprises: Determine the location information of the terminal device within a first time period according to the current location information of the terminal device and at least one historical location information, where the starting point of the first time period is not earlier than the current time; Determine the multipath distribution within the preset geographical range within the first time period according to the location information of the terminal device within the first time period and the multipath prediction model; Sending fourth information to the terminal device, where the fourth information is used to indicate relevant information about the multipath distribution within the preset geographical range within the first time period.

17. The method according to any one of claims 8 to 16, characterized in that: The input data of the multipath prediction model includes at least one of the following: environmental information of the preset geographical range, location information of the network device, and location information of the terminal device; The output information of the multipath prediction model includes multipath information corresponding to each grid area within the preset geographical range.

18. The method according to claim 17, characterized in that The multipath information includes at least one of the following parameters for each path: confidence, signal departure angle, signal arrival angle, signal strength, or signal arrival time, and the confidence is used to indicate the probability of multipath existing in the corresponding grid area.

19. A communication method, characterized in that: The method comprises: receiving a first signal from a network device; Determining sending parameters and receiving parameters of the first signal; Determine, according to the sending parameter and the receiving parameter of the first signal, a first grid area corresponding to the path corresponding to the first signal within a preset geographical range, wherein the preset geographical range is divided into a plurality of grid areas; A multipath prediction model is trained according to the transmission parameters of the first signal, the reception parameters of the first signal and the first grid area, and the multipath prediction model is used to predict the multipath characteristics of the terminal device and the network device communicating in the preset geographical range.

20. The method of claim 19, wherein: The training of the multipath prediction model according to the sending parameter of the first signal, the receiving parameter of the first signal and the first grid area includes: Inputting the environmental information of the preset geographical range, the location information of the network device, and the location information of the terminal device into the multipath prediction model to obtain output data of the multipath prediction model, wherein the output data includes at least one of the following parameters of each path in each grid area within the preset geographical range: confidence, a signal transmission parameter, or a signal reception parameter, wherein the confidence is used to indicate the probability that a multipath exists in the corresponding grid area; Comparing the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area with the output data of the multipath prediction model to obtain a comparison result; The multipath prediction model is adjusted according to the comparison result.

21. The method according to claim 19 or 20, characterized in that The method further comprises: Receive environmental information of the preset geographical range and / or location information of the network device from the network device.

22. The method according to any one of claims 19 to 21, characterized in that: The determining, according to the sending parameter and the receiving parameter of the first signal, a first grid area corresponding to the path corresponding to the first signal within the preset geographical range includes: Determining a reference point corresponding to the first signal according to a sending parameter and a receiving parameter of the first signal; The first grid area is determined according to a reference point corresponding to the first signal.

23. The method of claim 22, wherein: The method further comprises: First information is received from the network device, where the first information is used to indicate a method for determining the reference point.

24. The method according to any one of claims 19 to 23, characterized in that The method further comprises: Second information is received from the network device, where the second information is used to indicate a division method of grid areas in the preset geographical area.

25. The method according to any one of claims 19 to 24, characterized in that The transmission parameters include a signal departure angle.

26. The method according to any one of claims 19 to 25, characterized in that The receiving parameter includes at least one of the following: signal arrival angle, signal arrival time, or signal strength.

27. A communication method, characterized in that: The method comprises: Sending a first signal to a terminal device; At least one of the following is sent to the terminal device: environmental information of a preset geographical range, location information of the network device, first information, or second information, wherein the first information is used to indicate a method for determining a reference point, the reference point is used to determine a first grid area corresponding to a path corresponding to the first signal within the preset geographical range, and the second information is used to indicate a method for dividing grid areas in the preset geographical area.

28. A communication device, characterized in that: The device comprises: A communication unit, configured to receive a first signal from a network device; a processing unit, configured to determine first information, wherein the first information includes a receiving parameter of the first signal, or the first information includes a sending parameter and a receiving parameter of the first signal, and the first information is used to determine the first signal a first grid area corresponding to the path corresponding to the number within a preset geographical range, wherein the preset geographical range is divided into a plurality of grid areas; The communication unit is further used to send a measurement result of the first signal to the network device, where the measurement result includes the first information.

29. The device according to claim 28, characterized in that The processing unit is also used for: determining a first reference point corresponding to the first signal according to the first information; Determine the first grid area within the preset geographical range according to the first reference point corresponding to the first signal; The measurement result of the first signal also includes indication information of the first grid area.

30. The device according to claim 29, characterized in that The communication unit is also used for: Second information is received from the network device, where the second information is used to indicate a method for determining the first reference point.

31. The device according to any one of claims 28 to 30, characterized in that The communication unit is also used for: Receive third information from the network device, where the third information is used to indicate a division method of grid areas in the preset geographical area.

32. The device according to any one of claims 28 to 31, characterized in that The transmission parameters of the first signal include a departure angle of the first signal.

33. The device according to any one of claims 28 to 32, characterized in that The reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

34. The device according to any one of claims 28 to 33, characterized in that The communication unit is also used for: Fourth information is received from the network device, where the fourth information is used to indicate relevant information about multipath distribution within the preset geographical range within a first time period.

35. A communication device, characterized in that: The device comprises: A communication unit, configured to send a first signal to a terminal device; and receiving a measurement result of the first signal from the terminal device, the measurement result comprising first information, the first information comprising a reception parameter of the first signal, or the first information comprising a transmission parameter and a reception parameter of the first signal, the first information being used for a first grid area corresponding to a path corresponding to the first signal within a preset geographical range, the preset geographical range being divided into a plurality of grid areas; A processing unit is used to train a multipath prediction model according to the measurement results, wherein the multipath prediction model is used to predict the multipath characteristics of the terminal device and the network device communicating in the preset geographical range.

36. The device according to claim 35, characterized in that The measurement result of the first signal also includes indication information of the first grid area.

37. The device according to claim 35 or 36, characterized in that The communication unit is also used for: Sending second information to the terminal device, the second information is used to indicate a method for determining a first reference point of the first signal, the first reference point is used to be determined based on the first information, and the first reference point is used to determine the first grid area.

38. The device according to any one of claims 35 to 37, characterized in that The communication unit is also used for: Sending third information to the terminal device, where the third information is used to indicate a division method of grid areas in the preset geographical area.

39. The device according to any one of claims 36 to 38, characterized in that The first information includes a receiving parameter of the first signal, and the processing unit is further configured to: determining a second reference point corresponding to the first signal according to a sending parameter of the first signal; Determine a second grid area within the preset geographical range according to the second reference point; Determine a third grid area according to the first grid area and the second network area; The processing unit, when training the multipath prediction model according to the measurement result, is specifically used to: A multipath prediction model is trained according to the first information in the measurement result and the third grid area.

40. The device of claim 35, wherein: The first information includes a receiving parameter and a sending parameter of the first signal, and the processing unit is further used for: determining a first reference point corresponding to the first signal according to the first information; Determine the first grid area within the preset geographical range according to the first reference point; The processing unit, when training the multipath prediction model according to the measurement result, is specifically used to: The multipath prediction model is trained according to the measurement result and the first grid area.

41. The device according to any one of claims 35 to 40, characterized in that The transmission parameters of the first signal include a departure angle of the first signal.

42. The device according to any one of claims 35 to 41, characterized in that The reception parameter of the first signal includes at least one of the following: an arrival angle of the first signal, an arrival time of the first signal, or a signal strength of the first signal.

43. The device according to any one of claims 35 to 42, characterized in that The processing unit is also used for: Determine the location information of the terminal device within a first time period according to the current location information of the terminal device and at least one historical location information, where the starting point of the first time period is not earlier than the current time; and, determining the multipath distribution within the preset geographical range within the first time period according to the location information of the terminal device within the first time period and the multipath prediction model; The communication unit is further used for: Sending fourth information to the terminal device, where the fourth information is used to indicate: relevant information about the multipath distribution within the preset geographical range within a time period.

44. The device according to any one of claims 35 to 43, characterized in that The input data of the multipath prediction model includes at least one of the following: environmental information of the preset geographical range, location information of the network device, and location information of the terminal device; The output information of the multipath prediction model includes multipath information corresponding to each grid area within the preset geographical range.

45. The device according to claim 44, characterized in that The multipath information includes at least one of the following parameters for each path: confidence, signal departure angle, signal arrival angle, signal strength, or signal arrival time, and the confidence is used to indicate the probability of multipath existing in the corresponding grid area.

46. ​​A communication device, characterized in that: The device comprises: A communication unit, configured to receive a first signal from a network device; a processing unit, configured to determine a sending parameter and a receiving parameter of the first signal; and, determining, according to the sending parameters and the receiving parameters of the first signal, a first grid area corresponding to the path corresponding to the first signal within a preset geographical range, wherein the preset geographical range is divided into a plurality of grid areas; Furthermore, a multipath prediction model is trained based on the sending parameters of the first signal, the receiving parameters of the first signal and the first grid area, and the multipath prediction model is used to predict the multipath characteristics of the terminal device and the network device communicating within the preset geographical range.

47. The device according to claim 46, characterized in that The processing unit, when training the multipath prediction model according to the sending parameter of the first signal, the receiving parameter of the first signal, and the first grid area, is specifically used to: Inputting the environmental information of the preset geographical range, the location information of the network device, and the location information of the terminal device into the multipath prediction model to obtain output data of the multipath prediction model, wherein the output data includes at least one of the following parameters of each path in each grid area within the preset geographical range: confidence, a signal transmission parameter, or a signal reception parameter, wherein the confidence is used to indicate the probability that a multipath exists in the corresponding grid area; Comparing the transmission parameters of the first signal, the reception parameters of the first signal, and the first grid area with the output data of the multipath prediction model to obtain a comparison result; The multipath prediction model is adjusted according to the comparison result.

48. The device according to claim 46 or 47, characterized in that The communication unit is also used for: Receive environmental information of the preset geographical range and / or location information of the network device from the network device.

49. The device according to any one of claims 46 to 48, characterized in that The processing unit, when determining, according to the sending parameter and the receiving parameter of the first signal, a first grid area corresponding to the path corresponding to the first signal within the preset geographical range, is specifically configured to: Determining a reference point corresponding to the first signal according to a sending parameter and a receiving parameter of the first signal; The first grid area is determined according to a reference point corresponding to the first signal.

50. The device according to claim 49, characterized in that The communication unit is also used for: First information is received from the network device, where the first information is used to indicate a method for determining the reference point.

51. The device according to any one of claims 46 to 50, characterized in that The communication unit is also used for: Second information is received from the network device, where the second information is used to indicate a division method of grid areas in the preset geographical area.

52. The device according to any one of claims 46 to 51, characterized in that The transmission parameters include a signal departure angle.

53. The device according to any one of claims 46 to 52, characterized in that The receiving parameter includes at least one of the following: signal arrival angle, signal arrival time, or signal strength.

54. A communication device, characterized in that: The device comprises: A communication unit, used for communicating with a terminal device; A processing unit, configured to send a first signal to the terminal device through the communication unit; And, at least one of the following is sent to the terminal device through the communication unit: environmental information of a preset geographical range, location information of the network device, first information, or second information, the first information is used to indicate a method for determining a reference point, the reference point is used to determine a first grid area corresponding to a path corresponding to the first signal within the preset geographical range, and the second information is used to indicate a method for dividing grid areas in the preset geographical area.

55. A communication device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store program instructions, and when the processor executes the program instructions, the method according to any one of claims 1 to 7 is executed, or the method according to any one of claims 8 to 18 is executed, or the method according to any one of claims 19 to 26 is executed, or the method according to claim 27 is executed.

56. A computer-readable storage medium, characterized in that The computer storage medium stores computer-readable instructions, and when the computer-readable instructions are executed on the communication device, the method according to any one of claims 1 to 7 is executed, or the method according to any one of claims 8 to 18 is executed, or the method according to any one of claims 19 to 26 is executed, or the method according to claim 27 is executed.

57. A computer program product, characterized in that When the computer program product runs on a device, the device executes the method according to any one of claims 1 to 7, or the method according to any one of claims 8 to 18, or the method according to any one of claims 19 to 26, or the method according to claim 27.

Images